diff --git a/observability/lgtm-distributed/Chart.lock b/observability/lgtm-distributed/Chart.lock new file mode 100644 index 0000000..4797c4b --- /dev/null +++ b/observability/lgtm-distributed/Chart.lock @@ -0,0 +1,18 @@ +dependencies: +- name: grafana + repository: https://grafana.github.io/helm-charts + version: 7.3.12 +- name: loki-distributed + repository: https://grafana.github.io/helm-charts + version: 0.79.0 +- name: mimir-distributed + repository: https://grafana.github.io/helm-charts + version: 5.3.0 +- name: tempo-distributed + repository: https://grafana.github.io/helm-charts + version: 1.13.2 +- name: oncall + repository: https://grafana.github.io/helm-charts + version: 1.7.2 +digest: sha256:d986db60f560cc0d6343f3b7bbc2a562066941f65a69a334a96a0fca027f9f43 +generated: "2024-07-05T16:53:13.051607289Z" diff --git a/observability/lgtm-distributed/Chart.yaml b/observability/lgtm-distributed/Chart.yaml new file mode 100644 index 0000000..0e324a1 --- /dev/null +++ b/observability/lgtm-distributed/Chart.yaml @@ -0,0 +1,60 @@ +annotations: + artifacthub.io/license: Apache-2.0 + artifacthub.io/links: | + - name: Chart Source + url: https://github.com/grafana/helm-charts + - name: Grafana + url: https://github.com/grafana/grafana + - name: Loki + url: https://github.com/grafana/loki + - name: Mimir + url: https://github.com/grafana/mimir + - name: Tempo + url: https://github.com/grafana/tempo +apiVersion: v2 +appVersion: ^7.3.9 +dependencies: +- alias: grafana + condition: grafana.enabled + name: grafana + repository: https://grafana.github.io/helm-charts + version: ^7.3.9 +- alias: loki + condition: loki.enabled + name: loki-distributed + repository: https://grafana.github.io/helm-charts + version: ^0.79.0 +- alias: mimir + condition: mimir.enabled + name: mimir-distributed + repository: https://grafana.github.io/helm-charts + version: ^5.3.0 +- alias: tempo + condition: tempo.enabled + name: tempo-distributed + repository: https://grafana.github.io/helm-charts + version: ^1.9.2 +- alias: grafana-oncall + condition: grafana-oncall.enabled + name: oncall + repository: https://grafana.github.io/helm-charts + version: ^1.3.114 +description: Umbrella chart for a distributed Loki, Grafana, Tempo and Mimir stack +home: https://grafana.com/oss/ +icon: https://artifacthub.io/image/b4fed1a7-6c8f-4945-b99d-096efa3e4116 +keywords: +- monitoring +- traces +- metrics +- logs +maintainers: +- name: timberhill +name: lgtm-distributed +sources: +- https://grafana.github.io/helm-charts +- https://github.com/grafana/grafana +- https://github.com/grafana/loki +- https://github.com/grafana/mimir +- https://github.com/grafana/tempo +type: application +version: 2.1.0 diff --git a/observability/lgtm-distributed/README.md b/observability/lgtm-distributed/README.md new file mode 100644 index 0000000..12b92a0 --- /dev/null +++ b/observability/lgtm-distributed/README.md @@ -0,0 +1,48 @@ +# lgtm-distributed + +![Version: 2.1.0](https://img.shields.io/badge/Version-2.1.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: ^7.3.9](https://img.shields.io/badge/AppVersion-^7.3.9-informational?style=flat-square) + +Umbrella chart for a distributed Loki, Grafana, Tempo and Mimir stack + +**Homepage:** + +## Maintainers + +| Name | Email | Url | +| ---- | ------ | --- | +| timberhill | | | + +## Source Code + +* +* +* +* +* + +## Requirements + +| Repository | Name | Version | +|------------|------|---------| +| https://grafana.github.io/helm-charts | grafana(grafana) | ^7.3.9 | +| https://grafana.github.io/helm-charts | loki(loki-distributed) | ^0.79.0 | +| https://grafana.github.io/helm-charts | mimir(mimir-distributed) | ^5.3.0 | +| https://grafana.github.io/helm-charts | grafana-oncall(oncall) | ^1.3.114 | +| https://grafana.github.io/helm-charts | tempo(tempo-distributed) | ^1.9.2 | + +## Values + +| Key | Type | Default | Description | +|-----|------|---------|-------------| +| grafana-oncall.enabled | bool | `false` | Deploy Grafana OnCall if enabled. See [upstream values.yaml](https://github.com/grafana/oncall/blob/dev/helm/oncall/values.yaml) for full values reference. | +| grafana.datasources | object | `{"datasources.yaml":{"apiVersion":1,"datasources":[{"isDefault":false,"name":"Loki","type":"loki","uid":"loki","url":"http://{{ .Release.Name }}-loki-gateway"},{"isDefault":true,"name":"Mimir","type":"prometheus","uid":"prom","url":"http://{{ .Release.Name }}-mimir-nginx/prometheus"},{"isDefault":false,"jsonData":{"lokiSearch":{"datasourceUid":"loki"},"serviceMap":{"datasourceUid":"prom"},"tracesToLogsV2":{"datasourceUid":"loki"},"tracesToMetrics":{"datasourceUid":"prom"}},"name":"Tempo","type":"tempo","uid":"tempo","url":"http://{{ .Release.Name }}-tempo-query-frontend:3100"}]}}` | Grafana data sources config. Connects to all three by default | +| grafana.datasources."datasources.yaml".datasources | list | `[{"isDefault":false,"name":"Loki","type":"loki","uid":"loki","url":"http://{{ .Release.Name }}-loki-gateway"},{"isDefault":true,"name":"Mimir","type":"prometheus","uid":"prom","url":"http://{{ .Release.Name }}-mimir-nginx/prometheus"},{"isDefault":false,"jsonData":{"lokiSearch":{"datasourceUid":"loki"},"serviceMap":{"datasourceUid":"prom"},"tracesToLogsV2":{"datasourceUid":"loki"},"tracesToMetrics":{"datasourceUid":"prom"}},"name":"Tempo","type":"tempo","uid":"tempo","url":"http://{{ .Release.Name }}-tempo-query-frontend:3100"}]` | Datasources linked to the Grafana instance. Override if you disable any components. | +| grafana.enabled | bool | `true` | Deploy Grafana if enabled. See [upstream readme](https://github.com/grafana/helm-charts/tree/main/charts/grafana#configuration) for full values reference. | +| loki.enabled | bool | `true` | Deploy Loki if enabled. See [upstream readme](https://github.com/grafana/helm-charts/tree/main/charts/loki-distributed#values) for full values reference. | +| mimir | object | `{"alertmanager":{"resources":{"requests":{"cpu":"20m"}}},"compactor":{"resources":{"requests":{"cpu":"20m"}}},"distributor":{"resources":{"requests":{"cpu":"20m"}}},"enabled":true,"ingester":{"replicas":2,"resources":{"requests":{"cpu":"20m"}},"zoneAwareReplication":{"enabled":false}},"minio":{"resources":{"requests":{"cpu":"20m"}}},"overrides_exporter":{"resources":{"requests":{"cpu":"20m"}}},"querier":{"replicas":1,"resources":{"requests":{"cpu":"20m"}}},"query_frontend":{"resources":{"requests":{"cpu":"20m"}}},"query_scheduler":{"replicas":1,"resources":{"requests":{"cpu":"20m"}}},"rollout_operator":{"resources":{"requests":{"cpu":"20m"}}},"ruler":{"resources":{"requests":{"cpu":"20m"}}},"store_gateway":{"resources":{"requests":{"cpu":"20m"}},"zoneAwareReplication":{"enabled":false}}}` | Mimir chart values. Resources are set to a minimum by default. | +| mimir.enabled | bool | `true` | Deploy Mimir if enabled. See [upstream values.yaml](https://github.com/grafana/mimir/blob/main/operations/helm/charts/mimir-distributed/values.yaml) for full values reference. | +| tempo.enabled | bool | `true` | Deploy Tempo if enabled. See [upstream readme](https://github.com/grafana/helm-charts/blob/main/charts/tempo-distributed/README.md#values) for full values reference. | +| tempo.ingester.replicas | int | `1` | | + +---------------------------------------------- +Autogenerated from chart metadata using [helm-docs v1.8.1](https://github.com/norwoodj/helm-docs/releases/v1.8.1) diff --git a/observability/lgtm-distributed/charts/grafana/.helmignore b/observability/lgtm-distributed/charts/grafana/.helmignore new file mode 100644 index 0000000..8cade13 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/.helmignore @@ -0,0 +1,23 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.vscode +.project +.idea/ +*.tmproj +OWNERS diff --git a/observability/lgtm-distributed/charts/grafana/Chart.yaml b/observability/lgtm-distributed/charts/grafana/Chart.yaml new file mode 100644 index 0000000..15c68b5 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/Chart.yaml @@ -0,0 +1,33 @@ +annotations: + artifacthub.io/license: Apache-2.0 + artifacthub.io/links: | + - name: Chart Source + url: https://github.com/grafana/helm-charts + - name: Upstream Project + url: https://github.com/grafana/grafana +apiVersion: v2 +appVersion: 10.4.3 +description: The leading tool for querying and visualizing time series and metrics. +home: https://grafana.com +icon: https://artifacthub.io/image/b4fed1a7-6c8f-4945-b99d-096efa3e4116 +keywords: +- monitoring +- metric +kubeVersion: ^1.8.0-0 +maintainers: +- email: zanhsieh@gmail.com + name: zanhsieh +- email: rluckie@cisco.com + name: rtluckie +- email: maor.friedman@redhat.com + name: maorfr +- email: miroslav.hadzhiev@gmail.com + name: Xtigyro +- email: mail@torstenwalter.de + name: torstenwalter +name: grafana +sources: +- https://github.com/grafana/grafana +- https://github.com/grafana/helm-charts +type: application +version: 7.3.12 diff --git a/observability/lgtm-distributed/charts/grafana/README.md b/observability/lgtm-distributed/charts/grafana/README.md new file mode 100644 index 0000000..0ff07f2 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/README.md @@ -0,0 +1,770 @@ +# Grafana Helm Chart + +* Installs the web dashboarding system [Grafana](http://grafana.org/) + +## Get Repo Info + +```console +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update +``` + +_See [helm repo](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```console +helm install my-release grafana/grafana +``` + +## Uninstalling the Chart + +To uninstall/delete the my-release deployment: + +```console +helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + +## Upgrading an existing Release to a new major version + +A major chart version change (like v1.2.3 -> v2.0.0) indicates that there is an +incompatible breaking change needing manual actions. + +### To 4.0.0 (And 3.12.1) + +This version requires Helm >= 2.12.0. + +### To 5.0.0 + +You have to add --force to your helm upgrade command as the labels of the chart have changed. + +### To 6.0.0 + +This version requires Helm >= 3.1.0. + +### To 7.0.0 + +For consistency with other Helm charts, the `global.image.registry` parameter was renamed +to `global.imageRegistry`. If you were not previously setting `global.image.registry`, no action +is required on upgrade. If you were previously setting `global.image.registry`, you will +need to instead set `global.imageRegistry`. + +## Configuration + +| Parameter | Description | Default | +|-------------------------------------------|-----------------------------------------------|---------------------------------------------------------| +| `replicas` | Number of nodes | `1` | +| `podDisruptionBudget.minAvailable` | Pod disruption minimum available | `nil` | +| `podDisruptionBudget.maxUnavailable` | Pod disruption maximum unavailable | `nil` | +| `podDisruptionBudget.apiVersion` | Pod disruption apiVersion | `nil` | +| `deploymentStrategy` | Deployment strategy | `{ "type": "RollingUpdate" }` | +| `livenessProbe` | Liveness Probe settings | `{ "httpGet": { "path": "/api/health", "port": 3000 } "initialDelaySeconds": 60, "timeoutSeconds": 30, "failureThreshold": 10 }` | +| `readinessProbe` | Readiness Probe settings | `{ "httpGet": { "path": "/api/health", "port": 3000 } }`| +| `securityContext` | Deployment securityContext | `{"runAsUser": 472, "runAsGroup": 472, "fsGroup": 472}` | +| `priorityClassName` | Name of Priority Class to assign pods | `nil` | +| `image.registry` | Image registry | `docker.io` | +| `image.repository` | Image repository | `grafana/grafana` | +| `image.tag` | Overrides the Grafana image tag whose default is the chart appVersion (`Must be >= 5.0.0`) | `` | +| `image.sha` | Image sha (optional) | `` | +| `image.pullPolicy` | Image pull policy | `IfNotPresent` | +| `image.pullSecrets` | Image pull secrets (can be templated) | `[]` | +| `service.enabled` | Enable grafana service | `true` | +| `service.type` | Kubernetes service type | `ClusterIP` | +| `service.port` | Kubernetes port where service is exposed | `80` | +| `service.portName` | Name of the port on the service | `service` | +| `service.appProtocol` | Adds the appProtocol field to the service | `` | +| `service.targetPort` | Internal service is port | `3000` | +| `service.nodePort` | Kubernetes service nodePort | `nil` | +| `service.annotations` | Service annotations (can be templated) | `{}` | +| `service.labels` | Custom labels | `{}` | +| `service.clusterIP` | internal cluster service IP | `nil` | +| `service.loadBalancerIP` | IP address to assign to load balancer (if supported) | `nil` | +| `service.loadBalancerSourceRanges` | list of IP CIDRs allowed access to lb (if supported) | `[]` | +| `service.externalIPs` | service external IP addresses | `[]` | +| `service.externalTrafficPolicy` | change the default externalTrafficPolicy | `nil` | +| `headlessService` | Create a headless service | `false` | +| `extraExposePorts` | Additional service ports for sidecar containers| `[]` | +| `hostAliases` | adds rules to the pod's /etc/hosts | `[]` | +| `ingress.enabled` | Enables Ingress | `false` | +| `ingress.annotations` | Ingress annotations (values are templated) | `{}` | +| `ingress.labels` | Custom labels | `{}` | +| `ingress.path` | Ingress accepted path | `/` | +| `ingress.pathType` | Ingress type of path | `Prefix` | +| `ingress.hosts` | Ingress accepted hostnames | `["chart-example.local"]` | +| `ingress.extraPaths` | Ingress extra paths to prepend to every host configuration. Useful when configuring [custom actions with AWS ALB Ingress Controller](https://kubernetes-sigs.github.io/aws-load-balancer-controller/v2.6/guide/ingress/annotations/#actions). Requires `ingress.hosts` to have one or more host entries. | `[]` | +| `ingress.tls` | Ingress TLS configuration | `[]` | +| `ingress.ingressClassName` | Ingress Class Name. MAY be required for Kubernetes versions >= 1.18 | `""` | +| `resources` | CPU/Memory resource requests/limits | `{}` | +| `nodeSelector` | Node labels for pod assignment | `{}` | +| `tolerations` | Toleration labels for pod assignment | `[]` | +| `affinity` | Affinity settings for pod assignment | `{}` | +| `extraInitContainers` | Init containers to add to the grafana pod | `{}` | +| `extraContainers` | Sidecar containers to add to the grafana pod | `""` | +| `extraContainerVolumes` | Volumes that can be mounted in sidecar containers | `[]` | +| `extraLabels` | Custom labels for all manifests | `{}` | +| `schedulerName` | Name of the k8s scheduler (other than default) | `nil` | +| `persistence.enabled` | Use persistent volume to store data | `false` | +| `persistence.type` | Type of persistence (`pvc` or `statefulset`) | `pvc` | +| `persistence.size` | Size of persistent volume claim | `10Gi` | +| `persistence.existingClaim` | Use an existing PVC to persist data (can be templated) | `nil` | +| `persistence.storageClassName` | Type of persistent volume claim | `nil` | +| `persistence.accessModes` | Persistence access modes | `[ReadWriteOnce]` | +| `persistence.annotations` | PersistentVolumeClaim annotations | `{}` | +| `persistence.finalizers` | PersistentVolumeClaim finalizers | `[ "kubernetes.io/pvc-protection" ]` | +| `persistence.extraPvcLabels` | Extra labels to apply to a PVC. | `{}` | +| `persistence.subPath` | Mount a sub dir of the persistent volume (can be templated) | `nil` | +| `persistence.inMemory.enabled` | If persistence is not enabled, whether to mount the local storage in-memory to improve performance | `false` | +| `persistence.inMemory.sizeLimit` | SizeLimit for the in-memory local storage | `nil` | +| `initChownData.enabled` | If false, don't reset data ownership at startup | true | +| `initChownData.image.registry` | init-chown-data container image registry | `docker.io` | +| `initChownData.image.repository` | init-chown-data container image repository | `busybox` | +| `initChownData.image.tag` | init-chown-data container image tag | `1.31.1` | +| `initChownData.image.sha` | init-chown-data container image sha (optional)| `""` | +| `initChownData.image.pullPolicy` | init-chown-data container image pull policy | `IfNotPresent` | +| `initChownData.resources` | init-chown-data pod resource requests & limits | `{}` | +| `schedulerName` | Alternate scheduler name | `nil` | +| `env` | Extra environment variables passed to pods | `{}` | +| `envValueFrom` | Environment variables from alternate sources. See the API docs on [EnvVarSource](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.17/#envvarsource-v1-core) for format details. Can be templated | `{}` | +| `envFromSecret` | Name of a Kubernetes secret (must be manually created in the same namespace) containing values to be added to the environment. Can be templated | `""` | +| `envFromSecrets` | List of Kubernetes secrets (must be manually created in the same namespace) containing values to be added to the environment. Can be templated | `[]` | +| `envFromConfigMaps` | List of Kubernetes ConfigMaps (must be manually created in the same namespace) containing values to be added to the environment. Can be templated | `[]` | +| `envRenderSecret` | Sensible environment variables passed to pods and stored as secret. (passed through [tpl](https://helm.sh/docs/howto/charts_tips_and_tricks/#using-the-tpl-function)) | `{}` | +| `enableServiceLinks` | Inject Kubernetes services as environment variables. | `true` | +| `extraSecretMounts` | Additional grafana server secret mounts | `[]` | +| `extraVolumeMounts` | Additional grafana server volume mounts | `[]` | +| `extraVolumes` | Additional Grafana server volumes | `[]` | +| `automountServiceAccountToken` | Mounted the service account token on the grafana pod. Mandatory, if sidecars are enabled | `true` | +| `createConfigmap` | Enable creating the grafana configmap | `true` | +| `extraConfigmapMounts` | Additional grafana server configMap volume mounts (values are templated) | `[]` | +| `extraEmptyDirMounts` | Additional grafana server emptyDir volume mounts | `[]` | +| `plugins` | Plugins to be loaded along with Grafana | `[]` | +| `datasources` | Configure grafana datasources (passed through tpl) | `{}` | +| `alerting` | Configure grafana alerting (passed through tpl) | `{}` | +| `notifiers` | Configure grafana notifiers | `{}` | +| `dashboardProviders` | Configure grafana dashboard providers | `{}` | +| `dashboards` | Dashboards to import | `{}` | +| `dashboardsConfigMaps` | ConfigMaps reference that contains dashboards | `{}` | +| `grafana.ini` | Grafana's primary configuration | `{}` | +| `global.imageRegistry` | Global image pull registry for all images. | `null` | +| `global.imagePullSecrets` | Global image pull secrets (can be templated). Allows either an array of {name: pullSecret} maps (k8s-style), or an array of strings (more common helm-style). | `[]` | +| `ldap.enabled` | Enable LDAP authentication | `false` | +| `ldap.existingSecret` | The name of an existing secret containing the `ldap.toml` file, this must have the key `ldap-toml`. | `""` | +| `ldap.config` | Grafana's LDAP configuration | `""` | +| `annotations` | Deployment annotations | `{}` | +| `labels` | Deployment labels | `{}` | +| `podAnnotations` | Pod annotations | `{}` | +| `podLabels` | Pod labels | `{}` | +| `podPortName` | Name of the grafana port on the pod | `grafana` | +| `lifecycleHooks` | Lifecycle hooks for podStart and preStop [Example](https://kubernetes.io/docs/tasks/configure-pod-container/attach-handler-lifecycle-event/#define-poststart-and-prestop-handlers) | `{}` | +| `sidecar.image.registry` | Sidecar image registry | `quay.io` | +| `sidecar.image.repository` | Sidecar image repository | `kiwigrid/k8s-sidecar` | +| `sidecar.image.tag` | Sidecar image tag | `1.26.0` | +| `sidecar.image.sha` | Sidecar image sha (optional) | `""` | +| `sidecar.imagePullPolicy` | Sidecar image pull policy | `IfNotPresent` | +| `sidecar.resources` | Sidecar resources | `{}` | +| `sidecar.securityContext` | Sidecar securityContext | `{}` | +| `sidecar.enableUniqueFilenames` | Sets the kiwigrid/k8s-sidecar UNIQUE_FILENAMES environment variable. If set to `true` the sidecar will create unique filenames where duplicate data keys exist between ConfigMaps and/or Secrets within the same or multiple Namespaces. | `false` | +| `sidecar.alerts.enabled` | Enables the cluster wide search for alerts and adds/updates/deletes them in grafana |`false` | +| `sidecar.alerts.label` | Label that config maps with alerts should have to be added | `grafana_alert` | +| `sidecar.alerts.labelValue` | Label value that config maps with alerts should have to be added | `""` | +| `sidecar.alerts.searchNamespace` | Namespaces list. If specified, the sidecar will search for alerts config-maps inside these namespaces. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces. | `nil` | +| `sidecar.alerts.watchMethod` | Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. | `WATCH` | +| `sidecar.alerts.resource` | Should the sidecar looks into secrets, configmaps or both. | `both` | +| `sidecar.alerts.reloadURL` | Full url of datasource configuration reload API endpoint, to invoke after a config-map change | `"http://localhost:3000/api/admin/provisioning/alerting/reload"` | +| `sidecar.alerts.skipReload` | Enabling this omits defining the REQ_URL and REQ_METHOD environment variables | `false` | +| `sidecar.alerts.initAlerts` | Set to true to deploy the alerts sidecar as an initContainer. This is needed if skipReload is true, to load any alerts defined at startup time. | `false` | +| `sidecar.alerts.extraMounts` | Additional alerts sidecar volume mounts. | `[]` | +| `sidecar.dashboards.enabled` | Enables the cluster wide search for dashboards and adds/updates/deletes them in grafana | `false` | +| `sidecar.dashboards.SCProvider` | Enables creation of sidecar provider | `true` | +| `sidecar.dashboards.provider.name` | Unique name of the grafana provider | `sidecarProvider` | +| `sidecar.dashboards.provider.orgid` | Id of the organisation, to which the dashboards should be added | `1` | +| `sidecar.dashboards.provider.folder` | Logical folder in which grafana groups dashboards | `""` | +| `sidecar.dashboards.provider.disableDelete` | Activate to avoid the deletion of imported dashboards | `false` | +| `sidecar.dashboards.provider.allowUiUpdates` | Allow updating provisioned dashboards from the UI | `false` | +| `sidecar.dashboards.provider.type` | Provider type | `file` | +| `sidecar.dashboards.provider.foldersFromFilesStructure` | Allow Grafana to replicate dashboard structure from filesystem. | `false` | +| `sidecar.dashboards.watchMethod` | Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. | `WATCH` | +| `sidecar.skipTlsVerify` | Set to true to skip tls verification for kube api calls | `nil` | +| `sidecar.dashboards.label` | Label that config maps with dashboards should have to be added | `grafana_dashboard` | +| `sidecar.dashboards.labelValue` | Label value that config maps with dashboards should have to be added | `""` | +| `sidecar.dashboards.folder` | Folder in the pod that should hold the collected dashboards (unless `sidecar.dashboards.defaultFolderName` is set). This path will be mounted. | `/tmp/dashboards` | +| `sidecar.dashboards.folderAnnotation` | The annotation the sidecar will look for in configmaps to override the destination folder for files | `nil` | +| `sidecar.dashboards.defaultFolderName` | The default folder name, it will create a subfolder under the `sidecar.dashboards.folder` and put dashboards in there instead | `nil` | +| `sidecar.dashboards.searchNamespace` | Namespaces list. If specified, the sidecar will search for dashboards config-maps inside these namespaces. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces. | `nil` | +| `sidecar.dashboards.script` | Absolute path to shell script to execute after a configmap got reloaded. | `nil` | +| `sidecar.dashboards.reloadURL` | Full url of dashboards configuration reload API endpoint, to invoke after a config-map change | `"http://localhost:3000/api/admin/provisioning/dashboards/reload"` | +| `sidecar.dashboards.skipReload` | Enabling this omits defining the REQ_USERNAME, REQ_PASSWORD, REQ_URL and REQ_METHOD environment variables | `false` | +| `sidecar.dashboards.resource` | Should the sidecar looks into secrets, configmaps or both. | `both` | +| `sidecar.dashboards.extraMounts` | Additional dashboard sidecar volume mounts. | `[]` | +| `sidecar.datasources.enabled` | Enables the cluster wide search for datasources and adds/updates/deletes them in grafana |`false` | +| `sidecar.datasources.label` | Label that config maps with datasources should have to be added | `grafana_datasource` | +| `sidecar.datasources.labelValue` | Label value that config maps with datasources should have to be added | `""` | +| `sidecar.datasources.searchNamespace` | Namespaces list. If specified, the sidecar will search for datasources config-maps inside these namespaces. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces. | `nil` | +| `sidecar.datasources.watchMethod` | Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. | `WATCH` | +| `sidecar.datasources.resource` | Should the sidecar looks into secrets, configmaps or both. | `both` | +| `sidecar.datasources.reloadURL` | Full url of datasource configuration reload API endpoint, to invoke after a config-map change | `"http://localhost:3000/api/admin/provisioning/datasources/reload"` | +| `sidecar.datasources.skipReload` | Enabling this omits defining the REQ_URL and REQ_METHOD environment variables | `false` | +| `sidecar.datasources.initDatasources` | Set to true to deploy the datasource sidecar as an initContainer in addition to a container. This is needed if skipReload is true, to load any datasources defined at startup time. | `false` | +| `sidecar.notifiers.enabled` | Enables the cluster wide search for notifiers and adds/updates/deletes them in grafana | `false` | +| `sidecar.notifiers.label` | Label that config maps with notifiers should have to be added | `grafana_notifier` | +| `sidecar.notifiers.labelValue` | Label value that config maps with notifiers should have to be added | `""` | +| `sidecar.notifiers.searchNamespace` | Namespaces list. If specified, the sidecar will search for notifiers config-maps (or secrets) inside these namespaces. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces. | `nil` | +| `sidecar.notifiers.watchMethod` | Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. | `WATCH` | +| `sidecar.notifiers.resource` | Should the sidecar looks into secrets, configmaps or both. | `both` | +| `sidecar.notifiers.reloadURL` | Full url of notifier configuration reload API endpoint, to invoke after a config-map change | `"http://localhost:3000/api/admin/provisioning/notifications/reload"` | +| `sidecar.notifiers.skipReload` | Enabling this omits defining the REQ_URL and REQ_METHOD environment variables | `false` | +| `sidecar.notifiers.initNotifiers` | Set to true to deploy the notifier sidecar as an initContainer in addition to a container. This is needed if skipReload is true, to load any notifiers defined at startup time. | `false` | +| `smtp.existingSecret` | The name of an existing secret containing the SMTP credentials. | `""` | +| `smtp.userKey` | The key in the existing SMTP secret containing the username. | `"user"` | +| `smtp.passwordKey` | The key in the existing SMTP secret containing the password. | `"password"` | +| `admin.existingSecret` | The name of an existing secret containing the admin credentials (can be templated). | `""` | +| `admin.userKey` | The key in the existing admin secret containing the username. | `"admin-user"` | +| `admin.passwordKey` | The key in the existing admin secret containing the password. | `"admin-password"` | +| `serviceAccount.automountServiceAccountToken` | Automount the service account token on all pods where is service account is used | `false` | +| `serviceAccount.annotations` | ServiceAccount annotations | | +| `serviceAccount.create` | Create service account | `true` | +| `serviceAccount.labels` | ServiceAccount labels | `{}` | +| `serviceAccount.name` | Service account name to use, when empty will be set to created account if `serviceAccount.create` is set else to `default` | `` | +| `serviceAccount.nameTest` | Service account name to use for test, when empty will be set to created account if `serviceAccount.create` is set else to `default` | `nil` | +| `rbac.create` | Create and use RBAC resources | `true` | +| `rbac.namespaced` | Creates Role and Rolebinding instead of the default ClusterRole and ClusteRoleBindings for the grafana instance | `false` | +| `rbac.useExistingRole` | Set to a rolename to use existing role - skipping role creating - but still doing serviceaccount and rolebinding to the rolename set here. | `nil` | +| `rbac.pspEnabled` | Create PodSecurityPolicy (with `rbac.create`, grant roles permissions as well) | `false` | +| `rbac.pspUseAppArmor` | Enforce AppArmor in created PodSecurityPolicy (requires `rbac.pspEnabled`) | `false` | +| `rbac.extraRoleRules` | Additional rules to add to the Role | [] | +| `rbac.extraClusterRoleRules` | Additional rules to add to the ClusterRole | [] | +| `command` | Define command to be executed by grafana container at startup | `nil` | +| `args` | Define additional args if command is used | `nil` | +| `testFramework.enabled` | Whether to create test-related resources | `true` | +| `testFramework.image.registry` | `test-framework` image registry. | `docker.io` | +| `testFramework.image.repository` | `test-framework` image repository. | `bats/bats` | +| `testFramework.image.tag` | `test-framework` image tag. | `v1.4.1` | +| `testFramework.imagePullPolicy` | `test-framework` image pull policy. | `IfNotPresent` | +| `testFramework.securityContext` | `test-framework` securityContext | `{}` | +| `downloadDashboards.env` | Environment variables to be passed to the `download-dashboards` container | `{}` | +| `downloadDashboards.envFromSecret` | Name of a Kubernetes secret (must be manually created in the same namespace) containing values to be added to the environment. Can be templated | `""` | +| `downloadDashboards.resources` | Resources of `download-dashboards` container | `{}` | +| `downloadDashboardsImage.registry` | Curl docker image registry | `docker.io` | +| `downloadDashboardsImage.repository` | Curl docker image repository | `curlimages/curl` | +| `downloadDashboardsImage.tag` | Curl docker image tag | `7.73.0` | +| `downloadDashboardsImage.sha` | Curl docker image sha (optional) | `""` | +| `downloadDashboardsImage.pullPolicy` | Curl docker image pull policy | `IfNotPresent` | +| `namespaceOverride` | Override the deployment namespace | `""` (`Release.Namespace`) | +| `serviceMonitor.enabled` | Use servicemonitor from prometheus operator | `false` | +| `serviceMonitor.namespace` | Namespace this servicemonitor is installed in | | +| `serviceMonitor.interval` | How frequently Prometheus should scrape | `1m` | +| `serviceMonitor.path` | Path to scrape | `/metrics` | +| `serviceMonitor.scheme` | Scheme to use for metrics scraping | `http` | +| `serviceMonitor.tlsConfig` | TLS configuration block for the endpoint | `{}` | +| `serviceMonitor.labels` | Labels for the servicemonitor passed to Prometheus Operator | `{}` | +| `serviceMonitor.scrapeTimeout` | Timeout after which the scrape is ended | `30s` | +| `serviceMonitor.relabelings` | RelabelConfigs to apply to samples before scraping. | `[]` | +| `serviceMonitor.metricRelabelings` | MetricRelabelConfigs to apply to samples before ingestion. | `[]` | +| `revisionHistoryLimit` | Number of old ReplicaSets to retain | `10` | +| `imageRenderer.enabled` | Enable the image-renderer deployment & service | `false` | +| `imageRenderer.image.registry` | image-renderer Image registry | `docker.io` | +| `imageRenderer.image.repository` | image-renderer Image repository | `grafana/grafana-image-renderer` | +| `imageRenderer.image.tag` | image-renderer Image tag | `latest` | +| `imageRenderer.image.sha` | image-renderer Image sha (optional) | `""` | +| `imageRenderer.image.pullPolicy` | image-renderer ImagePullPolicy | `Always` | +| `imageRenderer.env` | extra env-vars for image-renderer | `{}` | +| `imageRenderer.envValueFrom` | Environment variables for image-renderer from alternate sources. See the API docs on [EnvVarSource](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.17/#envvarsource-v1-core) for format details. Can be templated | `{}` | +| `imageRenderer.serviceAccountName` | image-renderer deployment serviceAccountName | `""` | +| `imageRenderer.securityContext` | image-renderer deployment securityContext | `{}` | +| `imageRenderer.podAnnotations ` | image-renderer image-renderer pod annotation | `{}` | +| `imageRenderer.hostAliases` | image-renderer deployment Host Aliases | `[]` | +| `imageRenderer.priorityClassName` | image-renderer deployment priority class | `''` | +| `imageRenderer.service.enabled` | Enable the image-renderer service | `true` | +| `imageRenderer.service.portName` | image-renderer service port name | `http` | +| `imageRenderer.service.port` | image-renderer port used by deployment | `8081` | +| `imageRenderer.service.targetPort` | image-renderer service port used by service | `8081` | +| `imageRenderer.appProtocol` | Adds the appProtocol field to the service | `` | +| `imageRenderer.grafanaSubPath` | Grafana sub path to use for image renderer callback url | `''` | +| `imageRenderer.podPortName` | name of the image-renderer port on the pod | `http` | +| `imageRenderer.revisionHistoryLimit` | number of image-renderer replica sets to keep | `10` | +| `imageRenderer.networkPolicy.limitIngress` | Enable a NetworkPolicy to limit inbound traffic from only the created grafana pods | `true` | +| `imageRenderer.networkPolicy.limitEgress` | Enable a NetworkPolicy to limit outbound traffic to only the created grafana pods | `false` | +| `imageRenderer.resources` | Set resource limits for image-renderer pods | `{}` | +| `imageRenderer.nodeSelector` | Node labels for pod assignment | `{}` | +| `imageRenderer.tolerations` | Toleration labels for pod assignment | `[]` | +| `imageRenderer.affinity` | Affinity settings for pod assignment | `{}` | +| `networkPolicy.enabled` | Enable creation of NetworkPolicy resources. | `false` | +| `networkPolicy.allowExternal` | Don't require client label for connections | `true` | +| `networkPolicy.explicitNamespacesSelector` | A Kubernetes LabelSelector to explicitly select namespaces from which traffic could be allowed | `{}` | +| `networkPolicy.ingress` | Enable the creation of an ingress network policy | `true` | +| `networkPolicy.egress.enabled` | Enable the creation of an egress network policy | `false` | +| `networkPolicy.egress.ports` | An array of ports to allow for the egress | `[]` | +| `enableKubeBackwardCompatibility` | Enable backward compatibility of kubernetes where pod's defintion version below 1.13 doesn't have the enableServiceLinks option | `false` | + +### Example ingress with path + +With grafana 6.3 and above + +```yaml +grafana.ini: + server: + domain: monitoring.example.com + root_url: "%(protocol)s://%(domain)s/grafana" + serve_from_sub_path: true +ingress: + enabled: true + hosts: + - "monitoring.example.com" + path: "/grafana" +``` + +### Example of extraVolumeMounts and extraVolumes + +Configure additional volumes with `extraVolumes` and volume mounts with `extraVolumeMounts`. + +Example for `extraVolumeMounts` and corresponding `extraVolumes`: + +```yaml +extraVolumeMounts: + - name: plugins + mountPath: /var/lib/grafana/plugins + subPath: configs/grafana/plugins + readOnly: false + - name: dashboards + mountPath: /var/lib/grafana/dashboards + hostPath: /usr/shared/grafana/dashboards + readOnly: false + +extraVolumes: + - name: plugins + existingClaim: existing-grafana-claim + - name: dashboards + hostPath: /usr/shared/grafana/dashboards +``` + +Volumes default to `emptyDir`. Set to `persistentVolumeClaim`, +`hostPath`, `csi`, or `configMap` for other types. For a +`persistentVolumeClaim`, specify an existing claim name with +`existingClaim`. + +## Import dashboards + +There are a few methods to import dashboards to Grafana. Below are some examples and explanations as to how to use each method: + +```yaml +dashboards: + default: + some-dashboard: + json: | + { + "annotations": + + ... + # Complete json file here + ... + + "title": "Some Dashboard", + "uid": "abcd1234", + "version": 1 + } + custom-dashboard: + # This is a path to a file inside the dashboards directory inside the chart directory + file: dashboards/custom-dashboard.json + prometheus-stats: + # Ref: https://grafana.com/dashboards/2 + gnetId: 2 + revision: 2 + datasource: Prometheus + loki-dashboard-quick-search: + gnetId: 12019 + revision: 2 + datasource: + - name: DS_PROMETHEUS + value: Prometheus + - name: DS_LOKI + value: Loki + local-dashboard: + url: https://raw.githubusercontent.com/user/repository/master/dashboards/dashboard.json +``` + +## BASE64 dashboards + +Dashboards could be stored on a server that does not return JSON directly and instead of it returns a Base64 encoded file (e.g. Gerrit) +A new parameter has been added to the url use case so if you specify a b64content value equals to true after the url entry a Base64 decoding is applied before save the file to disk. +If this entry is not set or is equals to false not decoding is applied to the file before saving it to disk. + +### Gerrit use case + +Gerrit API for download files has the following schema: where {project-name} and +{file-id} usually has '/' in their values and so they MUST be replaced by %2F so if project-name is user/repo, branch-id is master and file-id is equals to dir1/dir2/dashboard +the url value is + +## Sidecar for dashboards + +If the parameter `sidecar.dashboards.enabled` is set, a sidecar container is deployed in the grafana +pod. This container watches all configmaps (or secrets) in the cluster and filters out the ones with +a label as defined in `sidecar.dashboards.label`. The files defined in those configmaps are written +to a folder and accessed by grafana. Changes to the configmaps are monitored and the imported +dashboards are deleted/updated. + +A recommendation is to use one configmap per dashboard, as a reduction of multiple dashboards inside +one configmap is currently not properly mirrored in grafana. + +Example dashboard config: + +```yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: sample-grafana-dashboard + labels: + grafana_dashboard: "1" +data: + k8s-dashboard.json: |- + [...] +``` + +## Sidecar for datasources + +If the parameter `sidecar.datasources.enabled` is set, an init container is deployed in the grafana +pod. This container lists all secrets (or configmaps, though not recommended) in the cluster and +filters out the ones with a label as defined in `sidecar.datasources.label`. The files defined in +those secrets are written to a folder and accessed by grafana on startup. Using these yaml files, +the data sources in grafana can be imported. + +Should you aim for reloading datasources in Grafana each time the config is changed, set `sidecar.datasources.skipReload: false` and adjust `sidecar.datasources.reloadURL` to `http://..svc.cluster.local/api/admin/provisioning/datasources/reload`. + +Secrets are recommended over configmaps for this usecase because datasources usually contain private +data like usernames and passwords. Secrets are the more appropriate cluster resource to manage those. + +Example values to add a postgres datasource as a kubernetes secret: +```yaml +apiVersion: v1 +kind: Secret +metadata: + name: grafana-datasources + labels: + grafana_datasource: 'true' # default value for: sidecar.datasources.label +stringData: + pg-db.yaml: |- + apiVersion: 1 + datasources: + - name: My pg db datasource + type: postgres + url: my-postgresql-db:5432 + user: db-readonly-user + secureJsonData: + password: 'SUperSEcretPa$$word' + jsonData: + database: my_datase + sslmode: 'disable' # disable/require/verify-ca/verify-full + maxOpenConns: 0 # Grafana v5.4+ + maxIdleConns: 2 # Grafana v5.4+ + connMaxLifetime: 14400 # Grafana v5.4+ + postgresVersion: 1000 # 903=9.3, 904=9.4, 905=9.5, 906=9.6, 1000=10 + timescaledb: false + # allow users to edit datasources from the UI. + editable: false +``` + +Example values to add a datasource adapted from [Grafana](http://docs.grafana.org/administration/provisioning/#example-datasource-config-file): + +```yaml +datasources: + datasources.yaml: + apiVersion: 1 + datasources: + # name of the datasource. Required + - name: Graphite + # datasource type. Required + type: graphite + # access mode. proxy or direct (Server or Browser in the UI). Required + access: proxy + # org id. will default to orgId 1 if not specified + orgId: 1 + # url + url: http://localhost:8080 + # database password, if used + password: + # database user, if used + user: + # database name, if used + database: + # enable/disable basic auth + basicAuth: + # basic auth username + basicAuthUser: + # basic auth password + basicAuthPassword: + # enable/disable with credentials headers + withCredentials: + # mark as default datasource. Max one per org + isDefault: + # fields that will be converted to json and stored in json_data + jsonData: + graphiteVersion: "1.1" + tlsAuth: true + tlsAuthWithCACert: true + # json object of data that will be encrypted. + secureJsonData: + tlsCACert: "..." + tlsClientCert: "..." + tlsClientKey: "..." + version: 1 + # allow users to edit datasources from the UI. + editable: false +``` + +## Sidecar for notifiers + +If the parameter `sidecar.notifiers.enabled` is set, an init container is deployed in the grafana +pod. This container lists all secrets (or configmaps, though not recommended) in the cluster and +filters out the ones with a label as defined in `sidecar.notifiers.label`. The files defined in +those secrets are written to a folder and accessed by grafana on startup. Using these yaml files, +the notification channels in grafana can be imported. The secrets must be created before +`helm install` so that the notifiers init container can list the secrets. + +Secrets are recommended over configmaps for this usecase because alert notification channels usually contain +private data like SMTP usernames and passwords. Secrets are the more appropriate cluster resource to manage those. + +Example datasource config adapted from [Grafana](https://grafana.com/docs/grafana/latest/administration/provisioning/#alert-notification-channels): + +```yaml +notifiers: + - name: notification-channel-1 + type: slack + uid: notifier1 + # either + org_id: 2 + # or + org_name: Main Org. + is_default: true + send_reminder: true + frequency: 1h + disable_resolve_message: false + # See `Supported Settings` section for settings supporter for each + # alert notification type. + settings: + recipient: 'XXX' + token: 'xoxb' + uploadImage: true + url: https://slack.com + +delete_notifiers: + - name: notification-channel-1 + uid: notifier1 + org_id: 2 + - name: notification-channel-2 + # default org_id: 1 +``` + +## Sidecar for alerting resources + +If the parameter `sidecar.alerts.enabled` is set, a sidecar container is deployed in the grafana +pod. This container watches all configmaps (or secrets) in the cluster (namespace defined by `sidecar.alerts.searchNamespace`) and filters out the ones with +a label as defined in `sidecar.alerts.label` (default is `grafana_alert`). The files defined in those configmaps are written +to a folder and accessed by grafana. Changes to the configmaps are monitored and the imported alerting resources are updated, however, deletions are a little more complicated (see below). + +This sidecar can be used to provision alert rules, contact points, notification policies, notification templates and mute timings as shown in [Grafana Documentation](https://grafana.com/docs/grafana/next/alerting/set-up/provision-alerting-resources/file-provisioning/). + +To fetch the alert config which will be provisioned, use the alert provisioning API ([Grafana Documentation](https://grafana.com/docs/grafana/next/developers/http_api/alerting_provisioning/)). +You can use either JSON or YAML format. + +Example config for an alert rule: + +```yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: sample-grafana-alert + labels: + grafana_alert: "1" +data: + k8s-alert.yml: |- + apiVersion: 1 + groups: + - orgId: 1 + name: k8s-alert + [...] +``` + +To delete provisioned alert rules is a two step process, you need to delete the configmap which defined the alert rule +and then create a configuration which deletes the alert rule. + +Example deletion configuration: +```yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: delete-sample-grafana-alert + namespace: monitoring + labels: + grafana_alert: "1" +data: + delete-k8s-alert.yml: |- + apiVersion: 1 + deleteRules: + - orgId: 1 + uid: 16624780-6564-45dc-825c-8bded4ad92d3 +``` + +## Statically provision alerting resources +If you don't need to change alerting resources (alert rules, contact points, notification policies and notification templates) regularly you could use the `alerting` config option instead of the sidecar option above. +This will grab the alerting config and apply it statically at build time for the helm file. + +There are two methods to statically provision alerting configuration in Grafana. Below are some examples and explanations as to how to use each method: + +```yaml +alerting: + team1-alert-rules.yaml: + file: alerting/team1/rules.yaml + team2-alert-rules.yaml: + file: alerting/team2/rules.yaml + team3-alert-rules.yaml: + file: alerting/team3/rules.yaml + notification-policies.yaml: + file: alerting/shared/notification-policies.yaml + notification-templates.yaml: + file: alerting/shared/notification-templates.yaml + contactpoints.yaml: + apiVersion: 1 + contactPoints: + - orgId: 1 + name: Slack channel + receivers: + - uid: default-receiver + type: slack + settings: + # Webhook URL to be filled in + url: "" + # We need to escape double curly braces for the tpl function. + text: '{{ `{{ template "default.message" . }}` }}' + title: '{{ `{{ template "default.title" . }}` }}' +``` + +The two possibilities for static alerting resource provisioning are: + +* Inlining the file contents as shown for contact points in the above example. +* Importing a file using a relative path starting from the chart root directory as shown for the alert rules in the above example. + +### Important notes on file provisioning + +* The format of the files is defined in the [Grafana documentation](https://grafana.com/docs/grafana/next/alerting/set-up/provision-alerting-resources/file-provisioning/) on file provisioning. +* The chart supports importing YAML and JSON files. +* The filename must be unique, otherwise one volume mount will overwrite the other. +* In case of inlining, double curly braces that arise from the Grafana configuration format and are not intended as templates for the chart must be escaped. +* The number of total files under `alerting:` is not limited. Each file will end up as a volume mount in the corresponding provisioning folder of the deployed Grafana instance. +* The file size for each import is limited by what the function `.Files.Get` can handle, which suffices for most cases. + +## How to serve Grafana with a path prefix (/grafana) + +In order to serve Grafana with a prefix (e.g., ), add the following to your values.yaml. + +```yaml +ingress: + enabled: true + annotations: + kubernetes.io/ingress.class: "nginx" + nginx.ingress.kubernetes.io/rewrite-target: /$1 + nginx.ingress.kubernetes.io/use-regex: "true" + + path: /grafana/?(.*) + hosts: + - k8s.example.dev + +grafana.ini: + server: + root_url: http://localhost:3000/grafana # this host can be localhost +``` + +## How to securely reference secrets in grafana.ini + +This example uses Grafana [file providers](https://grafana.com/docs/grafana/latest/administration/configuration/#file-provider) for secret values and the `extraSecretMounts` configuration flag (Additional grafana server secret mounts) to mount the secrets. + +In grafana.ini: + +```yaml +grafana.ini: + [auth.generic_oauth] + enabled = true + client_id = $__file{/etc/secrets/auth_generic_oauth/client_id} + client_secret = $__file{/etc/secrets/auth_generic_oauth/client_secret} +``` + +Existing secret, or created along with helm: + +```yaml +--- +apiVersion: v1 +kind: Secret +metadata: + name: auth-generic-oauth-secret +type: Opaque +stringData: + client_id: + client_secret: +``` + +Include in the `extraSecretMounts` configuration flag: + +```yaml +- extraSecretMounts: + - name: auth-generic-oauth-secret-mount + secretName: auth-generic-oauth-secret + defaultMode: 0440 + mountPath: /etc/secrets/auth_generic_oauth + readOnly: true +``` + +### extraSecretMounts using a Container Storage Interface (CSI) provider + +This example uses a CSI driver e.g. retrieving secrets using [Azure Key Vault Provider](https://github.com/Azure/secrets-store-csi-driver-provider-azure) + +```yaml +- extraSecretMounts: + - name: secrets-store-inline + mountPath: /run/secrets + readOnly: true + csi: + driver: secrets-store.csi.k8s.io + readOnly: true + volumeAttributes: + secretProviderClass: "my-provider" + nodePublishSecretRef: + name: akv-creds +``` + +## Image Renderer Plug-In + +This chart supports enabling [remote image rendering](https://github.com/grafana/grafana-image-renderer/blob/master/README.md#run-in-docker) + +```yaml +imageRenderer: + enabled: true +``` + +### Image Renderer NetworkPolicy + +By default the image-renderer pods will have a network policy which only allows ingress traffic from the created grafana instance + +### High Availability for unified alerting + +If you want to run Grafana in a high availability cluster you need to enable +the headless service by setting `headlessService: true` in your `values.yaml` +file. + +As next step you have to setup the `grafana.ini` in your `values.yaml` in a way +that it will make use of the headless service to obtain all the IPs of the +cluster. You should replace ``{{ Name }}`` with the name of your helm deployment. + +```yaml +grafana.ini: + ... + unified_alerting: + enabled: true + ha_peers: {{ Name }}-headless:9094 + ha_listen_address: ${POD_IP}:9094 + ha_advertise_address: ${POD_IP}:9094 + + alerting: + enabled: false +``` diff --git a/observability/lgtm-distributed/charts/grafana/ci/default-values.yaml b/observability/lgtm-distributed/charts/grafana/ci/default-values.yaml new file mode 100644 index 0000000..fc2ba60 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/ci/default-values.yaml @@ -0,0 +1 @@ +# Leave this file empty to ensure that CI runs builds against the default configuration in values.yaml. diff --git a/observability/lgtm-distributed/charts/grafana/ci/with-affinity-values.yaml b/observability/lgtm-distributed/charts/grafana/ci/with-affinity-values.yaml new file mode 100644 index 0000000..f5b9b53 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/ci/with-affinity-values.yaml @@ -0,0 +1,16 @@ +affinity: + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - podAffinityTerm: + labelSelector: + matchLabels: + app.kubernetes.io/instance: grafana-test + app.kubernetes.io/name: grafana + topologyKey: failure-domain.beta.kubernetes.io/zone + weight: 100 + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + app.kubernetes.io/instance: grafana-test + app.kubernetes.io/name: grafana + topologyKey: kubernetes.io/hostname diff --git a/observability/lgtm-distributed/charts/grafana/ci/with-dashboard-json-values.yaml b/observability/lgtm-distributed/charts/grafana/ci/with-dashboard-json-values.yaml new file mode 100644 index 0000000..e0c4e41 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/ci/with-dashboard-json-values.yaml @@ -0,0 +1,53 @@ +dashboards: + my-provider: + my-awesome-dashboard: + # An empty but valid dashboard + json: | + { + "__inputs": [], + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "6.3.5" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "id": null, + "links": [], + "panels": [], + "schemaVersion": 19, + "style": "dark", + "tags": [], + "templating": { + "list": [] + }, + "time": { + "from": "now-6h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": ["5s"] + }, + "timezone": "", + "title": "Dummy Dashboard", + "uid": "IdcYQooWk", + "version": 1 + } + datasource: Prometheus diff --git a/observability/lgtm-distributed/charts/grafana/ci/with-dashboard-values.yaml b/observability/lgtm-distributed/charts/grafana/ci/with-dashboard-values.yaml new file mode 100644 index 0000000..7b662c5 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/ci/with-dashboard-values.yaml @@ -0,0 +1,19 @@ +dashboards: + my-provider: + my-awesome-dashboard: + gnetId: 10000 + revision: 1 + datasource: Prometheus +dashboardProviders: + dashboardproviders.yaml: + apiVersion: 1 + providers: + - name: 'my-provider' + orgId: 1 + folder: '' + type: file + updateIntervalSeconds: 10 + disableDeletion: true + editable: true + options: + path: /var/lib/grafana/dashboards/my-provider diff --git a/observability/lgtm-distributed/charts/grafana/ci/with-extraconfigmapmounts-values.yaml b/observability/lgtm-distributed/charts/grafana/ci/with-extraconfigmapmounts-values.yaml new file mode 100644 index 0000000..5cc44a0 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/ci/with-extraconfigmapmounts-values.yaml @@ -0,0 +1,7 @@ +extraConfigmapMounts: + - name: '{{ include "grafana.fullname" . }}' + configMap: '{{ include "grafana.fullname" . }}' + mountPath: /var/lib/grafana/dashboards/test-dashboard.json + # This is not a realistic test, but for this we only care about extraConfigmapMounts not being empty and pointing to an existing ConfigMap + subPath: grafana.ini + readOnly: true diff --git a/observability/lgtm-distributed/charts/grafana/ci/with-image-renderer-values.yaml b/observability/lgtm-distributed/charts/grafana/ci/with-image-renderer-values.yaml new file mode 100644 index 0000000..32f3074 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/ci/with-image-renderer-values.yaml @@ -0,0 +1,19 @@ +podLabels: + customLableA: Aaaaa +imageRenderer: + enabled: true + env: + RENDERING_ARGS: --disable-gpu,--window-size=1280x758 + RENDERING_MODE: clustered + podLabels: + customLableB: Bbbbb + networkPolicy: + limitIngress: true + limitEgress: true + resources: + limits: + cpu: 1000m + memory: 1000Mi + requests: + cpu: 500m + memory: 50Mi diff --git a/observability/lgtm-distributed/charts/grafana/ci/with-persistence.yaml b/observability/lgtm-distributed/charts/grafana/ci/with-persistence.yaml new file mode 100644 index 0000000..b92ca02 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/ci/with-persistence.yaml @@ -0,0 +1,3 @@ +persistence: + type: pvc + enabled: true diff --git a/observability/lgtm-distributed/charts/grafana/dashboards/custom-dashboard.json b/observability/lgtm-distributed/charts/grafana/dashboards/custom-dashboard.json new file mode 100644 index 0000000..9e26dfe --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/dashboards/custom-dashboard.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/grafana/templates/NOTES.txt b/observability/lgtm-distributed/charts/grafana/templates/NOTES.txt new file mode 100644 index 0000000..d86419f --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/NOTES.txt @@ -0,0 +1,55 @@ +1. Get your '{{ .Values.adminUser }}' user password by running: + + kubectl get secret --namespace {{ include "grafana.namespace" . }} {{ .Values.admin.existingSecret | default (include "grafana.fullname" .) }} -o jsonpath="{.data.{{ .Values.admin.passwordKey | default "admin-password" }}}" | base64 --decode ; echo + + +2. The Grafana server can be accessed via port {{ .Values.service.port }} on the following DNS name from within your cluster: + + {{ include "grafana.fullname" . }}.{{ include "grafana.namespace" . }}.svc.cluster.local +{{ if .Values.ingress.enabled }} + If you bind grafana to 80, please update values in values.yaml and reinstall: + ``` + securityContext: + runAsUser: 0 + runAsGroup: 0 + fsGroup: 0 + + command: + - "setcap" + - "'cap_net_bind_service=+ep'" + - "/usr/sbin/grafana-server &&" + - "sh" + - "/run.sh" + ``` + Details refer to https://grafana.com/docs/installation/configuration/#http-port. + Or grafana would always crash. + + From outside the cluster, the server URL(s) are: + {{- range .Values.ingress.hosts }} + http://{{ . }} + {{- end }} +{{- else }} + Get the Grafana URL to visit by running these commands in the same shell: + {{- if contains "NodePort" .Values.service.type }} + export NODE_PORT=$(kubectl get --namespace {{ include "grafana.namespace" . }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "grafana.fullname" . }}) + export NODE_IP=$(kubectl get nodes --namespace {{ include "grafana.namespace" . }} -o jsonpath="{.items[0].status.addresses[0].address}") + echo http://$NODE_IP:$NODE_PORT + {{- else if contains "LoadBalancer" .Values.service.type }} + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + You can watch the status of by running 'kubectl get svc --namespace {{ include "grafana.namespace" . }} -w {{ include "grafana.fullname" . }}' + export SERVICE_IP=$(kubectl get svc --namespace {{ include "grafana.namespace" . }} {{ include "grafana.fullname" . }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}') + http://$SERVICE_IP:{{ .Values.service.port -}} + {{- else if contains "ClusterIP" .Values.service.type }} + export POD_NAME=$(kubectl get pods --namespace {{ include "grafana.namespace" . }} -l "app.kubernetes.io/name={{ include "grafana.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") + kubectl --namespace {{ include "grafana.namespace" . }} port-forward $POD_NAME 3000 + {{- end }} +{{- end }} + +3. Login with the password from step 1 and the username: {{ .Values.adminUser }} + +{{- if not .Values.persistence.enabled }} +################################################################################# +###### WARNING: Persistence is disabled!!! You will lose your data when ##### +###### the Grafana pod is terminated. ##### +################################################################################# +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/_config.tpl b/observability/lgtm-distributed/charts/grafana/templates/_config.tpl new file mode 100644 index 0000000..19df19c --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/_config.tpl @@ -0,0 +1,171 @@ +{{/* + Generate config map data + */}} +{{- define "grafana.configData" -}} +{{ include "grafana.assertNoLeakedSecrets" . }} +{{- $files := .Files }} +{{- $root := . -}} +{{- with .Values.plugins }} +plugins: {{ join "," . }} +{{- end }} +grafana.ini: | +{{- range $elem, $elemVal := index .Values "grafana.ini" }} + {{- if not (kindIs "map" $elemVal) }} + {{- if kindIs "invalid" $elemVal }} + {{ $elem }} = + {{- else if kindIs "string" $elemVal }} + {{ $elem }} = {{ tpl $elemVal $ }} + {{- else }} + {{ $elem }} = {{ $elemVal }} + {{- end }} + {{- end }} +{{- end }} +{{- range $key, $value := index .Values "grafana.ini" }} + {{- if kindIs "map" $value }} + [{{ $key }}] + {{- range $elem, $elemVal := $value }} + {{- if kindIs "invalid" $elemVal }} + {{ $elem }} = + {{- else if kindIs "string" $elemVal }} + {{ $elem }} = {{ tpl $elemVal $ }} + {{- else }} + {{ $elem }} = {{ $elemVal }} + {{- end }} + {{- end }} + {{- end }} +{{- end }} + +{{- range $key, $value := .Values.datasources }} +{{- if not (hasKey $value "secret") }} +{{ $key }}: | + {{- tpl (toYaml $value | nindent 2) $root }} +{{- end }} +{{- end }} + +{{- range $key, $value := .Values.notifiers }} +{{- if not (hasKey $value "secret") }} +{{ $key }}: | + {{- toYaml $value | nindent 2 }} +{{- end }} +{{- end }} + +{{- range $key, $value := .Values.alerting }} +{{- if (hasKey $value "file") }} +{{ $key }}: +{{- toYaml ( $files.Get $value.file ) | nindent 2 }} +{{- else if (or (hasKey $value "secret") (hasKey $value "secretFile"))}} +{{/* will be stored inside secret generated by "configSecret.yaml"*/}} +{{- else }} +{{ $key }}: | + {{- tpl (toYaml $value | nindent 2) $root }} +{{- end }} +{{- end }} + +{{- range $key, $value := .Values.dashboardProviders }} +{{ $key }}: | + {{- toYaml $value | nindent 2 }} +{{- end }} + +{{- if .Values.dashboards }} +download_dashboards.sh: | + #!/usr/bin/env sh + set -euf + {{- if .Values.dashboardProviders }} + {{- range $key, $value := .Values.dashboardProviders }} + {{- range $value.providers }} + mkdir -p {{ .options.path }} + {{- end }} + {{- end }} + {{- end }} +{{ $dashboardProviders := .Values.dashboardProviders }} +{{- range $provider, $dashboards := .Values.dashboards }} + {{- range $key, $value := $dashboards }} + {{- if (or (hasKey $value "gnetId") (hasKey $value "url")) }} + curl -skf \ + --connect-timeout 60 \ + --max-time 60 \ + {{- if not $value.b64content }} + {{- if not $value.acceptHeader }} + -H "Accept: application/json" \ + {{- else }} + -H "Accept: {{ $value.acceptHeader }}" \ + {{- end }} + {{- if $value.token }} + -H "Authorization: token {{ $value.token }}" \ + {{- end }} + {{- if $value.bearerToken }} + -H "Authorization: Bearer {{ $value.bearerToken }}" \ + {{- end }} + {{- if $value.basic }} + -H "Authorization: Basic {{ $value.basic }}" \ + {{- end }} + {{- if $value.gitlabToken }} + -H "PRIVATE-TOKEN: {{ $value.gitlabToken }}" \ + {{- end }} + -H "Content-Type: application/json;charset=UTF-8" \ + {{- end }} + {{- $dpPath := "" -}} + {{- range $kd := (index $dashboardProviders "dashboardproviders.yaml").providers }} + {{- if eq $kd.name $provider }} + {{- $dpPath = $kd.options.path }} + {{- end }} + {{- end }} + {{- if $value.url }} + "{{ $value.url }}" \ + {{- else }} + "https://grafana.com/api/dashboards/{{ $value.gnetId }}/revisions/{{- if $value.revision -}}{{ $value.revision }}{{- else -}}1{{- end -}}/download" \ + {{- end }} + {{- if $value.datasource }} + {{- if kindIs "string" $value.datasource }} + | sed '/-- .* --/! s/"datasource":.*,/"datasource": "{{ $value.datasource }}",/g' \ + {{- end }} + {{- if kindIs "slice" $value.datasource }} + {{- range $value.datasource }} + | sed '/-- .* --/! s/${{"{"}}{{ .name }}}/{{ .value }}/g' \ + {{- end }} + {{- end }} + {{- end }} + {{- if $value.b64content }} + | base64 -d \ + {{- end }} + > "{{- if $dpPath -}}{{ $dpPath }}{{- else -}}/var/lib/grafana/dashboards/{{ $provider }}{{- end -}}/{{ $key }}.json" + {{ end }} + {{- end }} +{{- end }} +{{- end }} +{{- end -}} + +{{/* + Generate dashboard json config map data + */}} +{{- define "grafana.configDashboardProviderData" -}} +provider.yaml: |- + apiVersion: 1 + providers: + - name: '{{ .Values.sidecar.dashboards.provider.name }}' + orgId: {{ .Values.sidecar.dashboards.provider.orgid }} + {{- if not .Values.sidecar.dashboards.provider.foldersFromFilesStructure }} + folder: '{{ .Values.sidecar.dashboards.provider.folder }}' + {{- end }} + type: {{ .Values.sidecar.dashboards.provider.type }} + disableDeletion: {{ .Values.sidecar.dashboards.provider.disableDelete }} + allowUiUpdates: {{ .Values.sidecar.dashboards.provider.allowUiUpdates }} + updateIntervalSeconds: {{ .Values.sidecar.dashboards.provider.updateIntervalSeconds | default 30 }} + options: + foldersFromFilesStructure: {{ .Values.sidecar.dashboards.provider.foldersFromFilesStructure }} + path: {{ .Values.sidecar.dashboards.folder }}{{- with .Values.sidecar.dashboards.defaultFolderName }}/{{ . }}{{- end }} +{{- end -}} + +{{- define "grafana.secretsData" -}} +{{- if and (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) }} +admin-user: {{ .Values.adminUser | b64enc | quote }} +{{- if .Values.adminPassword }} +admin-password: {{ .Values.adminPassword | b64enc | quote }} +{{- else }} +admin-password: {{ include "grafana.password" . }} +{{- end }} +{{- end }} +{{- if not .Values.ldap.existingSecret }} +ldap-toml: {{ tpl .Values.ldap.config $ | b64enc | quote }} +{{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/grafana/templates/_helpers.tpl b/observability/lgtm-distributed/charts/grafana/templates/_helpers.tpl new file mode 100644 index 0000000..f3ebc37 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/_helpers.tpl @@ -0,0 +1,276 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "grafana.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "grafana.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default .Chart.Name .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "grafana.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create the name of the service account +*/}} +{{- define "grafana.serviceAccountName" -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "grafana.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} + +{{- define "grafana.serviceAccountNameTest" -}} +{{- if .Values.serviceAccount.create }} +{{- default (print (include "grafana.fullname" .) "-test") .Values.serviceAccount.nameTest }} +{{- else }} +{{- default "default" .Values.serviceAccount.nameTest }} +{{- end }} +{{- end }} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts +*/}} +{{- define "grafana.namespace" -}} +{{- if .Values.namespaceOverride }} +{{- .Values.namespaceOverride }} +{{- else }} +{{- .Release.Namespace }} +{{- end }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "grafana.labels" -}} +helm.sh/chart: {{ include "grafana.chart" . }} +{{ include "grafana.selectorLabels" . }} +{{- if or .Chart.AppVersion .Values.image.tag }} +app.kubernetes.io/version: {{ mustRegexReplaceAllLiteral "@sha.*" .Values.image.tag "" | default .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- with .Values.extraLabels }} +{{ toYaml . }} +{{- end }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "grafana.selectorLabels" -}} +app.kubernetes.io/name: {{ include "grafana.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "grafana.imageRenderer.labels" -}} +helm.sh/chart: {{ include "grafana.chart" . }} +{{ include "grafana.imageRenderer.selectorLabels" . }} +{{- if or .Chart.AppVersion .Values.image.tag }} +app.kubernetes.io/version: {{ mustRegexReplaceAllLiteral "@sha.*" .Values.image.tag "" | default .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end }} + +{{/* +Selector labels ImageRenderer +*/}} +{{- define "grafana.imageRenderer.selectorLabels" -}} +app.kubernetes.io/name: {{ include "grafana.name" . }}-image-renderer +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Looks if there's an existing secret and reuse its password. If not it generates +new password and use it. +*/}} +{{- define "grafana.password" -}} +{{- $secret := (lookup "v1" "Secret" (include "grafana.namespace" .) (include "grafana.fullname" .) ) }} +{{- if $secret }} +{{- index $secret "data" "admin-password" }} +{{- else }} +{{- (randAlphaNum 40) | b64enc | quote }} +{{- end }} +{{- end }} + +{{/* +Return the appropriate apiVersion for rbac. +*/}} +{{- define "grafana.rbac.apiVersion" -}} +{{- if $.Capabilities.APIVersions.Has "rbac.authorization.k8s.io/v1" }} +{{- print "rbac.authorization.k8s.io/v1" }} +{{- else }} +{{- print "rbac.authorization.k8s.io/v1beta1" }} +{{- end }} +{{- end }} + +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "grafana.ingress.apiVersion" -}} +{{- if and ($.Capabilities.APIVersions.Has "networking.k8s.io/v1") (semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version) }} +{{- print "networking.k8s.io/v1" }} +{{- else if $.Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" }} +{{- print "networking.k8s.io/v1beta1" }} +{{- else }} +{{- print "extensions/v1beta1" }} +{{- end }} +{{- end }} + +{{/* +Return the appropriate apiVersion for Horizontal Pod Autoscaler. +*/}} +{{- define "grafana.hpa.apiVersion" -}} +{{- if .Capabilities.APIVersions.Has "autoscaling/v2" }} +{{- print "autoscaling/v2" }} +{{- else }} +{{- print "autoscaling/v2beta2" }} +{{- end }} +{{- end }} + +{{/* +Return the appropriate apiVersion for podDisruptionBudget. +*/}} +{{- define "grafana.podDisruptionBudget.apiVersion" -}} +{{- if $.Values.podDisruptionBudget.apiVersion }} +{{- print $.Values.podDisruptionBudget.apiVersion }} +{{- else if $.Capabilities.APIVersions.Has "policy/v1/PodDisruptionBudget" }} +{{- print "policy/v1" }} +{{- else }} +{{- print "policy/v1beta1" }} +{{- end }} +{{- end }} + +{{/* +Return if ingress is stable. +*/}} +{{- define "grafana.ingress.isStable" -}} +{{- eq (include "grafana.ingress.apiVersion" .) "networking.k8s.io/v1" }} +{{- end }} + +{{/* +Return if ingress supports ingressClassName. +*/}} +{{- define "grafana.ingress.supportsIngressClassName" -}} +{{- or (eq (include "grafana.ingress.isStable" .) "true") (and (eq (include "grafana.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) }} +{{- end }} + +{{/* +Return if ingress supports pathType. +*/}} +{{- define "grafana.ingress.supportsPathType" -}} +{{- or (eq (include "grafana.ingress.isStable" .) "true") (and (eq (include "grafana.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) }} +{{- end }} + +{{/* +Formats imagePullSecrets. Input is (dict "root" . "imagePullSecrets" .{specific imagePullSecrets}) +*/}} +{{- define "grafana.imagePullSecrets" -}} +{{- $root := .root }} +{{- range (concat .root.Values.global.imagePullSecrets .imagePullSecrets) }} +{{- if eq (typeOf .) "map[string]interface {}" }} +- {{ toYaml (dict "name" (tpl .name $root)) | trim }} +{{- else }} +- name: {{ tpl . $root }} +{{- end }} +{{- end }} +{{- end }} + + +{{/* + Checks whether or not the configSecret secret has to be created + */}} +{{- define "grafana.shouldCreateConfigSecret" -}} +{{- $secretFound := false -}} +{{- range $key, $value := .Values.datasources }} + {{- if hasKey $value "secret" }} + {{- $secretFound = true}} + {{- end }} +{{- end }} +{{- range $key, $value := .Values.notifiers }} + {{- if hasKey $value "secret" }} + {{- $secretFound = true}} + {{- end }} +{{- end }} +{{- range $key, $value := .Values.alerting }} + {{- if (or (hasKey $value "secret") (hasKey $value "secretFile")) }} + {{- $secretFound = true}} + {{- end }} +{{- end }} +{{- $secretFound}} +{{- end -}} + +{{/* + Checks whether the user is attempting to store secrets in plaintext + in the grafana.ini configmap +*/}} +{{/* grafana.assertNoLeakedSecrets checks for sensitive keys in values */}} +{{- define "grafana.assertNoLeakedSecrets" -}} + {{- $sensitiveKeysYaml := ` +sensitiveKeys: +- path: ["database", "password"] +- path: ["smtp", "password"] +- path: ["security", "secret_key"] +- path: ["security", "admin_password"] +- path: ["auth.basic", "password"] +- path: ["auth.ldap", "bind_password"] +- path: ["auth.google", "client_secret"] +- path: ["auth.github", "client_secret"] +- path: ["auth.gitlab", "client_secret"] +- path: ["auth.generic_oauth", "client_secret"] +- path: ["auth.okta", "client_secret"] +- path: ["auth.azuread", "client_secret"] +- path: ["auth.grafana_com", "client_secret"] +- path: ["auth.grafananet", "client_secret"] +- path: ["azure", "user_identity_client_secret"] +- path: ["unified_alerting", "ha_redis_password"] +- path: ["metrics", "basic_auth_password"] +- path: ["external_image_storage.s3", "secret_key"] +- path: ["external_image_storage.webdav", "password"] +- path: ["external_image_storage.azure_blob", "account_key"] +` | fromYaml -}} + {{- if $.Values.assertNoLeakedSecrets -}} + {{- $grafanaIni := index .Values "grafana.ini" -}} + {{- range $_, $secret := $sensitiveKeysYaml.sensitiveKeys -}} + {{- $currentMap := $grafanaIni -}} + {{- $shouldContinue := true -}} + {{- range $index, $elem := $secret.path -}} + {{- if and $shouldContinue (hasKey $currentMap $elem) -}} + {{- if eq (len $secret.path) (add1 $index) -}} + {{- if not (regexMatch "\\$(?:__(?:env|file|vault))?{[^}]+}" (index $currentMap $elem)) -}} + {{- fail (printf "Sensitive key '%s' should not be defined explicitly in values. Use variable expansion instead. You can disable this client-side validation by changing the value of assertNoLeakedSecrets." (join "." $secret.path)) -}} + {{- end -}} + {{- else -}} + {{- $currentMap = index $currentMap $elem -}} + {{- end -}} + {{- else -}} + {{- $shouldContinue = false -}} + {{- end -}} + {{- end -}} + {{- end -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/grafana/templates/_pod.tpl b/observability/lgtm-distributed/charts/grafana/templates/_pod.tpl new file mode 100644 index 0000000..ed22993 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/_pod.tpl @@ -0,0 +1,1296 @@ +{{- define "grafana.pod" -}} +{{- $sts := list "sts" "StatefulSet" "statefulset" -}} +{{- $root := . -}} +{{- with .Values.schedulerName }} +schedulerName: "{{ . }}" +{{- end }} +serviceAccountName: {{ include "grafana.serviceAccountName" . }} +automountServiceAccountToken: {{ .Values.automountServiceAccountToken }} +{{- with .Values.securityContext }} +securityContext: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.hostAliases }} +hostAliases: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- if .Values.dnsPolicy }} +dnsPolicy: {{ .Values.dnsPolicy }} +{{- end }} +{{- with .Values.dnsConfig }} +dnsConfig: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.priorityClassName }} +priorityClassName: {{ . }} +{{- end }} +{{- if ( or .Values.persistence.enabled .Values.dashboards .Values.extraInitContainers (and .Values.sidecar.alerts.enabled .Values.sidecar.alerts.initAlerts) (and .Values.sidecar.datasources.enabled .Values.sidecar.datasources.initDatasources) (and .Values.sidecar.notifiers.enabled .Values.sidecar.notifiers.initNotifiers)) }} +initContainers: +{{- end }} +{{- if ( and .Values.persistence.enabled .Values.initChownData.enabled ) }} + - name: init-chown-data + {{- $registry := .Values.global.imageRegistry | default .Values.initChownData.image.registry -}} + {{- if .Values.initChownData.image.sha }} + image: "{{ $registry }}/{{ .Values.initChownData.image.repository }}:{{ .Values.initChownData.image.tag }}@sha256:{{ .Values.initChownData.image.sha }}" + {{- else }} + image: "{{ $registry }}/{{ .Values.initChownData.image.repository }}:{{ .Values.initChownData.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.initChownData.image.pullPolicy }} + {{- with .Values.initChownData.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + command: + - chown + - -R + - {{ .Values.securityContext.runAsUser }}:{{ .Values.securityContext.runAsGroup }} + - /var/lib/grafana + {{- with .Values.initChownData.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: storage + mountPath: "/var/lib/grafana" + {{- with .Values.persistence.subPath }} + subPath: {{ tpl . $root }} + {{- end }} +{{- end }} +{{- if .Values.dashboards }} + - name: download-dashboards + {{- $registry := .Values.global.imageRegistry | default .Values.downloadDashboardsImage.registry -}} + {{- if .Values.downloadDashboardsImage.sha }} + image: "{{ $registry }}/{{ .Values.downloadDashboardsImage.repository }}:{{ .Values.downloadDashboardsImage.tag }}@sha256:{{ .Values.downloadDashboardsImage.sha }}" + {{- else }} + image: "{{ $registry }}/{{ .Values.downloadDashboardsImage.repository }}:{{ .Values.downloadDashboardsImage.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.downloadDashboardsImage.pullPolicy }} + command: ["/bin/sh"] + args: [ "-c", "mkdir -p /var/lib/grafana/dashboards/default && /bin/sh -x /etc/grafana/download_dashboards.sh" ] + {{- with .Values.downloadDashboards.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + env: + {{- range $key, $value := .Values.downloadDashboards.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- range $key, $value := .Values.downloadDashboards.envValueFrom }} + - name: {{ $key | quote }} + valueFrom: + {{- tpl (toYaml $value) $ | nindent 10 }} + {{- end }} + {{- with .Values.downloadDashboards.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.downloadDashboards.envFromSecret }} + envFrom: + - secretRef: + name: {{ tpl . $root }} + {{- end }} + volumeMounts: + - name: config + mountPath: "/etc/grafana/download_dashboards.sh" + subPath: download_dashboards.sh + - name: storage + mountPath: "/var/lib/grafana" + {{- with .Values.persistence.subPath }} + subPath: {{ tpl . $root }} + {{- end }} + {{- range .Values.extraSecretMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + readOnly: {{ .readOnly }} + {{- end }} +{{- end }} +{{- if and .Values.sidecar.alerts.enabled .Values.sidecar.alerts.initAlerts }} + - name: {{ include "grafana.name" . }}-init-sc-alerts + {{- $registry := .Values.global.imageRegistry | default .Values.sidecar.image.registry -}} + {{- if .Values.sidecar.image.sha }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.alerts.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.alerts.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: "LIST" + - name: LABEL + value: "{{ .Values.sidecar.alerts.label }}" + {{- with .Values.sidecar.alerts.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.alerts.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.alerts.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/alerting" + - name: RESOURCE + value: {{ quote .Values.sidecar.alerts.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.alerts.searchNamespace }} + - name: NAMESPACE + value: {{ . | join "," | quote }} + {{- end }} + {{- with .Values.sidecar.alerts.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: {{ quote . }} + {{- end }} + {{- with .Values.sidecar.alerts.script }} + - name: SCRIPT + value: {{ quote . }} + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-alerts-volume + mountPath: "/etc/grafana/provisioning/alerting" + {{- with .Values.sidecar.alerts.extraMounts }} + {{- toYaml . | trim | nindent 6 }} + {{- end }} +{{- end }} +{{- if and .Values.sidecar.datasources.enabled .Values.sidecar.datasources.initDatasources }} + - name: {{ include "grafana.name" . }}-init-sc-datasources + {{- $registry := .Values.global.imageRegistry | default .Values.sidecar.image.registry -}} + {{- if .Values.sidecar.image.sha }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.datasources.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.datasources.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: "LIST" + - name: LABEL + value: "{{ .Values.sidecar.datasources.label }}" + {{- with .Values.sidecar.datasources.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.datasources.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.datasources.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/datasources" + - name: RESOURCE + value: {{ quote .Values.sidecar.datasources.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- if .Values.sidecar.datasources.searchNamespace }} + - name: NAMESPACE + value: "{{ tpl (.Values.sidecar.datasources.searchNamespace | join ",") . }}" + {{- end }} + {{- with .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-datasources-volume + mountPath: "/etc/grafana/provisioning/datasources" +{{- end }} +{{- if and .Values.sidecar.notifiers.enabled .Values.sidecar.notifiers.initNotifiers }} + - name: {{ include "grafana.name" . }}-init-sc-notifiers + {{- $registry := .Values.global.imageRegistry | default .Values.sidecar.image.registry -}} + {{- if .Values.sidecar.image.sha }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.notifiers.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.notifiers.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: LIST + - name: LABEL + value: "{{ .Values.sidecar.notifiers.label }}" + {{- with .Values.sidecar.notifiers.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.notifiers.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.notifiers.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/notifiers" + - name: RESOURCE + value: {{ quote .Values.sidecar.notifiers.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.notifiers.searchNamespace }} + - name: NAMESPACE + value: "{{ tpl (. | join ",") $root }}" + {{- end }} + {{- with .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-notifiers-volume + mountPath: "/etc/grafana/provisioning/notifiers" +{{- end}} +{{- with .Values.extraInitContainers }} + {{- tpl (toYaml .) $root | nindent 2 }} +{{- end }} +{{- if or .Values.image.pullSecrets .Values.global.imagePullSecrets }} +imagePullSecrets: + {{- include "grafana.imagePullSecrets" (dict "root" $root "imagePullSecrets" .Values.image.pullSecrets) | nindent 2 }} +{{- end }} +{{- if not .Values.enableKubeBackwardCompatibility }} +enableServiceLinks: {{ .Values.enableServiceLinks }} +{{- end }} +containers: +{{- if and .Values.sidecar.alerts.enabled (not .Values.sidecar.alerts.initAlerts) }} + - name: {{ include "grafana.name" . }}-sc-alerts + {{- $registry := .Values.global.imageRegistry | default .Values.sidecar.image.registry -}} + {{- if .Values.sidecar.image.sha }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.alerts.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.alerts.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: {{ .Values.sidecar.alerts.watchMethod }} + - name: LABEL + value: "{{ .Values.sidecar.alerts.label }}" + {{- with .Values.sidecar.alerts.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.alerts.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.alerts.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/alerting" + - name: RESOURCE + value: {{ quote .Values.sidecar.alerts.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.alerts.searchNamespace }} + - name: NAMESPACE + value: {{ . | join "," | quote }} + {{- end }} + {{- with .Values.sidecar.alerts.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: {{ quote . }} + {{- end }} + {{- with .Values.sidecar.alerts.script }} + - name: SCRIPT + value: {{ quote . }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + {{- if not .Values.sidecar.alerts.skipReload }} + - name: REQ_URL + value: {{ .Values.sidecar.alerts.reloadURL }} + - name: REQ_METHOD + value: POST + {{- end }} + {{- if .Values.sidecar.alerts.watchServerTimeout }} + {{- if ne .Values.sidecar.alerts.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.alerts.watchServerTimeout with .Values.sidecar.alerts.watchMethod %s" .Values.sidecar.alerts.watchMethod) }} + {{- end }} + - name: WATCH_SERVER_TIMEOUT + value: "{{ .Values.sidecar.alerts.watchServerTimeout }}" + {{- end }} + {{- if .Values.sidecar.alerts.watchClientTimeout }} + {{- if ne .Values.sidecar.alerts.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.alerts.watchClientTimeout with .Values.sidecar.alerts.watchMethod %s" .Values.sidecar.alerts.watchMethod) }} + {{- end }} + - name: WATCH_CLIENT_TIMEOUT + value: "{{ .Values.sidecar.alerts.watchClientTimeout }}" + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-alerts-volume + mountPath: "/etc/grafana/provisioning/alerting" + {{- with .Values.sidecar.alerts.extraMounts }} + {{- toYaml . | trim | nindent 6 }} + {{- end }} +{{- end}} +{{- if .Values.sidecar.dashboards.enabled }} + - name: {{ include "grafana.name" . }}-sc-dashboard + {{- $registry := .Values.global.imageRegistry | default .Values.sidecar.image.registry -}} + {{- if .Values.sidecar.image.sha }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.dashboards.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- range $key, $value := .Values.sidecar.datasources.envValueFrom }} + - name: {{ $key | quote }} + valueFrom: + {{- tpl (toYaml $value) $ | nindent 10 }} + {{- end }} + {{- if .Values.sidecar.dashboards.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: {{ .Values.sidecar.dashboards.watchMethod }} + - name: LABEL + value: "{{ .Values.sidecar.dashboards.label }}" + {{- with .Values.sidecar.dashboards.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.dashboards.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.dashboards.logLevel }} + {{- end }} + - name: FOLDER + value: "{{ .Values.sidecar.dashboards.folder }}{{- with .Values.sidecar.dashboards.defaultFolderName }}/{{ . }}{{- end }}" + - name: RESOURCE + value: {{ quote .Values.sidecar.dashboards.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.dashboards.searchNamespace }} + - name: NAMESPACE + value: "{{ tpl (. | join ",") $root }}" + {{- end }} + {{- with .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.dashboards.folderAnnotation }} + - name: FOLDER_ANNOTATION + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.dashboards.script }} + - name: SCRIPT + value: "{{ . }}" + {{- end }} + {{- if not .Values.sidecar.dashboards.skipReload }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + - name: REQ_URL + value: {{ .Values.sidecar.dashboards.reloadURL }} + - name: REQ_METHOD + value: POST + {{- end }} + {{- if .Values.sidecar.dashboards.watchServerTimeout }} + {{- if ne .Values.sidecar.dashboards.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.dashboards.watchServerTimeout with .Values.sidecar.dashboards.watchMethod %s" .Values.sidecar.dashboards.watchMethod) }} + {{- end }} + - name: WATCH_SERVER_TIMEOUT + value: "{{ .Values.sidecar.dashboards.watchServerTimeout }}" + {{- end }} + {{- if .Values.sidecar.dashboards.watchClientTimeout }} + {{- if ne .Values.sidecar.dashboards.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.dashboards.watchClientTimeout with .Values.sidecar.dashboards.watchMethod %s" .Values.sidecar.dashboards.watchMethod) }} + {{- end }} + - name: WATCH_CLIENT_TIMEOUT + value: {{ .Values.sidecar.dashboards.watchClientTimeout | quote }} + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-dashboard-volume + mountPath: {{ .Values.sidecar.dashboards.folder | quote }} + {{- with .Values.sidecar.dashboards.extraMounts }} + {{- toYaml . | trim | nindent 6 }} + {{- end }} +{{- end}} +{{- if and .Values.sidecar.datasources.enabled (not .Values.sidecar.datasources.initDatasources) }} + - name: {{ include "grafana.name" . }}-sc-datasources + {{- $registry := .Values.global.imageRegistry | default .Values.sidecar.image.registry -}} + {{- if .Values.sidecar.image.sha }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.datasources.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.datasources.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: {{ .Values.sidecar.datasources.watchMethod }} + - name: LABEL + value: "{{ .Values.sidecar.datasources.label }}" + {{- with .Values.sidecar.datasources.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.datasources.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.datasources.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/datasources" + - name: RESOURCE + value: {{ quote .Values.sidecar.datasources.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.datasources.searchNamespace }} + - name: NAMESPACE + value: "{{ tpl (. | join ",") $root }}" + {{- end }} + {{- if .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ .Values.sidecar.skipTlsVerify }}" + {{- end }} + {{- if .Values.sidecar.datasources.script }} + - name: SCRIPT + value: "{{ .Values.sidecar.datasources.script }}" + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + {{- if not .Values.sidecar.datasources.skipReload }} + - name: REQ_URL + value: {{ .Values.sidecar.datasources.reloadURL }} + - name: REQ_METHOD + value: POST + {{- end }} + {{- if .Values.sidecar.datasources.watchServerTimeout }} + {{- if ne .Values.sidecar.datasources.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.datasources.watchServerTimeout with .Values.sidecar.datasources.watchMethod %s" .Values.sidecar.datasources.watchMethod) }} + {{- end }} + - name: WATCH_SERVER_TIMEOUT + value: "{{ .Values.sidecar.datasources.watchServerTimeout }}" + {{- end }} + {{- if .Values.sidecar.datasources.watchClientTimeout }} + {{- if ne .Values.sidecar.datasources.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.datasources.watchClientTimeout with .Values.sidecar.datasources.watchMethod %s" .Values.sidecar.datasources.watchMethod) }} + {{- end }} + - name: WATCH_CLIENT_TIMEOUT + value: "{{ .Values.sidecar.datasources.watchClientTimeout }}" + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-datasources-volume + mountPath: "/etc/grafana/provisioning/datasources" +{{- end}} +{{- if .Values.sidecar.notifiers.enabled }} + - name: {{ include "grafana.name" . }}-sc-notifiers + {{- $registry := .Values.global.imageRegistry | default .Values.sidecar.image.registry -}} + {{- if .Values.sidecar.image.sha }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.notifiers.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.notifiers.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: {{ .Values.sidecar.notifiers.watchMethod }} + - name: LABEL + value: "{{ .Values.sidecar.notifiers.label }}" + {{- with .Values.sidecar.notifiers.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.notifiers.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.notifiers.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/notifiers" + - name: RESOURCE + value: {{ quote .Values.sidecar.notifiers.resource }} + {{- if .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ .Values.sidecar.enableUniqueFilenames }}" + {{- end }} + {{- with .Values.sidecar.notifiers.searchNamespace }} + - name: NAMESPACE + value: "{{ tpl (. | join ",") $root }}" + {{- end }} + {{- with .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ . }}" + {{- end }} + {{- if .Values.sidecar.notifiers.script }} + - name: SCRIPT + value: "{{ .Values.sidecar.notifiers.script }}" + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + {{- if not .Values.sidecar.notifiers.skipReload }} + - name: REQ_URL + value: {{ .Values.sidecar.notifiers.reloadURL }} + - name: REQ_METHOD + value: POST + {{- end }} + {{- if .Values.sidecar.notifiers.watchServerTimeout }} + {{- if ne .Values.sidecar.notifiers.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.notifiers.watchServerTimeout with .Values.sidecar.notifiers.watchMethod %s" .Values.sidecar.notifiers.watchMethod) }} + {{- end }} + - name: WATCH_SERVER_TIMEOUT + value: "{{ .Values.sidecar.notifiers.watchServerTimeout }}" + {{- end }} + {{- if .Values.sidecar.notifiers.watchClientTimeout }} + {{- if ne .Values.sidecar.notifiers.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.notifiers.watchClientTimeout with .Values.sidecar.notifiers.watchMethod %s" .Values.sidecar.notifiers.watchMethod) }} + {{- end }} + - name: WATCH_CLIENT_TIMEOUT + value: "{{ .Values.sidecar.notifiers.watchClientTimeout }}" + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-notifiers-volume + mountPath: "/etc/grafana/provisioning/notifiers" +{{- end}} +{{- if .Values.sidecar.plugins.enabled }} + - name: {{ include "grafana.name" . }}-sc-plugins + {{- $registry := .Values.global.imageRegistry | default .Values.sidecar.image.registry -}} + {{- if .Values.sidecar.image.sha }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ $registry }}/{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.plugins.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.plugins.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: {{ .Values.sidecar.plugins.watchMethod }} + - name: LABEL + value: "{{ .Values.sidecar.plugins.label }}" + {{- if .Values.sidecar.plugins.labelValue }} + - name: LABEL_VALUE + value: {{ quote .Values.sidecar.plugins.labelValue }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.plugins.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.plugins.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/plugins" + - name: RESOURCE + value: {{ quote .Values.sidecar.plugins.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.plugins.searchNamespace }} + - name: NAMESPACE + value: "{{ tpl (. | join ",") $root }}" + {{- end }} + {{- with .Values.sidecar.plugins.script }} + - name: SCRIPT + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ . }}" + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + {{- if not .Values.sidecar.plugins.skipReload }} + - name: REQ_URL + value: {{ .Values.sidecar.plugins.reloadURL }} + - name: REQ_METHOD + value: POST + {{- end }} + {{- if .Values.sidecar.plugins.watchServerTimeout }} + {{- if ne .Values.sidecar.plugins.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.plugins.watchServerTimeout with .Values.sidecar.plugins.watchMethod %s" .Values.sidecar.plugins.watchMethod) }} + {{- end }} + - name: WATCH_SERVER_TIMEOUT + value: "{{ .Values.sidecar.plugins.watchServerTimeout }}" + {{- end }} + {{- if .Values.sidecar.plugins.watchClientTimeout }} + {{- if ne .Values.sidecar.plugins.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.plugins.watchClientTimeout with .Values.sidecar.plugins.watchMethod %s" .Values.sidecar.plugins.watchMethod) }} + {{- end }} + - name: WATCH_CLIENT_TIMEOUT + value: "{{ .Values.sidecar.plugins.watchClientTimeout }}" + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-plugins-volume + mountPath: "/etc/grafana/provisioning/plugins" +{{- end}} + - name: {{ .Chart.Name }} + {{- $registry := .Values.global.imageRegistry | default .Values.image.registry -}} + {{- if .Values.image.sha }} + image: "{{ $registry }}/{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}@sha256:{{ .Values.image.sha }}" + {{- else }} + image: "{{ $registry }}/{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" + {{- end }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + {{- if .Values.command }} + command: + {{- range .Values.command }} + - {{ . | quote }} + {{- end }} + {{- end }} + {{- if .Values.args }} + args: + {{- range .Values.args }} + - {{ . | quote }} + {{- end }} + {{- end }} + {{- with .Values.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: config + mountPath: "/etc/grafana/grafana.ini" + subPath: grafana.ini + {{- if .Values.ldap.enabled }} + - name: ldap + mountPath: "/etc/grafana/ldap.toml" + subPath: ldap.toml + {{- end }} + {{- range .Values.extraConfigmapMounts }} + - name: {{ tpl .name $root }} + mountPath: {{ tpl .mountPath $root }} + subPath: {{ tpl (.subPath | default "") $root }} + readOnly: {{ .readOnly }} + {{- end }} + - name: storage + mountPath: "/var/lib/grafana" + {{- with .Values.persistence.subPath }} + subPath: {{ tpl . $root }} + {{- end }} + {{- with .Values.dashboards }} + {{- range $provider, $dashboards := . }} + {{- range $key, $value := $dashboards }} + {{- if (or (hasKey $value "json") (hasKey $value "file")) }} + - name: dashboards-{{ $provider }} + mountPath: "/var/lib/grafana/dashboards/{{ $provider }}/{{ $key }}.json" + subPath: "{{ $key }}.json" + {{- end }} + {{- end }} + {{- end }} + {{- end }} + {{- with .Values.dashboardsConfigMaps }} + {{- range (keys . | sortAlpha) }} + - name: dashboards-{{ . }} + mountPath: "/var/lib/grafana/dashboards/{{ . }}" + {{- end }} + {{- end }} + {{- with .Values.datasources }} + {{- $datasources := . }} + {{- range (keys . | sortAlpha) }} + {{- if (or (hasKey (index $datasources .) "secret")) }} {{/*check if current datasource should be handeled as secret */}} + - name: config-secret + mountPath: "/etc/grafana/provisioning/datasources/{{ . }}" + subPath: {{ . | quote }} + {{- else }} + - name: config + mountPath: "/etc/grafana/provisioning/datasources/{{ . }}" + subPath: {{ . | quote }} + {{- end }} + {{- end }} + {{- end }} + {{- with .Values.notifiers }} + {{- $notifiers := . }} + {{- range (keys . | sortAlpha) }} + {{- if (or (hasKey (index $notifiers .) "secret")) }} {{/*check if current notifier should be handeled as secret */}} + - name: config-secret + mountPath: "/etc/grafana/provisioning/notifiers/{{ . }}" + subPath: {{ . | quote }} + {{- else }} + - name: config + mountPath: "/etc/grafana/provisioning/notifiers/{{ . }}" + subPath: {{ . | quote }} + {{- end }} + {{- end }} + {{- end }} + {{- with .Values.alerting }} + {{- $alertingmap := .}} + {{- range (keys . | sortAlpha) }} + {{- if (or (hasKey (index $.Values.alerting .) "secret") (hasKey (index $.Values.alerting .) "secretFile")) }} {{/*check if current alerting entry should be handeled as secret */}} + - name: config-secret + mountPath: "/etc/grafana/provisioning/alerting/{{ . }}" + subPath: {{ . | quote }} + {{- else }} + - name: config + mountPath: "/etc/grafana/provisioning/alerting/{{ . }}" + subPath: {{ . | quote }} + {{- end }} + {{- end }} + {{- end }} + {{- with .Values.dashboardProviders }} + {{- range (keys . | sortAlpha) }} + - name: config + mountPath: "/etc/grafana/provisioning/dashboards/{{ . }}" + subPath: {{ . | quote }} + {{- end }} + {{- end }} + {{- with .Values.sidecar.alerts.enabled }} + - name: sc-alerts-volume + mountPath: "/etc/grafana/provisioning/alerting" + {{- end}} + {{- if .Values.sidecar.dashboards.enabled }} + - name: sc-dashboard-volume + mountPath: {{ .Values.sidecar.dashboards.folder | quote }} + {{- if .Values.sidecar.dashboards.SCProvider }} + - name: sc-dashboard-provider + mountPath: "/etc/grafana/provisioning/dashboards/sc-dashboardproviders.yaml" + subPath: provider.yaml + {{- end}} + {{- end}} + {{- if .Values.sidecar.datasources.enabled }} + - name: sc-datasources-volume + mountPath: "/etc/grafana/provisioning/datasources" + {{- end}} + {{- if .Values.sidecar.plugins.enabled }} + - name: sc-plugins-volume + mountPath: "/etc/grafana/provisioning/plugins" + {{- end}} + {{- if .Values.sidecar.notifiers.enabled }} + - name: sc-notifiers-volume + mountPath: "/etc/grafana/provisioning/notifiers" + {{- end}} + {{- range .Values.extraSecretMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + readOnly: {{ .readOnly }} + subPath: {{ .subPath | default "" }} + {{- end }} + {{- range .Values.extraVolumeMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath | default "" }} + readOnly: {{ .readOnly }} + {{- end }} + {{- range .Values.extraEmptyDirMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + {{- end }} + ports: + - name: {{ .Values.podPortName }} + containerPort: {{ .Values.service.targetPort }} + protocol: TCP + - name: {{ .Values.gossipPortName }}-tcp + containerPort: 9094 + protocol: TCP + - name: {{ .Values.gossipPortName }}-udp + containerPort: 9094 + protocol: UDP + env: + - name: POD_IP + valueFrom: + fieldRef: + fieldPath: status.podIP + {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: GF_SECURITY_ADMIN_USER + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: GF_SECURITY_ADMIN_PASSWORD + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + {{- if .Values.plugins }} + - name: GF_INSTALL_PLUGINS + valueFrom: + configMapKeyRef: + name: {{ include "grafana.fullname" . }} + key: plugins + {{- end }} + {{- if .Values.smtp.existingSecret }} + - name: GF_SMTP_USER + valueFrom: + secretKeyRef: + name: {{ .Values.smtp.existingSecret }} + key: {{ .Values.smtp.userKey | default "user" }} + - name: GF_SMTP_PASSWORD + valueFrom: + secretKeyRef: + name: {{ .Values.smtp.existingSecret }} + key: {{ .Values.smtp.passwordKey | default "password" }} + {{- end }} + {{- if .Values.imageRenderer.enabled }} + - name: GF_RENDERING_SERVER_URL + value: http://{{ include "grafana.fullname" . }}-image-renderer.{{ include "grafana.namespace" . }}:{{ .Values.imageRenderer.service.port }}/render + - name: GF_RENDERING_CALLBACK_URL + value: {{ .Values.imageRenderer.grafanaProtocol }}://{{ include "grafana.fullname" . }}.{{ include "grafana.namespace" . }}:{{ .Values.service.port }}/{{ .Values.imageRenderer.grafanaSubPath }} + {{- end }} + - name: GF_PATHS_DATA + value: {{ (get .Values "grafana.ini").paths.data }} + - name: GF_PATHS_LOGS + value: {{ (get .Values "grafana.ini").paths.logs }} + - name: GF_PATHS_PLUGINS + value: {{ (get .Values "grafana.ini").paths.plugins }} + - name: GF_PATHS_PROVISIONING + value: {{ (get .Values "grafana.ini").paths.provisioning }} + {{- range $key, $value := .Values.envValueFrom }} + - name: {{ $key | quote }} + valueFrom: + {{- tpl (toYaml $value) $ | nindent 10 }} + {{- end }} + {{- range $key, $value := .Values.env }} + - name: "{{ tpl $key $ }}" + value: "{{ tpl (print $value) $ }}" + {{- end }} + {{- if or .Values.envFromSecret (or .Values.envRenderSecret .Values.envFromSecrets) .Values.envFromConfigMaps }} + envFrom: + {{- if .Values.envFromSecret }} + - secretRef: + name: {{ tpl .Values.envFromSecret . }} + {{- end }} + {{- if .Values.envRenderSecret }} + - secretRef: + name: {{ include "grafana.fullname" . }}-env + {{- end }} + {{- range .Values.envFromSecrets }} + - secretRef: + name: {{ tpl .name $ }} + optional: {{ .optional | default false }} + {{- if .prefix }} + prefix: {{ tpl .prefix $ }} + {{- end }} + {{- end }} + {{- range .Values.envFromConfigMaps }} + - configMapRef: + name: {{ tpl .name $ }} + optional: {{ .optional | default false }} + {{- if .prefix }} + prefix: {{ tpl .prefix $ }} + {{- end }} + {{- end }} + {{- end }} + {{- with .Values.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.lifecycleHooks }} + lifecycle: + {{- tpl (toYaml .) $root | nindent 6 }} + {{- end }} + {{- with .Values.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} +{{- with .Values.extraContainers }} + {{- tpl . $ | nindent 2 }} +{{- end }} +{{- with .Values.nodeSelector }} +nodeSelector: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.affinity }} +affinity: + {{- tpl (toYaml .) $root | nindent 2 }} +{{- end }} +{{- with .Values.topologySpreadConstraints }} +topologySpreadConstraints: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.tolerations }} +tolerations: + {{- toYaml . | nindent 2 }} +{{- end }} +volumes: + - name: config + configMap: + name: {{ include "grafana.fullname" . }} + {{- $createConfigSecret := eq (include "grafana.shouldCreateConfigSecret" .) "true" -}} + {{- if and .Values.createConfigmap $createConfigSecret }} + - name: config-secret + secret: + secretName: {{ include "grafana.fullname" . }}-config-secret + {{- end }} + {{- range .Values.extraConfigmapMounts }} + - name: {{ tpl .name $root }} + configMap: + name: {{ tpl .configMap $root }} + {{- with .items }} + items: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + {{- if .Values.dashboards }} + {{- range (keys .Values.dashboards | sortAlpha) }} + - name: dashboards-{{ . }} + configMap: + name: {{ include "grafana.fullname" $ }}-dashboards-{{ . }} + {{- end }} + {{- end }} + {{- if .Values.dashboardsConfigMaps }} + {{- range $provider, $name := .Values.dashboardsConfigMaps }} + - name: dashboards-{{ $provider }} + configMap: + name: {{ tpl $name $root }} + {{- end }} + {{- end }} + {{- if .Values.ldap.enabled }} + - name: ldap + secret: + {{- if .Values.ldap.existingSecret }} + secretName: {{ .Values.ldap.existingSecret }} + {{- else }} + secretName: {{ include "grafana.fullname" . }} + {{- end }} + items: + - key: ldap-toml + path: ldap.toml + {{- end }} + {{- if and .Values.persistence.enabled (eq .Values.persistence.type "pvc") }} + - name: storage + persistentVolumeClaim: + claimName: {{ tpl (.Values.persistence.existingClaim | default (include "grafana.fullname" .)) . }} + {{- else if and .Values.persistence.enabled (has .Values.persistence.type $sts) }} + {{/* nothing */}} + {{- else }} + - name: storage + {{- if .Values.persistence.inMemory.enabled }} + emptyDir: + medium: Memory + {{- with .Values.persistence.inMemory.sizeLimit }} + sizeLimit: {{ . }} + {{- end }} + {{- else }} + emptyDir: {} + {{- end }} + {{- end }} + {{- if .Values.sidecar.alerts.enabled }} + - name: sc-alerts-volume + emptyDir: + {{- with .Values.sidecar.alerts.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- end }} + {{- if .Values.sidecar.dashboards.enabled }} + - name: sc-dashboard-volume + emptyDir: + {{- with .Values.sidecar.dashboards.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- if .Values.sidecar.dashboards.SCProvider }} + - name: sc-dashboard-provider + configMap: + name: {{ include "grafana.fullname" . }}-config-dashboards + {{- end }} + {{- end }} + {{- if .Values.sidecar.datasources.enabled }} + - name: sc-datasources-volume + emptyDir: + {{- with .Values.sidecar.datasources.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- end }} + {{- if .Values.sidecar.plugins.enabled }} + - name: sc-plugins-volume + emptyDir: + {{- with .Values.sidecar.plugins.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- end }} + {{- if .Values.sidecar.notifiers.enabled }} + - name: sc-notifiers-volume + emptyDir: + {{- with .Values.sidecar.notifiers.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- end }} + {{- range .Values.extraSecretMounts }} + {{- if .secretName }} + - name: {{ .name }} + secret: + secretName: {{ .secretName }} + defaultMode: {{ .defaultMode }} + {{- with .items }} + items: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- else if .projected }} + - name: {{ .name }} + projected: + {{- toYaml .projected | nindent 6 }} + {{- else if .csi }} + - name: {{ .name }} + csi: + {{- toYaml .csi | nindent 6 }} + {{- end }} + {{- end }} + {{- range .Values.extraVolumes }} + - name: {{ .name }} + {{- if .existingClaim }} + persistentVolumeClaim: + claimName: {{ .existingClaim }} + {{- else if .hostPath }} + hostPath: + {{ toYaml .hostPath | nindent 6 }} + {{- else if .csi }} + csi: + {{- toYaml .csi | nindent 6 }} + {{- else if .configMap }} + configMap: + {{- toYaml .configMap | nindent 6 }} + {{- else if .emptyDir }} + emptyDir: + {{- toYaml .emptyDir | nindent 6 }} + {{- else }} + emptyDir: {} + {{- end }} + {{- end }} + {{- range .Values.extraEmptyDirMounts }} + - name: {{ .name }} + emptyDir: {} + {{- end }} + {{- with .Values.extraContainerVolumes }} + {{- tpl (toYaml .) $root | nindent 2 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/clusterrole.yaml b/observability/lgtm-distributed/charts/grafana/templates/clusterrole.yaml new file mode 100644 index 0000000..3af4b62 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/clusterrole.yaml @@ -0,0 +1,25 @@ +{{- if and .Values.rbac.create (or (not .Values.rbac.namespaced) .Values.rbac.extraClusterRoleRules) (not .Values.rbac.useExistingClusterRole) }} +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "grafana.fullname" . }}-clusterrole +{{- if or .Values.sidecar.dashboards.enabled .Values.rbac.extraClusterRoleRules .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled .Values.sidecar.alerts.enabled }} +rules: + {{- if or .Values.sidecar.dashboards.enabled .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled .Values.sidecar.alerts.enabled }} + - apiGroups: [""] # "" indicates the core API group + resources: ["configmaps", "secrets"] + verbs: ["get", "watch", "list"] + {{- end}} + {{- with .Values.rbac.extraClusterRoleRules }} + {{- toYaml . | nindent 2 }} + {{- end}} +{{- else }} +rules: [] +{{- end}} +{{- end}} diff --git a/observability/lgtm-distributed/charts/grafana/templates/clusterrolebinding.yaml b/observability/lgtm-distributed/charts/grafana/templates/clusterrolebinding.yaml new file mode 100644 index 0000000..bda9431 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/clusterrolebinding.yaml @@ -0,0 +1,24 @@ +{{- if and .Values.rbac.create (or (not .Values.rbac.namespaced) .Values.rbac.extraClusterRoleRules) }} +kind: ClusterRoleBinding +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ include "grafana.fullname" . }}-clusterrolebinding + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +subjects: + - kind: ServiceAccount + name: {{ include "grafana.serviceAccountName" . }} + namespace: {{ include "grafana.namespace" . }} +roleRef: + kind: ClusterRole + {{- if .Values.rbac.useExistingClusterRole }} + name: {{ .Values.rbac.useExistingClusterRole }} + {{- else }} + name: {{ include "grafana.fullname" . }}-clusterrole + {{- end }} + apiGroup: rbac.authorization.k8s.io +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/configSecret.yaml b/observability/lgtm-distributed/charts/grafana/templates/configSecret.yaml new file mode 100644 index 0000000..55574b9 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/configSecret.yaml @@ -0,0 +1,43 @@ +{{- $createConfigSecret := eq (include "grafana.shouldCreateConfigSecret" .) "true" -}} +{{- if and .Values.createConfigmap $createConfigSecret }} +{{- $files := .Files }} +{{- $root := . -}} +apiVersion: v1 +kind: Secret +metadata: + name: "{{ include "grafana.fullname" . }}-config-secret" + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +data: +{{- range $key, $value := .Values.alerting }} + {{- if (hasKey $value "secretFile") }} + {{- $key | nindent 2 }}: + {{- toYaml ( $files.Get $value.secretFile ) | b64enc | nindent 4}} + {{/* as of https://helm.sh/docs/chart_template_guide/accessing_files/ this will only work if you fork this chart and add files to it*/}} + {{- end }} +{{- end }} +stringData: +{{- range $key, $value := .Values.datasources }} +{{- if (hasKey $value "secret") }} +{{- $key | nindent 2 }}: | + {{- tpl (toYaml $value.secret | nindent 4) $root }} +{{- end }} +{{- end }} +{{- range $key, $value := .Values.notifiers }} +{{- if (hasKey $value "secret") }} +{{- $key | nindent 2 }}: | + {{- tpl (toYaml $value.secret | nindent 4) $root }} +{{- end }} +{{- end }} +{{- range $key, $value := .Values.alerting }} +{{ if (hasKey $value "secret") }} + {{- $key | nindent 2 }}: | + {{- tpl (toYaml $value.secret | nindent 4) $root }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/configmap-dashboard-provider.yaml b/observability/lgtm-distributed/charts/grafana/templates/configmap-dashboard-provider.yaml new file mode 100644 index 0000000..b412c4d --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/configmap-dashboard-provider.yaml @@ -0,0 +1,15 @@ +{{- if and .Values.sidecar.dashboards.enabled .Values.sidecar.dashboards.SCProvider }} +apiVersion: v1 +kind: ConfigMap +metadata: + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "grafana.fullname" . }}-config-dashboards + namespace: {{ include "grafana.namespace" . }} +data: + {{- include "grafana.configDashboardProviderData" . | nindent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/configmap.yaml b/observability/lgtm-distributed/charts/grafana/templates/configmap.yaml new file mode 100644 index 0000000..7d7428b --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/configmap.yaml @@ -0,0 +1,15 @@ +{{- if .Values.createConfigmap }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +data: + {{- include "grafana.configData" . | nindent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/dashboards-json-configmap.yaml b/observability/lgtm-distributed/charts/grafana/templates/dashboards-json-configmap.yaml new file mode 100644 index 0000000..b96ce72 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/dashboards-json-configmap.yaml @@ -0,0 +1,38 @@ +{{- if .Values.dashboards }} +{{ $files := .Files }} +{{- range $provider, $dashboards := .Values.dashboards }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "grafana.fullname" $ }}-dashboards-{{ $provider }} + namespace: {{ include "grafana.namespace" $ }} + labels: + {{- include "grafana.labels" $ | nindent 4 }} + dashboard-provider: {{ $provider }} + {{- if $.Values.sidecar.dashboards.enabled }} + {{ $.Values.sidecar.dashboards.label }}: {{ $.Values.sidecar.dashboards.labelValue | quote }} + {{- end }} +{{- if $dashboards }} +data: +{{- $dashboardFound := false }} +{{- range $key, $value := $dashboards }} +{{- if (or (hasKey $value "json") (hasKey $value "file")) }} +{{- $dashboardFound = true }} + {{- print $key | nindent 2 }}.json: + {{- if hasKey $value "json" }} + |- + {{- $value.json | nindent 6 }} + {{- end }} + {{- if hasKey $value "file" }} + {{- toYaml ( $files.Get $value.file ) | nindent 4}} + {{- end }} +{{- end }} +{{- end }} +{{- if not $dashboardFound }} + {} +{{- end }} +{{- end }} +--- +{{- end }} + +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/deployment.yaml b/observability/lgtm-distributed/charts/grafana/templates/deployment.yaml new file mode 100644 index 0000000..46c016f --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/deployment.yaml @@ -0,0 +1,53 @@ +{{- if (and (not .Values.useStatefulSet) (or (not .Values.persistence.enabled) (eq .Values.persistence.type "pvc"))) }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if and (not .Values.autoscaling.enabled) (.Values.replicas) }} + replicas: {{ .Values.replicas }} + {{- end }} + revisionHistoryLimit: {{ .Values.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} + {{- with .Values.deploymentStrategy }} + strategy: + {{- toYaml . | trim | nindent 4 }} + {{- end }} + template: + metadata: + labels: + {{- include "grafana.selectorLabels" . | nindent 8 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include "grafana.configData" . | sha256sum }} + {{- if .Values.dashboards }} + checksum/dashboards-json-config: {{ include (print $.Template.BasePath "/dashboards-json-configmap.yaml") . | sha256sum }} + {{- end }} + checksum/sc-dashboard-provider-config: {{ include "grafana.configDashboardProviderData" . | sha256sum }} + {{- if and (or (and (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD)) (and .Values.ldap.enabled (not .Values.ldap.existingSecret))) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + checksum/secret: {{ include "grafana.secretsData" . | sha256sum }} + {{- end }} + {{- if .Values.envRenderSecret }} + checksum/secret-env: {{ tpl (toYaml .Values.envRenderSecret) . | sha256sum }} + {{- end }} + kubectl.kubernetes.io/default-container: {{ .Chart.Name }} + {{- with .Values.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- include "grafana.pod" . | nindent 6 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/extra-manifests.yaml b/observability/lgtm-distributed/charts/grafana/templates/extra-manifests.yaml new file mode 100644 index 0000000..a9bb3b6 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/extra-manifests.yaml @@ -0,0 +1,4 @@ +{{ range .Values.extraObjects }} +--- +{{ tpl (toYaml .) $ }} +{{ end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/headless-service.yaml b/observability/lgtm-distributed/charts/grafana/templates/headless-service.yaml new file mode 100644 index 0000000..3028589 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/headless-service.yaml @@ -0,0 +1,22 @@ +{{- $sts := list "sts" "StatefulSet" "statefulset" -}} +{{- if or .Values.headlessService (and .Values.persistence.enabled (not .Values.persistence.existingClaim) (has .Values.persistence.type $sts)) }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "grafana.fullname" . }}-headless + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + clusterIP: None + selector: + {{- include "grafana.selectorLabels" . | nindent 4 }} + type: ClusterIP + ports: + - name: {{ .Values.gossipPortName }}-tcp + port: 9094 +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/hpa.yaml b/observability/lgtm-distributed/charts/grafana/templates/hpa.yaml new file mode 100644 index 0000000..46bbcb4 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/hpa.yaml @@ -0,0 +1,52 @@ +{{- $sts := list "sts" "StatefulSet" "statefulset" -}} +{{- if .Values.autoscaling.enabled }} +apiVersion: {{ include "grafana.hpa.apiVersion" . }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + app.kubernetes.io/name: {{ include "grafana.name" . }} + helm.sh/chart: {{ include "grafana.chart" . }} + app.kubernetes.io/managed-by: {{ .Release.Service }} + app.kubernetes.io/instance: {{ .Release.Name }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + {{- if has .Values.persistence.type $sts }} + kind: StatefulSet + {{- else }} + kind: Deployment + {{- end }} + name: {{ include "grafana.fullname" . }} + minReplicas: {{ .Values.autoscaling.minReplicas }} + maxReplicas: {{ .Values.autoscaling.maxReplicas }} + metrics: + {{- if .Values.autoscaling.targetMemory }} + - type: Resource + resource: + name: memory + {{- if eq (include "grafana.hpa.apiVersion" .) "autoscaling/v2beta1" }} + targetAverageUtilization: {{ .Values.autoscaling.targetMemory }} + {{- else }} + target: + type: Utilization + averageUtilization: {{ .Values.autoscaling.targetMemory }} + {{- end }} + {{- end }} + {{- if .Values.autoscaling.targetCPU }} + - type: Resource + resource: + name: cpu + {{- if eq (include "grafana.hpa.apiVersion" .) "autoscaling/v2beta1" }} + targetAverageUtilization: {{ .Values.autoscaling.targetCPU }} + {{- else }} + target: + type: Utilization + averageUtilization: {{ .Values.autoscaling.targetCPU }} + {{- end }} + {{- end }} + {{- if .Values.autoscaling.behavior }} + behavior: {{ toYaml .Values.autoscaling.behavior | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/image-renderer-deployment.yaml b/observability/lgtm-distributed/charts/grafana/templates/image-renderer-deployment.yaml new file mode 100644 index 0000000..ea97969 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/image-renderer-deployment.yaml @@ -0,0 +1,131 @@ +{{ if .Values.imageRenderer.enabled }} +{{- $root := . -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "grafana.fullname" . }}-image-renderer + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.imageRenderer.labels" . | nindent 4 }} + {{- with .Values.imageRenderer.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.imageRenderer.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if and (not .Values.imageRenderer.autoscaling.enabled) (.Values.imageRenderer.replicas) }} + replicas: {{ .Values.imageRenderer.replicas }} + {{- end }} + revisionHistoryLimit: {{ .Values.imageRenderer.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 6 }} + + {{- with .Values.imageRenderer.deploymentStrategy }} + strategy: + {{- toYaml . | trim | nindent 4 }} + {{- end }} + template: + metadata: + labels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 8 }} + {{- with .Values.imageRenderer.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + {{- with .Values.imageRenderer.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- with .Values.imageRenderer.schedulerName }} + schedulerName: "{{ . }}" + {{- end }} + {{- with .Values.imageRenderer.serviceAccountName }} + serviceAccountName: "{{ . }}" + {{- end }} + {{- with .Values.imageRenderer.securityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.imageRenderer.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.imageRenderer.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.imageRenderer.image.pullSecrets }} + imagePullSecrets: + {{- range . }} + - name: {{ tpl . $root }} + {{- end}} + {{- end }} + containers: + - name: {{ .Chart.Name }}-image-renderer + {{- $registry := .Values.global.imageRegistry | default .Values.imageRenderer.image.registry -}} + {{- if .Values.imageRenderer.image.sha }} + image: "{{ $registry }}/{{ .Values.imageRenderer.image.repository }}:{{ .Values.imageRenderer.image.tag }}@sha256:{{ .Values.imageRenderer.image.sha }}" + {{- else }} + image: "{{ $registry }}/{{ .Values.imageRenderer.image.repository }}:{{ .Values.imageRenderer.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.imageRenderer.image.pullPolicy }} + {{- if .Values.imageRenderer.command }} + command: + {{- range .Values.imageRenderer.command }} + - {{ . }} + {{- end }} + {{- end}} + ports: + - name: {{ .Values.imageRenderer.service.portName }} + containerPort: {{ .Values.imageRenderer.service.targetPort }} + protocol: TCP + livenessProbe: + httpGet: + path: / + port: {{ .Values.imageRenderer.service.portName }} + env: + - name: HTTP_PORT + value: {{ .Values.imageRenderer.service.targetPort | quote }} + {{- if .Values.imageRenderer.serviceMonitor.enabled }} + - name: ENABLE_METRICS + value: "true" + {{- end }} + {{- range $key, $value := .Values.imageRenderer.envValueFrom }} + - name: {{ $key | quote }} + valueFrom: + {{- tpl (toYaml $value) $ | nindent 16 }} + {{- end }} + {{- range $key, $value := .Values.imageRenderer.env }} + - name: {{ $key | quote }} + value: {{ $value | quote }} + {{- end }} + {{- with .Values.imageRenderer.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - mountPath: /tmp + name: image-renderer-tmpfs + {{- with .Values.imageRenderer.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.imageRenderer.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.imageRenderer.affinity }} + affinity: + {{- tpl (toYaml .) $root | nindent 8 }} + {{- end }} + {{- with .Values.imageRenderer.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: image-renderer-tmpfs + emptyDir: {} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/image-renderer-hpa.yaml b/observability/lgtm-distributed/charts/grafana/templates/image-renderer-hpa.yaml new file mode 100644 index 0000000..b0f0059 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/image-renderer-hpa.yaml @@ -0,0 +1,47 @@ +{{- if and .Values.imageRenderer.enabled .Values.imageRenderer.autoscaling.enabled }} +apiVersion: {{ include "grafana.hpa.apiVersion" . }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "grafana.fullname" . }}-image-renderer + namespace: {{ include "grafana.namespace" . }} + labels: + app.kubernetes.io/name: {{ include "grafana.name" . }}-image-renderer + helm.sh/chart: {{ include "grafana.chart" . }} + app.kubernetes.io/managed-by: {{ .Release.Service }} + app.kubernetes.io/instance: {{ .Release.Name }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "grafana.fullname" . }}-image-renderer + minReplicas: {{ .Values.imageRenderer.autoscaling.minReplicas }} + maxReplicas: {{ .Values.imageRenderer.autoscaling.maxReplicas }} + metrics: + {{- if .Values.imageRenderer.autoscaling.targetMemory }} + - type: Resource + resource: + name: memory + {{- if eq (include "grafana.hpa.apiVersion" .) "autoscaling/v2beta1" }} + targetAverageUtilization: {{ .Values.imageRenderer.autoscaling.targetMemory }} + {{- else }} + target: + type: Utilization + averageUtilization: {{ .Values.imageRenderer.autoscaling.targetMemory }} + {{- end }} + {{- end }} + {{- if .Values.imageRenderer.autoscaling.targetCPU }} + - type: Resource + resource: + name: cpu + {{- if eq (include "grafana.hpa.apiVersion" .) "autoscaling/v2beta1" }} + targetAverageUtilization: {{ .Values.imageRenderer.autoscaling.targetCPU }} + {{- else }} + target: + type: Utilization + averageUtilization: {{ .Values.imageRenderer.autoscaling.targetCPU }} + {{- end }} + {{- end }} + {{- if .Values.imageRenderer.autoscaling.behavior }} + behavior: {{ toYaml .Values.imageRenderer.autoscaling.behavior | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/image-renderer-network-policy.yaml b/observability/lgtm-distributed/charts/grafana/templates/image-renderer-network-policy.yaml new file mode 100644 index 0000000..d1a0eb3 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/image-renderer-network-policy.yaml @@ -0,0 +1,79 @@ +{{- if and .Values.imageRenderer.enabled .Values.imageRenderer.networkPolicy.limitIngress }} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "grafana.fullname" . }}-image-renderer-ingress + namespace: {{ include "grafana.namespace" . }} + annotations: + comment: Limit image-renderer ingress traffic from grafana +spec: + podSelector: + matchLabels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 6 }} + {{- with .Values.imageRenderer.podLabels }} + {{- toYaml . | nindent 6 }} + {{- end }} + + policyTypes: + - Ingress + ingress: + - ports: + - port: {{ .Values.imageRenderer.service.targetPort }} + protocol: TCP + from: + - namespaceSelector: + matchLabels: + kubernetes.io/metadata.name: {{ include "grafana.namespace" . }} + podSelector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 14 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 14 }} + {{- end }} + {{- with .Values.imageRenderer.networkPolicy.extraIngressSelectors -}} + {{ toYaml . | nindent 8 }} + {{- end }} +{{- end }} + +{{- if and .Values.imageRenderer.enabled .Values.imageRenderer.networkPolicy.limitEgress }} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "grafana.fullname" . }}-image-renderer-egress + namespace: {{ include "grafana.namespace" . }} + annotations: + comment: Limit image-renderer egress traffic to grafana +spec: + podSelector: + matchLabels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 6 }} + {{- with .Values.imageRenderer.podLabels }} + {{- toYaml . | nindent 6 }} + {{- end }} + + policyTypes: + - Egress + egress: + # allow dns resolution + - ports: + - port: 53 + protocol: UDP + - port: 53 + protocol: TCP + # talk only to grafana + - ports: + - port: {{ .Values.service.targetPort }} + protocol: TCP + to: + - namespaceSelector: + matchLabels: + name: {{ include "grafana.namespace" . }} + podSelector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 14 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 14 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/image-renderer-service.yaml b/observability/lgtm-distributed/charts/grafana/templates/image-renderer-service.yaml new file mode 100644 index 0000000..f8da127 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/image-renderer-service.yaml @@ -0,0 +1,31 @@ +{{- if and .Values.imageRenderer.enabled .Values.imageRenderer.service.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "grafana.fullname" . }}-image-renderer + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.imageRenderer.labels" . | nindent 4 }} + {{- with .Values.imageRenderer.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.imageRenderer.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + {{- with .Values.imageRenderer.service.clusterIP }} + clusterIP: {{ . }} + {{- end }} + ports: + - name: {{ .Values.imageRenderer.service.portName }} + port: {{ .Values.imageRenderer.service.port }} + protocol: TCP + targetPort: {{ .Values.imageRenderer.service.targetPort }} + {{- with .Values.imageRenderer.appProtocol }} + appProtocol: {{ . }} + {{- end }} + selector: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/image-renderer-servicemonitor.yaml b/observability/lgtm-distributed/charts/grafana/templates/image-renderer-servicemonitor.yaml new file mode 100644 index 0000000..5d9f09d --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/image-renderer-servicemonitor.yaml @@ -0,0 +1,48 @@ +{{- if .Values.imageRenderer.serviceMonitor.enabled }} +--- +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "grafana.fullname" . }}-image-renderer + {{- if .Values.imageRenderer.serviceMonitor.namespace }} + namespace: {{ tpl .Values.imageRenderer.serviceMonitor.namespace . }} + {{- else }} + namespace: {{ include "grafana.namespace" . }} + {{- end }} + labels: + {{- include "grafana.imageRenderer.labels" . | nindent 4 }} + {{- with .Values.imageRenderer.serviceMonitor.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + endpoints: + - port: {{ .Values.imageRenderer.service.portName }} + {{- with .Values.imageRenderer.serviceMonitor.interval }} + interval: {{ . }} + {{- end }} + {{- with .Values.imageRenderer.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + honorLabels: true + path: {{ .Values.imageRenderer.serviceMonitor.path }} + scheme: {{ .Values.imageRenderer.serviceMonitor.scheme }} + {{- with .Values.imageRenderer.serviceMonitor.tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.imageRenderer.serviceMonitor.relabelings }} + relabelings: + {{- toYaml . | nindent 6 }} + {{- end }} + jobLabel: "{{ .Release.Name }}-image-renderer" + selector: + matchLabels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 6 }} + namespaceSelector: + matchNames: + - {{ include "grafana.namespace" . }} + {{- with .Values.imageRenderer.serviceMonitor.targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/ingress.yaml b/observability/lgtm-distributed/charts/grafana/templates/ingress.yaml new file mode 100644 index 0000000..b2ffd81 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/ingress.yaml @@ -0,0 +1,78 @@ +{{- if .Values.ingress.enabled -}} +{{- $ingressApiIsStable := eq (include "grafana.ingress.isStable" .) "true" -}} +{{- $ingressSupportsIngressClassName := eq (include "grafana.ingress.supportsIngressClassName" .) "true" -}} +{{- $ingressSupportsPathType := eq (include "grafana.ingress.supportsPathType" .) "true" -}} +{{- $fullName := include "grafana.fullname" . -}} +{{- $servicePort := .Values.service.port -}} +{{- $ingressPath := .Values.ingress.path -}} +{{- $ingressPathType := .Values.ingress.pathType -}} +{{- $extraPaths := .Values.ingress.extraPaths -}} +apiVersion: {{ include "grafana.ingress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ $fullName }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.ingress.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.ingress.annotations }} + annotations: + {{- range $key, $value := . }} + {{ $key }}: {{ tpl $value $ | quote }} + {{- end }} + {{- end }} +spec: + {{- if and $ingressSupportsIngressClassName .Values.ingress.ingressClassName }} + ingressClassName: {{ .Values.ingress.ingressClassName }} + {{- end -}} + {{- with .Values.ingress.tls }} + tls: + {{- tpl (toYaml .) $ | nindent 4 }} + {{- end }} + rules: + {{- if .Values.ingress.hosts }} + {{- range .Values.ingress.hosts }} + - host: {{ tpl . $ | quote }} + http: + paths: + {{- with $extraPaths }} + {{- toYaml . | nindent 10 }} + {{- end }} + - path: {{ $ingressPath }} + {{- if $ingressSupportsPathType }} + pathType: {{ $ingressPathType }} + {{- end }} + backend: + {{- if $ingressApiIsStable }} + service: + name: {{ $fullName }} + port: + number: {{ $servicePort }} + {{- else }} + serviceName: {{ $fullName }} + servicePort: {{ $servicePort }} + {{- end }} + {{- end }} + {{- else }} + - http: + paths: + - backend: + {{- if $ingressApiIsStable }} + service: + name: {{ $fullName }} + port: + number: {{ $servicePort }} + {{- else }} + serviceName: {{ $fullName }} + servicePort: {{ $servicePort }} + {{- end }} + {{- with $ingressPath }} + path: {{ . }} + {{- end }} + {{- if $ingressSupportsPathType }} + pathType: {{ $ingressPathType }} + {{- end }} + {{- end -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/networkpolicy.yaml b/observability/lgtm-distributed/charts/grafana/templates/networkpolicy.yaml new file mode 100644 index 0000000..4cd3ed6 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/networkpolicy.yaml @@ -0,0 +1,61 @@ +{{- if .Values.networkPolicy.enabled }} +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + policyTypes: + {{- if .Values.networkPolicy.ingress }} + - Ingress + {{- end }} + {{- if .Values.networkPolicy.egress.enabled }} + - Egress + {{- end }} + podSelector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} + + {{- if .Values.networkPolicy.egress.enabled }} + egress: + {{- if not .Values.networkPolicy.egress.blockDNSResolution }} + - ports: + - port: 53 + protocol: UDP + {{- end }} + - ports: + {{ .Values.networkPolicy.egress.ports | toJson }} + {{- with .Values.networkPolicy.egress.to }} + to: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.networkPolicy.ingress }} + ingress: + - ports: + - port: {{ .Values.service.targetPort }} + {{- if not .Values.networkPolicy.allowExternal }} + from: + - podSelector: + matchLabels: + {{ include "grafana.fullname" . }}-client: "true" + {{- with .Values.networkPolicy.explicitNamespacesSelector }} + - namespaceSelector: + {{- toYaml . | nindent 12 }} + {{- end }} + - podSelector: + matchLabels: + {{- include "grafana.labels" . | nindent 14 }} + role: read + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/poddisruptionbudget.yaml b/observability/lgtm-distributed/charts/grafana/templates/poddisruptionbudget.yaml new file mode 100644 index 0000000..0525121 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/poddisruptionbudget.yaml @@ -0,0 +1,22 @@ +{{- if .Values.podDisruptionBudget }} +apiVersion: {{ include "grafana.podDisruptionBudget.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .Values.podDisruptionBudget.minAvailable }} + minAvailable: {{ . }} + {{- end }} + {{- with .Values.podDisruptionBudget.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} + selector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/podsecuritypolicy.yaml b/observability/lgtm-distributed/charts/grafana/templates/podsecuritypolicy.yaml new file mode 100644 index 0000000..eed7af9 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/podsecuritypolicy.yaml @@ -0,0 +1,49 @@ +{{- if and .Values.rbac.pspEnabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "grafana.fullname" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + annotations: + seccomp.security.alpha.kubernetes.io/allowedProfileNames: 'docker/default,runtime/default' + seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default' + {{- if .Values.rbac.pspUseAppArmor }} + apparmor.security.beta.kubernetes.io/allowedProfileNames: 'runtime/default' + apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default' + {{- end }} +spec: + privileged: false + allowPrivilegeEscalation: false + requiredDropCapabilities: + # Default set from Docker, with DAC_OVERRIDE and CHOWN + - ALL + volumes: + - 'configMap' + - 'emptyDir' + - 'projected' + - 'csi' + - 'secret' + - 'downwardAPI' + - 'persistentVolumeClaim' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + rule: 'RunAsAny' + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 1 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 1 + max: 65535 + readOnlyRootFilesystem: false +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/pvc.yaml b/observability/lgtm-distributed/charts/grafana/templates/pvc.yaml new file mode 100644 index 0000000..c0edad2 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/pvc.yaml @@ -0,0 +1,39 @@ +{{- if and .Values.persistence.enabled (not .Values.persistence.existingClaim) (eq .Values.persistence.type "pvc")}} +apiVersion: v1 +kind: PersistentVolumeClaim +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.persistence.extraPvcLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.persistence.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.persistence.finalizers }} + finalizers: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + accessModes: + {{- range .Values.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + resources: + requests: + storage: {{ .Values.persistence.size | quote }} + {{- if (lookup "v1" "PersistentVolumeClaim" (include "grafana.namespace" .) (include "grafana.fullname" .)) }} + volumeName: {{ (lookup "v1" "PersistentVolumeClaim" (include "grafana.namespace" .) (include "grafana.fullname" .)).spec.volumeName }} + {{- end }} + {{- with .Values.persistence.storageClassName }} + storageClassName: {{ . }} + {{- end }} + {{- with .Values.persistence.selectorLabels }} + selector: + matchLabels: + {{- toYaml . | nindent 6 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/role.yaml b/observability/lgtm-distributed/charts/grafana/templates/role.yaml new file mode 100644 index 0000000..4b5edd9 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/role.yaml @@ -0,0 +1,32 @@ +{{- if and .Values.rbac.create (not .Values.rbac.useExistingRole) -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- if or .Values.rbac.pspEnabled (and .Values.rbac.namespaced (or .Values.sidecar.dashboards.enabled .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled .Values.rbac.extraRoleRules)) }} +rules: + {{- if and .Values.rbac.pspEnabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} + - apiGroups: ['extensions'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: [{{ include "grafana.fullname" . }}] + {{- end }} + {{- if and .Values.rbac.namespaced (or .Values.sidecar.dashboards.enabled .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled) }} + - apiGroups: [""] # "" indicates the core API group + resources: ["configmaps", "secrets"] + verbs: ["get", "watch", "list"] + {{- end }} + {{- with .Values.rbac.extraRoleRules }} + {{- toYaml . | nindent 2 }} + {{- end}} +{{- else }} +rules: [] +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/grafana/templates/rolebinding.yaml new file mode 100644 index 0000000..58f77c6 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/rolebinding.yaml @@ -0,0 +1,25 @@ +{{- if .Values.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + {{- if .Values.rbac.useExistingRole }} + name: {{ .Values.rbac.useExistingRole }} + {{- else }} + name: {{ include "grafana.fullname" . }} + {{- end }} +subjects: +- kind: ServiceAccount + name: {{ include "grafana.serviceAccountName" . }} + namespace: {{ include "grafana.namespace" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/secret-env.yaml b/observability/lgtm-distributed/charts/grafana/templates/secret-env.yaml new file mode 100644 index 0000000..eb14aac --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/secret-env.yaml @@ -0,0 +1,14 @@ +{{- if .Values.envRenderSecret }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "grafana.fullname" . }}-env + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +type: Opaque +data: +{{- range $key, $val := .Values.envRenderSecret }} + {{ $key }}: {{ tpl ($val | toString) $ | b64enc | quote }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/secret.yaml b/observability/lgtm-distributed/charts/grafana/templates/secret.yaml new file mode 100644 index 0000000..fd2ca50 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/secret.yaml @@ -0,0 +1,16 @@ +{{- if or (and (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION)) (and .Values.ldap.enabled (not .Values.ldap.existingSecret)) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +type: Opaque +data: + {{- include "grafana.secretsData" . | nindent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/service.yaml b/observability/lgtm-distributed/charts/grafana/templates/service.yaml new file mode 100644 index 0000000..e9396a1 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/service.yaml @@ -0,0 +1,61 @@ +{{- if .Values.service.enabled }} +{{- $root := . }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.service.annotations }} + annotations: + {{- tpl (toYaml . | nindent 4) $root }} + {{- end }} +spec: + {{- if (or (eq .Values.service.type "ClusterIP") (empty .Values.service.type)) }} + type: ClusterIP + {{- with .Values.service.clusterIP }} + clusterIP: {{ . }} + {{- end }} + {{- else if eq .Values.service.type "LoadBalancer" }} + type: LoadBalancer + {{- with .Values.service.loadBalancerIP }} + loadBalancerIP: {{ . }} + {{- end }} + {{- with .Values.service.loadBalancerClass }} + loadBalancerClass: {{ . }} + {{- end }} + {{- with .Values.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- else }} + type: {{ .Values.service.type }} + {{- end }} + {{- with .Values.service.externalIPs }} + externalIPs: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.service.externalTrafficPolicy }} + externalTrafficPolicy: {{ . }} + {{- end }} + ports: + - name: {{ .Values.service.portName }} + port: {{ .Values.service.port }} + protocol: TCP + targetPort: {{ .Values.service.targetPort }} + {{- with .Values.service.appProtocol }} + appProtocol: {{ . }} + {{- end }} + {{- if (and (eq .Values.service.type "NodePort") (not (empty .Values.service.nodePort))) }} + nodePort: {{ .Values.service.nodePort }} + {{- end }} + {{- with .Values.extraExposePorts }} + {{- tpl (toYaml . | nindent 4) $root }} + {{- end }} + selector: + {{- include "grafana.selectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/grafana/templates/serviceaccount.yaml new file mode 100644 index 0000000..ffca071 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/serviceaccount.yaml @@ -0,0 +1,17 @@ +{{- if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +automountServiceAccountToken: {{ .Values.serviceAccount.autoMount | default .Values.serviceAccount.automountServiceAccountToken }} +metadata: + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.serviceAccount.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.serviceAccount.annotations }} + annotations: + {{- tpl (toYaml . | nindent 4) $ }} + {{- end }} + name: {{ include "grafana.serviceAccountName" . }} + namespace: {{ include "grafana.namespace" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/grafana/templates/servicemonitor.yaml new file mode 100644 index 0000000..0359013 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/servicemonitor.yaml @@ -0,0 +1,52 @@ +{{- if .Values.serviceMonitor.enabled }} +--- +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "grafana.fullname" . }} + {{- if .Values.serviceMonitor.namespace }} + namespace: {{ tpl .Values.serviceMonitor.namespace . }} + {{- else }} + namespace: {{ include "grafana.namespace" . }} + {{- end }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.serviceMonitor.labels }} + {{- tpl (toYaml . | nindent 4) $ }} + {{- end }} +spec: + endpoints: + - port: {{ .Values.service.portName }} + {{- with .Values.serviceMonitor.interval }} + interval: {{ . }} + {{- end }} + {{- with .Values.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + honorLabels: true + path: {{ .Values.serviceMonitor.path }} + scheme: {{ .Values.serviceMonitor.scheme }} + {{- with .Values.serviceMonitor.tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.serviceMonitor.relabelings }} + relabelings: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.serviceMonitor.metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 6 }} + {{- end }} + jobLabel: "{{ .Release.Name }}" + selector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} + namespaceSelector: + matchNames: + - {{ include "grafana.namespace" . }} + {{- with .Values.serviceMonitor.targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/statefulset.yaml b/observability/lgtm-distributed/charts/grafana/templates/statefulset.yaml new file mode 100644 index 0000000..e6c944a --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/statefulset.yaml @@ -0,0 +1,56 @@ +{{- $sts := list "sts" "StatefulSet" "statefulset" -}} +{{- if (or (.Values.useStatefulSet) (and .Values.persistence.enabled (not .Values.persistence.existingClaim) (has .Values.persistence.type $sts)))}} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.replicas }} + selector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} + serviceName: {{ include "grafana.fullname" . }}-headless + template: + metadata: + labels: + {{- include "grafana.selectorLabels" . | nindent 8 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + checksum/dashboards-json-config: {{ include (print $.Template.BasePath "/dashboards-json-configmap.yaml") . | sha256sum }} + checksum/sc-dashboard-provider-config: {{ include (print $.Template.BasePath "/configmap-dashboard-provider.yaml") . | sha256sum }} + {{- if and (or (and (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD)) (and .Values.ldap.enabled (not .Values.ldap.existingSecret))) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }} + {{- end }} + kubectl.kubernetes.io/default-container: {{ .Chart.Name }} + {{- with .Values.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- include "grafana.pod" . | nindent 6 }} + {{- if .Values.persistence.enabled}} + volumeClaimTemplates: + - metadata: + name: storage + spec: + accessModes: {{ .Values.persistence.accessModes }} + storageClassName: {{ .Values.persistence.storageClassName }} + resources: + requests: + storage: {{ .Values.persistence.size }} + {{- with .Values.persistence.selectorLabels }} + selector: + matchLabels: + {{- toYaml . | nindent 10 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/tests/test-configmap.yaml b/observability/lgtm-distributed/charts/grafana/templates/tests/test-configmap.yaml new file mode 100644 index 0000000..01c96c9 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/tests/test-configmap.yaml @@ -0,0 +1,20 @@ +{{- if .Values.testFramework.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "grafana.fullname" . }}-test + namespace: {{ include "grafana.namespace" . }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" + labels: + {{- include "grafana.labels" . | nindent 4 }} +data: + run.sh: |- + @test "Test Health" { + url="http://{{ include "grafana.fullname" . }}/api/health" + + code=$(wget --server-response --spider --timeout 90 --tries 10 ${url} 2>&1 | awk '/^ HTTP/{print $2}') + [ "$code" == "200" ] + } +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/tests/test-podsecuritypolicy.yaml b/observability/lgtm-distributed/charts/grafana/templates/tests/test-podsecuritypolicy.yaml new file mode 100644 index 0000000..1821772 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/tests/test-podsecuritypolicy.yaml @@ -0,0 +1,32 @@ +{{- if and (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") .Values.testFramework.enabled .Values.rbac.pspEnabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "grafana.fullname" . }}-test + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" + labels: + {{- include "grafana.labels" . | nindent 4 }} +spec: + allowPrivilegeEscalation: true + privileged: false + hostNetwork: false + hostIPC: false + hostPID: false + fsGroup: + rule: RunAsAny + seLinux: + rule: RunAsAny + supplementalGroups: + rule: RunAsAny + runAsUser: + rule: RunAsAny + volumes: + - configMap + - downwardAPI + - emptyDir + - projected + - csi + - secret +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/tests/test-role.yaml b/observability/lgtm-distributed/charts/grafana/templates/tests/test-role.yaml new file mode 100644 index 0000000..cb4c782 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/tests/test-role.yaml @@ -0,0 +1,17 @@ +{{- if and (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") .Values.testFramework.enabled .Values.rbac.pspEnabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ include "grafana.fullname" . }}-test + namespace: {{ include "grafana.namespace" . }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" + labels: + {{- include "grafana.labels" . | nindent 4 }} +rules: + - apiGroups: ['policy'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: [{{ include "grafana.fullname" . }}-test] +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/tests/test-rolebinding.yaml b/observability/lgtm-distributed/charts/grafana/templates/tests/test-rolebinding.yaml new file mode 100644 index 0000000..f40d791 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/tests/test-rolebinding.yaml @@ -0,0 +1,20 @@ +{{- if and (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") .Values.testFramework.enabled .Values.rbac.pspEnabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "grafana.fullname" . }}-test + namespace: {{ include "grafana.namespace" . }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" + labels: + {{- include "grafana.labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "grafana.fullname" . }}-test +subjects: + - kind: ServiceAccount + name: {{ include "grafana.serviceAccountNameTest" . }} + namespace: {{ include "grafana.namespace" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/tests/test-serviceaccount.yaml b/observability/lgtm-distributed/charts/grafana/templates/tests/test-serviceaccount.yaml new file mode 100644 index 0000000..38fba35 --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/tests/test-serviceaccount.yaml @@ -0,0 +1,12 @@ +{{- if and .Values.testFramework.enabled .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + {{- include "grafana.labels" . | nindent 4 }} + name: {{ include "grafana.serviceAccountNameTest" . }} + namespace: {{ include "grafana.namespace" . }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/templates/tests/test.yaml b/observability/lgtm-distributed/charts/grafana/templates/tests/test.yaml new file mode 100644 index 0000000..9e88afc --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/templates/tests/test.yaml @@ -0,0 +1,53 @@ +{{- if .Values.testFramework.enabled }} +{{- $root := . }} +apiVersion: v1 +kind: Pod +metadata: + name: {{ include "grafana.fullname" . }}-test + labels: + {{- include "grafana.labels" . | nindent 4 }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" + namespace: {{ include "grafana.namespace" . }} +spec: + serviceAccountName: {{ include "grafana.serviceAccountNameTest" . }} + {{- with .Values.testFramework.securityContext }} + securityContext: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- if or .Values.image.pullSecrets .Values.global.imagePullSecrets }} + imagePullSecrets: + {{- include "grafana.imagePullSecrets" (dict "root" $root "imagePullSecrets" .Values.image.pullSecrets) | nindent 4 }} + {{- end }} + {{- with .Values.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.affinity }} + affinity: + {{- tpl (toYaml .) $root | nindent 4 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: + {{- toYaml . | nindent 4 }} + {{- end }} + containers: + - name: {{ .Release.Name }}-test + image: "{{ .Values.global.imageRegistry | default .Values.testFramework.image.registry }}/{{ .Values.testFramework.image.repository }}:{{ .Values.testFramework.image.tag }}" + imagePullPolicy: "{{ .Values.testFramework.imagePullPolicy}}" + command: ["/opt/bats/bin/bats", "-t", "/tests/run.sh"] + volumeMounts: + - mountPath: /tests + name: tests + readOnly: true + {{- with .Values.testFramework.resources }} + resources: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: tests + configMap: + name: {{ include "grafana.fullname" . }}-test + restartPolicy: Never +{{- end }} diff --git a/observability/lgtm-distributed/charts/grafana/values.yaml b/observability/lgtm-distributed/charts/grafana/values.yaml new file mode 100644 index 0000000..a327a7a --- /dev/null +++ b/observability/lgtm-distributed/charts/grafana/values.yaml @@ -0,0 +1,1328 @@ +global: + # -- Overrides the Docker registry globally for all images + imageRegistry: null + + # To help compatibility with other charts which use global.imagePullSecrets. + # Allow either an array of {name: pullSecret} maps (k8s-style), or an array of strings (more common helm-style). + # Can be tempalted. + # global: + # imagePullSecrets: + # - name: pullSecret1 + # - name: pullSecret2 + # or + # global: + # imagePullSecrets: + # - pullSecret1 + # - pullSecret2 + imagePullSecrets: [] + +rbac: + create: true + ## Use an existing ClusterRole/Role (depending on rbac.namespaced false/true) + # useExistingRole: name-of-some-role + # useExistingClusterRole: name-of-some-clusterRole + pspEnabled: false + pspUseAppArmor: false + namespaced: false + extraRoleRules: [] + # - apiGroups: [] + # resources: [] + # verbs: [] + extraClusterRoleRules: [] + # - apiGroups: [] + # resources: [] + # verbs: [] +serviceAccount: + create: true + name: + nameTest: + ## ServiceAccount labels. + labels: {} + ## Service account annotations. Can be templated. + # annotations: + # eks.amazonaws.com/role-arn: arn:aws:iam::123456789000:role/iam-role-name-here + + ## autoMount is deprecated in favor of automountServiceAccountToken + # autoMount: false + automountServiceAccountToken: false + +replicas: 1 + +## Create a headless service for the deployment +headlessService: false + +## Should the service account be auto mounted on the pod +automountServiceAccountToken: true + +## Create HorizontalPodAutoscaler object for deployment type +# +autoscaling: + enabled: false + minReplicas: 1 + maxReplicas: 5 + targetCPU: "60" + targetMemory: "" + behavior: {} + +## See `kubectl explain poddisruptionbudget.spec` for more +## ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/ +podDisruptionBudget: {} +# apiVersion: "" +# minAvailable: 1 +# maxUnavailable: 1 + +## See `kubectl explain deployment.spec.strategy` for more +## ref: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy +deploymentStrategy: + type: RollingUpdate + +readinessProbe: + httpGet: + path: /api/health + port: 3000 + +livenessProbe: + httpGet: + path: /api/health + port: 3000 + initialDelaySeconds: 60 + timeoutSeconds: 30 + failureThreshold: 10 + +## Use an alternate scheduler, e.g. "stork". +## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ +## +# schedulerName: "default-scheduler" + +image: + # -- The Docker registry + registry: docker.io + # -- Docker image repository + repository: grafana/grafana + # Overrides the Grafana image tag whose default is the chart appVersion + tag: "" + sha: "" + pullPolicy: IfNotPresent + + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## Can be templated. + ## + pullSecrets: [] + # - myRegistrKeySecretName + +testFramework: + enabled: true + image: + # -- The Docker registry + registry: docker.io + repository: bats/bats + tag: "v1.4.1" + imagePullPolicy: IfNotPresent + securityContext: {} + resources: {} + # limits: + # cpu: 100m + # memory: 128Mi + # requests: + # cpu: 100m + # memory: 128Mi + +# dns configuration for pod +dnsPolicy: ~ +dnsConfig: {} + # nameservers: + # - 8.8.8.8 + # options: + # - name: ndots + # value: "2" + # - name: edns0 + +securityContext: + runAsNonRoot: true + runAsUser: 472 + runAsGroup: 472 + fsGroup: 472 + +containerSecurityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + +# Enable creating the grafana configmap +createConfigmap: true + +# Extra configmaps to mount in grafana pods +# Values are templated. +extraConfigmapMounts: [] + # - name: certs-configmap + # mountPath: /etc/grafana/ssl/ + # subPath: certificates.crt # (optional) + # configMap: certs-configmap + # readOnly: true + + +extraEmptyDirMounts: [] + # - name: provisioning-notifiers + # mountPath: /etc/grafana/provisioning/notifiers + + +# Apply extra labels to common labels. +extraLabels: {} + +## Assign a PriorityClassName to pods if set +# priorityClassName: + +downloadDashboardsImage: + # -- The Docker registry + registry: docker.io + repository: curlimages/curl + tag: 7.85.0 + sha: "" + pullPolicy: IfNotPresent + +downloadDashboards: + env: {} + envFromSecret: "" + resources: {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + envValueFrom: {} + # ENV_NAME: + # configMapKeyRef: + # name: configmap-name + # key: value_key + +## Pod Annotations +# podAnnotations: {} + +## Pod Labels +# podLabels: {} + +podPortName: grafana +gossipPortName: gossip +## Deployment annotations +# annotations: {} + +## Expose the grafana service to be accessed from outside the cluster (LoadBalancer service). +## or access it from within the cluster (ClusterIP service). Set the service type and the port to serve it. +## ref: http://kubernetes.io/docs/user-guide/services/ +## +service: + enabled: true + type: ClusterIP + loadBalancerIP: "" + loadBalancerClass: "" + loadBalancerSourceRanges: [] + port: 80 + targetPort: 3000 + # targetPort: 4181 To be used with a proxy extraContainer + ## Service annotations. Can be templated. + annotations: {} + labels: {} + portName: service + # Adds the appProtocol field to the service. This allows to work with istio protocol selection. Ex: "http" or "tcp" + appProtocol: "" + +serviceMonitor: + ## If true, a ServiceMonitor CRD is created for a prometheus operator + ## https://github.com/coreos/prometheus-operator + ## + enabled: false + path: /metrics + # namespace: monitoring (defaults to use the namespace this chart is deployed to) + labels: {} + interval: 30s + scheme: http + tlsConfig: {} + scrapeTimeout: 30s + relabelings: [] + metricRelabelings: [] + targetLabels: [] + +extraExposePorts: [] + # - name: keycloak + # port: 8080 + # targetPort: 8080 + +# overrides pod.spec.hostAliases in the grafana deployment's pods +hostAliases: [] + # - ip: "1.2.3.4" + # hostnames: + # - "my.host.com" + +ingress: + enabled: false + # For Kubernetes >= 1.18 you should specify the ingress-controller via the field ingressClassName + # See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#specifying-the-class-of-an-ingress + # ingressClassName: nginx + # Values can be templated + annotations: {} + # kubernetes.io/ingress.class: nginx + # kubernetes.io/tls-acme: "true" + labels: {} + path: / + + # pathType is only for k8s >= 1.1= + pathType: Prefix + + hosts: + - chart-example.local + ## Extra paths to prepend to every host configuration. This is useful when working with annotation based services. + extraPaths: [] + # - path: /* + # backend: + # serviceName: ssl-redirect + # servicePort: use-annotation + ## Or for k8s > 1.19 + # - path: /* + # pathType: Prefix + # backend: + # service: + # name: ssl-redirect + # port: + # name: use-annotation + + + tls: [] + # - secretName: chart-example-tls + # hosts: + # - chart-example.local + +resources: {} +# limits: +# cpu: 100m +# memory: 128Mi +# requests: +# cpu: 100m +# memory: 128Mi + +## Node labels for pod assignment +## ref: https://kubernetes.io/docs/user-guide/node-selection/ +# +nodeSelector: {} + +## Tolerations for pod assignment +## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ +## +tolerations: [] + +## Affinity for pod assignment (evaluated as template) +## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity +## +affinity: {} + +## Topology Spread Constraints +## ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ +## +topologySpreadConstraints: [] + +## Additional init containers (evaluated as template) +## ref: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/ +## +extraInitContainers: [] + +## Enable an Specify container in extraContainers. This is meant to allow adding an authentication proxy to a grafana pod +extraContainers: "" +# extraContainers: | +# - name: proxy +# image: quay.io/gambol99/keycloak-proxy:latest +# args: +# - -provider=github +# - -client-id= +# - -client-secret= +# - -github-org= +# - -email-domain=* +# - -cookie-secret= +# - -http-address=http://0.0.0.0:4181 +# - -upstream-url=http://127.0.0.1:3000 +# ports: +# - name: proxy-web +# containerPort: 4181 + +## Volumes that can be used in init containers that will not be mounted to deployment pods +extraContainerVolumes: [] +# - name: volume-from-secret +# secret: +# secretName: secret-to-mount +# - name: empty-dir-volume +# emptyDir: {} + +## Enable persistence using Persistent Volume Claims +## ref: http://kubernetes.io/docs/user-guide/persistent-volumes/ +## +persistence: + type: pvc + enabled: false + # storageClassName: default + accessModes: + - ReadWriteOnce + size: 10Gi + # annotations: {} + finalizers: + - kubernetes.io/pvc-protection + # selectorLabels: {} + ## Sub-directory of the PV to mount. Can be templated. + # subPath: "" + ## Name of an existing PVC. Can be templated. + # existingClaim: + ## Extra labels to apply to a PVC. + extraPvcLabels: {} + + ## If persistence is not enabled, this allows to mount the + ## local storage in-memory to improve performance + ## + inMemory: + enabled: false + ## The maximum usage on memory medium EmptyDir would be + ## the minimum value between the SizeLimit specified + ## here and the sum of memory limits of all containers in a pod + ## + # sizeLimit: 300Mi + +initChownData: + ## If false, data ownership will not be reset at startup + ## This allows the grafana-server to be run with an arbitrary user + ## + enabled: true + + ## initChownData container image + ## + image: + # -- The Docker registry + registry: docker.io + repository: library/busybox + tag: "1.31.1" + sha: "" + pullPolicy: IfNotPresent + + ## initChownData resource requests and limits + ## Ref: http://kubernetes.io/docs/user-guide/compute-resources/ + ## + resources: {} + # limits: + # cpu: 100m + # memory: 128Mi + # requests: + # cpu: 100m + # memory: 128Mi + securityContext: + runAsNonRoot: false + runAsUser: 0 + seccompProfile: + type: RuntimeDefault + capabilities: + add: + - CHOWN + +# Administrator credentials when not using an existing secret (see below) +adminUser: admin +# adminPassword: strongpassword + +# Use an existing secret for the admin user. +admin: + ## Name of the secret. Can be templated. + existingSecret: "" + userKey: admin-user + passwordKey: admin-password + +## Define command to be executed at startup by grafana container +## Needed if using `vault-env` to manage secrets (ref: https://banzaicloud.com/blog/inject-secrets-into-pods-vault/) +## Default is "run.sh" as defined in grafana's Dockerfile +# command: +# - "sh" +# - "/run.sh" + +## Optionally define args if command is used +## Needed if using `hashicorp/envconsul` to manage secrets +## By default no arguments are set +# args: +# - "-secret" +# - "secret/grafana" +# - "./grafana" + +## Extra environment variables that will be pass onto deployment pods +## +## to provide grafana with access to CloudWatch on AWS EKS: +## 1. create an iam role of type "Web identity" with provider oidc.eks.* (note the provider for later) +## 2. edit the "Trust relationships" of the role, add a line inside the StringEquals clause using the +## same oidc eks provider as noted before (same as the existing line) +## also, replace NAMESPACE and prometheus-operator-grafana with the service account namespace and name +## +## "oidc.eks.us-east-1.amazonaws.com/id/XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX:sub": "system:serviceaccount:NAMESPACE:prometheus-operator-grafana", +## +## 3. attach a policy to the role, you can use a built in policy called CloudWatchReadOnlyAccess +## 4. use the following env: (replace 123456789000 and iam-role-name-here with your aws account number and role name) +## +## env: +## AWS_ROLE_ARN: arn:aws:iam::123456789000:role/iam-role-name-here +## AWS_WEB_IDENTITY_TOKEN_FILE: /var/run/secrets/eks.amazonaws.com/serviceaccount/token +## AWS_REGION: us-east-1 +## +## 5. uncomment the EKS section in extraSecretMounts: below +## 6. uncomment the annotation section in the serviceAccount: above +## make sure to replace arn:aws:iam::123456789000:role/iam-role-name-here with your role arn + +env: {} + +## "valueFrom" environment variable references that will be added to deployment pods. Name is templated. +## ref: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.19/#envvarsource-v1-core +## Renders in container spec as: +## env: +## ... +## - name: +## valueFrom: +## +envValueFrom: {} + # ENV_NAME: + # configMapKeyRef: + # name: configmap-name + # key: value_key + +## The name of a secret in the same kubernetes namespace which contain values to be added to the environment +## This can be useful for auth tokens, etc. Value is templated. +envFromSecret: "" + +## Sensible environment variables that will be rendered as new secret object +## This can be useful for auth tokens, etc. +## If the secret values contains "{{", they'll need to be properly escaped so that they are not interpreted by Helm +## ref: https://helm.sh/docs/howto/charts_tips_and_tricks/#using-the-tpl-function +envRenderSecret: {} + +## The names of secrets in the same kubernetes namespace which contain values to be added to the environment +## Each entry should contain a name key, and can optionally specify whether the secret must be defined with an optional key. +## Name is templated. +envFromSecrets: [] +## - name: secret-name +## prefix: prefix +## optional: true + +## The names of conifgmaps in the same kubernetes namespace which contain values to be added to the environment +## Each entry should contain a name key, and can optionally specify whether the configmap must be defined with an optional key. +## Name is templated. +## ref: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#configmapenvsource-v1-core +envFromConfigMaps: [] +## - name: configmap-name +## prefix: prefix +## optional: true + +# Inject Kubernetes services as environment variables. +# See https://kubernetes.io/docs/concepts/services-networking/connect-applications-service/#environment-variables +enableServiceLinks: true + +## Additional grafana server secret mounts +# Defines additional mounts with secrets. Secrets must be manually created in the namespace. +extraSecretMounts: [] + # - name: secret-files + # mountPath: /etc/secrets + # secretName: grafana-secret-files + # readOnly: true + # subPath: "" + # + # for AWS EKS (cloudwatch) use the following (see also instruction in env: above) + # - name: aws-iam-token + # mountPath: /var/run/secrets/eks.amazonaws.com/serviceaccount + # readOnly: true + # projected: + # defaultMode: 420 + # sources: + # - serviceAccountToken: + # audience: sts.amazonaws.com + # expirationSeconds: 86400 + # path: token + # + # for CSI e.g. Azure Key Vault use the following + # - name: secrets-store-inline + # mountPath: /run/secrets + # readOnly: true + # csi: + # driver: secrets-store.csi.k8s.io + # readOnly: true + # volumeAttributes: + # secretProviderClass: "akv-grafana-spc" + # nodePublishSecretRef: # Only required when using service principal mode + # name: grafana-akv-creds # Only required when using service principal mode + +## Additional grafana server volume mounts +# Defines additional volume mounts. +extraVolumeMounts: [] + # - name: extra-volume-0 + # mountPath: /mnt/volume0 + # readOnly: true + # - name: extra-volume-1 + # mountPath: /mnt/volume1 + # readOnly: true + # - name: grafana-secrets + # mountPath: /mnt/volume2 + +## Additional Grafana server volumes +extraVolumes: [] + # - name: extra-volume-0 + # existingClaim: volume-claim + # - name: extra-volume-1 + # hostPath: + # path: /usr/shared/ + # type: "" + # - name: grafana-secrets + # csi: + # driver: secrets-store.csi.k8s.io + # readOnly: true + # volumeAttributes: + # secretProviderClass: "grafana-env-spc" + +## Container Lifecycle Hooks. Execute a specific bash command or make an HTTP request +lifecycleHooks: {} + # postStart: + # exec: + # command: [] + +## Pass the plugins you want installed as a list. +## +plugins: [] + # - digrich-bubblechart-panel + # - grafana-clock-panel + ## You can also use other plugin download URL, as long as they are valid zip files, + ## and specify the name of the plugin after the semicolon. Like this: + # - https://grafana.com/api/plugins/marcusolsson-json-datasource/versions/1.3.2/download;marcusolsson-json-datasource + +## Configure grafana datasources +## ref: http://docs.grafana.org/administration/provisioning/#datasources +## +datasources: {} +# datasources.yaml: +# apiVersion: 1 +# datasources: +# - name: Prometheus +# type: prometheus +# url: http://prometheus-prometheus-server +# access: proxy +# isDefault: true +# - name: CloudWatch +# type: cloudwatch +# access: proxy +# uid: cloudwatch +# editable: false +# jsonData: +# authType: default +# defaultRegion: us-east-1 +# deleteDatasources: [] +# - name: Prometheus + +## Configure grafana alerting (can be templated) +## ref: http://docs.grafana.org/administration/provisioning/#alerting +## +alerting: {} + # rules.yaml: + # apiVersion: 1 + # groups: + # - orgId: 1 + # name: '{{ .Chart.Name }}_my_rule_group' + # folder: my_first_folder + # interval: 60s + # rules: + # - uid: my_id_1 + # title: my_first_rule + # condition: A + # data: + # - refId: A + # datasourceUid: '-100' + # model: + # conditions: + # - evaluator: + # params: + # - 3 + # type: gt + # operator: + # type: and + # query: + # params: + # - A + # reducer: + # type: last + # type: query + # datasource: + # type: __expr__ + # uid: '-100' + # expression: 1==0 + # intervalMs: 1000 + # maxDataPoints: 43200 + # refId: A + # type: math + # dashboardUid: my_dashboard + # panelId: 123 + # noDataState: Alerting + # for: 60s + # annotations: + # some_key: some_value + # labels: + # team: sre_team_1 + # contactpoints.yaml: + # secret: + # apiVersion: 1 + # contactPoints: + # - orgId: 1 + # name: cp_1 + # receivers: + # - uid: first_uid + # type: pagerduty + # settings: + # integrationKey: XXX + # severity: critical + # class: ping failure + # component: Grafana + # group: app-stack + # summary: | + # {{ `{{ include "default.message" . }}` }} + +## Configure notifiers +## ref: http://docs.grafana.org/administration/provisioning/#alert-notification-channels +## +notifiers: {} +# notifiers.yaml: +# notifiers: +# - name: email-notifier +# type: email +# uid: email1 +# # either: +# org_id: 1 +# # or +# org_name: Main Org. +# is_default: true +# settings: +# addresses: an_email_address@example.com +# delete_notifiers: + +## Configure grafana dashboard providers +## ref: http://docs.grafana.org/administration/provisioning/#dashboards +## +## `path` must be /var/lib/grafana/dashboards/ +## +dashboardProviders: {} +# dashboardproviders.yaml: +# apiVersion: 1 +# providers: +# - name: 'default' +# orgId: 1 +# folder: '' +# type: file +# disableDeletion: false +# editable: true +# options: +# path: /var/lib/grafana/dashboards/default + +## Configure grafana dashboard to import +## NOTE: To use dashboards you must also enable/configure dashboardProviders +## ref: https://grafana.com/dashboards +## +## dashboards per provider, use provider name as key. +## +dashboards: {} + # default: + # some-dashboard: + # json: | + # $RAW_JSON + # custom-dashboard: + # file: dashboards/custom-dashboard.json + # prometheus-stats: + # gnetId: 2 + # revision: 2 + # datasource: Prometheus + # local-dashboard: + # url: https://example.com/repository/test.json + # token: '' + # local-dashboard-base64: + # url: https://example.com/repository/test-b64.json + # token: '' + # b64content: true + # local-dashboard-gitlab: + # url: https://example.com/repository/test-gitlab.json + # gitlabToken: '' + # local-dashboard-bitbucket: + # url: https://example.com/repository/test-bitbucket.json + # bearerToken: '' + # local-dashboard-azure: + # url: https://example.com/repository/test-azure.json + # basic: '' + # acceptHeader: '*/*' + +## Reference to external ConfigMap per provider. Use provider name as key and ConfigMap name as value. +## A provider dashboards must be defined either by external ConfigMaps or in values.yaml, not in both. +## ConfigMap data example: +## +## data: +## example-dashboard.json: | +## RAW_JSON +## +dashboardsConfigMaps: {} +# default: "" + +## Grafana's primary configuration +## NOTE: values in map will be converted to ini format +## ref: http://docs.grafana.org/installation/configuration/ +## +grafana.ini: + paths: + data: /var/lib/grafana/ + logs: /var/log/grafana + plugins: /var/lib/grafana/plugins + provisioning: /etc/grafana/provisioning + analytics: + check_for_updates: true + log: + mode: console + grafana_net: + url: https://grafana.net + server: + domain: "{{ if (and .Values.ingress.enabled .Values.ingress.hosts) }}{{ .Values.ingress.hosts | first }}{{ else }}''{{ end }}" +## grafana Authentication can be enabled with the following values on grafana.ini + # server: + # The full public facing url you use in browser, used for redirects and emails + # root_url: + # https://grafana.com/docs/grafana/latest/auth/github/#enable-github-in-grafana + # auth.github: + # enabled: false + # allow_sign_up: false + # scopes: user:email,read:org + # auth_url: https://github.com/login/oauth/authorize + # token_url: https://github.com/login/oauth/access_token + # api_url: https://api.github.com/user + # team_ids: + # allowed_organizations: + # client_id: + # client_secret: +## LDAP Authentication can be enabled with the following values on grafana.ini +## NOTE: Grafana will fail to start if the value for ldap.toml is invalid + # auth.ldap: + # enabled: true + # allow_sign_up: true + # config_file: /etc/grafana/ldap.toml + +## Grafana's LDAP configuration +## Templated by the template in _helpers.tpl +## NOTE: To enable the grafana.ini must be configured with auth.ldap.enabled +## ref: http://docs.grafana.org/installation/configuration/#auth-ldap +## ref: http://docs.grafana.org/installation/ldap/#configuration +ldap: + enabled: false + # `existingSecret` is a reference to an existing secret containing the ldap configuration + # for Grafana in a key `ldap-toml`. + existingSecret: "" + # `config` is the content of `ldap.toml` that will be stored in the created secret + config: "" + # config: |- + # verbose_logging = true + + # [[servers]] + # host = "my-ldap-server" + # port = 636 + # use_ssl = true + # start_tls = false + # ssl_skip_verify = false + # bind_dn = "uid=%s,ou=users,dc=myorg,dc=com" + +## Grafana's SMTP configuration +## NOTE: To enable, grafana.ini must be configured with smtp.enabled +## ref: http://docs.grafana.org/installation/configuration/#smtp +smtp: + # `existingSecret` is a reference to an existing secret containing the smtp configuration + # for Grafana. + existingSecret: "" + userKey: "user" + passwordKey: "password" + +## Sidecars that collect the configmaps with specified label and stores the included files them into the respective folders +## Requires at least Grafana 5 to work and can't be used together with parameters dashboardProviders, datasources and dashboards +sidecar: + image: + # -- The Docker registry + registry: quay.io + repository: kiwigrid/k8s-sidecar + tag: 1.26.1 + sha: "" + imagePullPolicy: IfNotPresent + resources: {} +# limits: +# cpu: 100m +# memory: 100Mi +# requests: +# cpu: 50m +# memory: 50Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + # skipTlsVerify Set to true to skip tls verification for kube api calls + # skipTlsVerify: true + enableUniqueFilenames: false + readinessProbe: {} + livenessProbe: {} + # Log level default for all sidecars. Can be one of: DEBUG, INFO, WARN, ERROR, CRITICAL. Defaults to INFO + # logLevel: INFO + alerts: + enabled: false + # Additional environment variables for the alerts sidecar + env: {} + # Do not reprocess already processed unchanged resources on k8s API reconnect. + # ignoreAlreadyProcessed: true + # label that the configmaps with alert are marked with + label: grafana_alert + # value of label that the configmaps with alert are set to + labelValue: "" + # Log level. Can be one of: DEBUG, INFO, WARN, ERROR, CRITICAL. + # logLevel: INFO + # If specified, the sidecar will search for alert config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: null + # Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. + watchMethod: WATCH + # search in configmap, secret or both + resource: both + # watchServerTimeout: request to the server, asking it to cleanly close the connection after that. + # defaults to 60sec; much higher values like 3600 seconds (1h) are feasible for non-Azure K8S + # watchServerTimeout: 3600 + # + # watchClientTimeout: is a client-side timeout, configuring your local socket. + # If you have a network outage dropping all packets with no RST/FIN, + # this is how long your client waits before realizing & dropping the connection. + # defaults to 66sec (sic!) + # watchClientTimeout: 60 + # + # Endpoint to send request to reload alerts + reloadURL: "http://localhost:3000/api/admin/provisioning/alerting/reload" + # Absolute path to shell script to execute after a alert got reloaded + script: null + skipReload: false + # This is needed if skipReload is true, to load any alerts defined at startup time. + # Deploy the alert sidecar as an initContainer. + initAlerts: false + # Additional alert sidecar volume mounts + extraMounts: [] + # Sets the size limit of the alert sidecar emptyDir volume + sizeLimit: {} + dashboards: + enabled: false + # Additional environment variables for the dashboards sidecar + env: {} + # Do not reprocess already processed unchanged resources on k8s API reconnect. + # ignoreAlreadyProcessed: true + SCProvider: true + # label that the configmaps with dashboards are marked with + label: grafana_dashboard + # value of label that the configmaps with dashboards are set to + labelValue: "" + # Log level. Can be one of: DEBUG, INFO, WARN, ERROR, CRITICAL. + # logLevel: INFO + # folder in the pod that should hold the collected dashboards (unless `defaultFolderName` is set) + folder: /tmp/dashboards + # The default folder name, it will create a subfolder under the `folder` and put dashboards in there instead + defaultFolderName: null + # Namespaces list. If specified, the sidecar will search for config-maps/secrets inside these namespaces. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces. + searchNamespace: null + # Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. + watchMethod: WATCH + # search in configmap, secret or both + resource: both + # If specified, the sidecar will look for annotation with this name to create folder and put graph here. + # You can use this parameter together with `provider.foldersFromFilesStructure`to annotate configmaps and create folder structure. + folderAnnotation: null + # Endpoint to send request to reload alerts + reloadURL: "http://localhost:3000/api/admin/provisioning/dashboards/reload" + # Absolute path to shell script to execute after a configmap got reloaded + script: null + skipReload: false + # watchServerTimeout: request to the server, asking it to cleanly close the connection after that. + # defaults to 60sec; much higher values like 3600 seconds (1h) are feasible for non-Azure K8S + # watchServerTimeout: 3600 + # + # watchClientTimeout: is a client-side timeout, configuring your local socket. + # If you have a network outage dropping all packets with no RST/FIN, + # this is how long your client waits before realizing & dropping the connection. + # defaults to 66sec (sic!) + # watchClientTimeout: 60 + # + # provider configuration that lets grafana manage the dashboards + provider: + # name of the provider, should be unique + name: sidecarProvider + # orgid as configured in grafana + orgid: 1 + # folder in which the dashboards should be imported in grafana + folder: '' + # type of the provider + type: file + # disableDelete to activate a import-only behaviour + disableDelete: false + # allow updating provisioned dashboards from the UI + allowUiUpdates: false + # allow Grafana to replicate dashboard structure from filesystem + foldersFromFilesStructure: false + # Additional dashboard sidecar volume mounts + extraMounts: [] + # Sets the size limit of the dashboard sidecar emptyDir volume + sizeLimit: {} + datasources: + enabled: false + # Additional environment variables for the datasourcessidecar + env: {} + envValueFrom: {} + # Do not reprocess already processed unchanged resources on k8s API reconnect. + # ignoreAlreadyProcessed: true + # label that the configmaps with datasources are marked with + label: grafana_datasource + # value of label that the configmaps with datasources are set to + labelValue: "" + # Log level. Can be one of: DEBUG, INFO, WARN, ERROR, CRITICAL. + # logLevel: INFO + # If specified, the sidecar will search for datasource config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: null + # Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. + watchMethod: WATCH + # search in configmap, secret or both + resource: both + # watchServerTimeout: request to the server, asking it to cleanly close the connection after that. + # defaults to 60sec; much higher values like 3600 seconds (1h) are feasible for non-Azure K8S + # watchServerTimeout: 3600 + # + # watchClientTimeout: is a client-side timeout, configuring your local socket. + # If you have a network outage dropping all packets with no RST/FIN, + # this is how long your client waits before realizing & dropping the connection. + # defaults to 66sec (sic!) + # watchClientTimeout: 60 + # + # Endpoint to send request to reload datasources + reloadURL: "http://localhost:3000/api/admin/provisioning/datasources/reload" + # Absolute path to shell script to execute after a datasource got reloaded + script: null + skipReload: false + # This is needed if skipReload is true, to load any datasources defined at startup time. + # Deploy the datasources sidecar as an initContainer. + initDatasources: false + # Sets the size limit of the datasource sidecar emptyDir volume + sizeLimit: {} + plugins: + enabled: false + # Additional environment variables for the plugins sidecar + env: {} + # Do not reprocess already processed unchanged resources on k8s API reconnect. + # ignoreAlreadyProcessed: true + # label that the configmaps with plugins are marked with + label: grafana_plugin + # value of label that the configmaps with plugins are set to + labelValue: "" + # Log level. Can be one of: DEBUG, INFO, WARN, ERROR, CRITICAL. + # logLevel: INFO + # If specified, the sidecar will search for plugin config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: null + # Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. + watchMethod: WATCH + # search in configmap, secret or both + resource: both + # watchServerTimeout: request to the server, asking it to cleanly close the connection after that. + # defaults to 60sec; much higher values like 3600 seconds (1h) are feasible for non-Azure K8S + # watchServerTimeout: 3600 + # + # watchClientTimeout: is a client-side timeout, configuring your local socket. + # If you have a network outage dropping all packets with no RST/FIN, + # this is how long your client waits before realizing & dropping the connection. + # defaults to 66sec (sic!) + # watchClientTimeout: 60 + # + # Endpoint to send request to reload plugins + reloadURL: "http://localhost:3000/api/admin/provisioning/plugins/reload" + # Absolute path to shell script to execute after a plugin got reloaded + script: null + skipReload: false + # Deploy the datasource sidecar as an initContainer in addition to a container. + # This is needed if skipReload is true, to load any plugins defined at startup time. + initPlugins: false + # Sets the size limit of the plugin sidecar emptyDir volume + sizeLimit: {} + notifiers: + enabled: false + # Additional environment variables for the notifierssidecar + env: {} + # Do not reprocess already processed unchanged resources on k8s API reconnect. + # ignoreAlreadyProcessed: true + # label that the configmaps with notifiers are marked with + label: grafana_notifier + # value of label that the configmaps with notifiers are set to + labelValue: "" + # Log level. Can be one of: DEBUG, INFO, WARN, ERROR, CRITICAL. + # logLevel: INFO + # If specified, the sidecar will search for notifier config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: null + # Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. + watchMethod: WATCH + # search in configmap, secret or both + resource: both + # watchServerTimeout: request to the server, asking it to cleanly close the connection after that. + # defaults to 60sec; much higher values like 3600 seconds (1h) are feasible for non-Azure K8S + # watchServerTimeout: 3600 + # + # watchClientTimeout: is a client-side timeout, configuring your local socket. + # If you have a network outage dropping all packets with no RST/FIN, + # this is how long your client waits before realizing & dropping the connection. + # defaults to 66sec (sic!) + # watchClientTimeout: 60 + # + # Endpoint to send request to reload notifiers + reloadURL: "http://localhost:3000/api/admin/provisioning/notifications/reload" + # Absolute path to shell script to execute after a notifier got reloaded + script: null + skipReload: false + # Deploy the notifier sidecar as an initContainer in addition to a container. + # This is needed if skipReload is true, to load any notifiers defined at startup time. + initNotifiers: false + # Sets the size limit of the notifier sidecar emptyDir volume + sizeLimit: {} + +## Override the deployment namespace +## +namespaceOverride: "" + +## Number of old ReplicaSets to retain +## +revisionHistoryLimit: 10 + +## Add a seperate remote image renderer deployment/service +imageRenderer: + deploymentStrategy: {} + # Enable the image-renderer deployment & service + enabled: false + replicas: 1 + autoscaling: + enabled: false + minReplicas: 1 + maxReplicas: 5 + targetCPU: "60" + targetMemory: "" + behavior: {} + image: + # -- The Docker registry + registry: docker.io + # image-renderer Image repository + repository: grafana/grafana-image-renderer + # image-renderer Image tag + tag: latest + # image-renderer Image sha (optional) + sha: "" + # image-renderer ImagePullPolicy + pullPolicy: Always + # extra environment variables + env: + HTTP_HOST: "0.0.0.0" + # RENDERING_ARGS: --no-sandbox,--disable-gpu,--window-size=1280x758 + # RENDERING_MODE: clustered + # IGNORE_HTTPS_ERRORS: true + + ## "valueFrom" environment variable references that will be added to deployment pods. Name is templated. + ## ref: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.19/#envvarsource-v1-core + ## Renders in container spec as: + ## env: + ## ... + ## - name: + ## valueFrom: + ## + envValueFrom: {} + # ENV_NAME: + # configMapKeyRef: + # name: configmap-name + # key: value_key + + # image-renderer deployment serviceAccount + serviceAccountName: "" + # image-renderer deployment securityContext + securityContext: {} + # image-renderer deployment container securityContext + containerSecurityContext: + seccompProfile: + type: RuntimeDefault + capabilities: + drop: ['ALL'] + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + ## image-renderer pod annotation + podAnnotations: {} + # image-renderer deployment Host Aliases + hostAliases: [] + # image-renderer deployment priority class + priorityClassName: '' + service: + # Enable the image-renderer service + enabled: true + # image-renderer service port name + portName: 'http' + # image-renderer service port used by both service and deployment + port: 8081 + targetPort: 8081 + # Adds the appProtocol field to the image-renderer service. This allows to work with istio protocol selection. Ex: "http" or "tcp" + appProtocol: "" + serviceMonitor: + ## If true, a ServiceMonitor CRD is created for a prometheus operator + ## https://github.com/coreos/prometheus-operator + ## + enabled: false + path: /metrics + # namespace: monitoring (defaults to use the namespace this chart is deployed to) + labels: {} + interval: 1m + scheme: http + tlsConfig: {} + scrapeTimeout: 30s + relabelings: [] + # See: https://doc.crds.dev/github.com/prometheus-operator/kube-prometheus/monitoring.coreos.com/ServiceMonitor/v1@v0.11.0#spec-targetLabels + targetLabels: [] + # - targetLabel1 + # - targetLabel2 + # If https is enabled in Grafana, this needs to be set as 'https' to correctly configure the callback used in Grafana + grafanaProtocol: http + # In case a sub_path is used this needs to be added to the image renderer callback + grafanaSubPath: "" + # name of the image-renderer port on the pod + podPortName: http + # number of image-renderer replica sets to keep + revisionHistoryLimit: 10 + networkPolicy: + # Enable a NetworkPolicy to limit inbound traffic to only the created grafana pods + limitIngress: true + # Enable a NetworkPolicy to limit outbound traffic to only the created grafana pods + limitEgress: false + # Allow additional services to access image-renderer (eg. Prometheus operator when ServiceMonitor is enabled) + extraIngressSelectors: [] + resources: {} +# limits: +# cpu: 100m +# memory: 100Mi +# requests: +# cpu: 50m +# memory: 50Mi + ## Node labels for pod assignment + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + # + nodeSelector: {} + + ## Tolerations for pod assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + ## + tolerations: [] + + ## Affinity for pod assignment (evaluated as template) + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + ## + affinity: {} + + ## Use an alternate scheduler, e.g. "stork". + ## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ + ## + # schedulerName: "default-scheduler" + +networkPolicy: + ## @param networkPolicy.enabled Enable creation of NetworkPolicy resources. Only Ingress traffic is filtered for now. + ## + enabled: false + ## @param networkPolicy.allowExternal Don't require client label for connections + ## The Policy model to apply. When set to false, only pods with the correct + ## client label will have network access to grafana port defined. + ## When true, grafana will accept connections from any source + ## (with the correct destination port). + ## + ingress: true + ## @param networkPolicy.ingress When true enables the creation + ## an ingress network policy + ## + allowExternal: true + ## @param networkPolicy.explicitNamespacesSelector A Kubernetes LabelSelector to explicitly select namespaces from which traffic could be allowed + ## If explicitNamespacesSelector is missing or set to {}, only client Pods that are in the networkPolicy's namespace + ## and that match other criteria, the ones that have the good label, can reach the grafana. + ## But sometimes, we want the grafana to be accessible to clients from other namespaces, in this case, we can use this + ## LabelSelector to select these namespaces, note that the networkPolicy's namespace should also be explicitly added. + ## + ## Example: + ## explicitNamespacesSelector: + ## matchLabels: + ## role: frontend + ## matchExpressions: + ## - {key: role, operator: In, values: [frontend]} + ## + explicitNamespacesSelector: {} + ## + ## + ## + ## + ## + ## + egress: + ## @param networkPolicy.egress.enabled When enabled, an egress network policy will be + ## created allowing grafana to connect to external data sources from kubernetes cluster. + enabled: false + ## + ## @param networkPolicy.egress.blockDNSResolution When enabled, DNS resolution will be blocked + ## for all pods in the grafana namespace. + blockDNSResolution: false + ## + ## @param networkPolicy.egress.ports Add individual ports to be allowed by the egress + ports: [] + ## Add ports to the egress by specifying - port: + ## E.X. + ## - port: 80 + ## - port: 443 + ## + ## @param networkPolicy.egress.to Allow egress traffic to specific destinations + to: [] + ## Add destinations to the egress by specifying - ipBlock: + ## E.X. + ## to: + ## - namespaceSelector: + ## matchExpressions: + ## - {key: role, operator: In, values: [grafana]} + ## + ## + ## + ## + ## + +# Enable backward compatibility of kubernetes where version below 1.13 doesn't have the enableServiceLinks option +enableKubeBackwardCompatibility: false +useStatefulSet: false +# Create a dynamic manifests via values: +extraObjects: [] + # - apiVersion: "kubernetes-client.io/v1" + # kind: ExternalSecret + # metadata: + # name: grafana-secrets + # spec: + # backendType: gcpSecretsManager + # data: + # - key: grafana-admin-password + # name: adminPassword + +# assertNoLeakedSecrets is a helper function defined in _helpers.tpl that checks if secret +# values are not exposed in the rendered grafana.ini configmap. It is enabled by default. +# +# To pass values into grafana.ini without exposing them in a configmap, use variable expansion: +# https://grafana.com/docs/grafana/latest/setup-grafana/configure-grafana/#variable-expansion +# +# Alternatively, if you wish to allow secret values to be exposed in the rendered grafana.ini configmap, +# you can disable this check by setting assertNoLeakedSecrets to false. +assertNoLeakedSecrets: true diff --git a/observability/lgtm-distributed/charts/loki-distributed/.helmignore b/observability/lgtm-distributed/charts/loki-distributed/.helmignore new file mode 100644 index 0000000..371a431 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/.helmignore @@ -0,0 +1,25 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*.orig +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ +doc.yaml +README.tpl diff --git a/observability/lgtm-distributed/charts/loki-distributed/Chart.yaml b/observability/lgtm-distributed/charts/loki-distributed/Chart.yaml new file mode 100644 index 0000000..671e0ed --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/Chart.yaml @@ -0,0 +1,14 @@ +apiVersion: v2 +appVersion: 2.9.6 +description: Helm chart for Grafana Loki in microservices mode +home: https://grafana.github.io/helm-charts +icon: https://grafana.com/docs/loki/latest/logo_and_name.png +maintainers: +- name: unguiculus +name: loki-distributed +sources: +- https://github.com/grafana/loki +- https://grafana.com/oss/loki/ +- https://grafana.com/docs/loki/latest/ +type: application +version: 0.79.0 diff --git a/observability/lgtm-distributed/charts/loki-distributed/README.md b/observability/lgtm-distributed/charts/loki-distributed/README.md new file mode 100644 index 0000000..d40ea8b --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/README.md @@ -0,0 +1,955 @@ +# loki-distributed + +![Version: 0.79.0](https://img.shields.io/badge/Version-0.79.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 2.9.6](https://img.shields.io/badge/AppVersion-2.9.6-informational?style=flat-square) + +Helm chart for Grafana Loki in microservices mode + +## Source Code + +* +* +* + +## Chart Repo + +Add the following repo to use the chart: + +```console +helm repo add grafana https://grafana.github.io/helm-charts +``` + +## Upgrading + +### Upgrading an existing Release to a new major version + +Major version upgrades listed here indicate that there is an incompatible breaking change needing manual actions. + +### From 0.78.x to 0.79.0 +Removed the hardcoded, deprecated `boltdb.shipper.compactor.working-directory` flag in the Compactor Deployment template, so that it can be set with `.Values.compactor.extraArgs` and the `compactor.working-directory` flag if necessary. + +### From 0.74.x to 0.75.0 +The Index Gateway and Query Scheduler now expose the memberlist port 7946. In order to join the +member list, you need to specify this in the `structuredConfig`: +```yaml +loki: + structuredConfig: + index_gateway: + mode: ring + query_scheduler: + use_scheduler_ring: true +``` + +### From 0.68.x to 0.69.0 +The in-memory `fifocache` has been renamed to more general `embedded_cache`, which currently doesn't have a `max_size_items` attribute. +```yaml +loki: + config: | + chunk_store_config: + chunk_cache_config: + embedded_cache: + enabled: false +``` + +`compactor_address` has to be explicitly set in the `common` section of the config. +```yaml +loki: + config: | + common: + compactor_address: {{ include "loki.compactorFullname" . }}:3100 +``` + +### From 0.41.x to 0.42.0 +All containers were previously named "loki". This version changes the container names to make the chart compatible with the loki-mixin. Now the container names correctly reflect the component (querier, distributor, ingester, ...). If you are using custom prometheus rules that use the container name you probably have to change them. + +### From 0.34.x to 0.35.0 +This version updates the `Ingress` API Version of the Loki Gateway component to `networking.k8s.io/v1` of course given that the cluster supports it. Here it's important to notice the change in the `values.yml` with regards to the ingress configuration section and its new structure. +```yaml +gateway: + ingress: + enabled: true + # Newly added optional property + ingressClassName: nginx + hosts: + - host: gateway.loki.example.com + paths: + # New data structure introduced + - path: / + # Newly added optional property + pathType: Prefix +``` + +### From 0.30.x to 0.31.0 +This version updates the `podManagementPolicy` of running the Loki components as `StatefulSet`'s to `Parallel` instead of the default `OrderedReady` in order to allow better scalability for Loki e.g. in case the pods weren't terminated gracefully. This change requires a manual action deleting the existing StatefulSets before upgrading with Helm. +```bash +# Delete the Ingesters StatefulSets +kubectl delete statefulset RELEASE_NAME-loki-distributed-ingester -n LOKI_NAMESPACE --cascade=orphan +# Delete the Queriers StatefulSets +kubectl delete statefulset RELEASE_NAME-loki-distributed-querier -n LOKI_NAMESPACE --cascade=orphan +``` + +## Values + +| Key | Type | Default | Description | +|-----|------|---------|-------------| +| compactor.affinity | string | Hard node and soft zone anti-affinity | Affinity for compactor pods. Passed through `tpl` and, thus, to be configured as string | +| compactor.appProtocol | object | `{"grpc":""}` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| compactor.command | string | `nil` | Command to execute instead of defined in Docker image | +| compactor.enabled | bool | `false` | Specifies whether compactor should be enabled | +| compactor.extraArgs | list | `[]` | Additional CLI args for the compactor | +| compactor.extraContainers | list | `[]` | Containers to add to the compactor pods | +| compactor.extraEnv | list | `[]` | Environment variables to add to the compactor pods | +| compactor.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the compactor pods | +| compactor.extraVolumeMounts | list | `[]` | Volume mounts to add to the compactor pods | +| compactor.extraVolumes | list | `[]` | Volumes to add to the compactor pods | +| compactor.hostAliases | list | `[]` | hostAliases to add | +| compactor.image.registry | string | `nil` | The Docker registry for the compactor image. Overrides `loki.image.registry` | +| compactor.image.repository | string | `nil` | Docker image repository for the compactor image. Overrides `loki.image.repository` | +| compactor.image.tag | string | `nil` | Docker image tag for the compactor image. Overrides `loki.image.tag` | +| compactor.initContainers | list | `[]` | Init containers to add to the compactor pods | +| compactor.kind | string | `"StatefulSet"` | Kind of deployment [StatefulSet/Deployment] | +| compactor.livenessProbe | object | `{}` | liveness probe settings for ingester pods. If empty use `loki.livenessProbe` | +| compactor.nodeSelector | object | `{}` | Node selector for compactor pods | +| compactor.persistence.annotations | object | `{}` | Annotations for compactor PVCs | +| compactor.persistence.claims | list | `[{"name":"data","size":"10Gi","storageClass":null}]` | List of the compactor PVCs @notationType -- list | +| compactor.persistence.enableStatefulSetAutoDeletePVC | bool | `false` | Enable StatefulSetAutoDeletePVC feature | +| compactor.persistence.enabled | bool | `false` | Enable creating PVCs for the compactor | +| compactor.persistence.size | string | `"10Gi"` | Size of persistent disk | +| compactor.persistence.storageClass | string | `nil` | Storage class to be used. If defined, storageClassName: . If set to "-", storageClassName: "", which disables dynamic provisioning. If empty or set to null, no storageClassName spec is set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). | +| compactor.persistence.whenDeleted | string | `"Retain"` | | +| compactor.persistence.whenScaled | string | `"Retain"` | | +| compactor.podAnnotations | object | `{}` | Annotations for compactor pods | +| compactor.podLabels | object | `{}` | Labels for compactor pods | +| compactor.priorityClassName | string | `nil` | The name of the PriorityClass for compactor pods | +| compactor.readinessProbe | object | `{}` | readiness probe settings for ingester pods. If empty, use `loki.readinessProbe` | +| compactor.replicas | int | `1` | Number of replicas for the compactor | +| compactor.resources | object | `{}` | Resource requests and limits for the compactor | +| compactor.serviceAccount.annotations | object | `{}` | Annotations for the compactor service account | +| compactor.serviceAccount.automountServiceAccountToken | bool | `true` | Set this toggle to false to opt out of automounting API credentials for the service account | +| compactor.serviceAccount.create | bool | `false` | | +| compactor.serviceAccount.imagePullSecrets | list | `[]` | Image pull secrets for the compactor service account | +| compactor.serviceAccount.name | string | `nil` | The name of the ServiceAccount to use for the compactor. If not set and create is true, a name is generated by appending "-compactor" to the common ServiceAccount. | +| compactor.serviceLabels | object | `{}` | Labels for compactor service | +| compactor.terminationGracePeriodSeconds | int | `30` | Grace period to allow the compactor to shutdown before it is killed | +| compactor.tolerations | list | `[]` | Tolerations for compactor pods | +| distributor.affinity | string | Hard node and soft zone anti-affinity | Affinity for distributor pods. Passed through `tpl` and, thus, to be configured as string | +| distributor.appProtocol | object | `{"grpc":""}` | Adds the appProtocol field to the distributor service. This allows distributor to work with istio protocol selection. | +| distributor.appProtocol.grpc | string | `""` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| distributor.autoscaling.behavior.enabled | bool | `false` | Enable autoscaling behaviours | +| distributor.autoscaling.behavior.scaleDown | object | `{}` | define scale down policies, must conform to HPAScalingRules | +| distributor.autoscaling.behavior.scaleUp | object | `{}` | define scale up policies, must conform to HPAScalingRules | +| distributor.autoscaling.customMetrics | list | `[]` | Allows one to define custom metrics using the HPA/v2 schema (for example, Pods, Object or External metrics) | +| distributor.autoscaling.enabled | bool | `false` | Enable autoscaling for the distributor | +| distributor.autoscaling.maxReplicas | int | `3` | Maximum autoscaling replicas for the distributor | +| distributor.autoscaling.minReplicas | int | `1` | Minimum autoscaling replicas for the distributor | +| distributor.autoscaling.targetCPUUtilizationPercentage | int | `60` | Target CPU utilisation percentage for the distributor | +| distributor.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | Target memory utilisation percentage for the distributor | +| distributor.command | string | `nil` | Command to execute instead of defined in Docker image | +| distributor.extraArgs | list | `[]` | Additional CLI args for the distributor | +| distributor.extraContainers | list | `[]` | Containers to add to the distributor pods | +| distributor.extraEnv | list | `[]` | Environment variables to add to the distributor pods | +| distributor.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the distributor pods | +| distributor.extraVolumeMounts | list | `[]` | Volume mounts to add to the distributor pods | +| distributor.extraVolumes | list | `[]` | Volumes to add to the distributor pods | +| distributor.hostAliases | list | `[]` | hostAliases to add | +| distributor.image.registry | string | `nil` | The Docker registry for the distributor image. Overrides `loki.image.registry` | +| distributor.image.repository | string | `nil` | Docker image repository for the distributor image. Overrides `loki.image.repository` | +| distributor.image.tag | string | `nil` | Docker image tag for the distributor image. Overrides `loki.image.tag` | +| distributor.maxSurge | int | `0` | Max Surge for distributor pods | +| distributor.maxUnavailable | string | `nil` | Pod Disruption Budget maxUnavailable | +| distributor.nodeSelector | object | `{}` | Node selector for distributor pods | +| distributor.podAnnotations | object | `{}` | Annotations for distributor pods | +| distributor.podLabels | object | `{}` | Labels for distributor pods | +| distributor.priorityClassName | string | `nil` | The name of the PriorityClass for distributor pods | +| distributor.replicas | int | `1` | Number of replicas for the distributor | +| distributor.resources | object | `{}` | Resource requests and limits for the distributor | +| distributor.serviceLabels | object | `{}` | Labels for distributor service | +| distributor.terminationGracePeriodSeconds | int | `30` | Grace period to allow the distributor to shutdown before it is killed | +| distributor.tolerations | list | `[]` | Tolerations for distributor pods | +| fullnameOverride | string | `nil` | Overrides the chart's computed fullname | +| gateway.affinity | string | Hard node and soft zone anti-affinity | Affinity for gateway pods. Passed through `tpl` and, thus, to be configured as string | +| gateway.autoscaling.behavior.enabled | bool | `false` | Enable autoscaling behaviours | +| gateway.autoscaling.behavior.scaleDown | object | `{}` | define scale down policies, must conform to HPAScalingRules | +| gateway.autoscaling.behavior.scaleUp | object | `{}` | define scale up policies, must conform to HPAScalingRules | +| gateway.autoscaling.customMetrics | list | `[]` | Allows one to define custom metrics using the HPA/v2 schema (for example, Resource, Object or External metrics) | +| gateway.autoscaling.enabled | bool | `false` | Enable autoscaling for the gateway | +| gateway.autoscaling.maxReplicas | int | `3` | Maximum autoscaling replicas for the gateway | +| gateway.autoscaling.minReplicas | int | `1` | Minimum autoscaling replicas for the gateway | +| gateway.autoscaling.targetCPUUtilizationPercentage | int | `60` | Target CPU utilisation percentage for the gateway | +| gateway.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | Target memory utilisation percentage for the gateway | +| gateway.basicAuth.enabled | bool | `false` | Enables basic authentication for the gateway | +| gateway.basicAuth.existingSecret | string | `nil` | Existing basic auth secret to use. Must contain '.htpasswd' | +| gateway.basicAuth.htpasswd | string | See values.yaml | Uses the specified username and password to compute a htpasswd using Sprig's `htpasswd` function. The value is templated using `tpl`. Override this to use a custom htpasswd, e.g. in case the default causes high CPU load. | +| gateway.basicAuth.password | string | `nil` | The basic auth password for the gateway | +| gateway.basicAuth.username | string | `nil` | The basic auth username for the gateway | +| gateway.containerSecurityContext | object | `{"allowPrivilegeEscalation":false,"capabilities":{"drop":["ALL"]},"readOnlyRootFilesystem":true}` | The SecurityContext for gateway containers | +| gateway.deploymentStrategy | object | `{"type":"RollingUpdate"}` | See `kubectl explain deployment.spec.strategy` for more, ref: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy | +| gateway.dnsConfig | object | `{}` | DNSConfig for gateway pods | +| gateway.enabled | bool | `true` | Specifies whether the gateway should be enabled | +| gateway.extraArgs | list | `[]` | Additional CLI args for the gateway | +| gateway.extraContainers | list | `[]` | Containers to add to the gateway pods | +| gateway.extraEnv | list | `[]` | Environment variables to add to the gateway pods | +| gateway.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the gateway pods | +| gateway.extraVolumeMounts | list | `[]` | Volume mounts to add to the gateway pods | +| gateway.extraVolumes | list | `[]` | Volumes to add to the gateway pods | +| gateway.hostAliases | list | `[]` | hostAliases to add | +| gateway.image.pullPolicy | string | `"IfNotPresent"` | The gateway image pull policy | +| gateway.image.registry | string | `"docker.io"` | The Docker registry for the gateway image | +| gateway.image.repository | string | `"nginxinc/nginx-unprivileged"` | The gateway image repository | +| gateway.image.tag | string | `"1.20.2-alpine"` | The gateway image tag | +| gateway.ingress.annotations | object | `{}` | Annotations for the gateway ingress | +| gateway.ingress.enabled | bool | `false` | Specifies whether an ingress for the gateway should be created | +| gateway.ingress.hosts | list | `[{"host":"gateway.loki.example.com","paths":[{"path":"/"}]}]` | Hosts configuration for the gateway ingress | +| gateway.ingress.ingressClassName | string | `""` | Ingress Class Name. MAY be required for Kubernetes versions >= 1.18 For example: `ingressClassName: nginx` | +| gateway.ingress.tls | list | `[]` | TLS configuration for the gateway ingress | +| gateway.livenessProbe.httpGet.path | string | `"/"` | | +| gateway.livenessProbe.httpGet.port | string | `"http"` | | +| gateway.livenessProbe.initialDelaySeconds | int | `30` | | +| gateway.maxUnavailable | string | `nil` | Pod Disruption Budget maxUnavailable | +| gateway.nginxConfig.file | string | See values.yaml | Config file contents for Nginx. Passed through the `tpl` function to allow templating | +| gateway.nginxConfig.httpSnippet | string | `""` | Allows appending custom configuration to the http block | +| gateway.nginxConfig.logFormat | string | See values.yaml | NGINX log format | +| gateway.nginxConfig.resolver | string | `""` | Allows overriding the DNS resolver address nginx will use. | +| gateway.nginxConfig.serverSnippet | string | `""` | Allows appending custom configuration to the server block | +| gateway.nodeSelector | object | `{}` | Node selector for gateway pods | +| gateway.podAnnotations | object | `{}` | Annotations for gateway pods | +| gateway.podLabels | object | `{}` | Labels for gateway pods | +| gateway.podSecurityContext | object | `{"fsGroup":101,"runAsGroup":101,"runAsNonRoot":true,"runAsUser":101}` | The SecurityContext for gateway containers | +| gateway.priorityClassName | string | `nil` | The name of the PriorityClass for gateway pods | +| gateway.readinessProbe.httpGet.path | string | `"/"` | | +| gateway.readinessProbe.httpGet.port | string | `"http"` | | +| gateway.readinessProbe.initialDelaySeconds | int | `15` | | +| gateway.readinessProbe.timeoutSeconds | int | `1` | | +| gateway.replicas | int | `1` | Number of replicas for the gateway | +| gateway.resources | object | `{}` | Resource requests and limits for the gateway | +| gateway.service.annotations | object | `{}` | Annotations for the gateway service | +| gateway.service.appProtocol | string | `nil` | Set appProtocol for the service | +| gateway.service.clusterIP | string | `nil` | ClusterIP of the gateway service | +| gateway.service.labels | object | `{}` | Labels for gateway service | +| gateway.service.loadBalancerIP | string | `nil` | Load balancer IPO address if service type is LoadBalancer | +| gateway.service.loadBalancerSourceRanges | list | `[]` | Load balancer allow traffic from CIDR list if service type is LoadBalancer | +| gateway.service.nodePort | string | `nil` | Node port if service type is NodePort | +| gateway.service.port | int | `80` | Port of the gateway service | +| gateway.service.type | string | `"ClusterIP"` | Type of the gateway service | +| gateway.terminationGracePeriodSeconds | int | `30` | Grace period to allow the gateway to shutdown before it is killed | +| gateway.tolerations | list | `[]` | Tolerations for gateway pods | +| gateway.verboseLogging | bool | `true` | Enable logging of 2xx and 3xx HTTP requests | +| global.clusterDomain | string | `"cluster.local"` | configures cluster domain ("cluster.local" by default) | +| global.dnsNamespace | string | `"kube-system"` | configures DNS service namespace | +| global.dnsService | string | `"kube-dns"` | configures DNS service name | +| global.image.registry | string | `nil` | Overrides the Docker registry globally for all images | +| global.priorityClassName | string | `nil` | Overrides the priorityClassName for all pods | +| hostAliases | list | `[]` | hostAliases to add | +| imagePullSecrets | list | `[]` | Image pull secrets for Docker images | +| indexGateway.affinity | string | Hard node and soft zone anti-affinity | Affinity for index-gateway pods. Passed through `tpl` and, thus, to be configured as string | +| indexGateway.appProtocol | object | `{"grpc":""}` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| indexGateway.enabled | bool | `false` | Specifies whether the index-gateway should be enabled | +| indexGateway.extraArgs | list | `[]` | Additional CLI args for the index-gateway | +| indexGateway.extraContainers | list | `[]` | Containers to add to the index-gateway pods | +| indexGateway.extraEnv | list | `[]` | Environment variables to add to the index-gateway pods | +| indexGateway.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the index-gateway pods | +| indexGateway.extraVolumeMounts | list | `[]` | Volume mounts to add to the index-gateway pods | +| indexGateway.extraVolumes | list | `[]` | Volumes to add to the index-gateway pods | +| indexGateway.hostAliases | list | `[]` | hostAliases to add | +| indexGateway.image.registry | string | `nil` | The Docker registry for the index-gateway image. Overrides `loki.image.registry` | +| indexGateway.image.repository | string | `nil` | Docker image repository for the index-gateway image. Overrides `loki.image.repository` | +| indexGateway.image.tag | string | `nil` | Docker image tag for the index-gateway image. Overrides `loki.image.tag` | +| indexGateway.initContainers | list | `[]` | Init containers to add to the index-gateway pods | +| indexGateway.joinMemberlist | bool | `true` | Whether the index gateway should join the memberlist hashring | +| indexGateway.maxUnavailable | string | `nil` | Pod Disruption Budget maxUnavailable | +| indexGateway.nodeSelector | object | `{}` | Node selector for index-gateway pods | +| indexGateway.persistence.annotations | object | `{}` | Annotations for index gateway PVCs | +| indexGateway.persistence.enableStatefulSetAutoDeletePVC | bool | `false` | Enable StatefulSetAutoDeletePVC feature | +| indexGateway.persistence.enabled | bool | `false` | Enable creating PVCs which is required when using boltdb-shipper | +| indexGateway.persistence.inMemory | bool | `false` | Use emptyDir with ramdisk for storage. **Please note that all data in indexGateway will be lost on pod restart** | +| indexGateway.persistence.size | string | `"10Gi"` | Size of persistent or memory disk | +| indexGateway.persistence.storageClass | string | `nil` | Storage class to be used. If defined, storageClassName: . If set to "-", storageClassName: "", which disables dynamic provisioning. If empty or set to null, no storageClassName spec is set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). | +| indexGateway.persistence.whenDeleted | string | `"Retain"` | | +| indexGateway.persistence.whenScaled | string | `"Retain"` | | +| indexGateway.podAnnotations | object | `{}` | Annotations for index-gateway pods | +| indexGateway.podLabels | object | `{}` | Labels for index-gateway pods | +| indexGateway.priorityClassName | string | `nil` | The name of the PriorityClass for index-gateway pods | +| indexGateway.replicas | int | `1` | Number of replicas for the index-gateway | +| indexGateway.resources | object | `{}` | Resource requests and limits for the index-gateway | +| indexGateway.serviceLabels | object | `{}` | Labels for index-gateway service | +| indexGateway.terminationGracePeriodSeconds | int | `300` | Grace period to allow the index-gateway to shutdown before it is killed. | +| indexGateway.tolerations | list | `[]` | Tolerations for index-gateway pods | +| ingester.affinity | string | Hard node and soft zone anti-affinity | Affinity for ingester pods. Passed through `tpl` and, thus, to be configured as string | +| ingester.appProtocol | object | `{"grpc":""}` | Adds the appProtocol field to the ingester service. This allows ingester to work with istio protocol selection. | +| ingester.appProtocol.grpc | string | `""` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| ingester.autoscaling.behavior.enabled | bool | `false` | Enable autoscaling behaviours | +| ingester.autoscaling.behavior.scaleDown | object | `{}` | define scale down policies, must conform to HPAScalingRules | +| ingester.autoscaling.behavior.scaleUp | object | `{}` | define scale up policies, must conform to HPAScalingRules | +| ingester.autoscaling.customMetrics | list | `[]` | Allows one to define custom metrics using the HPA/v2 schema (for example, Pods, Object or External metrics) | +| ingester.autoscaling.enabled | bool | `false` | Enable autoscaling for the ingester | +| ingester.autoscaling.maxReplicas | int | `3` | Maximum autoscaling replicas for the ingester | +| ingester.autoscaling.minReplicas | int | `1` | Minimum autoscaling replicas for the ingester | +| ingester.autoscaling.targetCPUUtilizationPercentage | int | `60` | Target CPU utilisation percentage for the ingester | +| ingester.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | Target memory utilisation percentage for the ingester | +| ingester.command | string | `nil` | Command to execute instead of defined in Docker image | +| ingester.extraArgs | list | `[]` | Additional CLI args for the ingester | +| ingester.extraContainers | list | `[]` | Containers to add to the ingester pods | +| ingester.extraEnv | list | `[]` | Environment variables to add to the ingester pods | +| ingester.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the ingester pods | +| ingester.extraVolumeMounts | list | `[]` | Volume mounts to add to the ingester pods | +| ingester.extraVolumes | list | `[]` | Volumes to add to the ingester pods | +| ingester.hostAliases | list | `[]` | hostAliases to add | +| ingester.image.registry | string | `nil` | The Docker registry for the ingester image. Overrides `loki.image.registry` | +| ingester.image.repository | string | `nil` | Docker image repository for the ingester image. Overrides `loki.image.repository` | +| ingester.image.tag | string | `nil` | Docker image tag for the ingester image. Overrides `loki.image.tag` | +| ingester.initContainers | list | `[]` | Init containers to add to the ingester pods | +| ingester.kind | string | `"StatefulSet"` | Kind of deployment [StatefulSet/Deployment] | +| ingester.lifecycle | object | `{}` | Lifecycle for the ingester container | +| ingester.livenessProbe | object | `{}` | liveness probe settings for ingester pods. If empty use `loki.livenessProbe` | +| ingester.maxSurge | int | `0` | Max Surge for ingester pods | +| ingester.maxUnavailable | string | `nil` | Pod Disruption Budget maxUnavailable | +| ingester.nodeSelector | object | `{}` | Node selector for ingester pods | +| ingester.persistence.claims | list | `[{"name":"data","size":"10Gi","storageClass":null}]` | List of the ingester PVCs @notationType -- list | +| ingester.persistence.enableStatefulSetAutoDeletePVC | bool | `false` | Enable StatefulSetAutoDeletePVC feature | +| ingester.persistence.enabled | bool | `false` | Enable creating PVCs which is required when using boltdb-shipper | +| ingester.persistence.inMemory | bool | `false` | Use emptyDir with ramdisk for storage. **Please note that all data in ingester will be lost on pod restart** | +| ingester.persistence.whenDeleted | string | `"Retain"` | | +| ingester.persistence.whenScaled | string | `"Retain"` | | +| ingester.podAnnotations | object | `{}` | Annotations for ingester pods | +| ingester.podLabels | object | `{}` | Labels for ingester pods | +| ingester.priorityClassName | string | `nil` | The name of the PriorityClass for ingester pods | +| ingester.readinessProbe | object | `{}` | readiness probe settings for ingester pods. If empty, use `loki.readinessProbe` | +| ingester.replicas | int | `1` | Number of replicas for the ingester | +| ingester.resources | object | `{}` | Resource requests and limits for the ingester | +| ingester.serviceLabels | object | `{}` | Labels for ingestor service | +| ingester.terminationGracePeriodSeconds | int | `300` | Grace period to allow the ingester to shutdown before it is killed. Especially for the ingestor, this must be increased. It must be long enough so ingesters can be gracefully shutdown flushing/transferring all data and to successfully leave the member ring on shutdown. | +| ingester.tolerations | list | `[]` | Tolerations for ingester pods | +| ingester.topologySpreadConstraints | string | Defaults to allow skew no more then 1 node per AZ | topologySpread for ingester pods. Passed through `tpl` and, thus, to be configured as string | +| ingress.annotations | object | `{}` | | +| ingress.enabled | bool | `false` | | +| ingress.hosts[0] | string | `"loki.example.com"` | | +| ingress.paths.distributor[0] | string | `"/api/prom/push"` | | +| ingress.paths.distributor[1] | string | `"/loki/api/v1/push"` | | +| ingress.paths.querier[0] | string | `"/api/prom/tail"` | | +| ingress.paths.querier[1] | string | `"/loki/api/v1/tail"` | | +| ingress.paths.query-frontend[0] | string | `"/loki/api"` | | +| ingress.paths.ruler[0] | string | `"/api/prom/rules"` | | +| ingress.paths.ruler[1] | string | `"/loki/api/v1/rules"` | | +| ingress.paths.ruler[2] | string | `"/prometheus/api/v1/rules"` | | +| ingress.paths.ruler[3] | string | `"/prometheus/api/v1/alerts"` | | +| loki.annotations | object | `{}` | If set, these annotations are added to all of the Kubernetes controllers (Deployments, StatefulSets, etc) that this chart launches. Use this to implement something like the "Wave" controller or another controller that is monitoring top level deployment resources. | +| loki.appProtocol | string | `""` | Adds the appProtocol field to the memberlist service. This allows memberlist to work with istio protocol selection. Ex: "http" or "tcp" | +| loki.command | string | `nil` | Common command override for all pods (except gateway) | +| loki.config | string | See values.yaml | Config file contents for Loki | +| loki.configAsSecret | bool | `false` | Store the loki configuration as a secret. | +| loki.configSecretAnnotations | object | `{}` | Annotations for the secret with loki configuration. | +| loki.configSecretLabels | object | `{}` | Additional labels for the secret with loki configuration. | +| loki.containerSecurityContext | object | `{"allowPrivilegeEscalation":false,"capabilities":{"drop":["ALL"]},"readOnlyRootFilesystem":true}` | The SecurityContext for Loki containers | +| loki.existingSecretForConfig | string | `""` | Specify an existing secret containing loki configuration. If non-empty, overrides `loki.config` | +| loki.image.pullPolicy | string | `"IfNotPresent"` | Docker image pull policy | +| loki.image.registry | string | `"docker.io"` | The Docker registry | +| loki.image.repository | string | `"grafana/loki"` | Docker image repository | +| loki.image.tag | string | `nil` | Overrides the image tag whose default is the chart's appVersion | +| loki.livenessProbe.httpGet.path | string | `"/ready"` | | +| loki.livenessProbe.httpGet.port | string | `"http"` | | +| loki.livenessProbe.initialDelaySeconds | int | `300` | | +| loki.podAnnotations | object | `{}` | Common annotations for all pods | +| loki.podLabels | object | `{}` | Common labels for all pods | +| loki.podSecurityContext | object | `{"fsGroup":10001,"runAsGroup":10001,"runAsNonRoot":true,"runAsUser":10001}` | The SecurityContext for Loki pods | +| loki.readinessProbe.httpGet.path | string | `"/ready"` | | +| loki.readinessProbe.httpGet.port | string | `"http"` | | +| loki.readinessProbe.initialDelaySeconds | int | `30` | | +| loki.readinessProbe.timeoutSeconds | int | `1` | | +| loki.revisionHistoryLimit | int | `10` | The number of old ReplicaSets to retain to allow rollback | +| loki.schemaConfig | object | `{"configs":[{"from":"2020-09-07","index":{"period":"24h","prefix":"loki_index_"},"object_store":"filesystem","schema":"v11","store":"boltdb-shipper"}]}` | Check https://grafana.com/docs/loki/latest/configuration/#schema_config for more info on how to configure schemas | +| loki.server.http_listen_port | int | `3100` | HTTP server listen port | +| loki.serviceAnnotations | object | `{}` | Common annotations for all loki services | +| loki.storageConfig | object | `{"boltdb_shipper":{"active_index_directory":"/var/loki/index","cache_location":"/var/loki/cache","cache_ttl":"168h","shared_store":"filesystem"},"filesystem":{"directory":"/var/loki/chunks"}}` | Check https://grafana.com/docs/loki/latest/configuration/#storage_config for more info on how to configure storages | +| loki.structuredConfig | object | `{}` | Structured loki configuration, takes precedence over `loki.config`, `loki.schemaConfig`, `loki.storageConfig` | +| memcached.appProtocol | string | `""` | Adds the appProtocol field to the memcached services. This allows memcached to work with istio protocol selection. Ex: "http" or "tcp" | +| memcached.containerSecurityContext | object | `{"allowPrivilegeEscalation":false,"capabilities":{"drop":["ALL"]},"readOnlyRootFilesystem":true}` | The SecurityContext for memcached containers | +| memcached.image.pullPolicy | string | `"IfNotPresent"` | Memcached Docker image pull policy | +| memcached.image.registry | string | `"docker.io"` | The Docker registry for the memcached | +| memcached.image.repository | string | `"memcached"` | Memcached Docker image repository | +| memcached.image.tag | string | `"1.6.21-alpine"` | Memcached Docker image tag | +| memcached.livenessProbe.initialDelaySeconds | int | `10` | | +| memcached.livenessProbe.tcpSocket.port | string | `"http"` | | +| memcached.podLabels | object | `{}` | Labels for memcached pods | +| memcached.podSecurityContext | object | `{"fsGroup":11211,"runAsGroup":11211,"runAsNonRoot":true,"runAsUser":11211}` | The SecurityContext for memcached pods | +| memcached.readinessProbe.initialDelaySeconds | int | `5` | | +| memcached.readinessProbe.tcpSocket.port | string | `"http"` | | +| memcached.readinessProbe.timeoutSeconds | int | `1` | | +| memcached.serviceAnnotations | object | `{}` | Common annotations for all memcached services | +| memcachedChunks.affinity | string | Hard node and soft zone anti-affinity | Affinity for memcached-chunks pods. Passed through `tpl` and, thus, to be configured as string | +| memcachedChunks.enabled | bool | `false` | Specifies whether the Memcached chunks cache should be enabled | +| memcachedChunks.extraArgs | list | `["-I 32m"]` | Additional CLI args for memcached-chunks | +| memcachedChunks.extraContainers | list | `[]` | Containers to add to the memcached-chunks pods | +| memcachedChunks.extraEnv | list | `[]` | Environment variables to add to memcached-chunks pods | +| memcachedChunks.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to memcached-chunks pods | +| memcachedChunks.extraVolumeMounts | list | `[]` | List of additional volumes to be mounted for the memcached-chunks statefulset | +| memcachedChunks.hostAliases | list | `[]` | hostAliases to add | +| memcachedChunks.maxUnavailable | string | `nil` | Pod Disruption Budget maxUnavailable | +| memcachedChunks.nodeSelector | object | `{}` | Node selector for memcached-chunks pods | +| memcachedChunks.persistence.enabled | bool | `false` | Enable creating PVCs which will persist cached data through restarts | +| memcachedChunks.persistence.size | string | `"10Gi"` | Size of persistent or memory disk | +| memcachedChunks.persistence.storageClass | string | `nil` | Storage class to be used. If defined, storageClassName: . If set to "-", storageClassName: "", which disables dynamic provisioning. If empty or set to null, no storageClassName spec is set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). | +| memcachedChunks.podAnnotations | object | `{}` | Annotations for memcached-chunks pods | +| memcachedChunks.podLabels | object | `{}` | Labels for memcached-chunks pods | +| memcachedChunks.priorityClassName | string | `nil` | The name of the PriorityClass for memcached-chunks pods | +| memcachedChunks.replicas | int | `1` | Number of replicas for memcached-chunks | +| memcachedChunks.resources | object | `{}` | Resource requests and limits for memcached-chunks | +| memcachedChunks.serviceLabels | object | `{}` | Labels for memcached-chunks service | +| memcachedChunks.terminationGracePeriodSeconds | int | `30` | Grace period to allow memcached-chunks to shutdown before it is killed | +| memcachedChunks.tolerations | list | `[]` | Tolerations for memcached-chunks pods | +| memcachedChunks.volumeClaimTemplates | list | `[]` | List of additional PVCs to be created for the memcached-chunks statefulset | +| memcachedExporter.containerSecurityContext | object | `{"allowPrivilegeEscalation":false,"capabilities":{"drop":["ALL"]},"readOnlyRootFilesystem":true}` | The SecurityContext for memcachedExporter containers | +| memcachedExporter.enabled | bool | `false` | Specifies whether the Memcached Exporter should be enabled | +| memcachedExporter.image.pullPolicy | string | `"IfNotPresent"` | Memcached Exporter Docker image pull policy | +| memcachedExporter.image.registry | string | `"docker.io"` | The Docker registry for the Memcached Exporter | +| memcachedExporter.image.repository | string | `"prom/memcached-exporter"` | Memcached Exporter Docker image repository | +| memcachedExporter.image.tag | string | `"v0.13.0"` | Memcached Exporter Docker image tag | +| memcachedExporter.podLabels | object | `{}` | Labels for memcached-exporter pods | +| memcachedExporter.resources | object | `{}` | Memcached Exporter resource requests and limits | +| memcachedFrontend.affinity | string | Hard node and soft zone anti-affinity | Affinity for memcached-frontend pods. Passed through `tpl` and, thus, to be configured as string | +| memcachedFrontend.enabled | bool | `false` | Specifies whether the Memcached frontend cache should be enabled | +| memcachedFrontend.extraArgs | list | `["-I 32m"]` | Additional CLI args for memcached-frontend | +| memcachedFrontend.extraContainers | list | `[]` | Containers to add to the memcached-frontend pods | +| memcachedFrontend.extraEnv | list | `[]` | Environment variables to add to memcached-frontend pods | +| memcachedFrontend.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to memcached-frontend pods | +| memcachedFrontend.hostAliases | list | `[]` | hostAliases to add | +| memcachedFrontend.maxUnavailable | int | `1` | Pod Disruption Budget maxUnavailable | +| memcachedFrontend.nodeSelector | object | `{}` | Node selector for memcached-frontend pods | +| memcachedFrontend.persistence.enabled | bool | `false` | Enable creating PVCs which will persist cached data through restarts | +| memcachedFrontend.persistence.size | string | `"10Gi"` | Size of persistent or memory disk | +| memcachedFrontend.persistence.storageClass | string | `nil` | Storage class to be used. If defined, storageClassName: . If set to "-", storageClassName: "", which disables dynamic provisioning. If empty or set to null, no storageClassName spec is set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). | +| memcachedFrontend.podAnnotations | object | `{}` | Annotations for memcached-frontend pods | +| memcachedFrontend.podLabels | object | `{}` | Labels for memcached-frontend pods | +| memcachedFrontend.priorityClassName | string | `nil` | The name of the PriorityClass for memcached-frontend pods | +| memcachedFrontend.replicas | int | `1` | Number of replicas for memcached-frontend | +| memcachedFrontend.resources | object | `{}` | Resource requests and limits for memcached-frontend | +| memcachedFrontend.serviceLabels | object | `{}` | Labels for memcached-frontend service | +| memcachedFrontend.terminationGracePeriodSeconds | int | `30` | Grace period to allow memcached-frontend to shutdown before it is killed | +| memcachedFrontend.tolerations | list | `[]` | Tolerations for memcached-frontend pods | +| memcachedIndexQueries.affinity | string | Hard node and soft zone anti-affinity | Affinity for memcached-index-queries pods. Passed through `tpl` and, thus, to be configured as string | +| memcachedIndexQueries.enabled | bool | `false` | Specifies whether the Memcached index queries cache should be enabled | +| memcachedIndexQueries.extraArgs | list | `["-I 32m"]` | Additional CLI args for memcached-index-queries | +| memcachedIndexQueries.extraContainers | list | `[]` | Containers to add to the memcached-index-queries pods | +| memcachedIndexQueries.extraEnv | list | `[]` | Environment variables to add to memcached-index-queries pods | +| memcachedIndexQueries.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to memcached-index-queries pods | +| memcachedIndexQueries.hostAliases | list | `[]` | hostAliases to add | +| memcachedIndexQueries.maxUnavailable | string | `nil` | Pod Disruption Budget maxUnavailable | +| memcachedIndexQueries.nodeSelector | object | `{}` | Node selector for memcached-index-queries pods | +| memcachedIndexQueries.persistence.enabled | bool | `false` | Enable creating PVCs which will persist cached data through restarts | +| memcachedIndexQueries.persistence.size | string | `"10Gi"` | Size of persistent or memory disk | +| memcachedIndexQueries.persistence.storageClass | string | `nil` | Storage class to be used. If defined, storageClassName: . If set to "-", storageClassName: "", which disables dynamic provisioning. If empty or set to null, no storageClassName spec is set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). | +| memcachedIndexQueries.podAnnotations | object | `{}` | Annotations for memcached-index-queries pods | +| memcachedIndexQueries.podLabels | object | `{}` | Labels for memcached-index-queries pods | +| memcachedIndexQueries.priorityClassName | string | `nil` | The name of the PriorityClass for memcached-index-queries pods | +| memcachedIndexQueries.replicas | int | `1` | Number of replicas for memcached-index-queries | +| memcachedIndexQueries.resources | object | `{}` | Resource requests and limits for memcached-index-queries | +| memcachedIndexQueries.serviceLabels | object | `{}` | Labels for memcached-index-queries service | +| memcachedIndexQueries.terminationGracePeriodSeconds | int | `30` | Grace period to allow memcached-index-queries to shutdown before it is killed | +| memcachedIndexQueries.tolerations | list | `[]` | Tolerations for memcached-index-queries pods | +| memcachedIndexWrites.affinity | string | Hard node and soft zone anti-affinity | Affinity for memcached-index-writes pods. Passed through `tpl` and, thus, to be configured as string | +| memcachedIndexWrites.enabled | bool | `false` | Specifies whether the Memcached index writes cache should be enabled | +| memcachedIndexWrites.extraArgs | list | `["-I 32m"]` | Additional CLI args for memcached-index-writes | +| memcachedIndexWrites.extraContainers | list | `[]` | Containers to add to the memcached-index-writes pods | +| memcachedIndexWrites.extraEnv | list | `[]` | Environment variables to add to memcached-index-writes pods | +| memcachedIndexWrites.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to memcached-index-writes pods | +| memcachedIndexWrites.hostAliases | list | `[]` | hostAliases to add | +| memcachedIndexWrites.maxUnavailable | string | `nil` | Pod Disruption Budget maxUnavailable | +| memcachedIndexWrites.nodeSelector | object | `{}` | Node selector for memcached-index-writes pods | +| memcachedIndexWrites.persistence.enabled | bool | `false` | Enable creating PVCs which will persist cached data through restarts | +| memcachedIndexWrites.persistence.size | string | `"10Gi"` | Size of persistent or memory disk | +| memcachedIndexWrites.persistence.storageClass | string | `nil` | Storage class to be used. If defined, storageClassName: . If set to "-", storageClassName: "", which disables dynamic provisioning. If empty or set to null, no storageClassName spec is set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). | +| memcachedIndexWrites.podAnnotations | object | `{}` | Annotations for memcached-index-writes pods | +| memcachedIndexWrites.podLabels | object | `{}` | Labels for memcached-index-writes pods | +| memcachedIndexWrites.priorityClassName | string | `nil` | The name of the PriorityClass for memcached-index-writes pods | +| memcachedIndexWrites.replicas | int | `1` | Number of replicas for memcached-index-writes | +| memcachedIndexWrites.resources | object | `{}` | Resource requests and limits for memcached-index-writes | +| memcachedIndexWrites.serviceLabels | object | `{}` | Labels for memcached-index-writes service | +| memcachedIndexWrites.terminationGracePeriodSeconds | int | `30` | Grace period to allow memcached-index-writes to shutdown before it is killed | +| memcachedIndexWrites.tolerations | list | `[]` | Tolerations for memcached-index-writes pods | +| nameOverride | string | `nil` | Overrides the chart's name | +| networkPolicy.alertmanager.namespaceSelector | object | `{}` | Specifies the namespace the alertmanager is running in | +| networkPolicy.alertmanager.podSelector | object | `{}` | Specifies the alertmanager Pods. As this is cross-namespace communication, you also need the namespaceSelector. | +| networkPolicy.alertmanager.port | int | `9093` | Specify the alertmanager port used for alerting | +| networkPolicy.discovery.namespaceSelector | object | `{}` | Specifies the namespace the discovery Pods are running in | +| networkPolicy.discovery.podSelector | object | `{}` | Specifies the Pods labels used for discovery. As this is cross-namespace communication, you also need the namespaceSelector. | +| networkPolicy.discovery.port | string | `nil` | Specify the port used for discovery | +| networkPolicy.enabled | bool | `false` | Specifies whether Network Policies should be created | +| networkPolicy.externalStorage.cidrs | list | `[]` | Specifies specific network CIDRs you want to limit access to | +| networkPolicy.externalStorage.ports | list | `[]` | Specify the port used for external storage, e.g. AWS S3 | +| networkPolicy.ingress.namespaceSelector | object | `{}` | Specifies the namespaces which are allowed to access the http port | +| networkPolicy.ingress.podSelector | object | `{}` | Specifies the Pods which are allowed to access the http port. As this is cross-namespace communication, you also need the namespaceSelector. | +| networkPolicy.metrics.cidrs | list | `[]` | Specifies specific network CIDRs which are allowed to access the metrics port. In case you use namespaceSelector, you also have to specify your kubelet networks here. The metrics ports are also used for probes. | +| networkPolicy.metrics.namespaceSelector | object | `{}` | Specifies the namespaces which are allowed to access the metrics port | +| networkPolicy.metrics.podSelector | object | `{}` | Specifies the Pods which are allowed to access the metrics port. As this is cross-namespace communication, you also need the namespaceSelector. | +| prometheusRule.annotations | object | `{}` | PrometheusRule annotations | +| prometheusRule.enabled | bool | `false` | If enabled, a PrometheusRule resource for Prometheus Operator is created | +| prometheusRule.groups | list | `[]` | Contents of Prometheus rules file | +| prometheusRule.labels | object | `{}` | Additional PrometheusRule labels | +| prometheusRule.namespace | string | `nil` | Alternative namespace for the PrometheusRule resource | +| querier.affinity | string | Hard node and soft zone anti-affinity | Affinity for querier pods. Passed through `tpl` and, thus, to be configured as string | +| querier.appProtocol | object | `{"grpc":""}` | Adds the appProtocol field to the querier service. This allows querier to work with istio protocol selection. | +| querier.appProtocol.grpc | string | `""` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| querier.autoscaling.behavior.enabled | bool | `false` | Enable autoscaling behaviours | +| querier.autoscaling.behavior.scaleDown | object | `{}` | define scale down policies, must conform to HPAScalingRules | +| querier.autoscaling.behavior.scaleUp | object | `{}` | define scale up policies, must conform to HPAScalingRules | +| querier.autoscaling.customMetrics | list | `[]` | Allows one to define custom metrics using the HPA/v2 schema (for example, Pods, Object or External metrics) | +| querier.autoscaling.enabled | bool | `false` | Enable autoscaling for the querier, this is only used if `indexGateway.enabled: true` | +| querier.autoscaling.maxReplicas | int | `3` | Maximum autoscaling replicas for the querier | +| querier.autoscaling.minReplicas | int | `1` | Minimum autoscaling replicas for the querier | +| querier.autoscaling.targetCPUUtilizationPercentage | int | `60` | Target CPU utilisation percentage for the querier | +| querier.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | Target memory utilisation percentage for the querier | +| querier.command | string | `nil` | Command to execute instead of defined in Docker image | +| querier.dnsConfig | object | `{}` | DNSConfig for querier pods | +| querier.extraArgs | list | `[]` | Additional CLI args for the querier | +| querier.extraContainers | list | `[]` | Containers to add to the querier pods | +| querier.extraEnv | list | `[]` | Environment variables to add to the querier pods | +| querier.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the querier pods | +| querier.extraVolumeMounts | list | `[]` | Volume mounts to add to the querier pods | +| querier.extraVolumes | list | `[]` | Volumes to add to the querier pods | +| querier.hostAliases | list | `[]` | hostAliases to add | +| querier.image.registry | string | `nil` | The Docker registry for the querier image. Overrides `loki.image.registry` | +| querier.image.repository | string | `nil` | Docker image repository for the querier image. Overrides `loki.image.repository` | +| querier.image.tag | string | `nil` | Docker image tag for the querier image. Overrides `loki.image.tag` | +| querier.initContainers | list | `[]` | Init containers to add to the querier pods | +| querier.maxSurge | int | `0` | Max Surge for querier pods | +| querier.maxUnavailable | string | `nil` | Pod Disruption Budget maxUnavailable | +| querier.nodeSelector | object | `{}` | Node selector for querier pods | +| querier.persistence.annotations | object | `{}` | Annotations for querier PVCs | +| querier.persistence.enabled | bool | `false` | Enable creating PVCs for the querier cache | +| querier.persistence.size | string | `"10Gi"` | Size of persistent disk | +| querier.persistence.storageClass | string | `nil` | Storage class to be used. If defined, storageClassName: . If set to "-", storageClassName: "", which disables dynamic provisioning. If empty or set to null, no storageClassName spec is set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). | +| querier.podAnnotations | object | `{}` | Annotations for querier pods | +| querier.podLabels | object | `{}` | Labels for querier pods | +| querier.priorityClassName | string | `nil` | The name of the PriorityClass for querier pods | +| querier.replicas | int | `1` | Number of replicas for the querier | +| querier.resources | object | `{}` | Resource requests and limits for the querier | +| querier.serviceLabels | object | `{}` | Labels for querier service | +| querier.terminationGracePeriodSeconds | int | `30` | Grace period to allow the querier to shutdown before it is killed | +| querier.tolerations | list | `[]` | Tolerations for querier pods | +| querier.topologySpreadConstraints | string | Defaults to allow skew no more then 1 node per AZ | topologySpread for querier pods. Passed through `tpl` and, thus, to be configured as string | +| queryFrontend.affinity | string | Hard node and soft zone anti-affinity | Affinity for query-frontend pods. Passed through `tpl` and, thus, to be configured as string | +| queryFrontend.appProtocol | object | `{"grpc":""}` | Adds the appProtocol field to the queryFrontend service. This allows queryFrontend to work with istio protocol selection. | +| queryFrontend.appProtocol.grpc | string | `""` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| queryFrontend.autoscaling.behavior.enabled | bool | `false` | Enable autoscaling behaviours | +| queryFrontend.autoscaling.behavior.scaleDown | object | `{}` | define scale down policies, must conform to HPAScalingRules | +| queryFrontend.autoscaling.behavior.scaleUp | object | `{}` | define scale up policies, must conform to HPAScalingRules | +| queryFrontend.autoscaling.customMetrics | list | `[]` | Allows one to define custom metrics using the HPA/v2 schema (for example, Pods, Object or External metrics) | +| queryFrontend.autoscaling.enabled | bool | `false` | Enable autoscaling for the query-frontend | +| queryFrontend.autoscaling.maxReplicas | int | `3` | Maximum autoscaling replicas for the query-frontend | +| queryFrontend.autoscaling.minReplicas | int | `1` | Minimum autoscaling replicas for the query-frontend | +| queryFrontend.autoscaling.targetCPUUtilizationPercentage | int | `60` | Target CPU utilisation percentage for the query-frontend | +| queryFrontend.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | Target memory utilisation percentage for the query-frontend | +| queryFrontend.command | string | `nil` | Command to execute instead of defined in Docker image | +| queryFrontend.extraArgs | list | `[]` | Additional CLI args for the query-frontend | +| queryFrontend.extraContainers | list | `[]` | Containers to add to the query-frontend pods | +| queryFrontend.extraEnv | list | `[]` | Environment variables to add to the query-frontend pods | +| queryFrontend.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the query-frontend pods | +| queryFrontend.extraVolumeMounts | list | `[]` | Volume mounts to add to the query-frontend pods | +| queryFrontend.extraVolumes | list | `[]` | Volumes to add to the query-frontend pods | +| queryFrontend.hostAliases | list | `[]` | hostAliases to add | +| queryFrontend.image.registry | string | `nil` | The Docker registry for the query-frontend image. Overrides `loki.image.registry` | +| queryFrontend.image.repository | string | `nil` | Docker image repository for the query-frontend image. Overrides `loki.image.repository` | +| queryFrontend.image.tag | string | `nil` | Docker image tag for the query-frontend image. Overrides `loki.image.tag` | +| queryFrontend.maxUnavailable | string | `nil` | Pod Disruption Budget maxUnavailable | +| queryFrontend.nodeSelector | object | `{}` | Node selector for query-frontend pods | +| queryFrontend.podAnnotations | object | `{}` | Annotations for query-frontend pods | +| queryFrontend.podLabels | object | `{}` | Labels for query-frontend pods | +| queryFrontend.priorityClassName | string | `nil` | The name of the PriorityClass for query-frontend pods | +| queryFrontend.replicas | int | `1` | Number of replicas for the query-frontend | +| queryFrontend.resources | object | `{}` | Resource requests and limits for the query-frontend | +| queryFrontend.serviceLabels | object | `{}` | Labels for query-frontend service | +| queryFrontend.terminationGracePeriodSeconds | int | `30` | Grace period to allow the query-frontend to shutdown before it is killed | +| queryFrontend.tolerations | list | `[]` | Tolerations for query-frontend pods | +| queryScheduler.affinity | string | Hard node and soft zone anti-affinity | Affinity for query-scheduler pods. Passed through `tpl` and, thus, to be configured as string | +| queryScheduler.appProtocol | object | `{"grpc":""}` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| queryScheduler.enabled | bool | `false` | Specifies whether the query-scheduler should be decoupled from the query-frontend | +| queryScheduler.extraArgs | list | `[]` | Additional CLI args for the query-scheduler | +| queryScheduler.extraContainers | list | `[]` | Containers to add to the query-scheduler pods | +| queryScheduler.extraEnv | list | `[]` | Environment variables to add to the query-scheduler pods | +| queryScheduler.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the query-scheduler pods | +| queryScheduler.extraVolumeMounts | list | `[]` | Volume mounts to add to the query-scheduler pods | +| queryScheduler.extraVolumes | list | `[]` | Volumes to add to the query-scheduler pods | +| queryScheduler.hostAliases | list | `[]` | hostAliases to add | +| queryScheduler.image.registry | string | `nil` | The Docker registry for the query-scheduler image. Overrides `loki.image.registry` | +| queryScheduler.image.repository | string | `nil` | Docker image repository for the query-scheduler image. Overrides `loki.image.repository` | +| queryScheduler.image.tag | string | `nil` | Docker image tag for the query-scheduler image. Overrides `loki.image.tag` | +| queryScheduler.maxUnavailable | int | `1` | Pod Disruption Budget maxUnavailable | +| queryScheduler.nodeSelector | object | `{}` | Node selector for query-scheduler pods | +| queryScheduler.podAnnotations | object | `{}` | Annotations for query-scheduler pods | +| queryScheduler.podLabels | object | `{}` | Labels for query-scheduler pods | +| queryScheduler.priorityClassName | string | `nil` | The name of the PriorityClass for query-scheduler pods | +| queryScheduler.replicas | int | `2` | Number of replicas for the query-scheduler. It should be lower than `-querier.max-concurrent` to avoid generating back-pressure in queriers; it's also recommended that this value evenly divides the latter | +| queryScheduler.resources | object | `{}` | Resource requests and limits for the query-scheduler | +| queryScheduler.serviceLabels | object | `{}` | Labels for query-scheduler service | +| queryScheduler.terminationGracePeriodSeconds | int | `30` | Grace period to allow the query-scheduler to shutdown before it is killed | +| queryScheduler.tolerations | list | `[]` | Tolerations for query-scheduler pods | +| rbac.pspEnabled | bool | `false` | If pspEnabled true, a PodSecurityPolicy is created for K8s that use psp. | +| rbac.sccEnabled | bool | `false` | For OpenShift set pspEnabled to 'false' and sccEnabled to 'true' to use the SecurityContextConstraints. | +| ruler.affinity | string | Hard node and soft zone anti-affinity | Affinity for ruler pods. Passed through `tpl` and, thus, to be configured as string | +| ruler.appProtocol | object | `{"grpc":""}` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| ruler.command | string | `nil` | Command to execute instead of defined in Docker image | +| ruler.directories | object | `{}` | Directories containing rules files | +| ruler.dnsConfig | object | `{}` | DNSConfig for ruler pods | +| ruler.enabled | bool | `false` | Specifies whether the ruler should be enabled | +| ruler.extraArgs | list | `[]` | Additional CLI args for the ruler | +| ruler.extraContainers | list | `[]` | Containers to add to the ruler pods | +| ruler.extraEnv | list | `[]` | Environment variables to add to the ruler pods | +| ruler.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the ruler pods | +| ruler.extraVolumeMounts | list | `[]` | Volume mounts to add to the ruler pods | +| ruler.extraVolumes | list | `[]` | Volumes to add to the ruler pods | +| ruler.hostAliases | list | `[]` | hostAliases to add | +| ruler.image.registry | string | `nil` | The Docker registry for the ruler image. Overrides `loki.image.registry` | +| ruler.image.repository | string | `nil` | Docker image repository for the ruler image. Overrides `loki.image.repository` | +| ruler.image.tag | string | `nil` | Docker image tag for the ruler image. Overrides `loki.image.tag` | +| ruler.initContainers | list | `[]` | Init containers to add to the ruler pods | +| ruler.kind | string | `"Deployment"` | Kind of deployment [StatefulSet/Deployment] | +| ruler.maxUnavailable | string | `nil` | Pod Disruption Budget maxUnavailable | +| ruler.nodeSelector | object | `{}` | Node selector for ruler pods | +| ruler.persistence.annotations | object | `{}` | Annotations for ruler PVCs | +| ruler.persistence.enabled | bool | `false` | Enable creating PVCs which is required when using recording rules | +| ruler.persistence.size | string | `"10Gi"` | Size of persistent disk | +| ruler.persistence.storageClass | string | `nil` | Storage class to be used. If defined, storageClassName: . If set to "-", storageClassName: "", which disables dynamic provisioning. If empty or set to null, no storageClassName spec is set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). | +| ruler.podAnnotations | object | `{}` | Annotations for ruler pods | +| ruler.podLabels | object | `{}` | Labels for compactor pods | +| ruler.priorityClassName | string | `nil` | The name of the PriorityClass for ruler pods | +| ruler.replicas | int | `1` | Number of replicas for the ruler | +| ruler.resources | object | `{}` | Resource requests and limits for the ruler | +| ruler.serviceLabels | object | `{}` | Labels for ruler service | +| ruler.terminationGracePeriodSeconds | int | `300` | Grace period to allow the ruler to shutdown before it is killed | +| ruler.tolerations | list | `[]` | Tolerations for ruler pods | +| runtimeConfig | object | `{}` | Provides a reloadable runtime configuration file for some specific configuration | +| serviceAccount.annotations | object | `{}` | Annotations for the service account | +| serviceAccount.automountServiceAccountToken | bool | `true` | Set this toggle to false to opt out of automounting API credentials for the service account | +| serviceAccount.create | bool | `true` | Specifies whether a ServiceAccount should be created | +| serviceAccount.imagePullSecrets | list | `[]` | Image pull secrets for the service account | +| serviceAccount.labels | object | `{}` | Labels for the service account | +| serviceAccount.name | string | `nil` | The name of the ServiceAccount to use. If not set and create is true, a name is generated using the fullname template | +| serviceMonitor.annotations | object | `{}` | ServiceMonitor annotations | +| serviceMonitor.enabled | bool | `false` | If enabled, ServiceMonitor resources for Prometheus Operator are created | +| serviceMonitor.interval | string | `nil` | ServiceMonitor scrape interval | +| serviceMonitor.labels | object | `{}` | Additional ServiceMonitor labels | +| serviceMonitor.matchExpressions | list | `[]` | Optional expressions to match on | +| serviceMonitor.metricRelabelings | list | `[]` | ServiceMonitor metric relabel configs to apply to samples before ingestion https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#endpoint | +| serviceMonitor.namespace | string | `nil` | Alternative namespace for ServiceMonitor resources | +| serviceMonitor.namespaceSelector | object | `{}` | Namespace selector for ServiceMonitor resources | +| serviceMonitor.relabelings | list | `[]` | ServiceMonitor relabel configs to apply to samples before scraping https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig | +| serviceMonitor.scheme | string | `"http"` | ServiceMonitor will use http by default, but you can pick https as well | +| serviceMonitor.scrapeTimeout | string | `nil` | ServiceMonitor scrape timeout in Go duration format (e.g. 15s) | +| serviceMonitor.targetLabels | list | `[]` | ServiceMonitor will add labels from the service to the Prometheus metric https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#servicemonitorspec | +| serviceMonitor.tlsConfig | string | `nil` | ServiceMonitor will use these tlsConfig settings to make the health check requests | +| tableManager.affinity | string | Hard node and soft zone anti-affinity | Affinity for table-manager pods. Passed through `tpl` and, thus, to be configured as string | +| tableManager.command | string | `nil` | Command to execute instead of defined in Docker image | +| tableManager.enabled | bool | `false` | Specifies whether the table-manager should be enabled | +| tableManager.extraArgs | list | `[]` | Additional CLI args for the table-manager | +| tableManager.extraContainers | list | `[]` | Containers to add to the table-manager pods | +| tableManager.extraEnv | list | `[]` | Environment variables to add to the table-manager pods | +| tableManager.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the table-manager pods | +| tableManager.extraVolumeMounts | list | `[]` | Volume mounts to add to the table-manager pods | +| tableManager.extraVolumes | list | `[]` | Volumes to add to the table-manager pods | +| tableManager.hostAliases | list | `[]` | hostAliases to add | +| tableManager.image.registry | string | `nil` | The Docker registry for the table-manager image. Overrides `loki.image.registry` | +| tableManager.image.repository | string | `nil` | Docker image repository for the table-manager image. Overrides `loki.image.repository` | +| tableManager.image.tag | string | `nil` | Docker image tag for the table-manager image. Overrides `loki.image.tag` | +| tableManager.nodeSelector | object | `{}` | Node selector for table-manager pods | +| tableManager.podAnnotations | object | `{}` | Annotations for table-manager pods | +| tableManager.podLabels | object | `{}` | Labels for table-manager pods | +| tableManager.priorityClassName | string | `nil` | The name of the PriorityClass for table-manager pods | +| tableManager.resources | object | `{}` | Resource requests and limits for the table-manager | +| tableManager.serviceLabels | object | `{}` | Labels for table-manager service | +| tableManager.terminationGracePeriodSeconds | int | `30` | Grace period to allow the table-manager to shutdown before it is killed | +| tableManager.tolerations | list | `[]` | Tolerations for table-manager pods | + +## Components + +The chart supports the components shown in the following table. +Ingester, distributor, querier, and query-frontend are always installed. +The other components are optional. + +| Component | Optional | Enabled by default | +| --- | --- | --- | +| gateway | ✅ | ✅ | +| ingester | ❎ | n/a | +| distributor | ❎ | n/a | +| querier | ❎ | n/a | +| query-frontend | ❎ | n/a | +| table-manager | ✅ | ❎ | +| compactor | ✅ | ❎ | +| ruler | ✅ | ❎ | +| index-gateway | ✅ | ❎ | +| memcached-chunks | ✅ | ❎ | +| memcached-frontend | ✅ | ❎ | +| memcached-index-queries | ✅ | ❎ | +| memcached-index-writes | ✅ | ❎ | + +## Configuration + +This chart configures Loki in microservices mode. +It has been tested to work with [boltdb-shipper](https://grafana.com/docs/loki/latest/operations/storage/boltdb-shipper/) +and [memberlist](https://grafana.com/docs/loki/latest/configuration/#memberlist_config) while other storage and discovery options should work as well. +However, the chart does not support setting up Consul or Etcd for discovery, +and it is not intended to support these going forward. +They would have to be set up separately. +Instead, memberlist can be used which does not require a separate key/value store. +The chart creates a headless service for the memberlist which ingester, distributor, querier, and ruler are part of. + +---- + +**NOTE:** +In its default configuration, the chart uses `boltdb-shipper` and `filesystem` as storage. +The reason for this is that the chart can be validated and installed in a CI pipeline. +However, this setup is not fully functional. +Querying will not be possible (or limited to the ingesters' in-memory caches) because that would otherwise require shared storage between ingesters and queriers +which the chart does not support and would require a volume that supports `ReadWriteMany` access mode anyways. +The recommendation is to use object storage, such as S3, GCS, MinIO, etc., or one of the other options documented at https://grafana.com/docs/loki/latest/storage/. + +Alternatively, in order to quickly test Loki using the filestore, the [single binary chart](https://github.com/grafana/helm-charts/tree/main/charts/loki) can be used. + +---- + +### Directory and File Locations + +* Volumes are mounted to `/var/loki`. The various directories Loki needs should be configured as subdirectories (e. g. `/var/loki/index`, `/var/loki/cache`). Loki will create the directories automatically. +* The config file is mounted to `/etc/loki/config/config.yaml` and passed as CLI arg. + +### Example configuration using memberlist, boltdb-shipper, and S3 for storage + +```yaml +loki: + structuredConfig: + ingester: + # Disable chunk transfer which is not possible with statefulsets + # and unnecessary for boltdb-shipper + max_transfer_retries: 0 + chunk_idle_period: 1h + chunk_target_size: 1536000 + max_chunk_age: 1h + storage_config: + aws: + s3: s3://eu-central-1 + bucketnames: my-loki-s3-bucket + boltdb_shipper: + shared_store: s3 + schema_config: + configs: + - from: 2020-09-07 + store: boltdb-shipper + object_store: aws + schema: v11 + index: + prefix: loki_index_ + period: 24h +``` + +The above configuration selectively overrides default values found in the `loki.config` template file. + +Using `loki.structuredConfig` it is possible to externally set most any configuration parameter (special considerations for elements of an array). + +``` +helm upgrade loki-distributed --install -f values.yaml --set loki.structuredConfig.storage_config.aws.bucketnames=my-loki-bucket +``` + +`loki.config`, `loki.schemaConfig` and `loki.storageConfig` may also be used in conjuction with `loki.structuredConfig`. Values found in `loki.structuredConfig` will take precedence. Array values, such as those found in `loki.schema_config` will be overridden wholesale and not amended to. + +For `loki.schema_config` its generally expected that this will always be configured per usage as its values over time are in reference to the history of loki schema versions and schema configurations throughout the lifetime of a given loki instance. + +Note that when using `loki.config` must be configured as string. +That's required because it is passed through the `tpl` function in order to support templating. + +When using `loki.config` the passed in template must include template sections for `loki.schemaConfig` and `loki.storageConfig` for those to continue to work as expected. + +Because the config file is templated, it is also possible to reference other values provided to helm e.g. externalize S3 bucket names: + +```yaml +loki: + config: | + storage_config: + aws: + s3: s3://eu-central-1 + bucketnames: {{ .Values.bucketnames }} +``` + +```console +helm upgrade loki-distributed --install -f values.yaml --set bucketnames=my-loki-bucket +``` + +## Gateway + +By default and inspired by Grafana's [Tanka setup](https://github.com/grafana/loki/tree/master/production/ksonnet/loki), the chart installs the gateway component which is an NGINX that exposes Loki's API +and automatically proxies requests to the correct Loki components (distributor, querier, query-frontend). +The gateway must be enabled if an Ingress is required, since the Ingress exposes the gateway only. +If the gateway is enabled, Grafana and log shipping agents, such as Promtail, should be configured to use the gateway. +If NetworkPolicies are enabled, they are more restrictive if the gateway is enabled. + +## Metrics + +Loki exposes Prometheus metrics. +The chart can create ServiceMonitor objects for all Loki components. + +```yaml +serviceMonitor: + enabled: true +``` + +Furthermore, it is possible to add Prometheus rules: + +```yaml +prometheusRule: + enabled: true + groups: + - name: loki-rules + rules: + - record: job:loki_request_duration_seconds_bucket:sum_rate + expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job) + - record: job_route:loki_request_duration_seconds_bucket:sum_rate + expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route) + - record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate + expr: sum(rate(container_cpu_usage_seconds_total[1m])) by (node, namespace, pod, container) +``` + +## Caching + +The chart can configure up to four Memcached instances for the various caches Lokis can use. +Configuration works the same for all caches. +The configuration of `memcached-chunks` below demonstrates setting additional options. + +Exporters for the Memcached instances can be configured as well. + +```yaml +memcachedExporter: + enabled: true +``` + +### memcached-chunks + +```yaml +memcachedChunks: + enabled: true + replicas: 2 + extraArgs: + - -m 2048 + - -I 2m + - -v + resources: + requests: + cpu: 500m + memory: 3Gi + limits: + cpu: "2" + memory: 3Gi + +loki: + config: | + chunk_store_config: + chunk_cache_config: + memcached: + batch_size: 100 + parallelism: 100 + memcached_client: + consistent_hash: true + host: {{ include "loki.memcachedChunksFullname" . }} + service: memcached-client +``` + +### memcached-frontend + +```yaml +memcachedFrontend: + enabled: true + +loki: + config: | + query_range: + cache_results: true + results_cache: + cache: + memcached_client: + consistent_hash: true + host: {{ include "loki.memcachedFrontendFullname" . }} + max_idle_conns: 16 + service: memcached-client + timeout: 500ms + update_interval: 1m +``` + +### memcached-index-queries + +```yaml +memcachedIndexQueries: + enabled: true + +loki: + config: | + storage_config: + index_queries_cache_config: + memcached: + batch_size: 100 + parallelism: 100 + memcached_client: + consistent_hash: true + host: {{ include "loki.memcachedIndexQueriesFullname" . }} + service: memcached-client +``` + +### memcached-index-writes + +NOTE: This cache is not used with `boltdb-shipper` and should not be enabled in that case. + +```yaml +memcachedIndexWrite: + enabled: true + +loki: + config: | + chunk_store_config: + write_dedupe_cache_config: + memcached: + batch_size: 100 + parallelism: 100 + memcached_client: + consistent_hash: true + host: {{ include "loki.memcachedIndexWritesFullname" . }} + service: memcached-client +``` + +## Compactor + +Compactor is an optional component which must explicitly be enabled. +The chart automatically sets the correct working directory as command-line arg. +The correct storage backend must be configured, e.g. `s3`. + +```yaml +compactor: + enabled: true + +loki: + config: | + compactor: + shared_store: s3 +``` + +## Ruler + +Ruler is an optional component which must explicitly be enabled. +In addition to installing the ruler, the chart also supports creating rules. +Rules files must be added to directories named after the tenants. +See `values.yaml` for a more detailed example. + +```yaml +ruler: + enabled: true + directories: + fake: + rules.txt: | + groups: + - name: should_fire + rules: + - alert: HighPercentageError + expr: | + sum(rate({app="loki"} |= "error" [5m])) by (job) + / + sum(rate({app="loki"}[5m])) by (job) + > 0.05 + for: 10m + labels: + severity: warning + annotations: + summary: High error percentage +``` diff --git a/observability/lgtm-distributed/charts/loki-distributed/README.md.gotmpl b/observability/lgtm-distributed/charts/loki-distributed/README.md.gotmpl new file mode 100644 index 0000000..23153d1 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/README.md.gotmpl @@ -0,0 +1,385 @@ +{{ template "chart.header" . }} + +{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }} + +{{ template "chart.description" . }} + +{{ template "chart.sourcesSection" . }} + +{{ template "chart.requirementsSection" . }} + +## Chart Repo + +Add the following repo to use the chart: + +```console +helm repo add grafana https://grafana.github.io/helm-charts +``` + +## Upgrading + +### Upgrading an existing Release to a new major version + +Major version upgrades listed here indicate that there is an incompatible breaking change needing manual actions. + +### From 0.78.x to 0.79.0 +Removed the hardcoded, deprecated `boltdb.shipper.compactor.working-directory` flag in the Compactor Deployment template, so that it can be set with `.Values.compactor.extraArgs` and the `compactor.working-directory` flag if necessary. + +### From 0.74.x to 0.75.0 +The Index Gateway and Query Scheduler now expose the memberlist port 7946. In order to join the +member list, you need to specify this in the `structuredConfig`: +```yaml +loki: + structuredConfig: + index_gateway: + mode: ring + query_scheduler: + use_scheduler_ring: true +``` + +### From 0.68.x to 0.69.0 +The in-memory `fifocache` has been renamed to more general `embedded_cache`, which currently doesn't have a `max_size_items` attribute. +```yaml +loki: + config: | + chunk_store_config: + chunk_cache_config: + embedded_cache: + enabled: false +``` + +`compactor_address` has to be explicitly set in the `common` section of the config. +```yaml +loki: + config: | + common: + compactor_address: {{"{{"}} include "loki.compactorFullname" . {{"}}"}}:3100 +``` + +### From 0.41.x to 0.42.0 +All containers were previously named "loki". This version changes the container names to make the chart compatible with the loki-mixin. Now the container names correctly reflect the component (querier, distributor, ingester, ...). If you are using custom prometheus rules that use the container name you probably have to change them. + +### From 0.34.x to 0.35.0 +This version updates the `Ingress` API Version of the Loki Gateway component to `networking.k8s.io/v1` of course given that the cluster supports it. Here it's important to notice the change in the `values.yml` with regards to the ingress configuration section and its new structure. +```yaml +gateway: + ingress: + enabled: true + # Newly added optional property + ingressClassName: nginx + hosts: + - host: gateway.loki.example.com + paths: + # New data structure introduced + - path: / + # Newly added optional property + pathType: Prefix +``` + +### From 0.30.x to 0.31.0 +This version updates the `podManagementPolicy` of running the Loki components as `StatefulSet`'s to `Parallel` instead of the default `OrderedReady` in order to allow better scalability for Loki e.g. in case the pods weren't terminated gracefully. This change requires a manual action deleting the existing StatefulSets before upgrading with Helm. +```bash +# Delete the Ingesters StatefulSets +kubectl delete statefulset RELEASE_NAME-loki-distributed-ingester -n LOKI_NAMESPACE --cascade=orphan +# Delete the Queriers StatefulSets +kubectl delete statefulset RELEASE_NAME-loki-distributed-querier -n LOKI_NAMESPACE --cascade=orphan +``` + +{{ template "chart.valuesSection" . }} + +## Components + +The chart supports the components shown in the following table. +Ingester, distributor, querier, and query-frontend are always installed. +The other components are optional. + +| Component | Optional | Enabled by default | +| --- | --- | --- | +| gateway | ✅ | ✅ | +| ingester | ❎ | n/a | +| distributor | ❎ | n/a | +| querier | ❎ | n/a | +| query-frontend | ❎ | n/a | +| table-manager | ✅ | ❎ | +| compactor | ✅ | ❎ | +| ruler | ✅ | ❎ | +| index-gateway | ✅ | ❎ | +| memcached-chunks | ✅ | ❎ | +| memcached-frontend | ✅ | ❎ | +| memcached-index-queries | ✅ | ❎ | +| memcached-index-writes | ✅ | ❎ | + +## Configuration + +This chart configures Loki in microservices mode. +It has been tested to work with [boltdb-shipper](https://grafana.com/docs/loki/latest/operations/storage/boltdb-shipper/) +and [memberlist](https://grafana.com/docs/loki/latest/configuration/#memberlist_config) while other storage and discovery options should work as well. +However, the chart does not support setting up Consul or Etcd for discovery, +and it is not intended to support these going forward. +They would have to be set up separately. +Instead, memberlist can be used which does not require a separate key/value store. +The chart creates a headless service for the memberlist which ingester, distributor, querier, and ruler are part of. + +---- + +**NOTE:** +In its default configuration, the chart uses `boltdb-shipper` and `filesystem` as storage. +The reason for this is that the chart can be validated and installed in a CI pipeline. +However, this setup is not fully functional. +Querying will not be possible (or limited to the ingesters' in-memory caches) because that would otherwise require shared storage between ingesters and queriers +which the chart does not support and would require a volume that supports `ReadWriteMany` access mode anyways. +The recommendation is to use object storage, such as S3, GCS, MinIO, etc., or one of the other options documented at https://grafana.com/docs/loki/latest/storage/. + +Alternatively, in order to quickly test Loki using the filestore, the [single binary chart](https://github.com/grafana/helm-charts/tree/main/charts/loki) can be used. + +---- + +### Directory and File Locations + +* Volumes are mounted to `/var/loki`. The various directories Loki needs should be configured as subdirectories (e. g. `/var/loki/index`, `/var/loki/cache`). Loki will create the directories automatically. +* The config file is mounted to `/etc/loki/config/config.yaml` and passed as CLI arg. + +### Example configuration using memberlist, boltdb-shipper, and S3 for storage + +```yaml +loki: + structuredConfig: + ingester: + # Disable chunk transfer which is not possible with statefulsets + # and unnecessary for boltdb-shipper + max_transfer_retries: 0 + chunk_idle_period: 1h + chunk_target_size: 1536000 + max_chunk_age: 1h + storage_config: + aws: + s3: s3://eu-central-1 + bucketnames: my-loki-s3-bucket + boltdb_shipper: + shared_store: s3 + schema_config: + configs: + - from: 2020-09-07 + store: boltdb-shipper + object_store: aws + schema: v11 + index: + prefix: loki_index_ + period: 24h +``` + +The above configuration selectively overrides default values found in the `loki.config` template file. + +Using `loki.structuredConfig` it is possible to externally set most any configuration parameter (special considerations for elements of an array). + +``` +helm upgrade loki-distributed --install -f values.yaml --set loki.structuredConfig.storage_config.aws.bucketnames=my-loki-bucket +``` + +`loki.config`, `loki.schemaConfig` and `loki.storageConfig` may also be used in conjuction with `loki.structuredConfig`. Values found in `loki.structuredConfig` will take precedence. Array values, such as those found in `loki.schema_config` will be overridden wholesale and not amended to. + +For `loki.schema_config` its generally expected that this will always be configured per usage as its values over time are in reference to the history of loki schema versions and schema configurations throughout the lifetime of a given loki instance. + +Note that when using `loki.config` must be configured as string. +That's required because it is passed through the `tpl` function in order to support templating. + +When using `loki.config` the passed in template must include template sections for `loki.schemaConfig` and `loki.storageConfig` for those to continue to work as expected. + +Because the config file is templated, it is also possible to reference other values provided to helm e.g. externalize S3 bucket names: + +```yaml +loki: + config: | + storage_config: + aws: + s3: s3://eu-central-1 + bucketnames: {{"{{"}} .Values.bucketnames {{"}}"}} +``` + +```console +helm upgrade loki-distributed --install -f values.yaml --set bucketnames=my-loki-bucket +``` + +## Gateway + +By default and inspired by Grafana's [Tanka setup](https://github.com/grafana/loki/tree/master/production/ksonnet/loki), the chart installs the gateway component which is an NGINX that exposes Loki's API +and automatically proxies requests to the correct Loki components (distributor, querier, query-frontend). +The gateway must be enabled if an Ingress is required, since the Ingress exposes the gateway only. +If the gateway is enabled, Grafana and log shipping agents, such as Promtail, should be configured to use the gateway. +If NetworkPolicies are enabled, they are more restrictive if the gateway is enabled. + +## Metrics + +Loki exposes Prometheus metrics. +The chart can create ServiceMonitor objects for all Loki components. + +```yaml +serviceMonitor: + enabled: true +``` + +Furthermore, it is possible to add Prometheus rules: + +```yaml +prometheusRule: + enabled: true + groups: + - name: loki-rules + rules: + - record: job:loki_request_duration_seconds_bucket:sum_rate + expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job) + - record: job_route:loki_request_duration_seconds_bucket:sum_rate + expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route) + - record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate + expr: sum(rate(container_cpu_usage_seconds_total[1m])) by (node, namespace, pod, container) +``` + +## Caching + +The chart can configure up to four Memcached instances for the various caches Lokis can use. +Configuration works the same for all caches. +The configuration of `memcached-chunks` below demonstrates setting additional options. + +Exporters for the Memcached instances can be configured as well. + +```yaml +memcachedExporter: + enabled: true +``` + +### memcached-chunks + +```yaml +memcachedChunks: + enabled: true + replicas: 2 + extraArgs: + - -m 2048 + - -I 2m + - -v + resources: + requests: + cpu: 500m + memory: 3Gi + limits: + cpu: "2" + memory: 3Gi + +loki: + config: | + chunk_store_config: + chunk_cache_config: + memcached: + batch_size: 100 + parallelism: 100 + memcached_client: + consistent_hash: true + host: {{"{{"}} include "loki.memcachedChunksFullname" . {{"}}"}} + service: memcached-client +``` + +### memcached-frontend + +```yaml +memcachedFrontend: + enabled: true + +loki: + config: | + query_range: + cache_results: true + results_cache: + cache: + memcached_client: + consistent_hash: true + host: {{"{{"}} include "loki.memcachedFrontendFullname" . {{"}}"}} + max_idle_conns: 16 + service: memcached-client + timeout: 500ms + update_interval: 1m +``` + +### memcached-index-queries + +```yaml +memcachedIndexQueries: + enabled: true + +loki: + config: | + storage_config: + index_queries_cache_config: + memcached: + batch_size: 100 + parallelism: 100 + memcached_client: + consistent_hash: true + host: {{"{{"}} include "loki.memcachedIndexQueriesFullname" . {{"}}"}} + service: memcached-client +``` + +### memcached-index-writes + +NOTE: This cache is not used with `boltdb-shipper` and should not be enabled in that case. + +```yaml +memcachedIndexWrite: + enabled: true + +loki: + config: | + chunk_store_config: + write_dedupe_cache_config: + memcached: + batch_size: 100 + parallelism: 100 + memcached_client: + consistent_hash: true + host: {{"{{"}} include "loki.memcachedIndexWritesFullname" . {{"}}"}} + service: memcached-client +``` + +## Compactor + +Compactor is an optional component which must explicitly be enabled. +The chart automatically sets the correct working directory as command-line arg. +The correct storage backend must be configured, e.g. `s3`. + +```yaml +compactor: + enabled: true + +loki: + config: | + compactor: + shared_store: s3 +``` + +## Ruler + +Ruler is an optional component which must explicitly be enabled. +In addition to installing the ruler, the chart also supports creating rules. +Rules files must be added to directories named after the tenants. +See `values.yaml` for a more detailed example. + +```yaml +ruler: + enabled: true + directories: + fake: + rules.txt: | + groups: + - name: should_fire + rules: + - alert: HighPercentageError + expr: | + sum(rate({app="loki"} |= "error" [5m])) by (job) + / + sum(rate({app="loki"}[5m])) by (job) + > 0.05 + for: 10m + labels: + severity: warning + annotations: + summary: High error percentage +``` diff --git a/observability/lgtm-distributed/charts/loki-distributed/ci/cache-values.yaml b/observability/lgtm-distributed/charts/loki-distributed/ci/cache-values.yaml new file mode 100644 index 0000000..4ca99e6 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/ci/cache-values.yaml @@ -0,0 +1,116 @@ +loki: + config: | + auth_enabled: false + + server: + http_listen_port: 3100 + + common: + compactor_address: {{ include "loki.compactorFullname" . }}:3100 + + distributor: + ring: + kvstore: + store: memberlist + + memberlist: + join_members: + - {{ include "loki.fullname" . }}-memberlist + + ingester: + lifecycler: + ring: + kvstore: + store: memberlist + replication_factor: 1 + chunk_idle_period: 30m + chunk_block_size: 262144 + chunk_retain_period: 1m + max_transfer_retries: 0 + wal: + dir: /var/loki/wal + + limits_config: + enforce_metric_name: false + reject_old_samples: true + reject_old_samples_max_age: 168h + ingestion_burst_size_mb: 20 + ingestion_rate_mb: 10 + split_queries_by_interval: 30m + + schema_config: + configs: + - from: 2020-09-07 + store: boltdb-shipper + object_store: filesystem + schema: v11 + index: + prefix: loki_index_ + period: 24h + + storage_config: + boltdb_shipper: + shared_store: filesystem + active_index_directory: /var/loki/index + cache_location: /var/loki/cache + cache_ttl: 168h + filesystem: + directory: /var/loki/chunks + index_queries_cache_config: + memcached: + batch_size: 100 + parallelism: 100 + memcached_client: + consistent_hash: true + host: {{ include "loki.memcachedIndexQueriesFullname" . }} + service: http + + chunk_store_config: + max_look_back_period: 0 + chunk_cache_config: + memcached: + batch_size: 100 + parallelism: 100 + memcached_client: + consistent_hash: true + host: {{ include "loki.memcachedChunksFullname" . }} + service: http + + query_range: + align_queries_with_step: true + max_retries: 5 + cache_results: true + results_cache: + cache: + memcached_client: + consistent_hash: true + host: {{ include "loki.memcachedFrontendFullname" . }} + max_idle_conns: 16 + service: http + timeout: 500ms + update_interval: 1m + + frontend_worker: + frontend_address: {{ include "loki.queryFrontendFullname" . }}:9095 + + frontend: + log_queries_longer_than: 5s + compress_responses: true + +memcachedExporter: + enabled: true + +memcachedChunks: + enabled: true + extraArgs: + - -vv + +memcachedFrontend: + enabled: true + extraArgs: + - -vv + +memcachedIndexQueries: + enabled: true + extraArgs: + - -vv diff --git a/observability/lgtm-distributed/charts/loki-distributed/ci/default-values.yaml b/observability/lgtm-distributed/charts/loki-distributed/ci/default-values.yaml new file mode 100644 index 0000000..e69de29 diff --git a/observability/lgtm-distributed/charts/loki-distributed/ci/ingress-values.yaml b/observability/lgtm-distributed/charts/loki-distributed/ci/ingress-values.yaml new file mode 100644 index 0000000..b6beb94 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/ci/ingress-values.yaml @@ -0,0 +1,9 @@ +gateway: + ingress: + enabled: true + annotations: {} + hosts: + - host: gateway.loki.example.com + paths: + - path: / + pathType: Prefix diff --git a/observability/lgtm-distributed/charts/loki-distributed/ci/persistence-values.yaml b/observability/lgtm-distributed/charts/loki-distributed/ci/persistence-values.yaml new file mode 100644 index 0000000..3867eec --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/ci/persistence-values.yaml @@ -0,0 +1,21 @@ +ingester: + persistence: + enabled: true + size: 100Mi + +querier: + persistence: + enabled: true + size: 100Mi + +gateway: + nginxConfig: + httpSnippet: |- + client_max_body_size 100M; + serverSnippet: |- + client_max_body_size 100M; + + basicAuth: + enabled: true + username: user + password: pass diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/NOTES.txt b/observability/lgtm-distributed/charts/loki-distributed/templates/NOTES.txt new file mode 100644 index 0000000..bfd931f --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/NOTES.txt @@ -0,0 +1,41 @@ +*********************************************************************** + Welcome to Grafana Loki + Chart version: {{ .Chart.Version }} + Loki version: {{ .Chart.AppVersion }} +*********************************************************************** + +Installed components: +{{- if .Values.gateway.enabled }} +* gateway +{{- end }} +* ingester +* distributor +* querier +* query-frontend +{{- if .Values.queryScheduler.enabled }} +* query-scheduler +{{- end }} +{{- if .Values.tableManager.enabled }} +* table-manager +{{- end }} +{{- if .Values.compactor.enabled }} +* compactor +{{- end }} +{{- if .Values.ruler.enabled }} +* ruler +{{- end }} +{{- if .Values.indexGateway.enabled }} +* index-gateway +{{- end }} +{{- if .Values.memcachedChunks.enabled }} +* memcached-chunks +{{- end }} +{{- if .Values.memcachedFrontend.enabled }} +* memcached-frontend +{{- end }} +{{- if .Values.memcachedIndexQueries.enabled }} +* memcached-index-queries +{{- end }} +{{- if .Values.memcachedIndexWrites.enabled }} +* memcached-index-writes +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/_helpers.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/_helpers.tpl new file mode 100644 index 0000000..749debb --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/_helpers.tpl @@ -0,0 +1,181 @@ +{{/* +Expand the name of the chart. +*/}} +{{- define "loki.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "loki.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default .Chart.Name .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "loki.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "loki.labels" -}} +helm.sh/chart: {{ include "loki.chart" . }} +{{ include "loki.selectorLabels" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "loki.selectorLabels" -}} +app.kubernetes.io/name: {{ include "loki.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Create the name of the service account to use +*/}} +{{- define "loki.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "loki.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Docker image name for Loki +*/}} +{{- define "loki.lokiImage" -}} +{{- $registry := coalesce .global.registry .service.registry .loki.registry -}} +{{- $repository := coalesce .service.repository .loki.repository -}} +{{- $tag := coalesce .service.tag .loki.tag .defaultVersion | toString -}} +{{- printf "%s/%s:%s" $registry $repository $tag -}} +{{- end -}} + +{{/* +Docker image name +*/}} +{{- define "loki.image" -}} +{{- $registry := coalesce .global.registry .service.registry -}} +{{- $tag := .service.tag | toString -}} +{{- printf "%s/%s:%s" $registry .service.repository (.service.tag | toString) -}} +{{- end -}} + +{{/* +Memcached Docker image +*/}} +{{- define "loki.memcachedImage" -}} +{{- $dict := dict "service" .Values.memcached.image "global" .Values.global.image -}} +{{- include "loki.image" $dict -}} +{{- end }} + +{{/* +Memcached Exporter Docker image +*/}} +{{- define "loki.memcachedExporterImage" -}} +{{- $dict := dict "service" .Values.memcachedExporter.image "global" .Values.global.image -}} +{{- include "loki.image" $dict -}} +{{- end }} + +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "loki.ingress.apiVersion" -}} + {{- if and (.Capabilities.APIVersions.Has "networking.k8s.io/v1") (semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version) -}} + {{- print "networking.k8s.io/v1" -}} + {{- else if .Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" -}} + {{- print "networking.k8s.io/v1beta1" -}} + {{- else -}} + {{- print "extensions/v1beta1" -}} + {{- end -}} +{{- end -}} + +{{/* +Return if ingress is stable. +*/}} +{{- define "loki.ingress.isStable" -}} + {{- eq (include "loki.ingress.apiVersion" .) "networking.k8s.io/v1" -}} +{{- end -}} + +{{/* +Return if ingress supports ingressClassName. +*/}} +{{- define "loki.ingress.supportsIngressClassName" -}} + {{- or (eq (include "loki.ingress.isStable" .) "true") (and (eq (include "loki.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) -}} +{{- end -}} + +{{/* +Return if ingress supports pathType. +*/}} +{{- define "loki.ingress.supportsPathType" -}} + {{- or (eq (include "loki.ingress.isStable" .) "true") (and (eq (include "loki.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for PodDisruptionBudget. +*/}} +{{- define "loki.pdb.apiVersion" -}} + {{- if and (.Capabilities.APIVersions.Has "policy/v1") (semverCompare ">=1.21-0" .Capabilities.KubeVersion.Version) -}} + {{- print "policy/v1" -}} + {{- else -}} + {{- print "policy/v1beta1" -}} + {{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for HorizontalPodAutoscaler. +*/}} +{{- define "loki.hpa.apiVersion" -}} + {{- if and (.Capabilities.APIVersions.Has "autoscaling/v2") (semverCompare ">=1.23-0" .Capabilities.KubeVersion.Version) -}} + {{- print "autoscaling/v2" -}} + {{- else -}} + {{- print "autoscaling/v2beta1" -}} + {{- end -}} +{{- end -}} + +{{- define "loki.ingester.readinessProbe" -}} +{{- with .Values.ingester.readinessProbe }} +readinessProbe: + {{- toYaml . | nindent 2 }} +{{- else }} +{{- with .Values.loki.readinessProbe }} +readinessProbe: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- end }} +{{- end -}} + +{{- define "loki.ingester.livenessProbe" -}} +{{- with .Values.ingester.livenessProbe }} +livenessProbe: + {{- toYaml . | nindent 2 }} +{{- else }} +{{- with .Values.loki.livenessProbe }} +livenessProbe: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- end }} +{{- end -}} + +{{- define "loki.config.checksum" -}} +checksum/config: {{ tpl (mergeOverwrite (tpl .Values.loki.config . | fromYaml) .Values.loki.structuredConfig | toYaml) . | sha256sum }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/_helpers-compactor.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/_helpers-compactor.tpl new file mode 100644 index 0000000..75c21db --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/_helpers-compactor.tpl @@ -0,0 +1,81 @@ +{{/* +compactor fullname +*/}} +{{- define "loki.compactorFullname" -}} +{{ include "loki.fullname" . }}-compactor +{{- end }} + +{{/* +compactor common labels +*/}} +{{- define "loki.compactorLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: compactor +{{- end }} + +{{/* +compactor selector labels +*/}} +{{- define "loki.compactorSelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: compactor +{{- end }} + +{{/* +compactor image +*/}} +{{- define "loki.compactorImage" -}} +{{- $dict := dict "loki" .Values.loki.image "service" .Values.compactor.image "global" .Values.global.image "defaultVersion" .Chart.AppVersion -}} +{{- include "loki.lokiImage" $dict -}} +{{- end }} + +{{/* +compactor readinessProbe +*/}} +{{- define "loki.compactor.readinessProbe" -}} +{{- with .Values.compactor.readinessProbe }} +readinessProbe: + {{- toYaml . | nindent 2 }} +{{- else }} +{{- with .Values.loki.readinessProbe }} +readinessProbe: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- end }} +{{- end -}} + +{{/* +compactor livenessProbe +*/}} +{{- define "loki.compactor.livenessProbe" -}} +{{- with .Values.compactor.livenessProbe }} +livenessProbe: + {{- toYaml . | nindent 2 }} +{{- else }} +{{- with .Values.loki.livenessProbe }} +livenessProbe: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- end }} +{{- end -}} + +{{/* +compactor priority class name +*/}} +{{- define "loki.compactorPriorityClassName" }} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.compactor.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} + +{{/* +Create the name of the compactor service account +*/}} +{{- define "loki.compactorServiceAccountName" -}} +{{- if .Values.compactor.serviceAccount.create -}} + {{ default (print (include "loki.serviceAccountName" .) "-compactor") .Values.compactor.serviceAccount.name }} +{{- else -}} + {{ default (include "loki.serviceAccountName" .) .Values.compactor.serviceAccount.name }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/deployment-compactor.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/deployment-compactor.yaml new file mode 100644 index 0000000..80601c7 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/deployment-compactor.yaml @@ -0,0 +1,154 @@ +{{- if .Values.compactor.enabled }} +{{- if eq .Values.compactor.kind "Deployment"}} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "loki.compactorFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.compactorLabels" . | nindent 4 }} + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: 1 + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + strategy: + type: Recreate + selector: + matchLabels: + {{- include "loki.compactorSelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.compactor.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.compactorSelectorLabels" . | nindent 8 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.compactor.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ include "loki.compactorServiceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.compactor.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.compactorPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.compactor.terminationGracePeriodSeconds }} + {{- with .Values.compactor.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: compactor + image: {{ include "loki.compactorImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + {{- if or .Values.loki.command .Values.compactor.command }} + command: + - {{ coalesce .Values.compactor.command .Values.loki.command | quote }} + {{- end }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=compactor + {{- with .Values.compactor.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + - name: http-memberlist + containerPort: 7946 + protocol: TCP + {{- with .Values.compactor.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.compactor.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.loki.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.loki.livenessProbe | nindent 12 }} + volumeMounts: + - name: temp + mountPath: /tmp + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + - name: data + mountPath: /var/loki + {{- with .Values.compactor.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.compactor.resources | nindent 12 }} + {{- if .Values.compactor.extraContainers }} + {{- toYaml .Values.compactor.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.compactor.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.compactor.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.compactor.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: temp + emptyDir: {} + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + - name: data + {{- if .Values.compactor.persistence.enabled }} + persistentVolumeClaim: + claimName: data-{{ include "loki.compactorFullname" . }} + {{- else }} + emptyDir: {} + {{- end }} + {{- with .Values.compactor.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/persistentvolumeclaim-compactor.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/persistentvolumeclaim-compactor.yaml new file mode 100644 index 0000000..de71a01 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/persistentvolumeclaim-compactor.yaml @@ -0,0 +1,24 @@ +{{- if and .Values.compactor.enabled .Values.compactor.persistence.enabled }} +{{- if eq .Values.compactor.kind "Deployment"}} +apiVersion: v1 +kind: PersistentVolumeClaim +metadata: + name: data-{{ include "loki.compactorFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.compactorLabels" . | nindent 4 }} + {{- with .Values.compactor.persistence.annotations }} + annotations: + {{- . | toYaml | nindent 4 }} + {{- end }} +spec: + accessModes: + - ReadWriteOnce + {{- with .Values.compactor.persistence.storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: "{{ .Values.compactor.persistence.size }}" +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/service-compactor.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/service-compactor.yaml new file mode 100644 index 0000000..b4ebec8 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/service-compactor.yaml @@ -0,0 +1,34 @@ +{{- if .Values.compactor.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.compactorFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.labels" . | nindent 4 }} + {{- with .Values.compactor.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + app.kubernetes.io/component: compactor + {{- with .Values.loki.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + {{- if .Values.compactor.appProtocol.grpc }} + appProtocol: {{ .Values.compactor.appProtocol.grpc }} + {{- end }} + selector: + {{- include "loki.selectorLabels" . | nindent 4 }} + app.kubernetes.io/component: compactor +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/serviceaccount-compactor.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/serviceaccount-compactor.yaml new file mode 100644 index 0000000..bad7730 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/serviceaccount-compactor.yaml @@ -0,0 +1,18 @@ +{{ if and .Values.compactor.enabled .Values.compactor.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "loki.compactorServiceAccountName" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.labels" . | nindent 4 }} + {{- with .Values.compactor.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +automountServiceAccountToken: {{ .Values.compactor.serviceAccount.automountServiceAccountToken }} +{{- with .Values.compactor.serviceAccount.imagePullSecrets }} +imagePullSecrets: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/servicemonitor-compactor.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/servicemonitor-compactor.yaml new file mode 100644 index 0000000..11523f9 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/servicemonitor-compactor.yaml @@ -0,0 +1,61 @@ +{{- if .Values.compactor.enabled }} +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.compactorFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.compactorLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.compactorSelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/statefulset-compactor.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/statefulset-compactor.yaml new file mode 100644 index 0000000..ed92975 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/compactor/statefulset-compactor.yaml @@ -0,0 +1,190 @@ +{{- if .Values.compactor.enabled }} +{{- if eq .Values.compactor.kind "StatefulSet"}} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "loki.compactorFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.compactorLabels" . | nindent 4 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.compactor.replicas }} + podManagementPolicy: Parallel + updateStrategy: + rollingUpdate: + partition: 0 + serviceName: {{ include "loki.compactorFullname" . }}-headless + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + {{- if and (semverCompare ">= 1.23-0" .Capabilities.KubeVersion.Version) (.Values.compactor.persistence.enableStatefulSetAutoDeletePVC) }} + persistentVolumeClaimRetentionPolicy: + whenDeleted: {{ .Values.compactor.persistence.whenDeleted }} + whenScaled: {{ .Values.compactor.persistence.whenScaled }} + {{- end }} + selector: + matchLabels: + {{- include "loki.compactorSelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.compactor.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.compactorSelectorLabels" . | nindent 8 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.compactor.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }} + {{- with .Values.compactor.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.compactor.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.compactorPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.compactor.terminationGracePeriodSeconds }} + {{- with .Values.compactor.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: compactor + image: {{ include "loki.compactorImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + {{- if or .Values.loki.command .Values.compactor.command }} + command: + - {{ coalesce .Values.compactor.command .Values.loki.command | quote }} + {{- end }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=compactor + {{- with .Values.compactor.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + - name: http-memberlist + containerPort: 7946 + protocol: TCP + {{- with .Values.compactor.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.compactor.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + {{- include "loki.compactor.readinessProbe" . | nindent 10 }} + {{- include "loki.compactor.livenessProbe" . | nindent 10 }} + volumeMounts: + - name: temp + mountPath: /tmp + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + - name: data + mountPath: /var/loki + {{- with .Values.compactor.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.compactor.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.compactor.lifecycle }} + lifecycle: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.compactor.extraContainers }} + {{- toYaml .Values.compactor.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.compactor.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.compactor.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.compactor.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: temp + emptyDir: {} + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + {{- if not .Values.compactor.persistence.enabled }} + - name: data + emptyDir: {} + {{- end }} + {{- with .Values.compactor.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.compactor.persistence.enabled }} + volumeClaimTemplates: + {{- range .Values.compactor.persistence.claims }} + - metadata: + name: {{ .name }} + {{- with .annotations }} + annotations: + {{- . | toYaml | nindent 10 }} + {{- end }} + spec: + accessModes: + - ReadWriteOnce + {{- with .storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: {{ .size | quote }} + {{- end }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/config-secret.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/config-secret.yaml new file mode 100644 index 0000000..6551ab3 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/config-secret.yaml @@ -0,0 +1,19 @@ +{{- if and (.Values.loki.configAsSecret) (not .Values.loki.existingSecretForConfig) -}} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "loki.fullname" . }}-config + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.labels" . | nindent 4 }} + {{- with .Values.loki.configSecretLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.loki.configSecretAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +stringData: + config.yaml: | + {{- tpl (mergeOverwrite (tpl .Values.loki.config . | fromYaml) .Values.loki.structuredConfig | toYaml) . | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/configmap.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/configmap.yaml new file mode 100644 index 0000000..db068b5 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/configmap.yaml @@ -0,0 +1,12 @@ +{{- if and (not .Values.loki.existingSecretForConfig) (not .Values.loki.configAsSecret) -}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "loki.fullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.labels" . | nindent 4 }} +data: + config.yaml: | + {{- tpl (mergeOverwrite (tpl .Values.loki.config . | fromYaml) .Values.loki.structuredConfig | toYaml) . | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/_helpers-distributor.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/_helpers-distributor.tpl new file mode 100644 index 0000000..8cb638b --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/_helpers-distributor.tpl @@ -0,0 +1,40 @@ +{{/* +distributor fullname +*/}} +{{- define "loki.distributorFullname" -}} +{{ include "loki.fullname" . }}-distributor +{{- end }} + +{{/* +distributor common labels +*/}} +{{- define "loki.distributorLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: distributor +{{- end }} + +{{/* +distributor selector labels +*/}} +{{- define "loki.distributorSelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: distributor +{{- end }} + +{{/* +distributor image +*/}} +{{- define "loki.distributorImage" -}} +{{- $dict := dict "loki" .Values.loki.image "service" .Values.distributor.image "global" .Values.global.image "defaultVersion" .Chart.AppVersion -}} +{{- include "loki.lokiImage" $dict -}} +{{- end }} + +{{/* +distributor priority class name +*/}} +{{- define "loki.distributorPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.distributor.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/deployment-distributor.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/deployment-distributor.yaml new file mode 100644 index 0000000..6cfc218 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/deployment-distributor.yaml @@ -0,0 +1,138 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "loki.distributorFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.distributorLabels" . | nindent 4 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: +{{- if not .Values.distributor.autoscaling.enabled }} + replicas: {{ .Values.distributor.replicas }} +{{- end }} + strategy: + rollingUpdate: + maxSurge: {{ .Values.distributor.maxSurge }} + maxUnavailable: 1 + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.distributorSelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.distributor.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.distributorSelectorLabels" . | nindent 8 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.distributor.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.distributor.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.distributorPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.distributor.terminationGracePeriodSeconds }} + containers: + - name: distributor + image: {{ include "loki.distributorImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + {{- if or .Values.loki.command .Values.distributor.command }} + command: + - {{ coalesce .Values.distributor.command .Values.loki.command | quote }} + {{- end }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=distributor + {{- with .Values.distributor.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + - name: http-memberlist + containerPort: 7946 + protocol: TCP + {{- with .Values.distributor.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.distributor.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.loki.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.loki.livenessProbe | nindent 12 }} + volumeMounts: + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + {{- with .Values.distributor.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.distributor.resources | nindent 12 }} + {{- if .Values.distributor.extraContainers }} + {{- toYaml .Values.distributor.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.distributor.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.distributor.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.distributor.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + {{- with .Values.distributor.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/hpa.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/hpa.yaml new file mode 100644 index 0000000..7a90739 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/hpa.yaml @@ -0,0 +1,53 @@ +{{- if .Values.distributor.autoscaling.enabled }} +{{- $apiVersion := include "loki.hpa.apiVersion" . -}} +apiVersion: {{ $apiVersion }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "loki.distributorFullname" . }} + labels: + {{- include "loki.distributorLabels" . | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "loki.distributorFullname" . }} + minReplicas: {{ .Values.distributor.autoscaling.minReplicas }} + maxReplicas: {{ .Values.distributor.autoscaling.maxReplicas }} + metrics: + {{- with .Values.distributor.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.distributor.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.distributor.autoscaling.customMetrics }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- if .Values.distributor.autoscaling.behavior.enabled }} + behavior: + {{- with .Values.distributor.autoscaling.behavior.scaleDown }} + scaleDown: {{ toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.distributor.autoscaling.behavior.scaleUp }} + scaleUp: {{ toYaml . | nindent 6 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/poddisruptionbudget-distributor.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/poddisruptionbudget-distributor.yaml new file mode 100644 index 0000000..8de6fd3 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/poddisruptionbudget-distributor.yaml @@ -0,0 +1,20 @@ +{{- if gt (int .Values.distributor.replicas) 1 }} +{{- if kindIs "invalid" .Values.distributor.maxUnavailable }} +{{- fail "`.Values.distributor.maxUnavailable` must be set when `.Values.distributor.replicas` is greater than 1." }} +{{- else }} +apiVersion: {{ include "loki.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "loki.distributorFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.distributorLabels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "loki.distributorSelectorLabels" . | nindent 6 }} + {{- with .Values.distributor.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/service-distributor.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/service-distributor.yaml new file mode 100644 index 0000000..0345da6 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/service-distributor.yaml @@ -0,0 +1,30 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.distributorFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.distributorLabels" . | nindent 4 }} + {{- with .Values.distributor.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.loki.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + {{- if .Values.distributor.appProtocol.grpc }} + appProtocol: {{ .Values.distributor.appProtocol.grpc }} + {{- end }} + selector: + {{- include "loki.distributorSelectorLabels" . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/servicemonitor-distributor.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/servicemonitor-distributor.yaml new file mode 100644 index 0000000..1f1e525 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/distributor/servicemonitor-distributor.yaml @@ -0,0 +1,59 @@ +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.distributorFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.distributorLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.distributorSelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/_helpers-gateway.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/_helpers-gateway.tpl new file mode 100644 index 0000000..f6546c3 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/_helpers-gateway.tpl @@ -0,0 +1,51 @@ +{{/* +gateway fullname +*/}} +{{- define "loki.gatewayFullname" -}} +{{ include "loki.fullname" . }}-gateway +{{- end }} + +{{/* +gateway common labels +*/}} +{{- define "loki.gatewayLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: gateway +{{- end }} + +{{/* +gateway selector labels +*/}} +{{- define "loki.gatewaySelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: gateway +{{- end }} + +{{/* +gateway auth secret name +*/}} +{{- define "loki.gatewayAuthSecret" -}} +{{ .Values.gateway.basicAuth.existingSecret | default (include "loki.gatewayFullname" . ) }} +{{- end }} + +{{/* +gateway Docker image +*/}} +{{- define "loki.gatewayImage" -}} +{{- $dict := dict "service" .Values.gateway.image "global" .Values.global.image -}} +{{- include "loki.image" $dict -}} +{{- end }} + +{{/* +gateway priority class name +*/}} +{{- define "loki.gatewayPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.gateway.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} + +{{- define "loki.gatewayConfigChecksum" -}} +checksum/config: {{ tpl .Values.gateway.nginxConfig.file . | sha256sum }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/configmap-gateway.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/configmap-gateway.yaml new file mode 100644 index 0000000..9d99b3e --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/configmap-gateway.yaml @@ -0,0 +1,11 @@ +{{- if .Values.gateway.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "loki.gatewayFullname" . }} + labels: + {{- include "loki.gatewayLabels" . | nindent 4 }} +data: + nginx.conf: | + {{- tpl .Values.gateway.nginxConfig.file . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/deployment-gateway.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/deployment-gateway.yaml new file mode 100644 index 0000000..c3c2d61 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/deployment-gateway.yaml @@ -0,0 +1,129 @@ +{{- if .Values.gateway.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "loki.gatewayFullname" . }} + labels: + {{- include "loki.gatewayLabels" . | nindent 4 }} + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: +{{- if not .Values.gateway.autoscaling.enabled }} + replicas: {{ .Values.gateway.replicas }} +{{- end }} +{{- with .Values.gateway.deploymentStrategy }} + strategy: +{{ toYaml . | trim | indent 4 }} +{{- end }} + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.gatewaySelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.gatewayConfigChecksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.gateway.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.gatewaySelectorLabels" . | nindent 8 }} + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.gateway.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.gateway.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.gatewayPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.gateway.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.gateway.terminationGracePeriodSeconds }} + containers: + - name: nginx + image: {{ include "loki.gatewayImage" . }} + imagePullPolicy: {{ .Values.gateway.image.pullPolicy }} + ports: + - name: http + containerPort: 8080 + protocol: TCP + {{- with .Values.gateway.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.gateway.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + readinessProbe: + {{- toYaml .Values.gateway.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.gateway.livenessProbe | nindent 12 }} + securityContext: + {{- toYaml .Values.gateway.containerSecurityContext | nindent 12 }} + volumeMounts: + - name: config + mountPath: /etc/nginx + {{- if .Values.gateway.basicAuth.enabled }} + - name: auth + mountPath: /etc/nginx/secrets + {{- end }} + - name: tmp + mountPath: /tmp + - name: docker-entrypoint-d-override + mountPath: /docker-entrypoint.d + {{- if .Values.gateway.extraVolumeMounts }} + {{- toYaml .Values.gateway.extraVolumeMounts | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.gateway.resources | nindent 12 }} + {{- if .Values.gateway.extraContainers }} + {{- toYaml .Values.gateway.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.gateway.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.gateway.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.gateway.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.gateway.dnsConfig }} + dnsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + configMap: + name: {{ include "loki.gatewayFullname" . }} + {{- if .Values.gateway.basicAuth.enabled }} + - name: auth + secret: + secretName: {{ include "loki.gatewayAuthSecret" . }} + {{- end }} + - name: tmp + emptyDir: {} + - name: docker-entrypoint-d-override + emptyDir: {} + {{- if .Values.gateway.extraVolumes }} + {{- toYaml .Values.gateway.extraVolumes | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/hpa.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/hpa.yaml new file mode 100644 index 0000000..937d447 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/hpa.yaml @@ -0,0 +1,53 @@ +{{- if .Values.gateway.autoscaling.enabled }} +{{- $apiVersion := include "loki.hpa.apiVersion" . -}} +apiVersion: {{ $apiVersion }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "loki.gatewayFullname" . }} + labels: + {{- include "loki.gatewayLabels" . | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "loki.gatewayFullname" . }} + minReplicas: {{ .Values.gateway.autoscaling.minReplicas }} + maxReplicas: {{ .Values.gateway.autoscaling.maxReplicas }} + metrics: + {{- with .Values.gateway.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.gateway.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.gateway.autoscaling.customMetrics }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- if .Values.gateway.autoscaling.behavior.enabled }} + behavior: + {{- with .Values.gateway.autoscaling.behavior.scaleDown }} + scaleDown: {{ toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.gateway.autoscaling.behavior.scaleUp }} + scaleUp: {{ toYaml . | nindent 6 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/ingress-gateway.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/ingress-gateway.yaml new file mode 100644 index 0000000..9242a3e --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/ingress-gateway.yaml @@ -0,0 +1,55 @@ +{{- if .Values.gateway.enabled -}} +{{- if .Values.gateway.ingress.enabled -}} +{{- $ingressApiIsStable := eq (include "loki.ingress.isStable" .) "true" -}} +{{- $ingressSupportsIngressClassName := eq (include "loki.ingress.supportsIngressClassName" .) "true" -}} +{{- $ingressSupportsPathType := eq (include "loki.ingress.supportsPathType" .) "true" -}} +apiVersion: {{ include "loki.ingress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ include "loki.gatewayFullname" . }} + labels: + {{- include "loki.gatewayLabels" . | nindent 4 }} + {{- with .Values.gateway.ingress.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if and $ingressSupportsIngressClassName .Values.gateway.ingress.ingressClassName }} + ingressClassName: {{ .Values.gateway.ingress.ingressClassName }} + {{- end -}} + {{- if .Values.gateway.ingress.tls }} + tls: + {{- range .Values.gateway.ingress.tls }} + - hosts: + {{- range .hosts }} + - {{ . | quote }} + {{- end }} + {{- with .secretName }} + secretName: {{ . }} + {{- end }} + {{- end }} + {{- end }} + rules: + {{- range .Values.gateway.ingress.hosts }} + - host: {{ .host | quote }} + http: + paths: + {{- range .paths }} + - path: {{ .path }} + {{- if $ingressSupportsPathType }} + pathType: {{ .pathType }} + {{- end }} + backend: + {{- if $ingressApiIsStable }} + service: + name: {{ include "loki.gatewayFullname" $ }} + port: + number: {{ $.Values.gateway.service.port }} + {{- else }} + serviceName: {{ include "loki.gatewayFullname" $ }} + servicePort: {{ $.Values.gateway.service.port }} + {{- end }} + {{- end }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/poddisruptionbudget-gateway.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/poddisruptionbudget-gateway.yaml new file mode 100644 index 0000000..8b2279f --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/poddisruptionbudget-gateway.yaml @@ -0,0 +1,19 @@ +{{- if and .Values.gateway.enabled (gt (int .Values.gateway.replicas) 1) }} +{{- if kindIs "invalid" .Values.gateway.maxUnavailable }} +{{- fail "`.Values.gateway.maxUnavailable` must be set when `.Values.gateway.replicas` is greater than 1." }} +{{- else }} +apiVersion: {{ include "loki.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "loki.gatewayFullname" . }} + labels: + {{- include "loki.gatewayLabels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "loki.gatewaySelectorLabels" . | nindent 6 }} + {{- with .Values.gateway.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/secret-gateway.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/secret-gateway.yaml new file mode 100644 index 0000000..f7cc8a6 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/secret-gateway.yaml @@ -0,0 +1,13 @@ +{{- with .Values.gateway }} +{{- if and .enabled .basicAuth.enabled (not .basicAuth.existingSecret) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "loki.gatewayFullname" $ }} + labels: + {{- include "loki.gatewayLabels" $ | nindent 4 }} +stringData: + .htpasswd: | + {{- tpl .basicAuth.htpasswd $ | nindent 4 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/service-gateway.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/service-gateway.yaml new file mode 100644 index 0000000..0c9afc1 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/gateway/service-gateway.yaml @@ -0,0 +1,42 @@ +{{- if .Values.gateway.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.gatewayFullname" . }} + labels: + {{- include "loki.gatewayLabels" . | nindent 4 }} + {{- with .Values.gateway.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.gateway.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.gateway.service.type }} + {{- with .Values.gateway.service.clusterIP }} + clusterIP: {{ . }} + {{- end }} + {{- if eq "LoadBalancer" .Values.gateway.service.type }} + {{- with .Values.gateway.service.loadBalancerIP }} + loadBalancerIP: {{ . }} + {{- end }} + {{- with .Values.gateway.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- end }} + ports: + - name: http + port: {{ .Values.gateway.service.port }} + targetPort: http + {{- if and (eq "NodePort" .Values.gateway.service.type) .Values.gateway.service.nodePort }} + nodePort: {{ .Values.gateway.service.nodePort }} + {{- end }} + protocol: TCP + {{- with .Values.gateway.service.appProtocol }} + appProtocol: {{ . }} + {{- end }} + selector: + {{- include "loki.gatewaySelectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/_helpers-index-gateway.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/_helpers-index-gateway.tpl new file mode 100644 index 0000000..f42dff3 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/_helpers-index-gateway.tpl @@ -0,0 +1,40 @@ +{{/* +index-gateway fullname +*/}} +{{- define "loki.indexGatewayFullname" -}} +{{ include "loki.fullname" . }}-index-gateway +{{- end }} + +{{/* +index-gateway common labels +*/}} +{{- define "loki.indexGatewayLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: index-gateway +{{- end }} + +{{/* +index-gateway selector labels +*/}} +{{- define "loki.indexGatewaySelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: index-gateway +{{- end }} + +{{/* +index-gateway image +*/}} +{{- define "loki.indexGatewayImage" -}} +{{- $dict := dict "loki" .Values.loki.image "service" .Values.indexGateway.image "global" .Values.global.image "defaultVersion" .Chart.AppVersion -}} +{{- include "loki.lokiImage" $dict -}} +{{- end }} + +{{/* +index-gateway priority class name +*/}} +{{- define "loki.indexGatewayPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.indexGateway.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/poddisruptionbudget-index-gateway.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/poddisruptionbudget-index-gateway.yaml new file mode 100644 index 0000000..acf73a5 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/poddisruptionbudget-index-gateway.yaml @@ -0,0 +1,19 @@ +{{- if and .Values.indexGateway.enabled (gt (int .Values.indexGateway.replicas) 1) }} +{{- if kindIs "invalid" .Values.indexGateway.maxUnavailable }} +{{- fail "`.Values.indexGateway.maxUnavailable` must be set when `.Values.indexGateway.replicas` is greater than 1." }} +{{- else }} +apiVersion: {{ include "loki.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "loki.indexGatewayFullname" . }} + labels: + {{- include "loki.indexGatewayLabels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "loki.indexGatewaySelectorLabels" . | nindent 6 }} + {{- with .Values.indexGateway.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/service-index-gateway-headless.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/service-index-gateway-headless.yaml new file mode 100644 index 0000000..5763437 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/service-index-gateway-headless.yaml @@ -0,0 +1,26 @@ +{{- if .Values.indexGateway.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.indexGatewayFullname" . }}-headless + labels: + {{- include "loki.indexGatewaySelectorLabels" . | nindent 4 }} + prometheus.io/service-monitor: "false" +spec: + type: ClusterIP + clusterIP: None + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + {{- with .Values.indexGateway.appProtocol.grpc }} + appProtocol: {{ . }} + {{- end }} + selector: + {{- include "loki.indexGatewaySelectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/service-index-gateway.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/service-index-gateway.yaml new file mode 100644 index 0000000..81984ac --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/service-index-gateway.yaml @@ -0,0 +1,31 @@ +{{- if .Values.indexGateway.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.indexGatewayFullname" . }} + labels: + {{- include "loki.indexGatewayLabels" . | nindent 4 }} + {{- with .Values.indexGateway.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.loki.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + {{- with .Values.indexGateway.appProtocol.grpc }} + appProtocol: {{ . }} + {{- end }} + selector: + {{- include "loki.indexGatewaySelectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/servicemonitor-index-gateway.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/servicemonitor-index-gateway.yaml new file mode 100644 index 0000000..400a592 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/servicemonitor-index-gateway.yaml @@ -0,0 +1,61 @@ +{{- if .Values.indexGateway.enabled }} +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.indexGatewayFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.indexGatewayLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.indexGatewaySelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/statefulset-index-gateway.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/statefulset-index-gateway.yaml new file mode 100644 index 0000000..b91a291 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/index-gateway/statefulset-index-gateway.yaml @@ -0,0 +1,181 @@ +{{- if .Values.indexGateway.enabled }} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "loki.indexGatewayFullname" . }} + labels: + {{- include "loki.indexGatewayLabels" . | nindent 4 }} + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.indexGateway.replicas }} + updateStrategy: + rollingUpdate: + partition: 0 + serviceName: {{ include "loki.indexGatewayFullname" . }}-headless + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + {{- if and (semverCompare ">= 1.23-0" .Capabilities.KubeVersion.Version) (.Values.indexGateway.persistence.enableStatefulSetAutoDeletePVC) }} + {{/* + Data on the read nodes is easy to replace, so we want to always delete PVCs to make + operation easier, and will rely on re-fetching data when needed. + */}} + persistentVolumeClaimRetentionPolicy: + whenDeleted: {{ .Values.indexGateway.persistence.whenDeleted }} + whenScaled: {{ .Values.indexGateway.persistence.whenScaled }} + {{- end }} + selector: + matchLabels: + {{- include "loki.indexGatewaySelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.indexGateway.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.indexGatewaySelectorLabels" . | nindent 8 }} + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.indexGateway.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.indexGateway.joinMemberlist }} + app.kubernetes.io/part-of: memberlist + {{- end }} + spec: + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.indexGateway.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.indexGatewayPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.indexGateway.terminationGracePeriodSeconds }} + {{- with .Values.indexGateway.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: index-gateway + image: {{ include "loki.indexGatewayImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=index-gateway + {{- with .Values.indexGateway.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + {{- if .Values.indexGateway.joinMemberlist }} + - name: http-memberlist + containerPort: 7946 + protocol: TCP + {{- end }} + {{- with .Values.indexGateway.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.indexGateway.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.loki.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.loki.livenessProbe | nindent 12 }} + volumeMounts: + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + - name: data + mountPath: /var/loki + {{- with .Values.indexGateway.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.indexGateway.resources | nindent 12 }} + {{- if .Values.indexGateway.extraContainers }} + {{- toYaml .Values.indexGateway.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.indexGateway.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.indexGateway.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.indexGateway.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + {{- with .Values.indexGateway.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if not .Values.indexGateway.persistence.enabled }} + - name: data + emptyDir: {} + {{- else if .Values.indexGateway.persistence.inMemory }} + - name: data + {{- if .Values.indexGateway.persistence.inMemory }} + emptyDir: + medium: Memory + {{- end }} + {{- if .Values.indexGateway.persistence.size }} + sizeLimit: {{ .Values.indexGateway.persistence.size }} + {{- end }} + {{- else }} + volumeClaimTemplates: + - metadata: + name: data + {{- with .Values.indexGateway.persistence.annotations }} + annotations: + {{- . | toYaml | nindent 10 }} + {{- end }} + spec: + accessModes: + - ReadWriteOnce + {{- with .Values.indexGateway.persistence.storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: {{ .Values.indexGateway.persistence.size | quote }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/_helpers-ingester.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/_helpers-ingester.tpl new file mode 100644 index 0000000..5a6a986 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/_helpers-ingester.tpl @@ -0,0 +1,40 @@ +{{/* +ingester fullname +*/}} +{{- define "loki.ingesterFullname" -}} +{{ include "loki.fullname" . }}-ingester +{{- end }} + +{{/* +ingester common labels +*/}} +{{- define "loki.ingesterLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: ingester +{{- end }} + +{{/* +ingester selector labels +*/}} +{{- define "loki.ingesterSelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: ingester +{{- end }} + +{{/* +ingester image +*/}} +{{- define "loki.ingesterImage" -}} +{{- $dict := dict "loki" .Values.loki.image "service" .Values.ingester.image "global" .Values.global.image "defaultVersion" .Chart.AppVersion -}} +{{- include "loki.lokiImage" $dict -}} +{{- end }} + +{{/* +ingester priority class name +*/}} +{{- define "loki.ingesterPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.ingester.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/deployment-ingester.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/deployment-ingester.yaml new file mode 100644 index 0000000..d263588 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/deployment-ingester.yaml @@ -0,0 +1,166 @@ +{{- if eq .Values.ingester.kind "Deployment"}} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "loki.ingesterFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.ingesterLabels" . | nindent 4 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: +{{- if not .Values.ingester.autoscaling.enabled }} + replicas: {{ .Values.ingester.replicas }} +{{- end }} + strategy: + rollingUpdate: + maxSurge: {{ .Values.ingester.maxSurge }} + maxUnavailable: 1 + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.ingesterSelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ingester.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.ingesterSelectorLabels" . | nindent 8 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ingester.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }} + {{- with .Values.ingester.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ingester.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.ingesterPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.ingester.terminationGracePeriodSeconds }} + {{- with .Values.ingester.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: ingester + image: {{ include "loki.ingesterImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + {{- if or .Values.loki.command .Values.ingester.command }} + command: + - {{ coalesce .Values.ingester.command .Values.loki.command | quote }} + {{- end }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=ingester + {{- with .Values.ingester.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + - name: http-memberlist + containerPort: 7946 + protocol: TCP + {{- with .Values.ingester.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ingester.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + {{- include "loki.ingester.readinessProbe" . | nindent 10 }} + {{- include "loki.ingester.livenessProbe" . | nindent 10 }} + volumeMounts: + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + - name: data + mountPath: /var/loki + {{- with .Values.ingester.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ingester.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ingester.lifecycle }} + lifecycle: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.ingester.extraContainers }} + {{- toYaml .Values.ingester.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.ingester.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.ingester.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ingester.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + {{- with .Values.ingester.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} + - name: data + {{- if .Values.ingester.persistence.inMemory }} + emptyDir: + medium: Memory + {{- if .Values.ingester.persistence.size }} + sizeLimit: {{ .Values.ingester.persistence.size }} + {{- end }} + {{- else }} + emptyDir: {} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/hpa.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/hpa.yaml new file mode 100644 index 0000000..937d270 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/hpa.yaml @@ -0,0 +1,54 @@ +{{- if .Values.ingester.autoscaling.enabled }} +{{- $apiVersion := include "loki.hpa.apiVersion" . -}} +apiVersion: {{ $apiVersion }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "loki.ingesterFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.ingesterLabels" . | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: {{ .Values.ingester.kind }} + name: {{ include "loki.ingesterFullname" . }} + minReplicas: {{ .Values.ingester.autoscaling.minReplicas }} + maxReplicas: {{ .Values.ingester.autoscaling.maxReplicas }} + metrics: + {{- with .Values.ingester.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.ingester.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.ingester.autoscaling.customMetrics }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- if .Values.ingester.autoscaling.behavior.enabled }} + behavior: + {{- with .Values.ingester.autoscaling.behavior.scaleDown }} + scaleDown: {{ toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.ingester.autoscaling.behavior.scaleUp }} + scaleUp: {{ toYaml . | nindent 6 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/poddisruptionbudget-ingester.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/poddisruptionbudget-ingester.yaml new file mode 100644 index 0000000..0e56f8b --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/poddisruptionbudget-ingester.yaml @@ -0,0 +1,20 @@ +{{- if gt (int .Values.ingester.replicas) 1 }} +{{- if kindIs "invalid" .Values.ingester.maxUnavailable }} +{{- fail "`.Values.ingester.maxUnavailable` must be set when `.Values.ingester.replicas` is greater than 1." }} +{{- else }} +apiVersion: {{ include "loki.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "loki.ingesterFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.ingesterLabels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "loki.ingesterSelectorLabels" . | nindent 6 }} + {{- with .Values.ingester.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/service-ingester-headless.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/service-ingester-headless.yaml new file mode 100644 index 0000000..fed4835 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/service-ingester-headless.yaml @@ -0,0 +1,29 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.ingesterFullname" . }}-headless + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.ingesterSelectorLabels" . | nindent 4 }} + prometheus.io/service-monitor: "false" + {{- with .Values.loki.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + {{- if .Values.ingester.appProtocol.grpc }} + appProtocol: {{ .Values.ingester.appProtocol.grpc }} + {{- end }} + selector: + {{- include "loki.ingesterSelectorLabels" . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/service-ingester.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/service-ingester.yaml new file mode 100644 index 0000000..838b442 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/service-ingester.yaml @@ -0,0 +1,30 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.ingesterFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.ingesterLabels" . | nindent 4 }} + {{- with .Values.ingester.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.loki.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + {{- if .Values.ingester.appProtocol.grpc }} + appProtocol: {{ .Values.ingester.appProtocol.grpc }} + {{- end }} + selector: + {{- include "loki.ingesterSelectorLabels" . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/servicemonitor-ingester.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/servicemonitor-ingester.yaml new file mode 100644 index 0000000..349785a --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/servicemonitor-ingester.yaml @@ -0,0 +1,59 @@ +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.ingesterFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.ingesterLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.ingesterSelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/statefulset-ingester.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/statefulset-ingester.yaml new file mode 100644 index 0000000..236d29a --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ingester/statefulset-ingester.yaml @@ -0,0 +1,198 @@ +{{- if eq .Values.ingester.kind "StatefulSet"}} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "loki.ingesterFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.ingesterLabels" . | nindent 4 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: +{{- if not .Values.ingester.autoscaling.enabled }} + replicas: {{ .Values.ingester.replicas }} +{{- end }} + podManagementPolicy: Parallel + updateStrategy: + rollingUpdate: + partition: 0 + serviceName: {{ include "loki.ingesterFullname" . }}-headless + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + {{- if and (semverCompare ">= 1.23-0" .Capabilities.KubeVersion.Version) (.Values.ingester.persistence.enableStatefulSetAutoDeletePVC) }} + {{/* + Data on the read nodes is easy to replace, so we want to always delete PVCs to make + operation easier, and will rely on re-fetching data when needed. + */}} + persistentVolumeClaimRetentionPolicy: + whenDeleted: {{ .Values.ingester.persistence.whenDeleted }} + whenScaled: {{ .Values.ingester.persistence.whenScaled }} + {{- end }} + selector: + matchLabels: + {{- include "loki.ingesterSelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ingester.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.ingesterSelectorLabels" . | nindent 8 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ingester.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }} + {{- with .Values.ingester.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ingester.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.ingesterPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.ingester.terminationGracePeriodSeconds }} + {{- with .Values.ingester.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: ingester + image: {{ include "loki.ingesterImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + {{- if or .Values.loki.command .Values.ingester.command }} + command: + - {{ coalesce .Values.ingester.command .Values.loki.command | quote }} + {{- end }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=ingester + {{- with .Values.ingester.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + - name: http-memberlist + containerPort: 7946 + protocol: TCP + {{- with .Values.ingester.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ingester.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + {{- include "loki.ingester.readinessProbe" . | nindent 10 }} + {{- include "loki.ingester.livenessProbe" . | nindent 10 }} + volumeMounts: + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + - name: data + mountPath: /var/loki + {{- with .Values.ingester.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ingester.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ingester.lifecycle }} + lifecycle: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.ingester.extraContainers }} + {{- toYaml .Values.ingester.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.ingester.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.ingester.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ingester.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + {{- with .Values.ingester.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if not .Values.ingester.persistence.enabled }} + - name: data + emptyDir: {} + {{- else if .Values.ingester.persistence.inMemory }} + - name: data + {{- if .Values.ingester.persistence.inMemory }} + emptyDir: + medium: Memory + {{- end }} + {{- if .Values.ingester.persistence.size }} + sizeLimit: {{ .Values.ingester.persistence.size }} + {{- end }} + {{- else }} + volumeClaimTemplates: + {{- range .Values.ingester.persistence.claims }} + - metadata: + name: {{ .name }} + {{- with .annotations }} + annotations: + {{- . | toYaml | nindent 10 }} + {{- end }} + spec: + accessModes: + - ReadWriteOnce + {{- with .storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: {{ .size | quote }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ingress.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ingress.yaml new file mode 100644 index 0000000..956603a --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ingress.yaml @@ -0,0 +1,56 @@ +{{- if .Values.ingress.enabled }} +{{- $ingressApiIsStable := eq (include "loki.ingress.isStable" .) "true" -}} +{{- $ingressSupportsIngressClassName := eq (include "loki.ingress.supportsIngressClassName" .) "true" -}} +{{- $ingressSupportsPathType := eq (include "loki.ingress.supportsPathType" .) "true" -}} +apiVersion: {{ include "loki.ingress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ include "loki.fullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.labels" . | nindent 4 }} + {{- with .Values.ingress.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if and $ingressSupportsIngressClassName .Values.ingress.ingressClassName }} + ingressClassName: {{ .Values.ingress.ingressClassName }} + {{- end -}} + {{- if .Values.ingress.tls }} + tls: + {{- range .Values.ingress.tls }} + - hosts: + {{- range .hosts }} + - {{ . | quote }} + {{- end }} + {{- with .secretName }} + secretName: {{ . }} + {{- end }} + {{- end }} + {{- end }} + rules: + {{- range $.Values.ingress.hosts }} + - host: {{ . | quote }} + http: + paths: + {{- range $svcName, $paths := $.Values.ingress.paths }} + {{- range $paths }} + - path: {{ . }} + {{- if $ingressSupportsPathType }} + pathType: Prefix + {{- end }} + backend: + {{- if $ingressApiIsStable }} + service: + name: {{ include "loki.fullname" $ }}-{{ $svcName }} + port: + number: 3100 + {{- else }} + serviceName: {{ include "loki.fullname" $ }}-{{ $svcName }} + servicePort: 3100 + {{- end }} + {{- end }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/_helpers-memcached-chunks.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/_helpers-memcached-chunks.tpl new file mode 100644 index 0000000..e561365 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/_helpers-memcached-chunks.tpl @@ -0,0 +1,32 @@ +{{/* +memcached-chunks fullname +*/}} +{{- define "loki.memcachedChunksFullname" -}} +{{ include "loki.fullname" . }}-memcached-chunks +{{- end }} + +{{/* +memcached-chunks fullname +*/}} +{{- define "loki.memcachedChunksLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: memcached-chunks +{{- end }} + +{{/* +memcached-chunks selector labels +*/}} +{{- define "loki.memcachedChunksSelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: memcached-chunks +{{- end }} + +{{/* +memcached-chunks priority class name +*/}} +{{- define "loki.memcachedChunksPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.memcachedChunks.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/poddisruptionbudget-memcached-chunks.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/poddisruptionbudget-memcached-chunks.yaml new file mode 100644 index 0000000..8510de5 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/poddisruptionbudget-memcached-chunks.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.memcachedChunks.enabled (gt (int .Values.memcachedChunks.replicas) 1) }} +{{- if kindIs "invalid" .Values.memcachedChunks.maxUnavailable }} +{{- fail "`.Values.memcachedChunks.maxUnavailable` must be set when `.Values.memcachedChunks.replicas` is greater than 1." }} +{{- else }} +apiVersion: {{ include "loki.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "loki.memcachedChunksFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.memcachedChunksLabels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "loki.memcachedChunksSelectorLabels" . | nindent 6 }} + {{- with .Values.memcachedChunks.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/service-memcached-chunks.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/service-memcached-chunks.yaml new file mode 100644 index 0000000..7de4d11 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/service-memcached-chunks.yaml @@ -0,0 +1,33 @@ +{{- if .Values.memcachedChunks.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.memcachedChunksFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.memcachedChunksSelectorLabels" . | nindent 4 }} + {{- with .Values.memcachedChunks.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.memcached.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: memcached-client + port: 11211 + targetPort: http + protocol: TCP + {{- if .Values.memcached.appProtocol }} + appProtocol: {{ .Values.memcached.appProtocol }} + {{- end }} + - name: http-metrics + port: 9150 + targetPort: http-metrics + protocol: TCP + selector: + {{- include "loki.memcachedChunksSelectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/servicemonitor-memcached-chunks.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/servicemonitor-memcached-chunks.yaml new file mode 100644 index 0000000..529c0cb --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/servicemonitor-memcached-chunks.yaml @@ -0,0 +1,61 @@ +{{- if .Values.memcachedChunks.enabled }} +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.memcachedChunksFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.memcachedChunksLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.memcachedChunksSelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http-metrics + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig}} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/statefulset-memcached-chunks.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/statefulset-memcached-chunks.yaml new file mode 100644 index 0000000..1035e03 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-chunks/statefulset-memcached-chunks.yaml @@ -0,0 +1,160 @@ +{{- if .Values.memcachedChunks.enabled }} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "loki.memcachedChunksFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.memcachedChunksLabels" . | nindent 4 }} + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.memcachedChunks.replicas }} + updateStrategy: + rollingUpdate: + partition: 0 + serviceName: {{ include "loki.memcachedChunksFullname" . }} + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.memcachedChunksSelectorLabels" . | nindent 6 }} + template: + metadata: + {{- if or .Values.loki.podAnnotations .Values.memcachedChunks.podAnnotations }} + annotations: + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedChunks.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + labels: + {{- include "loki.memcachedChunksSelectorLabels" . | nindent 8 }} + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedChunks.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedChunks.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.memcachedChunksPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.memcached.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.memcachedChunks.terminationGracePeriodSeconds }} + containers: + - name: memcached + {{- if .Values.memcachedChunks.persistence.enabled }} + lifecycle: + preStop: + exec: + command: + - /bin/sh + - -ec + - | + /usr/bin/pkill -10 memcached + sleep 60s + {{- end }} + image: {{ include "loki.memcachedImage" . }} + imagePullPolicy: {{ .Values.memcached.image.pullPolicy }} + {{- if or .Values.memcachedChunks.extraArgs .Values.memcachedChunks.persistence.enabled }} + args: + {{- if .Values.memcachedChunks.persistence.enabled }} + - --memory-file=/cache-state/memory_file + {{- end }} + {{- with .Values.memcachedChunks.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- end }} + ports: + - name: http + containerPort: 11211 + protocol: TCP + {{- with .Values.memcachedChunks.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.memcachedChunks.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.memcached.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.memcached.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.memcached.livenessProbe | nindent 12 }} + {{- if or .Values.memcachedChunks.persistence.enabled .Values.memcachedChunks.extraVolumeMounts }} + volumeMounts: + {{- if .Values.memcachedChunks.persistence.enabled }} + - name: data + mountPath: /cache-state + {{- end }} + {{- if .Values.memcachedChunks.extraVolumeMounts }} + {{- toYaml .Values.memcachedChunks.extraVolumeMounts | nindent 12 }} + {{- end }} + {{- end }} + resources: + {{- toYaml .Values.memcachedChunks.resources | nindent 12 }} + {{- if .Values.memcachedExporter.enabled }} + - name: exporter + args: + - --memcached.address=localhost:11211 + - --web.listen-address=0.0.0.0:9150 + image: {{ include "loki.memcachedExporterImage" . }} + imagePullPolicy: {{ .Values.memcachedExporter.image.pullPolicy }} + ports: + - name: http-metrics + containerPort: 9150 + protocol: TCP + securityContext: + {{- toYaml .Values.memcachedExporter.containerSecurityContext | nindent 12 }} + resources: + {{- toYaml .Values.memcachedExporter.resources | nindent 12 }} + {{- end }} + {{- if .Values.memcachedChunks.extraContainers }} + {{- toYaml .Values.memcachedChunks.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.memcachedChunks.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.memcachedChunks.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedChunks.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if or .Values.memcachedChunks.persistence.enabled .Values.memcachedChunks.volumeClaimTemplates }} + volumeClaimTemplates: + {{- if .Values.memcachedChunks.persistence.enabled }} + - metadata: + name: data + spec: + accessModes: + - ReadWriteOnce + {{- with .Values.memcachedChunks.persistence.storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: {{ .Values.memcachedChunks.persistence.size | quote }} + {{- end }} + {{- with .Values.memcachedChunks.volumeClaimTemplates }} + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/_helpers-memcached-frontend.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/_helpers-memcached-frontend.tpl new file mode 100644 index 0000000..bfe61f9 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/_helpers-memcached-frontend.tpl @@ -0,0 +1,32 @@ +{{/* +memcached-frontend fullname +*/}} +{{- define "loki.memcachedFrontendFullname" -}} +{{ include "loki.fullname" . }}-memcached-frontend +{{- end }} + +{{/* +memcached-frontend labels +*/}} +{{- define "loki.memcachedFrontendLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: memcached-frontend +{{- end }} + +{{/* +memcached-frontend selector labels +*/}} +{{- define "loki.memcachedFrontendSelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: memcached-frontend +{{- end }} + +{{/* +memcached-frontend priority class name +*/}} +{{- define "loki.memcachedFrontendPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.memcachedFrontend.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/poddisruptionbudget-memcached-frontend.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/poddisruptionbudget-memcached-frontend.yaml new file mode 100644 index 0000000..b1d4966 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/poddisruptionbudget-memcached-frontend.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.memcachedFrontend.enabled (gt (int .Values.memcachedFrontend.replicas) 1) }} +{{- if kindIs "invalid" .Values.memcachedFrontend.maxUnavailable }} +{{- fail "`.Values.memcachedFrontend.maxUnavailable` must be set when `.Values.memcachedFrontend.replicas` is greater than 1." }} +{{- else }} +apiVersion: {{ include "loki.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "loki.memcachedFrontendFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.memcachedFrontendLabels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "loki.memcachedFrontendSelectorLabels" . | nindent 6 }} + {{- with .Values.memcachedFrontend.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/service-memcached-frontend.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/service-memcached-frontend.yaml new file mode 100644 index 0000000..92c7cb9 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/service-memcached-frontend.yaml @@ -0,0 +1,33 @@ +{{- if .Values.memcachedFrontend.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.memcachedFrontendFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.memcachedFrontendSelectorLabels" . | nindent 4 }} + {{- with .Values.memcachedFrontend.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.memcached.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: memcached-client + port: 11211 + targetPort: http + protocol: TCP + {{- if .Values.memcached.appProtocol }} + appProtocol: {{ .Values.memcached.appProtocol }} + {{- end }} + - name: http-metrics + port: 9150 + targetPort: http-metrics + protocol: TCP + selector: + {{- include "loki.memcachedFrontendSelectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/servicemonitor-memcached-frontend.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/servicemonitor-memcached-frontend.yaml new file mode 100644 index 0000000..05698f3 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/servicemonitor-memcached-frontend.yaml @@ -0,0 +1,61 @@ +{{- if .Values.memcachedFrontend.enabled }} +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.memcachedFrontendFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.memcachedFrontendLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.memcachedFrontendSelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http-metrics + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig}} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/statefulset-memcached-frontend.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/statefulset-memcached-frontend.yaml new file mode 100644 index 0000000..24a3a9e --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-frontend/statefulset-memcached-frontend.yaml @@ -0,0 +1,150 @@ +{{- if .Values.memcachedFrontend.enabled }} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "loki.memcachedFrontendFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.memcachedFrontendLabels" . | nindent 4 }} + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.memcachedFrontend.replicas }} + updateStrategy: + rollingUpdate: + partition: 0 + serviceName: {{ include "loki.memcachedFrontendFullname" . }} + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.memcachedFrontendSelectorLabels" . | nindent 6 }} + template: + metadata: + {{- if or .Values.loki.podAnnotations .Values.memcachedFrontend.podAnnotations }} + annotations: + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedFrontend.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + labels: + {{- include "loki.memcachedFrontendSelectorLabels" . | nindent 8 }} + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedFrontend.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedFrontend.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.memcachedFrontendPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.memcached.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.memcachedFrontend.terminationGracePeriodSeconds }} + containers: + - name: memcached + {{- if .Values.memcachedFrontend.persistence.enabled }} + lifecycle: + preStop: + exec: + command: + - /bin/sh + - -ec + - | + /usr/bin/pkill -10 memcached + sleep 60s + {{- end }} + image: {{ include "loki.memcachedImage" . }} + imagePullPolicy: {{ .Values.memcached.image.pullPolicy }} + {{- if or .Values.memcachedFrontend.extraArgs .Values.memcachedFrontend.persistence.enabled }} + args: + {{- if .Values.memcachedFrontend.persistence.enabled }} + - --memory-file=/cache-state/memory_file + {{- end }} + {{- with .Values.memcachedFrontend.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- end }} + ports: + - name: http + containerPort: 11211 + protocol: TCP + {{- with .Values.memcachedFrontend.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.memcachedFrontend.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.memcached.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.memcached.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.memcached.livenessProbe | nindent 12 }} + {{- if .Values.memcachedFrontend.persistence.enabled }} + volumeMounts: + - name: data + mountPath: /cache-state + {{- end }} + resources: + {{- toYaml .Values.memcachedFrontend.resources | nindent 12 }} + {{- if .Values.memcachedExporter.enabled }} + - name: exporter + args: + - --memcached.address=localhost:11211 + - --web.listen-address=0.0.0.0:9150 + image: {{ include "loki.memcachedExporterImage" . }} + imagePullPolicy: {{ .Values.memcachedExporter.image.pullPolicy }} + ports: + - name: http-metrics + containerPort: 9150 + protocol: TCP + securityContext: + {{- toYaml .Values.memcachedExporter.containerSecurityContext | nindent 12 }} + resources: + {{- toYaml .Values.memcachedExporter.resources | nindent 12 }} + {{- end }} + {{- if .Values.memcachedFrontend.extraContainers }} + {{- toYaml .Values.memcachedFrontend.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.memcachedFrontend.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.memcachedFrontend.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedFrontend.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.memcachedFrontend.persistence.enabled }} + volumeClaimTemplates: + - metadata: + name: data + spec: + accessModes: + - ReadWriteOnce + {{- with .Values.memcachedFrontend.persistence.storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: {{ .Values.memcachedFrontend.persistence.size | quote }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/_helpers-memcached-index-queries.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/_helpers-memcached-index-queries.tpl new file mode 100644 index 0000000..02a2c46 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/_helpers-memcached-index-queries.tpl @@ -0,0 +1,32 @@ +{{/* +memcached-index-queries fullname +*/}} +{{- define "loki.memcachedIndexQueriesFullname" -}} +{{ include "loki.fullname" . }}-memcached-index-queries +{{- end }} + +{{/* +memcached-index-queries fullname +*/}} +{{- define "loki.memcachedIndexQueriesLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: memcached-index-queries +{{- end }} + +{{/* +memcached-index-queries selector labels +*/}} +{{- define "loki.memcachedIndexQueriesSelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: memcached-index-queries +{{- end }} + +{{/* +memcached-index-queries priority class name +*/}} +{{- define "loki.memcachedIndexQueriesPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.memcachedIndexQueries.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/poddisruptionbudget-memcached-index-queries.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/poddisruptionbudget-memcached-index-queries.yaml new file mode 100644 index 0000000..78e6b2e --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/poddisruptionbudget-memcached-index-queries.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.memcachedIndexQueries.enabled (gt (int .Values.memcachedIndexQueries.replicas) 1) }} +{{- if kindIs "invalid" .Values.memcachedIndexQueries.maxUnavailable }} +{{- fail "`.Values.memcachedIndexQueries.maxUnavailable` must be set when `.Values.memcachedIndexQueries.replicas` is greater than 1." }} +{{- else }} +apiVersion: {{ include "loki.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "loki.memcachedIndexQueriesFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.memcachedIndexQueriesLabels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "loki.memcachedIndexQueriesSelectorLabels" . | nindent 6 }} + {{- with .Values.memcachedIndexQueries.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/service-memcached-index-queries.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/service-memcached-index-queries.yaml new file mode 100644 index 0000000..6051e0b --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/service-memcached-index-queries.yaml @@ -0,0 +1,33 @@ +{{- if .Values.memcachedIndexQueries.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.memcachedIndexQueriesFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.memcachedIndexQueriesSelectorLabels" . | nindent 4 }} + {{- with .Values.memcachedIndexQueries.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.memcached.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: memcached-client + port: 11211 + targetPort: http + protocol: TCP + {{- if .Values.memcached.appProtocol }} + appProtocol: {{ .Values.memcached.appProtocol }} + {{- end }} + - name: http-metrics + port: 9150 + targetPort: http-metrics + protocol: TCP + selector: + {{- include "loki.memcachedIndexQueriesSelectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/servicemonitor-memcached-index-queries.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/servicemonitor-memcached-index-queries.yaml new file mode 100644 index 0000000..88be48d --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/servicemonitor-memcached-index-queries.yaml @@ -0,0 +1,61 @@ +{{- if .Values.memcachedIndexQueries.enabled }} +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.memcachedIndexQueriesFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.memcachedIndexQueriesLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.memcachedIndexQueriesSelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http-metrics + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig}} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/statefulset-memcached-index-queries.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/statefulset-memcached-index-queries.yaml new file mode 100644 index 0000000..d09d69b --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-queries/statefulset-memcached-index-queries.yaml @@ -0,0 +1,150 @@ +{{- if .Values.memcachedIndexQueries.enabled }} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "loki.memcachedIndexQueriesFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.memcachedIndexQueriesLabels" . | nindent 4 }} + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.memcachedIndexQueries.replicas }} + updateStrategy: + rollingUpdate: + partition: 0 + serviceName: {{ include "loki.memcachedIndexQueriesFullname" . }} + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.memcachedIndexQueriesSelectorLabels" . | nindent 6 }} + template: + metadata: + {{- if or .Values.loki.podAnnotations .Values.memcachedIndexQueries.podAnnotations }} + annotations: + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedIndexQueries.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + labels: + {{- include "loki.memcachedIndexQueriesSelectorLabels" . | nindent 8 }} + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedIndexQueries.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedIndexQueries.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.memcachedIndexQueriesPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.memcached.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.memcachedIndexQueries.terminationGracePeriodSeconds }} + containers: + - name: memcached + {{- if .Values.memcachedIndexQueries.persistence.enabled }} + lifecycle: + preStop: + exec: + command: + - /bin/sh + - -ec + - | + /usr/bin/pkill -10 memcached + sleep 60s + {{- end }} + image: {{ include "loki.memcachedImage" . }} + imagePullPolicy: {{ .Values.memcached.image.pullPolicy }} + {{- if or .Values.memcachedIndexQueries.extraArgs .Values.memcachedIndexQueries.persistence.enabled }} + args: + {{- if .Values.memcachedIndexQueries.persistence.enabled }} + - --memory-file=/cache-state/memory_file + {{- end }} + {{- with .Values.memcachedIndexQueries.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- end }} + ports: + - name: http + containerPort: 11211 + protocol: TCP + {{- with .Values.memcachedIndexQueries.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.memcachedIndexQueries.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.memcached.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.memcached.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.memcached.livenessProbe | nindent 12 }} + {{- if .Values.memcachedIndexQueries.persistence.enabled }} + volumeMounts: + - name: data + mountPath: /cache-state + {{- end }} + resources: + {{- toYaml .Values.memcachedIndexQueries.resources | nindent 12 }} + {{- if .Values.memcachedExporter.enabled }} + - name: exporter + args: + - --memcached.address=localhost:11211 + - --web.listen-address=0.0.0.0:9150 + image: {{ include "loki.memcachedExporterImage" . }} + imagePullPolicy: {{ .Values.memcachedExporter.image.pullPolicy }} + ports: + - name: http-metrics + containerPort: 9150 + protocol: TCP + securityContext: + {{- toYaml .Values.memcachedExporter.containerSecurityContext | nindent 12 }} + resources: + {{- toYaml .Values.memcachedExporter.resources | nindent 12 }} + {{- end }} + {{- if .Values.memcachedIndexQueries.extraContainers }} + {{- toYaml .Values.memcachedIndexQueries.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.memcachedIndexQueries.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.memcachedIndexQueries.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedIndexQueries.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.memcachedIndexQueries.persistence.enabled }} + volumeClaimTemplates: + - metadata: + name: data + spec: + accessModes: + - ReadWriteOnce + {{- with .Values.memcachedIndexQueries.persistence.storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: {{ .Values.memcachedIndexQueries.persistence.size | quote }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/_helpers-memcached-index-writes.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/_helpers-memcached-index-writes.tpl new file mode 100644 index 0000000..9bda326 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/_helpers-memcached-index-writes.tpl @@ -0,0 +1,32 @@ +{{/* +memcached-index-writes fullname +*/}} +{{- define "loki.memcachedIndexWritesFullname" -}} +{{ include "loki.fullname" . }}-memcached-index-writes +{{- end }} + +{{/* +memcached-index-writes fullname +*/}} +{{- define "loki.memcachedIndexWritesLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: memcached-index-writes +{{- end }} + +{{/* +memcached-index-writes selector labels +*/}} +{{- define "loki.memcachedIndexWritesSelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: memcached-index-writes +{{- end }} + +{{/* +memcached-index-writes priority class name +*/}} +{{- define "loki.memcachedIndexWritesPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.memcachedIndexWrites.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/poddisruptionbudget-memcached-index-writes.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/poddisruptionbudget-memcached-index-writes.yaml new file mode 100644 index 0000000..f444582 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/poddisruptionbudget-memcached-index-writes.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.memcachedIndexWrites.enabled (gt (int .Values.memcachedIndexWrites.replicas) 1) }} +{{- if kindIs "invalid" .Values.memcachedIndexWrites.maxUnavailable }} +{{- fail "`.Values.memcachedIndexWrites.maxUnavailable` must be set when `.Values.memcachedIndexWrites.replicas` is greater than 1." }} +{{- else }} +apiVersion: {{ include "loki.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "loki.memcachedIndexWritesFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.memcachedIndexWritesLabels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "loki.memcachedIndexWritesSelectorLabels" . | nindent 6 }} + {{- with .Values.memcachedIndexWrites.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/service-memcached-index-writes.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/service-memcached-index-writes.yaml new file mode 100644 index 0000000..0084077 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/service-memcached-index-writes.yaml @@ -0,0 +1,33 @@ +{{- if .Values.memcachedIndexWrites.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.memcachedIndexWritesFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.memcachedIndexWritesSelectorLabels" . | nindent 4 }} + {{- with .Values.memcachedIndexWrites.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.memcached.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: memcached-client + port: 11211 + targetPort: http + protocol: TCP + {{- if .Values.memcached.appProtocol }} + appProtocol: {{ .Values.memcached.appProtocol }} + {{- end }} + - name: http-metrics + port: 9150 + targetPort: http-metrics + protocol: TCP + selector: + {{- include "loki.memcachedIndexWritesSelectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/servicemonitor-memcached-index-writes.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/servicemonitor-memcached-index-writes.yaml new file mode 100644 index 0000000..e15ad04 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/servicemonitor-memcached-index-writes.yaml @@ -0,0 +1,61 @@ +{{- if .Values.memcachedIndexWrites.enabled }} +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.memcachedIndexWritesFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.memcachedIndexWritesLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.memcachedIndexWritesSelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http-metrics + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig}} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/statefulset-memcached-index-writes.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/statefulset-memcached-index-writes.yaml new file mode 100644 index 0000000..bbff176 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/memcached-index-writes/statefulset-memcached-index-writes.yaml @@ -0,0 +1,150 @@ +{{- if .Values.memcachedIndexWrites.enabled }} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "loki.memcachedIndexWritesFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.memcachedIndexWritesLabels" . | nindent 4 }} + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.memcachedIndexWrites.replicas }} + updateStrategy: + rollingUpdate: + partition: 0 + serviceName: {{ include "loki.memcachedIndexWritesFullname" . }} + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.memcachedIndexWritesSelectorLabels" . | nindent 6 }} + template: + metadata: + {{- if or .Values.loki.podAnnotations .Values.memcachedIndexWrites.podAnnotations }} + annotations: + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedIndexWrites.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + labels: + {{- include "loki.memcachedIndexWritesSelectorLabels" . | nindent 8 }} + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedIndexWrites.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedIndexWrites.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.memcachedIndexWritesPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.memcached.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.memcachedIndexWrites.terminationGracePeriodSeconds }} + containers: + - name: memcached + {{- if .Values.memcachedIndexWrites.persistence.enabled }} + lifecycle: + preStop: + exec: + command: + - /bin/sh + - -ec + - | + /usr/bin/pkill -10 memcached + sleep 60s + {{- end }} + image: {{ include "loki.memcachedImage" . }} + imagePullPolicy: {{ .Values.memcached.image.pullPolicy }} + {{- if or .Values.memcachedIndexWrites.extraArgs .Values.memcachedIndexWrites.persistence.enabled }} + args: + {{- if .Values.memcachedIndexWrites.persistence.enabled }} + - --memory-file=/cache-state/memory_file + {{- end }} + {{- with .Values.memcachedIndexWrites.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- end }} + ports: + - name: http + containerPort: 11211 + protocol: TCP + {{- with .Values.memcachedIndexWrites.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.memcachedIndexWrites.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.memcached.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.memcached.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.memcached.livenessProbe | nindent 12 }} + {{- if .Values.memcachedIndexWrites.persistence.enabled }} + volumeMounts: + - name: data + mountPath: /cache-state + {{- end }} + resources: + {{- toYaml .Values.memcachedIndexWrites.resources | nindent 12 }} + {{- if .Values.memcachedExporter.enabled }} + - name: exporter + args: + - --memcached.address=localhost:11211 + - --web.listen-address=0.0.0.0:9150 + image: {{ include "loki.memcachedExporterImage" . }} + imagePullPolicy: {{ .Values.memcachedExporter.image.pullPolicy }} + ports: + - name: http-metrics + containerPort: 9150 + protocol: TCP + securityContext: + {{- toYaml .Values.memcachedExporter.containerSecurityContext | nindent 12 }} + resources: + {{- toYaml .Values.memcachedExporter.resources | nindent 12 }} + {{- end }} + {{- if .Values.memcachedIndexWrites.extraContainers }} + {{- toYaml .Values.memcachedIndexWrites.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.memcachedIndexWrites.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.memcachedIndexWrites.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcachedIndexWrites.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.memcachedIndexWrites.persistence.enabled }} + volumeClaimTemplates: + - metadata: + name: data + spec: + accessModes: + - ReadWriteOnce + {{- with .Values.memcachedIndexWrites.persistence.storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: {{ .Values.memcachedIndexWrites.persistence.size | quote }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/networkpolicy.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/networkpolicy.yaml new file mode 100644 index 0000000..b8c0d98 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/networkpolicy.yaml @@ -0,0 +1,199 @@ +{{- if .Values.networkPolicy.enabled }} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "loki.name" . }}-namespace-only + labels: + {{- include "loki.labels" . | nindent 4 }} +spec: + policyTypes: + - Ingress + - Egress + podSelector: {} + egress: + - to: + - podSelector: {} + ingress: + - from: + - podSelector: {} + +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "loki.name" . }}-egress-dns + labels: + {{- include "loki.labels" . | nindent 4 }} +spec: + policyTypes: + - Egress + podSelector: + matchLabels: + {{- include "loki.selectorLabels" . | nindent 6 }} + egress: + - ports: + - port: 53 + protocol: UDP + to: + - namespaceSelector: {} + +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "loki.name" . }}-ingress + labels: + {{- include "loki.labels" . | nindent 4 }} +spec: + policyTypes: + - Ingress + podSelector: + matchExpressions: + - key: app.kubernetes.io/component + operator: In + values: + {{- if .Values.gateway.enabled }} + - gateway + {{- else }} + - distributor + - querier + - query-frontend + {{- end }} + matchLabels: + {{- include "loki.selectorLabels" . | nindent 6 }} + ingress: + - ports: + - port: http + protocol: TCP + {{- if .Values.networkPolicy.ingress.namespaceSelector }} + from: + - namespaceSelector: + {{- toYaml .Values.networkPolicy.ingress.namespaceSelector | nindent 12 }} + {{- if .Values.networkPolicy.ingress.podSelector }} + podSelector: + {{- toYaml .Values.networkPolicy.ingress.podSelector | nindent 12 }} + {{- end }} + {{- end }} + +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "loki.name" . }}-ingress-metrics + labels: + {{- include "loki.labels" . | nindent 4 }} +spec: + policyTypes: + - Ingress + podSelector: + matchLabels: + {{- include "loki.selectorLabels" . | nindent 6 }} + ingress: + - ports: + - port: http-metrics + protocol: TCP + {{- if .Values.networkPolicy.metrics.cidrs }} + from: + {{- range $cidr := .Values.networkPolicy.metrics.cidrs }} + - ipBlock: + cidr: {{ $cidr }} + {{- end }} + {{- if .Values.networkPolicy.metrics.namespaceSelector }} + - namespaceSelector: + {{- toYaml .Values.networkPolicy.metrics.namespaceSelector | nindent 12 }} + {{- if .Values.networkPolicy.metrics.podSelector }} + podSelector: + {{- toYaml .Values.networkPolicy.metrics.podSelector | nindent 12 }} + {{- end }} + {{- end }} + {{- end }} + +{{- if .Values.ruler.enabled }} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "loki.name" . }}-egress-alertmanager + labels: + {{- include "loki.labels" . | nindent 4 }} +spec: + policyTypes: + - Egress + podSelector: + matchLabels: + {{- include "loki.rulerSelectorLabels" . | nindent 6 }} + egress: + - ports: + - port: {{ .Values.networkPolicy.alertmanager.port }} + protocol: TCP + {{- if .Values.networkPolicy.alertmanager.namespaceSelector }} + to: + - namespaceSelector: + {{- toYaml .Values.networkPolicy.alertmanager.namespaceSelector | nindent 12 }} + {{- if .Values.networkPolicy.alertmanager.podSelector }} + podSelector: + {{- toYaml .Values.networkPolicy.alertmanager.podSelector | nindent 12 }} + {{- end }} + {{- end }} +{{- end }} + +{{- if .Values.networkPolicy.externalStorage.ports }} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "loki.name" . }}-egress-external-storage + labels: + {{- include "loki.labels" . | nindent 4 }} +spec: + policyTypes: + - Egress + podSelector: + matchLabels: + {{- include "loki.selectorLabels" . | nindent 6 }} + egress: + - ports: + {{- range $port := .Values.networkPolicy.externalStorage.ports }} + - port: {{ $port }} + protocol: TCP + {{- end }} + {{- if .Values.networkPolicy.externalStorage.cidrs }} + to: + {{- range $cidr := .Values.networkPolicy.externalStorage.cidrs }} + - ipBlock: + cidr: {{ $cidr }} + {{- end }} + {{- end }} +{{- end }} + +{{- end }} + +{{- if .Values.networkPolicy.discovery.port }} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "loki.name" . }}-egress-discovery + labels: + {{- include "loki.labels" . | nindent 4 }} +spec: + policyTypes: + - Egress + podSelector: + matchLabels: + {{- include "loki.selectorLabels" . | nindent 6 }} + egress: + - ports: + - port: {{ .Values.networkPolicy.discovery.port }} + protocol: TCP + {{- if .Values.networkPolicy.discovery.namespaceSelector }} + to: + - namespaceSelector: + {{- toYaml .Values.networkPolicy.discovery.namespaceSelector | nindent 12 }} + {{- if .Values.networkPolicy.discovery.podSelector }} + podSelector: + {{- toYaml .Values.networkPolicy.discovery.podSelector | nindent 12 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/podsecuritypolicy.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/podsecuritypolicy.yaml new file mode 100644 index 0000000..d0b1212 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/podsecuritypolicy.yaml @@ -0,0 +1,38 @@ +{{- if .Values.rbac.pspEnabled }} +{{- if .Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy" }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "loki.fullname" . }} + labels: + {{- include "loki.labels" . | nindent 4 }} +spec: + privileged: false + allowPrivilegeEscalation: false + volumes: + - 'configMap' + - 'emptyDir' + - 'persistentVolumeClaim' + - 'secret' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + rule: 'MustRunAsNonRoot' + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + - min: 1 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + - min: 1 + max: 65535 + readOnlyRootFilesystem: true + requiredDropCapabilities: + - ALL +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/prometheusrule.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/prometheusrule.yaml new file mode 100644 index 0000000..185492b --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/prometheusrule.yaml @@ -0,0 +1,23 @@ +{{- with .Values.prometheusRule }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ include "loki.fullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.labels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + groups: + {{- toYaml .groups | nindent 4 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/querier/_helpers-querier.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/_helpers-querier.tpl new file mode 100644 index 0000000..c2ed646 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/_helpers-querier.tpl @@ -0,0 +1,40 @@ +{{/* +querier fullname +*/}} +{{- define "loki.querierFullname" -}} +{{ include "loki.fullname" . }}-querier +{{- end }} + +{{/* +querier common labels +*/}} +{{- define "loki.querierLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: querier +{{- end }} + +{{/* +querier selector labels +*/}} +{{- define "loki.querierSelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: querier +{{- end }} + +{{/* +querier image +*/}} +{{- define "loki.querierImage" -}} +{{- $dict := dict "loki" .Values.loki.image "service" .Values.querier.image "global" .Values.global.image "defaultVersion" .Chart.AppVersion -}} +{{- include "loki.lokiImage" $dict -}} +{{- end }} + +{{/* +querier priority class name +*/}} +{{- define "loki.querierPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.querier.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/querier/deployment-querier.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/deployment-querier.yaml new file mode 100644 index 0000000..2e864da --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/deployment-querier.yaml @@ -0,0 +1,154 @@ +{{- if .Values.indexGateway.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "loki.querierFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.querierLabels" . | nindent 4 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: +{{- if not .Values.querier.autoscaling.enabled }} + replicas: {{ .Values.querier.replicas }} +{{- end }} + strategy: + rollingUpdate: + maxSurge: {{ .Values.querier.maxSurge }} + maxUnavailable: 1 + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.querierSelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.querierSelectorLabels" . | nindent 8 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }} + {{- with .Values.querier.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.querierPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.querier.terminationGracePeriodSeconds }} + {{- with .Values.querier.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: querier + image: {{ include "loki.querierImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=querier + {{- with .Values.querier.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + - name: http-memberlist + containerPort: 7946 + protocol: TCP + {{- with .Values.querier.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.querier.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.loki.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.loki.livenessProbe | nindent 12 }} + volumeMounts: + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + - name: data + mountPath: /var/loki + {{- with .Values.querier.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.querier.resources | nindent 12 }} + {{- if .Values.querier.extraContainers }} + {{- toYaml .Values.querier.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.querier.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.querier.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.dnsConfig }} + dnsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + - name: data + emptyDir: {} + {{- with .Values.querier.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/querier/hpa.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/hpa.yaml new file mode 100644 index 0000000..456e66f --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/hpa.yaml @@ -0,0 +1,54 @@ +{{- if and .Values.indexGateway.enabled .Values.querier.autoscaling.enabled }} +{{- $apiVersion := include "loki.hpa.apiVersion" . -}} +apiVersion: {{ $apiVersion }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "loki.querierFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.querierLabels" . | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "loki.querierFullname" . }} + minReplicas: {{ .Values.querier.autoscaling.minReplicas }} + maxReplicas: {{ .Values.querier.autoscaling.maxReplicas }} + metrics: + {{- with .Values.querier.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.querier.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.querier.autoscaling.customMetrics }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- if .Values.querier.autoscaling.behavior.enabled }} + behavior: + {{- with .Values.querier.autoscaling.behavior.scaleDown }} + scaleDown: {{ toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.querier.autoscaling.behavior.scaleUp }} + scaleUp: {{ toYaml . | nindent 6 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/querier/poddisruptionbudget-querier.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/poddisruptionbudget-querier.yaml new file mode 100644 index 0000000..f178a29 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/poddisruptionbudget-querier.yaml @@ -0,0 +1,20 @@ +{{- if gt (int .Values.querier.replicas) 1 }} +{{- if kindIs "invalid" .Values.querier.maxUnavailable }} +{{- fail "`.Values.querier.maxUnavailable` must be set when `.Values.querier.replicas` is greater than 1." }} +{{- else }} +apiVersion: {{ include "loki.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "loki.querierFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.querierLabels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "loki.querierSelectorLabels" . | nindent 6 }} + {{- with .Values.querier.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/querier/service-querier-headless.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/service-querier-headless.yaml new file mode 100644 index 0000000..a5c659e --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/service-querier-headless.yaml @@ -0,0 +1,27 @@ +{{- if not .Values.indexGateway.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.querierFullname" . }}-headless + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.querierSelectorLabels" . | nindent 4 }} + prometheus.io/service-monitor: "false" +spec: + type: ClusterIP + clusterIP: None + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + {{- if .Values.querier.appProtocol.grpc }} + appProtocol: {{ .Values.querier.appProtocol.grpc }} + {{- end }} + selector: + {{- include "loki.querierSelectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/querier/service-querier.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/service-querier.yaml new file mode 100644 index 0000000..382b99f --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/service-querier.yaml @@ -0,0 +1,30 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.querierFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.querierLabels" . | nindent 4 }} + {{- with .Values.querier.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.loki.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + {{- if .Values.querier.appProtocol.grpc }} + appProtocol: {{ .Values.querier.appProtocol.grpc }} + {{- end }} + selector: + {{- include "loki.querierSelectorLabels" . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/querier/servicemonitor-querier.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/servicemonitor-querier.yaml new file mode 100644 index 0000000..d38db2d --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/servicemonitor-querier.yaml @@ -0,0 +1,59 @@ +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.querierFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.querierLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.querierSelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/querier/statefulset-querier.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/statefulset-querier.yaml new file mode 100644 index 0000000..8a0a741 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/querier/statefulset-querier.yaml @@ -0,0 +1,176 @@ +{{- if not .Values.indexGateway.enabled }} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "loki.querierFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.querierLabels" . | nindent 4 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.querier.replicas }} + podManagementPolicy: Parallel + updateStrategy: + rollingUpdate: + partition: 0 + serviceName: {{ include "loki.querierFullname" . }}-headless + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.querierSelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.querierSelectorLabels" . | nindent 8 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }} + {{- with .Values.querier.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.querierPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.querier.terminationGracePeriodSeconds }} + {{- with .Values.querier.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: querier + image: {{ include "loki.querierImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + {{- if or .Values.loki.command .Values.querier.command }} + command: + - {{ coalesce .Values.querier.command .Values.loki.command | quote }} + {{- end }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=querier + {{- with .Values.querier.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + - name: http-memberlist + containerPort: 7946 + protocol: TCP + {{- with .Values.querier.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.querier.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.loki.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.loki.livenessProbe | nindent 12 }} + volumeMounts: + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + - name: data + mountPath: /var/loki + {{- with .Values.querier.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.querier.resources | nindent 12 }} + {{- if .Values.querier.extraContainers }} + {{- toYaml .Values.querier.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.querier.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.querier.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.dnsConfig }} + dnsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + {{- with .Values.querier.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if not .Values.querier.persistence.enabled }} + - name: data + emptyDir: {} + {{- else }} + volumeClaimTemplates: + - metadata: + name: data + {{- with .Values.querier.persistence.annotations }} + annotations: + {{- . | toYaml | nindent 10 }} + {{- end }} + spec: + accessModes: + - ReadWriteOnce + {{- with .Values.querier.persistence.storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: {{ .Values.querier.persistence.size | quote }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/_helpers-query-frontend.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/_helpers-query-frontend.tpl new file mode 100644 index 0000000..ac7a7d2 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/_helpers-query-frontend.tpl @@ -0,0 +1,40 @@ +{{/* +query-frontend fullname +*/}} +{{- define "loki.queryFrontendFullname" -}} +{{ include "loki.fullname" . }}-query-frontend +{{- end }} + +{{/* +query-frontend common labels +*/}} +{{- define "loki.queryFrontendLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: query-frontend +{{- end }} + +{{/* +query-frontend selector labels +*/}} +{{- define "loki.queryFrontendSelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: query-frontend +{{- end }} + +{{/* +query-frontend image +*/}} +{{- define "loki.queryFrontendImage" -}} +{{- $dict := dict "loki" .Values.loki.image "service" .Values.queryFrontend.image "global" .Values.global.image "defaultVersion" .Chart.AppVersion -}} +{{- include "loki.lokiImage" $dict -}} +{{- end }} + +{{/* +query-frontend priority class name +*/}} +{{- define "loki.queryFrontendPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.queryFrontend.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/deployment-query-frontend.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/deployment-query-frontend.yaml new file mode 100644 index 0000000..dd4f90f --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/deployment-query-frontend.yaml @@ -0,0 +1,137 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "loki.queryFrontendFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.queryFrontendLabels" . | nindent 4 }} + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: +{{- if not .Values.queryFrontend.autoscaling.enabled }} + replicas: {{ .Values.queryFrontend.replicas }} +{{- end }} + strategy: + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.queryFrontendSelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.queryFrontend.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.queryFrontendSelectorLabels" . | nindent 8 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.queryFrontend.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.queryFrontend.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.queryFrontendPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.queryFrontend.terminationGracePeriodSeconds }} + containers: + - name: query-frontend + image: {{ include "loki.queryFrontendImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + {{- if or .Values.loki.command .Values.queryFrontend.command }} + command: + - {{ coalesce .Values.queryFrontend.command .Values.loki.command | quote }} + {{- end }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=query-frontend + {{- with .Values.queryFrontend.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + - name: http-memberlist + containerPort: 7946 + protocol: TCP + {{- with .Values.queryFrontend.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.queryFrontend.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.loki.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.loki.livenessProbe | nindent 12 }} + volumeMounts: + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + {{- with .Values.queryFrontend.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.queryFrontend.resources | nindent 12 }} + {{- if .Values.queryFrontend.extraContainers }} + {{- toYaml .Values.queryFrontend.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.queryFrontend.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.queryFrontend.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.queryFrontend.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + {{- with .Values.queryFrontend.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/hpa.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/hpa.yaml new file mode 100644 index 0000000..8c4a185 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/hpa.yaml @@ -0,0 +1,54 @@ +{{- if .Values.queryFrontend.autoscaling.enabled }} +{{- $apiVersion := include "loki.hpa.apiVersion" . -}} +apiVersion: {{ $apiVersion }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "loki.queryFrontendFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.queryFrontendLabels" . | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "loki.queryFrontendFullname" . }} + minReplicas: {{ .Values.queryFrontend.autoscaling.minReplicas }} + maxReplicas: {{ .Values.queryFrontend.autoscaling.maxReplicas }} + metrics: + {{- with .Values.queryFrontend.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.queryFrontend.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.queryFrontend.autoscaling.customMetrics }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- if .Values.queryFrontend.autoscaling.behavior.enabled }} + behavior: + {{- with .Values.queryFrontend.autoscaling.behavior.scaleDown }} + scaleDown: {{ toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.queryFrontend.autoscaling.behavior.scaleUp }} + scaleUp: {{ toYaml . | nindent 6 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/poddisruptionbudget-query-frontent.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/poddisruptionbudget-query-frontent.yaml new file mode 100644 index 0000000..f6022e8 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/poddisruptionbudget-query-frontent.yaml @@ -0,0 +1,20 @@ +{{- if gt (int .Values.queryFrontend.replicas) 1 }} +{{- if kindIs "invalid" .Values.queryFrontend.maxUnavailable }} +{{- fail "`.Values.queryFrontend.maxUnavailable` must be set when `.Values.queryFrontend.replicas` is greater than 1." }} +{{- else }} +apiVersion: {{ include "loki.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "loki.queryFrontendFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.queryFrontendLabels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "loki.queryFrontendSelectorLabels" . | nindent 6 }} + {{- with .Values.queryFrontend.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/service-query-frontend-headless.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/service-query-frontend-headless.yaml new file mode 100644 index 0000000..7bcc7c3 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/service-query-frontend-headless.yaml @@ -0,0 +1,40 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.queryFrontendFullname" . }}-headless + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.queryFrontendLabels" . | nindent 4 }} + {{- with .Values.queryFrontend.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + prometheus.io/service-monitor: "false" + {{- with .Values.loki.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + clusterIP: None + type: ClusterIP + publishNotReadyAddresses: true + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + {{- if .Values.queryFrontend.appProtocol.grpc }} + appProtocol: {{ .Values.queryFrontend.appProtocol.grpc }} + {{- end }} + - name: grpclb + port: 9096 + targetPort: grpc + protocol: TCP + {{- if .Values.queryFrontend.appProtocol.grpc }} + appProtocol: {{ .Values.queryFrontend.appProtocol.grpc }} + {{- end }} + selector: + {{- include "loki.queryFrontendSelectorLabels" . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/service-query-frontend.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/service-query-frontend.yaml new file mode 100644 index 0000000..ba77e40 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/service-query-frontend.yaml @@ -0,0 +1,38 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.queryFrontendFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.queryFrontendLabels" . | nindent 4 }} + {{- with .Values.queryFrontend.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.loki.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + publishNotReadyAddresses: true + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + {{- if .Values.queryFrontend.appProtocol.grpc }} + appProtocol: {{ .Values.queryFrontend.appProtocol.grpc }} + {{- end }} + - name: grpclb + port: 9096 + targetPort: grpc + protocol: TCP + {{- if .Values.queryFrontend.appProtocol.grpc }} + appProtocol: {{ .Values.queryFrontend.appProtocol.grpc }} + {{- end }} + selector: + {{- include "loki.queryFrontendSelectorLabels" . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/servicemonitor-query-frontend.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/servicemonitor-query-frontend.yaml new file mode 100644 index 0000000..6a4c7ce --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/query-frontend/servicemonitor-query-frontend.yaml @@ -0,0 +1,59 @@ +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.queryFrontendFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.queryFrontendLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.queryFrontendSelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/_helpers-query-scheduler.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/_helpers-query-scheduler.tpl new file mode 100644 index 0000000..1f64802 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/_helpers-query-scheduler.tpl @@ -0,0 +1,40 @@ +{{/* +query-scheduler fullname +*/}} +{{- define "loki.querySchedulerFullname" -}} +{{ include "loki.fullname" . }}-query-scheduler +{{- end }} + +{{/* +query-scheduler common labels +*/}} +{{- define "loki.querySchedulerLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: query-scheduler +{{- end }} + +{{/* +query-scheduler selector labels +*/}} +{{- define "loki.querySchedulerSelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: query-scheduler +{{- end }} + +{{/* +query-scheduler image +*/}} +{{- define "loki.querySchedulerImage" -}} +{{- $dict := dict "loki" .Values.loki.image "service" .Values.queryScheduler.image "global" .Values.global.image "defaultVersion" .Chart.AppVersion -}} +{{- include "loki.lokiImage" $dict -}} +{{- end }} + +{{/* +query-scheduler priority class name +*/}} +{{- define "loki.querySchedulerPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.queryScheduler.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/deployment-query-scheduler.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/deployment-query-scheduler.yaml new file mode 100644 index 0000000..70a95ab --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/deployment-query-scheduler.yaml @@ -0,0 +1,135 @@ +{{- if .Values.queryScheduler.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "loki.querySchedulerFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.querySchedulerLabels" . | nindent 4 }} + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.queryScheduler.replicas }} + strategy: + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.querySchedulerSelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.queryScheduler.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.querySchedulerSelectorLabels" . | nindent 8 }} + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.queryScheduler.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + app.kubernetes.io/part-of: memberlist + spec: + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.queryScheduler.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.querySchedulerPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.queryScheduler.terminationGracePeriodSeconds }} + containers: + - name: query-scheduler + image: {{ include "loki.querySchedulerImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=query-scheduler + {{- with .Values.queryScheduler.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + - name: http-memberlist + containerPort: 7946 + protocol: TCP + {{- with .Values.queryScheduler.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.queryScheduler.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.loki.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.loki.livenessProbe | nindent 12 }} + volumeMounts: + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + {{- with .Values.queryScheduler.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.queryScheduler.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.queryScheduler.extraContainers }} + {{- toYaml .Values.queryScheduler.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.queryScheduler.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.queryScheduler.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.queryScheduler.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + {{- with .Values.queryScheduler.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/poddisruptionbudget-query-scheduler.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/poddisruptionbudget-query-scheduler.yaml new file mode 100644 index 0000000..9b1a893 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/poddisruptionbudget-query-scheduler.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.queryScheduler.enabled (gt (int .Values.queryScheduler.replicas) 1) }} +{{- if kindIs "invalid" .Values.queryScheduler.maxUnavailable }} +{{- fail "`.Values.queryScheduler.maxUnavailable` must be set when `.Values.queryScheduler.replicas` is greater than 1." }} +{{- else }} +apiVersion: {{ include "loki.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "loki.querySchedulerFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.querySchedulerLabels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "loki.querySchedulerSelectorLabels" . | nindent 6 }} + {{- with .Values.queryScheduler.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/service-query-scheduler.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/service-query-scheduler.yaml new file mode 100644 index 0000000..40f7927 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/service-query-scheduler.yaml @@ -0,0 +1,34 @@ +{{- if .Values.queryScheduler.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.querySchedulerFullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.querySchedulerLabels" . | nindent 4 }} + {{- with .Values.queryScheduler.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.loki.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + clusterIP: None + publishNotReadyAddresses: true + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpclb + port: 9095 + targetPort: grpc + protocol: TCP + {{- with .Values.queryScheduler.appProtocol.grpc }} + appProtocol: {{ . }} + {{- end }} + selector: + {{- include "loki.querySchedulerSelectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/servicemonitor-query-scheduler.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/servicemonitor-query-scheduler.yaml new file mode 100644 index 0000000..9ee893b --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/query-scheduler/servicemonitor-query-scheduler.yaml @@ -0,0 +1,57 @@ +{{- if .Values.queryScheduler.enabled }} +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.querySchedulerFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.querySchedulerLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.querySchedulerSelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/role.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/role.yaml new file mode 100644 index 0000000..b281fdb --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/role.yaml @@ -0,0 +1,31 @@ +{{- if or .Values.rbac.pspEnabled .Values.rbac.sccEnabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ include "loki.fullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.labels" . | nindent 4 }} +{{- if .Values.rbac.pspEnabled }} +rules: + - apiGroups: + - policy + resources: + - podsecuritypolicies + verbs: + - use + resourceNames: + - {{ include "loki.fullname" . }} +{{- end }} +{{- if .Values.rbac.sccEnabled }} +rules: +- apiGroups: + - security.openshift.io + resources: + - securitycontextconstraints + verbs: + - use + resourceNames: + - {{ include "loki.fullname" . }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/rolebinding.yaml new file mode 100644 index 0000000..46a3f6a --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/rolebinding.yaml @@ -0,0 +1,16 @@ +{{- if or .Values.rbac.pspEnabled .Values.rbac.sccEnabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "loki.fullname" . }} + labels: + {{- include "loki.labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "loki.fullname" . }} +subjects: + - kind: ServiceAccount + name: {{ include "loki.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/_helpers-ruler.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/_helpers-ruler.tpl new file mode 100644 index 0000000..2079e03 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/_helpers-ruler.tpl @@ -0,0 +1,47 @@ +{{/* +ruler fullname +*/}} +{{- define "loki.rulerFullname" -}} +{{ include "loki.fullname" . }}-ruler +{{- end }} + +{{/* +ruler common labels +*/}} +{{- define "loki.rulerLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: ruler +{{- end }} + +{{/* +ruler selector labels +*/}} +{{- define "loki.rulerSelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: ruler +{{- end }} + +{{/* +ruler image +*/}} +{{- define "loki.rulerImage" -}} +{{- $dict := dict "loki" .Values.loki.image "service" .Values.ruler.image "global" .Values.global.image "defaultVersion" .Chart.AppVersion -}} +{{- include "loki.lokiImage" $dict -}} +{{- end }} + +{{/* +format rules dir +*/}} +{{- define "loki.rulerRulesDirName" -}} +rules-{{ . | replace "_" "-" | trimSuffix "-" | lower }} +{{- end }} + +{{/* +ruler priority class name +*/}} +{{- define "loki.rulerPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.ruler.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/configmap-ruler.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/configmap-ruler.yaml new file mode 100644 index 0000000..c0599d5 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/configmap-ruler.yaml @@ -0,0 +1,13 @@ +{{- if .Values.ruler.enabled }} +{{- range $dir, $files := .Values.ruler.directories }} +--- +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "loki.rulerFullname" $ }}-{{ include "loki.rulerRulesDirName" $dir }} + labels: + {{- include "loki.rulerLabels" $ | nindent 4 }} +data: + {{- toYaml $files | nindent 2}} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/deployment-ruler.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/deployment-ruler.yaml new file mode 100644 index 0000000..955c5e6 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/deployment-ruler.yaml @@ -0,0 +1,167 @@ +{{- if and (eq .Values.ruler.kind "Deployment") .Values.ruler.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "loki.rulerFullname" . }} + labels: + {{- include "loki.rulerLabels" . | nindent 4 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.ruler.replicas }} + strategy: + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.rulerSelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ruler.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.rulerSelectorLabels" . | nindent 8 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ruler.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ruler.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.rulerPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.ruler.terminationGracePeriodSeconds }} + {{- with .Values.ruler.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: ruler + image: {{ include "loki.rulerImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + {{- if or .Values.loki.command .Values.ruler.command }} + command: + - {{ coalesce .Values.ruler.command .Values.loki.command | quote }} + {{- end }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=ruler + {{- with .Values.ruler.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + - name: http-memberlist + containerPort: 7946 + protocol: TCP + {{- with .Values.ruler.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ruler.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.loki.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.loki.livenessProbe | nindent 12 }} + volumeMounts: + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + - name: data + mountPath: /var/loki + - name: tmp + mountPath: /tmp/loki + {{- range $dir, $_ := .Values.ruler.directories }} + - name: {{ include "loki.rulerRulesDirName" $dir }} + mountPath: /etc/loki/rules/{{ $dir }} + {{- end }} + {{- with .Values.ruler.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.ruler.resources | nindent 12 }} + {{- if .Values.ruler.extraContainers }} + {{- toYaml .Values.ruler.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.ruler.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.ruler.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ruler.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ruler.dnsConfig }} + dnsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + {{- range $dir, $_ := .Values.ruler.directories }} + - name: {{ include "loki.rulerRulesDirName" $dir }} + configMap: + name: {{ include "loki.rulerFullname" $ }}-{{ include "loki.rulerRulesDirName" $dir }} + {{- end }} + - name: tmp + emptyDir: {} + - name: data + {{- if .Values.ruler.persistence.enabled }} + persistentVolumeClaim: + claimName: data-{{ include "loki.rulerFullname" . }} + {{- else }} + emptyDir: {} + {{- end }} + {{- with .Values.ruler.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/persistentvolumeclaim-ruler.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/persistentvolumeclaim-ruler.yaml new file mode 100644 index 0000000..2fde96d --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/persistentvolumeclaim-ruler.yaml @@ -0,0 +1,21 @@ +{{- if and (eq .Values.ruler.kind "Deployment") .Values.ruler.enabled .Values.ruler.persistence.enabled }} +apiVersion: v1 +kind: PersistentVolumeClaim +metadata: + name: data-{{ include "loki.rulerFullname" . }} + labels: + {{- include "loki.rulerLabels" . | nindent 4 }} + {{- with .Values.ruler.persistence.annotations }} + annotations: + {{- . | toYaml | nindent 4 }} + {{- end }} +spec: + accessModes: + - ReadWriteOnce + {{- with .Values.ruler.persistence.storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: "{{ .Values.ruler.persistence.size }}" +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/poddisruptionbudget-ruler.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/poddisruptionbudget-ruler.yaml new file mode 100644 index 0000000..09925a8 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/poddisruptionbudget-ruler.yaml @@ -0,0 +1,19 @@ +{{- if and .Values.ruler.enabled (gt (int .Values.ruler.replicas) 1) }} +{{- if kindIs "invalid" .Values.ruler.maxUnavailable }} +{{- fail "`.Values.ruler.maxUnavailable` must be set when `.Values.ruler.replicas` is greater than 1." }} +{{- else }} +apiVersion: {{ include "loki.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "loki.rulerFullname" . }} + labels: + {{- include "loki.rulerLabels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "loki.rulerSelectorLabels" . | nindent 6 }} + {{- with .Values.ruler.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/service-ruler.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/service-ruler.yaml new file mode 100644 index 0000000..710ab82 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/service-ruler.yaml @@ -0,0 +1,32 @@ +{{- if .Values.ruler.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.rulerFullname" . }} + labels: + {{- include "loki.rulerSelectorLabels" . | nindent 4 }} + {{- with .Values.ruler.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.loki.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + {{- with .Values.ruler.appProtocol.grpc }} + appProtocol: {{ . }} + {{- end }} + selector: + {{- include "loki.rulerSelectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/servicemonitor-ruler.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/servicemonitor-ruler.yaml new file mode 100644 index 0000000..827b3d4 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/servicemonitor-ruler.yaml @@ -0,0 +1,61 @@ +{{- if .Values.ruler.enabled }} +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.rulerFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.rulerLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.rulerSelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/statefulset-ruler.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/statefulset-ruler.yaml new file mode 100644 index 0000000..2172851 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/ruler/statefulset-ruler.yaml @@ -0,0 +1,174 @@ +{{- if and (eq .Values.ruler.kind "StatefulSet") .Values.ruler.enabled }} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "loki.rulerFullname" . }} + labels: + {{- include "loki.rulerLabels" . | nindent 4 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.ruler.replicas }} + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + serviceName: {{ include "loki.rulerFullname" . }} + selector: + matchLabels: + {{- include "loki.rulerSelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ruler.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.rulerSelectorLabels" . | nindent 8 }} + app.kubernetes.io/part-of: memberlist + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ruler.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ruler.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.rulerPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.ruler.terminationGracePeriodSeconds }} + {{- with .Values.ruler.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: ruler + image: {{ include "loki.rulerImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=ruler + {{- with .Values.ruler.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + - name: http-memberlist + containerPort: 7946 + protocol: TCP + {{- with .Values.ruler.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ruler.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.loki.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.loki.livenessProbe | nindent 12 }} + volumeMounts: + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + - name: data + mountPath: /var/loki + - name: tmp + mountPath: /tmp/loki + {{- range $dir, $_ := .Values.ruler.directories }} + - name: {{ include "loki.rulerRulesDirName" $dir }} + mountPath: /etc/loki/rules/{{ $dir }} + {{- end }} + {{- with .Values.ruler.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.ruler.resources | nindent 12 }} + {{- with .Values.ruler.extraContainers }} + {{- toYaml . | nindent 8}} + {{- end }} + {{- with .Values.ruler.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.ruler.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ruler.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ruler.dnsConfig }} + dnsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + {{- range $dir, $_ := .Values.ruler.directories }} + - name: {{ include "loki.rulerRulesDirName" $dir }} + configMap: + name: {{ include "loki.rulerFullname" $ }}-{{ include "loki.rulerRulesDirName" $dir }} + {{- end }} + - name: tmp + emptyDir: {} + {{- with .Values.ruler.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if not .Values.ruler.persistence.enabled }} + - name: data + emptyDir: {} + {{- else }} + volumeClaimTemplates: + - metadata: + name: data + {{- with .Values.ruler.persistence.annotations }} + annotations: + {{- . | toYaml | nindent 10 }} + {{- end }} + spec: + accessModes: + - ReadWriteOnce + {{- with .Values.ruler.persistence.storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: {{ .Values.ruler.persistence.size | quote }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/runtime-configmap.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/runtime-configmap.yaml new file mode 100644 index 0000000..89e42ee --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/runtime-configmap.yaml @@ -0,0 +1,10 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "loki.fullname" . }}-runtime + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.labels" . | nindent 4 }} +data: + runtime.yaml: | + {{ tpl (toYaml .Values.runtimeConfig) . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/securitycontextconstraints.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/securitycontextconstraints.yaml new file mode 100644 index 0000000..290d3f6 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/securitycontextconstraints.yaml @@ -0,0 +1,40 @@ +{{- if .Values.rbac.sccEnabled }} +apiVersion: security.openshift.io/v1 +kind: SecurityContextConstraints +metadata: + name: {{ include "loki.fullname" . }} + labels: + {{- include "loki.labels" . | nindent 4 }} +allowHostDirVolumePlugin: false +allowHostIPC: false +allowHostNetwork: false +allowHostPID: false +allowHostPorts: false +allowPrivilegeEscalation: true +allowPrivilegedContainer: false +allowedCapabilities: [] +defaultAddCapabilities: null +fsGroup: + type: RunAsAny +groups: [] +priority: null +readOnlyRootFilesystem: false +requiredDropCapabilities: + - ALL +runAsUser: + type: RunAsAny +seLinuxContext: + type: MustRunAs +seccompProfiles: + - '*' +supplementalGroups: + type: RunAsAny +volumes: + - configMap + - downwardAPI + - emptyDir + - hostPath + - persistentVolumeClaim + - projected + - secret +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/service-memberlist.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/service-memberlist.yaml new file mode 100644 index 0000000..79affd2 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/service-memberlist.yaml @@ -0,0 +1,21 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.fullname" . }}-memberlist + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.labels" . | nindent 4 }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: tcp + port: 7946 + targetPort: http-memberlist + protocol: TCP + {{- if .Values.loki.appProtocol }} + appProtocol: {{ .Values.loki.appProtocol }} + {{- end }} + selector: + {{- include "loki.selectorLabels" . | nindent 4 }} + app.kubernetes.io/part-of: memberlist diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/serviceaccount.yaml new file mode 100644 index 0000000..5cc4de5 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/serviceaccount.yaml @@ -0,0 +1,22 @@ +{{ if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "loki.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "loki.labels" . | nindent 4 }} + {{- with .Values.serviceAccount.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }} +{{- with .Values.serviceAccount.imagePullSecrets }} +imagePullSecrets: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- end }} + diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/table-manager/_helpers-table-manager.tpl b/observability/lgtm-distributed/charts/loki-distributed/templates/table-manager/_helpers-table-manager.tpl new file mode 100644 index 0000000..4905d90 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/table-manager/_helpers-table-manager.tpl @@ -0,0 +1,40 @@ +{{/* +table-manager fullname +*/}} +{{- define "loki.tableManagerFullname" -}} +{{ include "loki.fullname" . }}-table-manager +{{- end }} + +{{/* +table-manager common labels +*/}} +{{- define "loki.tableManagerLabels" -}} +{{ include "loki.labels" . }} +app.kubernetes.io/component: table-manager +{{- end }} + +{{/* +table-manager selector labels +*/}} +{{- define "loki.tableManagerSelectorLabels" -}} +{{ include "loki.selectorLabels" . }} +app.kubernetes.io/component: table-manager +{{- end }} + +{{/* +table-manager image +*/}} +{{- define "loki.tableManagerImage" -}} +{{- $dict := dict "loki" .Values.loki.image "service" .Values.tableManager.image "global" .Values.global.image "defaultVersion" .Chart.AppVersion -}} +{{- include "loki.lokiImage" $dict -}} +{{- end }} + +{{/* +table-manager priority class name +*/}} +{{- define "loki.tableManagerPriorityClassName" -}} +{{- $pcn := coalesce .Values.global.priorityClassName .Values.tableManager.priorityClassName -}} +{{- if $pcn }} +priorityClassName: {{ $pcn }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/table-manager/deployment-table-manager.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/table-manager/deployment-table-manager.yaml new file mode 100644 index 0000000..f550ae8 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/table-manager/deployment-table-manager.yaml @@ -0,0 +1,132 @@ +{{- if .Values.tableManager.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "loki.tableManagerFullname" . }} + labels: + {{- include "loki.tableManagerLabels" . | nindent 4 }} + {{- with .Values.loki.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: 1 + revisionHistoryLimit: {{ .Values.loki.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "loki.tableManagerSelectorLabels" . | nindent 6 }} + template: + metadata: + annotations: + {{- include "loki.config.checksum" . | nindent 8 }} + {{- with .Values.loki.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tableManager.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "loki.tableManagerSelectorLabels" . | nindent 8 }} + {{- with .Values.loki.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tableManager.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ include "loki.serviceAccountName" . }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tableManager.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "loki.tableManagerPriorityClassName" . | nindent 6 }} + securityContext: + {{- toYaml .Values.loki.podSecurityContext | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.tableManager.terminationGracePeriodSeconds }} + containers: + - name: table-manager + image: {{ include "loki.tableManagerImage" . }} + imagePullPolicy: {{ .Values.loki.image.pullPolicy }} + {{- if or .Values.loki.command .Values.tableManager.command }} + command: + - {{ coalesce .Values.tableManager.command .Values.loki.command | quote }} + {{- end }} + args: + - -config.file=/etc/loki/config/config.yaml + - -target=table-manager + {{- with .Values.tableManager.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: http + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + {{- with .Values.tableManager.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.tableManager.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.loki.containerSecurityContext | nindent 12 }} + readinessProbe: + {{- toYaml .Values.loki.readinessProbe | nindent 12 }} + livenessProbe: + {{- toYaml .Values.loki.livenessProbe | nindent 12 }} + volumeMounts: + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /var/{{ include "loki.name" . }}-runtime + - name: data + mountPath: /var/loki + {{- with .Values.tableManager.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.tableManager.resources | nindent 12 }} + {{- if .Values.tableManager.extraContainers }} + {{- toYaml .Values.tableManager.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.tableManager.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.tableManager.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tableManager.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- if .Values.loki.existingSecretForConfig }} + secret: + secretName: {{ .Values.loki.existingSecretForConfig }} + {{- else if .Values.loki.configAsSecret }} + secret: + secretName: {{ include "loki.fullname" . }}-config + {{- else }} + configMap: + name: {{ include "loki.fullname" . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "loki.fullname" . }}-runtime + - name: data + emptyDir: {} + {{- with .Values.tableManager.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/table-manager/service-table-manager.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/table-manager/service-table-manager.yaml new file mode 100644 index 0000000..91a41af --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/table-manager/service-table-manager.yaml @@ -0,0 +1,30 @@ +{{- if .Values.tableManager.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "loki.fullname" . }}-table-manager + labels: + {{- include "loki.labels" . | nindent 4 }} + {{- with .Values.tableManager.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + app.kubernetes.io/component: table-manager + {{- with .Values.loki.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + ports: + - name: http + port: 3100 + targetPort: http + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + selector: + {{- include "loki.selectorLabels" . | nindent 4 }} + app.kubernetes.io/component: table-manager +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/table-manager/servicemonitor-table-manager.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/table-manager/servicemonitor-table-manager.yaml new file mode 100644 index 0000000..6a0626a --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/table-manager/servicemonitor-table-manager.yaml @@ -0,0 +1,61 @@ +{{- if .Values.tableManager.enabled }} +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "loki.tableManagerFullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "loki.tableManagerLabels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "loki.tableManagerSelectorLabels" $ | nindent 6 }} + {{- with .matchExpressions }} + matchExpressions: + {{- toYaml . | nindent 6 }} + {{- end }} + endpoints: + - port: http + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/templates/validate.yaml b/observability/lgtm-distributed/charts/loki-distributed/templates/validate.yaml new file mode 100644 index 0000000..74f22f0 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/templates/validate.yaml @@ -0,0 +1,4 @@ + +{{- if and .Values.ingress.enabled .Values.gateway.enabled }} +{{- fail "The 'top level' ingress and gateway service shouldn't both be enabled. If you'd like to use the gateway service, there's an ingress configuration under it. See values.yaml for further details" -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/loki-distributed/values.test.yaml b/observability/lgtm-distributed/charts/loki-distributed/values.test.yaml new file mode 100644 index 0000000..1d7a959 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/values.test.yaml @@ -0,0 +1,3 @@ +loki: + annotations: + foo: bar diff --git a/observability/lgtm-distributed/charts/loki-distributed/values.yaml b/observability/lgtm-distributed/charts/loki-distributed/values.yaml new file mode 100644 index 0000000..15e9343 --- /dev/null +++ b/observability/lgtm-distributed/charts/loki-distributed/values.yaml @@ -0,0 +1,2062 @@ +global: + image: + # -- Overrides the Docker registry globally for all images + registry: null + # -- Overrides the priorityClassName for all pods + priorityClassName: null + # -- configures cluster domain ("cluster.local" by default) + clusterDomain: "cluster.local" + # -- configures DNS service name + dnsService: "kube-dns" + # -- configures DNS service namespace + dnsNamespace: "kube-system" + +# -- Overrides the chart's name +nameOverride: null + +# -- Overrides the chart's computed fullname +fullnameOverride: null + +# -- Image pull secrets for Docker images +imagePullSecrets: [] + +# -- hostAliases to add +hostAliases: [] +# - ip: 1.2.3.4 +# hostnames: +# - domain.tld + +loki: + # -- If set, these annotations are added to all of the Kubernetes controllers + # (Deployments, StatefulSets, etc) that this chart launches. Use this to + # implement something like the "Wave" controller or another controller that + # is monitoring top level deployment resources. + annotations: {} + # Configures the readiness probe for all of the Loki pods + readinessProbe: + httpGet: + path: /ready + port: http + initialDelaySeconds: 30 + timeoutSeconds: 1 + livenessProbe: + httpGet: + path: /ready + port: http + initialDelaySeconds: 300 + image: + # -- The Docker registry + registry: docker.io + # -- Docker image repository + repository: grafana/loki + # -- Overrides the image tag whose default is the chart's appVersion + tag: null + # -- Docker image pull policy + pullPolicy: IfNotPresent + # -- Common labels for all pods + podLabels: {} + # -- Common annotations for all pods + podAnnotations: {} + # -- Common command override for all pods (except gateway) + command: null + # -- The number of old ReplicaSets to retain to allow rollback + revisionHistoryLimit: 10 + # -- The SecurityContext for Loki pods + podSecurityContext: + fsGroup: 10001 + runAsGroup: 10001 + runAsNonRoot: true + runAsUser: 10001 + # -- The SecurityContext for Loki containers + containerSecurityContext: + readOnlyRootFilesystem: true + capabilities: + drop: + - ALL + allowPrivilegeEscalation: false + # -- Specify an existing secret containing loki configuration. If non-empty, overrides `loki.config` + existingSecretForConfig: "" + # -- Store the loki configuration as a secret. + configAsSecret: false + # -- Annotations for the secret with loki configuration. + configSecretAnnotations: {} + # -- Additional labels for the secret with loki configuration. + configSecretLabels: {} + # -- Adds the appProtocol field to the memberlist service. This allows memberlist to work with istio protocol selection. Ex: "http" or "tcp" + appProtocol: "" + # -- Common annotations for all loki services + serviceAnnotations: {} + # Loki server configuration + # Refers to https://grafana.com/docs/loki/latest/configuration/#server + server: + # -- HTTP server listen port + http_listen_port: 3100 + # -- Config file contents for Loki + # @default -- See values.yaml + config: | + auth_enabled: false + + server: + {{- toYaml .Values.loki.server | nindent 6 }} + + common: + compactor_address: http://{{ include "loki.compactorFullname" . }}:3100 + + distributor: + ring: + kvstore: + store: memberlist + + memberlist: + join_members: + - {{ include "loki.fullname" . }}-memberlist + + ingester_client: + grpc_client_config: + grpc_compression: gzip + + ingester: + lifecycler: + ring: + kvstore: + store: memberlist + replication_factor: 1 + chunk_idle_period: 30m + chunk_block_size: 262144 + chunk_encoding: snappy + chunk_retain_period: 1m + max_transfer_retries: 0 + wal: + dir: /var/loki/wal + + limits_config: + enforce_metric_name: false + reject_old_samples: true + reject_old_samples_max_age: 168h + max_cache_freshness_per_query: 10m + split_queries_by_interval: 15m + + {{- if .Values.loki.schemaConfig}} + schema_config: + {{- toYaml .Values.loki.schemaConfig | nindent 2}} + {{- end}} + {{- if .Values.loki.storageConfig}} + storage_config: + {{- if .Values.indexGateway.enabled}} + {{- $indexGatewayClient := dict "server_address" (printf "dns:///%s:9095" (include "loki.indexGatewayFullname" .)) }} + {{- $_ := set .Values.loki.storageConfig.boltdb_shipper "index_gateway_client" $indexGatewayClient }} + {{- end}} + {{- toYaml .Values.loki.storageConfig | nindent 2}} + {{- if .Values.memcachedIndexQueries.enabled }} + index_queries_cache_config: + memcached_client: + addresses: dnssrv+_memcached-client._tcp.{{ include "loki.memcachedIndexQueriesFullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }} + consistent_hash: true + {{- end}} + {{- end}} + + runtime_config: + file: /var/{{ include "loki.name" . }}-runtime/runtime.yaml + + chunk_store_config: + max_look_back_period: 0s + {{- if .Values.memcachedChunks.enabled }} + chunk_cache_config: + embedded_cache: + enabled: false + memcached_client: + consistent_hash: true + addresses: dnssrv+_memcached-client._tcp.{{ include "loki.memcachedChunksFullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }} + {{- end }} + {{- if .Values.memcachedIndexWrites.enabled }} + write_dedupe_cache_config: + memcached_client: + consistent_hash: true + addresses: dnssrv+_memcached-client._tcp.{{ include "loki.memcachedIndexWritesFullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }} + {{- end }} + + table_manager: + retention_deletes_enabled: false + retention_period: 0s + + query_range: + align_queries_with_step: true + max_retries: 5 + cache_results: true + results_cache: + cache: + {{- if .Values.memcachedFrontend.enabled }} + memcached_client: + addresses: dnssrv+_memcached-client._tcp.{{ include "loki.memcachedFrontendFullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }} + consistent_hash: true + {{- else }} + embedded_cache: + enabled: true + ttl: 24h + {{- end }} + + frontend_worker: + {{- if .Values.queryScheduler.enabled }} + scheduler_address: {{ include "loki.querySchedulerFullname" . }}:9095 + {{- else }} + frontend_address: {{ include "loki.queryFrontendFullname" . }}-headless:9095 + {{- end }} + + frontend: + log_queries_longer_than: 5s + compress_responses: true + {{- if .Values.queryScheduler.enabled }} + scheduler_address: {{ include "loki.querySchedulerFullname" . }}:9095 + {{- end }} + tail_proxy_url: http://{{ include "loki.querierFullname" . }}:3100 + + compactor: + shared_store: filesystem + working_directory: /var/loki/compactor + + ruler: + storage: + type: local + local: + directory: /etc/loki/rules + ring: + kvstore: + store: memberlist + rule_path: /tmp/loki/scratch + alertmanager_url: https://alertmanager.xx + external_url: https://alertmanager.xx + + # -- Check https://grafana.com/docs/loki/latest/configuration/#schema_config for more info on how to configure schemas + schemaConfig: + configs: + - from: "2020-09-07" + store: boltdb-shipper + object_store: filesystem + schema: v11 + index: + prefix: loki_index_ + period: 24h + + # -- Check https://grafana.com/docs/loki/latest/configuration/#storage_config for more info on how to configure storages + storageConfig: + boltdb_shipper: + shared_store: filesystem + active_index_directory: /var/loki/index + cache_location: /var/loki/cache + cache_ttl: 168h + filesystem: + directory: /var/loki/chunks +# -- Uncomment to configure each storage individually +# azure: {} +# gcs: {} +# s3: {} +# boltdb: {} + + # -- Structured loki configuration, takes precedence over `loki.config`, `loki.schemaConfig`, `loki.storageConfig` + structuredConfig: {} + +# -- Provides a reloadable runtime configuration file for some specific configuration +runtimeConfig: {} + +serviceAccount: + # -- Specifies whether a ServiceAccount should be created + create: true + # -- The name of the ServiceAccount to use. + # If not set and create is true, a name is generated using the fullname template + name: null + # -- Image pull secrets for the service account + imagePullSecrets: [] + # -- Labels for the service account + labels: {} + # -- Annotations for the service account + annotations: {} + # -- Set this toggle to false to opt out of automounting API credentials for the service account + automountServiceAccountToken: true + +# RBAC configuration +rbac: + # -- If pspEnabled true, a PodSecurityPolicy is created for K8s that use psp. + pspEnabled: false + # -- For OpenShift set pspEnabled to 'false' and sccEnabled to 'true' to use the SecurityContextConstraints. + sccEnabled: false + +# ServiceMonitor configuration +serviceMonitor: + # -- If enabled, ServiceMonitor resources for Prometheus Operator are created + enabled: false + # -- Alternative namespace for ServiceMonitor resources + namespace: null + # -- Namespace selector for ServiceMonitor resources + namespaceSelector: {} + # -- Optional expressions to match on + matchExpressions: [] + # - key: prometheus.io/service-monitor + # operator: NotIn + # values: + # - "false" + # -- ServiceMonitor annotations + annotations: {} + # -- Additional ServiceMonitor labels + labels: {} + # -- ServiceMonitor scrape interval + interval: null + # -- ServiceMonitor scrape timeout in Go duration format (e.g. 15s) + scrapeTimeout: null + # -- ServiceMonitor relabel configs to apply to samples before scraping + # https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig + relabelings: [] + # -- ServiceMonitor metric relabel configs to apply to samples before ingestion + # https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#endpoint + metricRelabelings: [] + # --ServiceMonitor will add labels from the service to the Prometheus metric + # https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#servicemonitorspec + targetLabels: [] + # -- ServiceMonitor will use http by default, but you can pick https as well + scheme: http + # -- ServiceMonitor will use these tlsConfig settings to make the health check requests + tlsConfig: null + +# Rules for the Prometheus Operator +prometheusRule: + # -- If enabled, a PrometheusRule resource for Prometheus Operator is created + enabled: false + # -- Alternative namespace for the PrometheusRule resource + namespace: null + # -- PrometheusRule annotations + annotations: {} + # -- Additional PrometheusRule labels + labels: {} + # -- Contents of Prometheus rules file + groups: [] + # - name: loki_rules + # rules: + # - expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) + # by (le, cluster, job)) + # record: cluster_job:loki_request_duration_seconds:99quantile + # - expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) + # by (le, cluster, job)) + # record: cluster_job:loki_request_duration_seconds:50quantile + # - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job) / sum(rate(loki_request_duration_seconds_count[1m])) + # by (cluster, job) + # record: cluster_job:loki_request_duration_seconds:avg + # - expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, job) + # record: cluster_job:loki_request_duration_seconds_bucket:sum_rate + # - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job) + # record: cluster_job:loki_request_duration_seconds_sum:sum_rate + # - expr: sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job) + # record: cluster_job:loki_request_duration_seconds_count:sum_rate + # - expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) + # by (le, cluster, job, route)) + # record: cluster_job_route:loki_request_duration_seconds:99quantile + # - expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) + # by (le, cluster, job, route)) + # record: cluster_job_route:loki_request_duration_seconds:50quantile + # - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job, route) + # / sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job, route) + # record: cluster_job_route:loki_request_duration_seconds:avg + # - expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, job, + # route) + # record: cluster_job_route:loki_request_duration_seconds_bucket:sum_rate + # - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, job, route) + # record: cluster_job_route:loki_request_duration_seconds_sum:sum_rate + # - expr: sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, job, route) + # record: cluster_job_route:loki_request_duration_seconds_count:sum_rate + # - expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) + # by (le, cluster, namespace, job, route)) + # record: cluster_namespace_job_route:loki_request_duration_seconds:99quantile + # - expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) + # by (le, cluster, namespace, job, route)) + # record: cluster_namespace_job_route:loki_request_duration_seconds:50quantile + # - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, namespace, + # job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, + # namespace, job, route) + # record: cluster_namespace_job_route:loki_request_duration_seconds:avg + # - expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, cluster, namespace, + # job, route) + # record: cluster_namespace_job_route:loki_request_duration_seconds_bucket:sum_rate + # - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (cluster, namespace, + # job, route) + # record: cluster_namespace_job_route:loki_request_duration_seconds_sum:sum_rate + # - expr: sum(rate(loki_request_duration_seconds_count[1m])) by (cluster, namespace, + # job, route) + # record: cluster_namespace_job_route:loki_request_duration_seconds_count:sum_rate + +# Configuration for the ingester +ingester: + # -- Kind of deployment [StatefulSet/Deployment] + kind: StatefulSet + # -- Number of replicas for the ingester + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + autoscaling: + # -- Enable autoscaling for the ingester + enabled: false + # -- Minimum autoscaling replicas for the ingester + minReplicas: 1 + # -- Maximum autoscaling replicas for the ingester + maxReplicas: 3 + # -- Target CPU utilisation percentage for the ingester + targetCPUUtilizationPercentage: 60 + # -- Target memory utilisation percentage for the ingester + targetMemoryUtilizationPercentage: null + # -- Allows one to define custom metrics using the HPA/v2 schema (for example, Pods, Object or External metrics) + customMetrics: [] + # - type: Pods + # pods: + # metric: + # name: loki_lines_total + # target: + # type: AverageValue + # averageValue: 10k + behavior: + # -- Enable autoscaling behaviours + enabled: false + # -- define scale down policies, must conform to HPAScalingRules + scaleDown: {} + # -- define scale up policies, must conform to HPAScalingRules + scaleUp: {} + image: + # -- The Docker registry for the ingester image. Overrides `loki.image.registry` + registry: null + # -- Docker image repository for the ingester image. Overrides `loki.image.repository` + repository: null + # -- Docker image tag for the ingester image. Overrides `loki.image.tag` + tag: null + # -- Command to execute instead of defined in Docker image + command: null + # -- The name of the PriorityClass for ingester pods + priorityClassName: null + # -- Labels for ingester pods + podLabels: {} + # -- Annotations for ingester pods + podAnnotations: {} + # -- Labels for ingestor service + serviceLabels: {} + # -- Additional CLI args for the ingester + extraArgs: [] + # -- Environment variables to add to the ingester pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the ingester pods + extraEnvFrom: [] + # -- Volume mounts to add to the ingester pods + extraVolumeMounts: [] + # -- Volumes to add to the ingester pods + extraVolumes: [] + # -- Resource requests and limits for the ingester + resources: {} + # -- Containers to add to the ingester pods + extraContainers: [] + # -- Init containers to add to the ingester pods + initContainers: [] + # -- Grace period to allow the ingester to shutdown before it is killed. Especially for the ingestor, + # this must be increased. It must be long enough so ingesters can be gracefully shutdown flushing/transferring + # all data and to successfully leave the member ring on shutdown. + terminationGracePeriodSeconds: 300 + # -- Lifecycle for the ingester container + lifecycle: {} + # -- topologySpread for ingester pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Defaults to allow skew no more then 1 node per AZ + topologySpreadConstraints: | + - maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + labelSelector: + matchLabels: + {{- include "loki.ingesterSelectorLabels" . | nindent 6 }} + # -- Affinity for ingester pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.ingesterSelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.ingesterSelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Pod Disruption Budget maxUnavailable + maxUnavailable: null + # -- Max Surge for ingester pods + maxSurge: 0 + # -- Node selector for ingester pods + nodeSelector: {} + # -- Tolerations for ingester pods + tolerations: [] + # -- readiness probe settings for ingester pods. If empty, use `loki.readinessProbe` + readinessProbe: {} + # -- liveness probe settings for ingester pods. If empty use `loki.livenessProbe` + livenessProbe: {} + persistence: + # -- Enable creating PVCs which is required when using boltdb-shipper + enabled: false + # -- Use emptyDir with ramdisk for storage. **Please note that all data in ingester will be lost on pod restart** + inMemory: false + # -- List of the ingester PVCs + # @notationType -- list + claims: + - name: data + size: 10Gi + # -- Storage class to be used. + # If defined, storageClassName: . + # If set to "-", storageClassName: "", which disables dynamic provisioning. + # If empty or set to null, no storageClassName spec is + # set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). + storageClass: null + # - name: wal + # size: 150Gi + # -- Enable StatefulSetAutoDeletePVC feature + enableStatefulSetAutoDeletePVC: false + whenDeleted: Retain + whenScaled: Retain + # -- Adds the appProtocol field to the ingester service. This allows ingester to work with istio protocol selection. + appProtocol: + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + grpc: "" + +# Configuration for the distributor +distributor: + # -- Number of replicas for the distributor + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + autoscaling: + # -- Enable autoscaling for the distributor + enabled: false + # -- Minimum autoscaling replicas for the distributor + minReplicas: 1 + # -- Maximum autoscaling replicas for the distributor + maxReplicas: 3 + # -- Target CPU utilisation percentage for the distributor + targetCPUUtilizationPercentage: 60 + # -- Target memory utilisation percentage for the distributor + targetMemoryUtilizationPercentage: null + # -- Allows one to define custom metrics using the HPA/v2 schema (for example, Pods, Object or External metrics) + customMetrics: [] + # - type: Pods + # pods: + # metric: + # name: loki_lines_total + # target: + # type: AverageValue + # averageValue: 10k + behavior: + # -- Enable autoscaling behaviours + enabled: false + # -- define scale down policies, must conform to HPAScalingRules + scaleDown: {} + # -- define scale up policies, must conform to HPAScalingRules + scaleUp: {} + image: + # -- The Docker registry for the distributor image. Overrides `loki.image.registry` + registry: null + # -- Docker image repository for the distributor image. Overrides `loki.image.repository` + repository: null + # -- Docker image tag for the distributor image. Overrides `loki.image.tag` + tag: null + # -- Command to execute instead of defined in Docker image + command: null + # -- The name of the PriorityClass for distributor pods + priorityClassName: null + # -- Labels for distributor pods + podLabels: {} + # -- Annotations for distributor pods + podAnnotations: {} + # -- Labels for distributor service + serviceLabels: {} + # -- Additional CLI args for the distributor + extraArgs: [] + # -- Environment variables to add to the distributor pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the distributor pods + extraEnvFrom: [] + # -- Volume mounts to add to the distributor pods + extraVolumeMounts: [] + # -- Volumes to add to the distributor pods + extraVolumes: [] + # -- Resource requests and limits for the distributor + resources: {} + # -- Containers to add to the distributor pods + extraContainers: [] + # -- Grace period to allow the distributor to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- Affinity for distributor pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.distributorSelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.distributorSelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Pod Disruption Budget maxUnavailable + maxUnavailable: null + # -- Max Surge for distributor pods + maxSurge: 0 + # -- Node selector for distributor pods + nodeSelector: {} + # -- Tolerations for distributor pods + tolerations: [] + # -- Adds the appProtocol field to the distributor service. This allows distributor to work with istio protocol selection. + appProtocol: + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + grpc: "" + +# Configuration for the querier +querier: + # -- Number of replicas for the querier + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + autoscaling: + # -- Enable autoscaling for the querier, this is only used if `indexGateway.enabled: true` + enabled: false + # -- Minimum autoscaling replicas for the querier + minReplicas: 1 + # -- Maximum autoscaling replicas for the querier + maxReplicas: 3 + # -- Target CPU utilisation percentage for the querier + targetCPUUtilizationPercentage: 60 + # -- Target memory utilisation percentage for the querier + targetMemoryUtilizationPercentage: null + # -- Allows one to define custom metrics using the HPA/v2 schema (for example, Pods, Object or External metrics) + customMetrics: [] + # - type: External + # external: + # metric: + # name: loki_inflight_queries + # target: + # type: AverageValue + # averageValue: 12 + behavior: + # -- Enable autoscaling behaviours + enabled: false + # -- define scale down policies, must conform to HPAScalingRules + scaleDown: {} + # -- define scale up policies, must conform to HPAScalingRules + scaleUp: {} + image: + # -- The Docker registry for the querier image. Overrides `loki.image.registry` + registry: null + # -- Docker image repository for the querier image. Overrides `loki.image.repository` + repository: null + # -- Docker image tag for the querier image. Overrides `loki.image.tag` + tag: null + # -- Command to execute instead of defined in Docker image + command: null + # -- The name of the PriorityClass for querier pods + priorityClassName: null + # -- Labels for querier pods + podLabels: {} + # -- Annotations for querier pods + podAnnotations: {} + # -- Labels for querier service + serviceLabels: {} + # -- Additional CLI args for the querier + extraArgs: [] + # -- Environment variables to add to the querier pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the querier pods + extraEnvFrom: [] + # -- Volume mounts to add to the querier pods + extraVolumeMounts: [] + # -- Volumes to add to the querier pods + extraVolumes: [] + # -- Resource requests and limits for the querier + resources: {} + # -- Containers to add to the querier pods + extraContainers: [] + # -- Init containers to add to the querier pods + initContainers: [] + # -- Grace period to allow the querier to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- topologySpread for querier pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Defaults to allow skew no more then 1 node per AZ + topologySpreadConstraints: | + - maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + labelSelector: + matchLabels: + {{- include "loki.querierSelectorLabels" . | nindent 6 }} + # -- Affinity for querier pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.querierSelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.querierSelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Pod Disruption Budget maxUnavailable + maxUnavailable: null + # -- Max Surge for querier pods + maxSurge: 0 + # -- Node selector for querier pods + nodeSelector: {} + # -- Tolerations for querier pods + tolerations: [] + # -- DNSConfig for querier pods + dnsConfig: {} + persistence: + # -- Enable creating PVCs for the querier cache + enabled: false + # -- Size of persistent disk + size: 10Gi + # -- Storage class to be used. + # If defined, storageClassName: . + # If set to "-", storageClassName: "", which disables dynamic provisioning. + # If empty or set to null, no storageClassName spec is + # set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). + storageClass: null + # -- Annotations for querier PVCs + annotations: {} + # -- Adds the appProtocol field to the querier service. This allows querier to work with istio protocol selection. + appProtocol: + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + grpc: "" + +# Configuration for the query-frontend +queryFrontend: + # -- Number of replicas for the query-frontend + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + autoscaling: + # -- Enable autoscaling for the query-frontend + enabled: false + # -- Minimum autoscaling replicas for the query-frontend + minReplicas: 1 + # -- Maximum autoscaling replicas for the query-frontend + maxReplicas: 3 + # -- Target CPU utilisation percentage for the query-frontend + targetCPUUtilizationPercentage: 60 + # -- Target memory utilisation percentage for the query-frontend + targetMemoryUtilizationPercentage: null + # -- Allows one to define custom metrics using the HPA/v2 schema (for example, Pods, Object or External metrics) + customMetrics: [] + # - type: Pods + # pods: + # metric: + # name: loki_query_rate + # target: + # type: AverageValue + # averageValue: 100 + behavior: + # -- Enable autoscaling behaviours + enabled: false + # -- define scale down policies, must conform to HPAScalingRules + scaleDown: {} + # -- define scale up policies, must conform to HPAScalingRules + scaleUp: {} + image: + # -- The Docker registry for the query-frontend image. Overrides `loki.image.registry` + registry: null + # -- Docker image repository for the query-frontend image. Overrides `loki.image.repository` + repository: null + # -- Docker image tag for the query-frontend image. Overrides `loki.image.tag` + tag: null + # -- Command to execute instead of defined in Docker image + command: null + # -- The name of the PriorityClass for query-frontend pods + priorityClassName: null + # -- Labels for query-frontend pods + podLabels: {} + # -- Annotations for query-frontend pods + podAnnotations: {} + # -- Labels for query-frontend service + serviceLabels: {} + # -- Additional CLI args for the query-frontend + extraArgs: [] + # -- Environment variables to add to the query-frontend pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the query-frontend pods + extraEnvFrom: [] + # -- Volume mounts to add to the query-frontend pods + extraVolumeMounts: [] + # -- Volumes to add to the query-frontend pods + extraVolumes: [] + # -- Resource requests and limits for the query-frontend + resources: {} + # -- Containers to add to the query-frontend pods + extraContainers: [] + # -- Grace period to allow the query-frontend to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- Affinity for query-frontend pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.queryFrontendSelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.queryFrontendSelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Pod Disruption Budget maxUnavailable + maxUnavailable: null + # -- Node selector for query-frontend pods + nodeSelector: {} + # -- Tolerations for query-frontend pods + tolerations: [] + # -- Adds the appProtocol field to the queryFrontend service. This allows queryFrontend to work with istio protocol selection. + appProtocol: + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + grpc: "" + +# Configuration for the query-scheduler +queryScheduler: + # -- Specifies whether the query-scheduler should be decoupled from the query-frontend + enabled: false + # -- Number of replicas for the query-scheduler. + # It should be lower than `-querier.max-concurrent` to avoid generating back-pressure in queriers; + # it's also recommended that this value evenly divides the latter + replicas: 2 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + image: + # -- The Docker registry for the query-scheduler image. Overrides `loki.image.registry` + registry: null + # -- Docker image repository for the query-scheduler image. Overrides `loki.image.repository` + repository: null + # -- Docker image tag for the query-scheduler image. Overrides `loki.image.tag` + tag: null + # -- The name of the PriorityClass for query-scheduler pods + priorityClassName: null + # -- Labels for query-scheduler pods + podLabels: {} + # -- Annotations for query-scheduler pods + podAnnotations: {} + # -- Labels for query-scheduler service + serviceLabels: {} + # -- Additional CLI args for the query-scheduler + extraArgs: [] + # -- Environment variables to add to the query-scheduler pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the query-scheduler pods + extraEnvFrom: [] + # -- Volume mounts to add to the query-scheduler pods + extraVolumeMounts: [] + # -- Volumes to add to the query-scheduler pods + extraVolumes: [] + # -- Resource requests and limits for the query-scheduler + resources: {} + # -- Containers to add to the query-scheduler pods + extraContainers: [] + # -- Grace period to allow the query-scheduler to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- Affinity for query-scheduler pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.querySchedulerSelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.querySchedulerSelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Pod Disruption Budget maxUnavailable + maxUnavailable: 1 + # -- Node selector for query-scheduler pods + nodeSelector: {} + # -- Tolerations for query-scheduler pods + tolerations: [] + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + appProtocol: + grpc: "" + +# Configuration for the table-manager +tableManager: + # -- Specifies whether the table-manager should be enabled + enabled: false + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + image: + # -- The Docker registry for the table-manager image. Overrides `loki.image.registry` + registry: null + # -- Docker image repository for the table-manager image. Overrides `loki.image.repository` + repository: null + # -- Docker image tag for the table-manager image. Overrides `loki.image.tag` + tag: null + # -- Command to execute instead of defined in Docker image + command: null + # -- The name of the PriorityClass for table-manager pods + priorityClassName: null + # -- Labels for table-manager pods + podLabels: {} + # -- Annotations for table-manager pods + podAnnotations: {} + # -- Labels for table-manager service + serviceLabels: {} + # -- Additional CLI args for the table-manager + extraArgs: [] + # -- Environment variables to add to the table-manager pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the table-manager pods + extraEnvFrom: [] + # -- Volume mounts to add to the table-manager pods + extraVolumeMounts: [] + # -- Volumes to add to the table-manager pods + extraVolumes: [] + # -- Resource requests and limits for the table-manager + resources: {} + # -- Containers to add to the table-manager pods + extraContainers: [] + # -- Grace period to allow the table-manager to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- Affinity for table-manager pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.tableManagerSelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.tableManagerSelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Node selector for table-manager pods + nodeSelector: {} + # -- Tolerations for table-manager pods + tolerations: [] + +# Use either this ingress or the gateway, but not both at once. +# If you enable this, make sure to disable the gateway. +# You'll need to supply authn configuration for your ingress controller. +ingress: + enabled: false +# ingressClassName: nginx + annotations: {} +# nginx.ingress.kubernetes.io/auth-type: basic +# nginx.ingress.kubernetes.io/auth-secret: loki-distributed-basic-auth +# nginx.ingress.kubernetes.io/auth-secret-type: auth-map +# nginx.ingress.kubernetes.io/configuration-snippet: | +# proxy_set_header X-Scope-OrgID $remote_user; + paths: + distributor: + - /api/prom/push + - /loki/api/v1/push + querier: + - /api/prom/tail + - /loki/api/v1/tail + query-frontend: + - /loki/api + ruler: + - /api/prom/rules + - /loki/api/v1/rules + - /prometheus/api/v1/rules + - /prometheus/api/v1/alerts + hosts: + - loki.example.com + # tls: + # - secretName: loki-distributed-tls + # hosts: + # - loki.example.com + +# Configuration for the gateway +gateway: + # -- Specifies whether the gateway should be enabled + enabled: true + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + # -- Number of replicas for the gateway + replicas: 1 + # -- Enable logging of 2xx and 3xx HTTP requests + verboseLogging: true + autoscaling: + # -- Enable autoscaling for the gateway + enabled: false + # -- Minimum autoscaling replicas for the gateway + minReplicas: 1 + # -- Maximum autoscaling replicas for the gateway + maxReplicas: 3 + # -- Target CPU utilisation percentage for the gateway + targetCPUUtilizationPercentage: 60 + # -- Target memory utilisation percentage for the gateway + targetMemoryUtilizationPercentage: null + # -- Allows one to define custom metrics using the HPA/v2 schema (for example, Resource, Object or External metrics) + customMetrics: [] + # - type: Object + # object: + # metric: + # name: requests-per-second + # describedObject: + # apiVersion: networking.k8s.io/v1 + # kind: Ingress + # name: main-route + # target: + # type: Values + # averageValue: 10k + behavior: + # -- Enable autoscaling behaviours + enabled: false + # -- define scale down policies, must conform to HPAScalingRules + scaleDown: {} + # -- define scale up policies, must conform to HPAScalingRules + scaleUp: {} + # -- See `kubectl explain deployment.spec.strategy` for more, + # ref: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy + deploymentStrategy: + type: RollingUpdate + image: + # -- The Docker registry for the gateway image + registry: docker.io + # -- The gateway image repository + repository: nginxinc/nginx-unprivileged + # -- The gateway image tag + tag: 1.20.2-alpine + # -- The gateway image pull policy + pullPolicy: IfNotPresent + # -- The name of the PriorityClass for gateway pods + priorityClassName: null + # -- Labels for gateway pods + podLabels: {} + # -- Annotations for gateway pods + podAnnotations: {} + # -- Additional CLI args for the gateway + extraArgs: [] + # -- Environment variables to add to the gateway pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the gateway pods + extraEnvFrom: [] + # -- Volumes to add to the gateway pods + extraVolumes: [] + # -- Volume mounts to add to the gateway pods + extraVolumeMounts: [] + # -- The SecurityContext for gateway containers + podSecurityContext: + fsGroup: 101 + runAsGroup: 101 + runAsNonRoot: true + runAsUser: 101 + # -- The SecurityContext for gateway containers + containerSecurityContext: + readOnlyRootFilesystem: true + capabilities: + drop: + - ALL + allowPrivilegeEscalation: false + # -- Resource requests and limits for the gateway + resources: {} + # -- Containers to add to the gateway pods + extraContainers: [] + # -- Grace period to allow the gateway to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- Affinity for gateway pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.gatewaySelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.gatewaySelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Pod Disruption Budget maxUnavailable + maxUnavailable: null + # -- Node selector for gateway pods + nodeSelector: {} + # -- Tolerations for gateway pods + tolerations: [] + # -- DNSConfig for gateway pods + dnsConfig: {} + # Gateway service configuration + service: + # -- Port of the gateway service + port: 80 + # -- Type of the gateway service + type: ClusterIP + # -- ClusterIP of the gateway service + clusterIP: null + # -- Node port if service type is NodePort + nodePort: null + # -- Load balancer IPO address if service type is LoadBalancer + loadBalancerIP: null + # -- Load balancer allow traffic from CIDR list if service type is LoadBalancer + loadBalancerSourceRanges: [] + # -- Set appProtocol for the service + appProtocol: null + # -- Annotations for the gateway service + annotations: {} + # -- Labels for gateway service + labels: {} + # Gateway ingress configuration + ingress: + # -- Specifies whether an ingress for the gateway should be created + enabled: false + # -- Ingress Class Name. MAY be required for Kubernetes versions >= 1.18 + # For example: `ingressClassName: nginx` + ingressClassName: '' + + # -- Annotations for the gateway ingress + annotations: {} + # -- Hosts configuration for the gateway ingress + hosts: + - host: gateway.loki.example.com + paths: + - path: / + # -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers + # pathType: Prefix + # -- TLS configuration for the gateway ingress + tls: [] + # tls: + # - secretName: loki-gateway-tls + # hosts: + # - gateway.loki.example.com + + # Basic auth configuration + basicAuth: + # -- Enables basic authentication for the gateway + enabled: false + # -- The basic auth username for the gateway + username: null + # -- The basic auth password for the gateway + password: null + # -- Uses the specified username and password to compute a htpasswd using Sprig's `htpasswd` function. + # The value is templated using `tpl`. Override this to use a custom htpasswd, e.g. in case the default causes + # high CPU load. + # @default -- See values.yaml + htpasswd: >- + {{ htpasswd (required "'gateway.basicAuth.username' is required" .Values.gateway.basicAuth.username) (required "'gateway.basicAuth.password' is required" .Values.gateway.basicAuth.password) }} + # -- Existing basic auth secret to use. Must contain '.htpasswd' + existingSecret: null + # Configures the readiness probe for the gateway + readinessProbe: + httpGet: + path: / + port: http + initialDelaySeconds: 15 + timeoutSeconds: 1 + livenessProbe: + httpGet: + path: / + port: http + initialDelaySeconds: 30 + nginxConfig: + # -- NGINX log format + # @default -- See values.yaml + logFormat: |- + main '$remote_addr - $remote_user [$time_local] $status ' + '"$request" $body_bytes_sent "$http_referer" ' + '"$http_user_agent" "$http_x_forwarded_for"'; + # -- Allows appending custom configuration to the server block + serverSnippet: "" + # -- Allows appending custom configuration to the http block + httpSnippet: "" + # -- Allows overriding the DNS resolver address nginx will use. + resolver: "" + # -- Config file contents for Nginx. Passed through the `tpl` function to allow templating + # @default -- See values.yaml + file: | + worker_processes 5; ## Default: 1 + error_log /dev/stderr; + pid /tmp/nginx.pid; + worker_rlimit_nofile 8192; + + events { + worker_connections 4096; ## Default: 1024 + } + + http { + client_body_temp_path /tmp/client_temp; + proxy_temp_path /tmp/proxy_temp_path; + fastcgi_temp_path /tmp/fastcgi_temp; + uwsgi_temp_path /tmp/uwsgi_temp; + scgi_temp_path /tmp/scgi_temp; + + proxy_http_version 1.1; + + default_type application/octet-stream; + log_format {{ .Values.gateway.nginxConfig.logFormat }} + + {{- if .Values.gateway.verboseLogging }} + access_log /dev/stderr main; + {{- else }} + + map $status $loggable { + ~^[23] 0; + default 1; + } + access_log /dev/stderr main if=$loggable; + {{- end }} + + sendfile on; + tcp_nopush on; + {{- if .Values.gateway.nginxConfig.resolver }} + resolver {{ .Values.gateway.nginxConfig.resolver }}; + {{- else }} + resolver {{ .Values.global.dnsService }}.{{ .Values.global.dnsNamespace }}.svc.{{ .Values.global.clusterDomain }}; + {{- end }} + + {{- with .Values.gateway.nginxConfig.httpSnippet }} + {{ . | nindent 2 }} + {{- end }} + + server { + listen 8080; + + {{- if .Values.gateway.basicAuth.enabled }} + auth_basic "Loki"; + auth_basic_user_file /etc/nginx/secrets/.htpasswd; + {{- end }} + + location = / { + return 200 'OK'; + auth_basic off; + access_log off; + } + + location = /api/prom/push { + set $api_prom_push_backend http://{{ include "loki.distributorFullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass $api_prom_push_backend:3100$request_uri; + proxy_http_version 1.1; + } + + location = /api/prom/tail { + set $api_prom_tail_backend http://{{ include "loki.querierFullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass $api_prom_tail_backend:3100$request_uri; + proxy_set_header Upgrade $http_upgrade; + proxy_set_header Connection "upgrade"; + proxy_http_version 1.1; + } + + # Ruler + location ~ /prometheus/api/v1/alerts.* { + proxy_pass http://{{ include "loki.rulerFullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:3100$request_uri; + } + location ~ /prometheus/api/v1/rules.* { + proxy_pass http://{{ include "loki.rulerFullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:3100$request_uri; + } + location ~ /api/prom/rules.* { + proxy_pass http://{{ include "loki.rulerFullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:3100$request_uri; + } + location ~ /api/prom/alerts.* { + proxy_pass http://{{ include "loki.rulerFullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:3100$request_uri; + } + + location ~ /api/prom/.* { + set $api_prom_backend http://{{ include "loki.queryFrontendFullname" . }}-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass $api_prom_backend:3100$request_uri; + proxy_http_version 1.1; + } + + location = /loki/api/v1/push { + set $loki_api_v1_push_backend http://{{ include "loki.distributorFullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass $loki_api_v1_push_backend:3100$request_uri; + proxy_http_version 1.1; + } + + location = /loki/api/v1/tail { + set $loki_api_v1_tail_backend http://{{ include "loki.querierFullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass $loki_api_v1_tail_backend:3100$request_uri; + proxy_set_header Upgrade $http_upgrade; + proxy_set_header Connection "upgrade"; + proxy_http_version 1.1; + } + + location ~ /loki/api/.* { + set $loki_api_backend http://{{ include "loki.queryFrontendFullname" . }}-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass $loki_api_backend:3100$request_uri; + proxy_http_version 1.1; + } + + {{- with .Values.gateway.nginxConfig.serverSnippet }} + {{ . | nindent 4 }} + {{- end }} + } + } + +# Configuration for the compactor +compactor: + # -- Kind of deployment [StatefulSet/Deployment] + kind: StatefulSet + # -- Number of replicas for the compactor + replicas: 1 + # -- Specifies whether compactor should be enabled + enabled: false + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + image: + # -- The Docker registry for the compactor image. Overrides `loki.image.registry` + registry: null + # -- Docker image repository for the compactor image. Overrides `loki.image.repository` + repository: null + # -- Docker image tag for the compactor image. Overrides `loki.image.tag` + tag: null + # -- Command to execute instead of defined in Docker image + command: null + # -- The name of the PriorityClass for compactor pods + priorityClassName: null + # -- Labels for compactor pods + podLabels: {} + # -- Annotations for compactor pods + podAnnotations: {} + # -- Affinity for compactor pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.compactorSelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.compactorSelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Labels for compactor service + serviceLabels: {} + # -- Additional CLI args for the compactor + extraArgs: [] + # -- Environment variables to add to the compactor pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the compactor pods + extraEnvFrom: [] + # -- Volume mounts to add to the compactor pods + extraVolumeMounts: [] + # -- Volumes to add to the compactor pods + extraVolumes: [] + # -- readiness probe settings for ingester pods. If empty, use `loki.readinessProbe` + readinessProbe: {} + # -- liveness probe settings for ingester pods. If empty use `loki.livenessProbe` + livenessProbe: {} + # -- Resource requests and limits for the compactor + resources: {} + # -- Containers to add to the compactor pods + extraContainers: [] + # -- Init containers to add to the compactor pods + initContainers: [] + # -- Grace period to allow the compactor to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- Node selector for compactor pods + nodeSelector: {} + # -- Tolerations for compactor pods + tolerations: [] + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + appProtocol: + grpc: "" + persistence: + # -- Enable creating PVCs for the compactor + enabled: false + # -- Size of persistent disk + size: 10Gi + # -- Storage class to be used. + # If defined, storageClassName: . + # If set to "-", storageClassName: "", which disables dynamic provisioning. + # If empty or set to null, no storageClassName spec is + # set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). + storageClass: null + # -- Annotations for compactor PVCs + annotations: {} + # -- List of the compactor PVCs + # @notationType -- list + claims: + - name: data + size: 10Gi + # -- Storage class to be used. + # If defined, storageClassName: . + # If set to "-", storageClassName: "", which disables dynamic provisioning. + # If empty or set to null, no storageClassName spec is + # set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). + storageClass: null + # - name: wal + # size: 150Gi + # -- Enable StatefulSetAutoDeletePVC feature + enableStatefulSetAutoDeletePVC: false + whenDeleted: Retain + whenScaled: Retain + + serviceAccount: + create: false + # -- The name of the ServiceAccount to use for the compactor. + # If not set and create is true, a name is generated by appending + # "-compactor" to the common ServiceAccount. + name: null + # -- Image pull secrets for the compactor service account + imagePullSecrets: [] + # -- Annotations for the compactor service account + annotations: {} + # -- Set this toggle to false to opt out of automounting API credentials for the service account + automountServiceAccountToken: true + +# Configuration for the ruler +ruler: + # -- Specifies whether the ruler should be enabled + enabled: false + # -- Kind of deployment [StatefulSet/Deployment] + kind: Deployment + # -- Number of replicas for the ruler + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + image: + # -- The Docker registry for the ruler image. Overrides `loki.image.registry` + registry: null + # -- Docker image repository for the ruler image. Overrides `loki.image.repository` + repository: null + # -- Docker image tag for the ruler image. Overrides `loki.image.tag` + tag: null + # -- Command to execute instead of defined in Docker image + command: null + # -- The name of the PriorityClass for ruler pods + priorityClassName: null + # -- Labels for compactor pods + podLabels: {} + # -- Annotations for ruler pods + podAnnotations: {} + # -- Labels for ruler service + serviceLabels: {} + # -- Additional CLI args for the ruler + extraArgs: [] + # -- Environment variables to add to the ruler pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the ruler pods + extraEnvFrom: [] + # -- Volume mounts to add to the ruler pods + extraVolumeMounts: [] + # -- Volumes to add to the ruler pods + extraVolumes: [] + # -- Resource requests and limits for the ruler + resources: {} + # -- Containers to add to the ruler pods + extraContainers: [] + # -- Init containers to add to the ruler pods + initContainers: [] + # -- Grace period to allow the ruler to shutdown before it is killed + terminationGracePeriodSeconds: 300 + # -- Affinity for ruler pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.rulerSelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.rulerSelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Pod Disruption Budget maxUnavailable + maxUnavailable: null + # -- Node selector for ruler pods + nodeSelector: {} + # -- Tolerations for ruler pods + tolerations: [] + # -- DNSConfig for ruler pods + dnsConfig: {} + persistence: + # -- Enable creating PVCs which is required when using recording rules + enabled: false + # -- Size of persistent disk + size: 10Gi + # -- Storage class to be used. + # If defined, storageClassName: . + # If set to "-", storageClassName: "", which disables dynamic provisioning. + # If empty or set to null, no storageClassName spec is + # set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). + storageClass: null + # -- Annotations for ruler PVCs + annotations: {} + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + appProtocol: + grpc: "" + # -- Directories containing rules files + directories: {} + # tenant_foo: + # rules1.txt: | + # groups: + # - name: should_fire + # rules: + # - alert: HighPercentageError + # expr: | + # sum(rate({app="foo", env="production"} |= "error" [5m])) by (job) + # / + # sum(rate({app="foo", env="production"}[5m])) by (job) + # > 0.05 + # for: 10m + # labels: + # severity: warning + # annotations: + # summary: High error rate + # - name: credentials_leak + # rules: + # - alert: http-credentials-leaked + # annotations: + # message: "{{ $labels.job }} is leaking http basic auth credentials." + # expr: 'sum by (cluster, job, pod) (count_over_time({namespace="prod"} |~ "http(s?)://(\\w+):(\\w+)@" [5m]) > 0)' + # for: 10m + # labels: + # severity: critical + # rules2.txt: | + # groups: + # - name: example + # rules: + # - alert: HighThroughputLogStreams + # expr: sum by(container) (rate({job=~"loki-dev/.*"}[1m])) > 1000 + # for: 2m + # tenant_bar: + # rules1.txt: | + # groups: + # - name: should_fire + # rules: + # - alert: HighPercentageError + # expr: | + # sum(rate({app="foo", env="production"} |= "error" [5m])) by (job) + # / + # sum(rate({app="foo", env="production"}[5m])) by (job) + # > 0.05 + # for: 10m + # labels: + # severity: warning + # annotations: + # summary: High error rate + # - name: credentials_leak + # rules: + # - alert: http-credentials-leaked + # annotations: + # message: "{{ $labels.job }} is leaking http basic auth credentials." + # expr: 'sum by (cluster, job, pod) (count_over_time({namespace="prod"} |~ "http(s?)://(\\w+):(\\w+)@" [5m]) > 0)' + # for: 10m + # labels: + # severity: critical + # rules2.txt: | + # groups: + # - name: example + # rules: + # - alert: HighThroughputLogStreams + # expr: sum by(container) (rate({job=~"loki-dev/.*"}[1m])) > 1000 + # for: 2m + +# Configuration for the index-gateway +indexGateway: + # -- Specifies whether the index-gateway should be enabled + enabled: false + # -- Number of replicas for the index-gateway + replicas: 1 + # -- Whether the index gateway should join the memberlist hashring + joinMemberlist: true + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + image: + # -- The Docker registry for the index-gateway image. Overrides `loki.image.registry` + registry: null + # -- Docker image repository for the index-gateway image. Overrides `loki.image.repository` + repository: null + # -- Docker image tag for the index-gateway image. Overrides `loki.image.tag` + tag: null + # -- The name of the PriorityClass for index-gateway pods + priorityClassName: null + # -- Labels for index-gateway pods + podLabels: {} + # -- Annotations for index-gateway pods + podAnnotations: {} + # -- Labels for index-gateway service + serviceLabels: {} + # -- Additional CLI args for the index-gateway + extraArgs: [] + # -- Environment variables to add to the index-gateway pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the index-gateway pods + extraEnvFrom: [] + # -- Volume mounts to add to the index-gateway pods + extraVolumeMounts: [] + # -- Volumes to add to the index-gateway pods + extraVolumes: [] + # -- Resource requests and limits for the index-gateway + resources: {} + # -- Containers to add to the index-gateway pods + extraContainers: [] + # -- Init containers to add to the index-gateway pods + initContainers: [] + # -- Grace period to allow the index-gateway to shutdown before it is killed. + terminationGracePeriodSeconds: 300 + # -- Affinity for index-gateway pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.indexGatewaySelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.indexGatewaySelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Pod Disruption Budget maxUnavailable + maxUnavailable: null + # -- Node selector for index-gateway pods + nodeSelector: {} + # -- Tolerations for index-gateway pods + tolerations: [] + persistence: + # -- Enable creating PVCs which is required when using boltdb-shipper + enabled: false + # -- Use emptyDir with ramdisk for storage. **Please note that all data in indexGateway will be lost on pod restart** + inMemory: false + # -- Size of persistent or memory disk + size: 10Gi + # -- Storage class to be used. + # If defined, storageClassName: . + # If set to "-", storageClassName: "", which disables dynamic provisioning. + # If empty or set to null, no storageClassName spec is + # set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). + storageClass: null + # -- Annotations for index gateway PVCs + annotations: {} + # -- Enable StatefulSetAutoDeletePVC feature + enableStatefulSetAutoDeletePVC: false + whenDeleted: Retain + whenScaled: Retain + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + appProtocol: + grpc: "" + +memcached: + readinessProbe: + tcpSocket: + port: http + initialDelaySeconds: 5 + timeoutSeconds: 1 + livenessProbe: + tcpSocket: + port: http + initialDelaySeconds: 10 + image: + # -- The Docker registry for the memcached + registry: docker.io + # -- Memcached Docker image repository + repository: memcached + # -- Memcached Docker image tag + tag: 1.6.21-alpine + # -- Memcached Docker image pull policy + pullPolicy: IfNotPresent + # -- Labels for memcached pods + podLabels: {} + # -- The SecurityContext for memcached pods + podSecurityContext: + fsGroup: 11211 + runAsGroup: 11211 + runAsNonRoot: true + runAsUser: 11211 + # -- The SecurityContext for memcached containers + containerSecurityContext: + readOnlyRootFilesystem: true + capabilities: + drop: + - ALL + allowPrivilegeEscalation: false + # -- Common annotations for all memcached services + serviceAnnotations: {} + # -- Adds the appProtocol field to the memcached services. This allows memcached to work with istio protocol selection. Ex: "http" or "tcp" + appProtocol: "" + +memcachedExporter: + # -- Specifies whether the Memcached Exporter should be enabled + enabled: false + image: + # -- The Docker registry for the Memcached Exporter + registry: docker.io + # -- Memcached Exporter Docker image repository + repository: prom/memcached-exporter + # -- Memcached Exporter Docker image tag + tag: v0.13.0 + # -- Memcached Exporter Docker image pull policy + pullPolicy: IfNotPresent + # -- Labels for memcached-exporter pods + podLabels: {} + # -- Memcached Exporter resource requests and limits + resources: {} + # -- The SecurityContext for memcachedExporter containers + containerSecurityContext: + readOnlyRootFilesystem: true + capabilities: + drop: + - ALL + allowPrivilegeEscalation: false + +memcachedChunks: + # -- Specifies whether the Memcached chunks cache should be enabled + enabled: false + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + # -- Number of replicas for memcached-chunks + replicas: 1 + # -- The name of the PriorityClass for memcached-chunks pods + priorityClassName: null + # -- Labels for memcached-chunks pods + podLabels: {} + # -- Annotations for memcached-chunks pods + podAnnotations: {} + # -- Labels for memcached-chunks service + serviceLabels: {} + # -- Additional CLI args for memcached-chunks + extraArgs: + - -I 32m + # -- Environment variables to add to memcached-chunks pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to memcached-chunks pods + extraEnvFrom: [] + # -- Resource requests and limits for memcached-chunks + resources: {} + # -- Containers to add to the memcached-chunks pods + extraContainers: [] + # -- Grace period to allow memcached-chunks to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- Affinity for memcached-chunks pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.memcachedChunksSelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.memcachedChunksSelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Pod Disruption Budget maxUnavailable + maxUnavailable: null + # -- Node selector for memcached-chunks pods + nodeSelector: {} + # -- Tolerations for memcached-chunks pods + tolerations: [] + persistence: + # -- Enable creating PVCs which will persist cached data through restarts + enabled: false + # -- Size of persistent or memory disk + size: 10Gi + # -- Storage class to be used. + # If defined, storageClassName: . + # If set to "-", storageClassName: "", which disables dynamic provisioning. + # If empty or set to null, no storageClassName spec is + # set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). + storageClass: null + # -- List of additional PVCs to be created for the memcached-chunks statefulset + volumeClaimTemplates: [] + # -- List of additional volumes to be mounted for the memcached-chunks statefulset + extraVolumeMounts: [] + +memcachedFrontend: + # -- Specifies whether the Memcached frontend cache should be enabled + enabled: false + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + # -- Number of replicas for memcached-frontend + replicas: 1 + # -- The name of the PriorityClass for memcached-frontend pods + priorityClassName: null + # -- Labels for memcached-frontend pods + podLabels: {} + # -- Annotations for memcached-frontend pods + podAnnotations: {} + # -- Labels for memcached-frontend service + serviceLabels: {} + # -- Additional CLI args for memcached-frontend + extraArgs: + - -I 32m + # -- Environment variables to add to memcached-frontend pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to memcached-frontend pods + extraEnvFrom: [] + # -- Resource requests and limits for memcached-frontend + resources: {} + # -- Containers to add to the memcached-frontend pods + extraContainers: [] + # -- Grace period to allow memcached-frontend to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- Affinity for memcached-frontend pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.memcachedFrontendSelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.memcachedFrontendSelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Pod Disruption Budget maxUnavailable + maxUnavailable: 1 + # -- Node selector for memcached-frontend pods + nodeSelector: {} + # -- Tolerations for memcached-frontend pods + tolerations: [] + persistence: + # -- Enable creating PVCs which will persist cached data through restarts + enabled: false + # -- Size of persistent or memory disk + size: 10Gi + # -- Storage class to be used. + # If defined, storageClassName: . + # If set to "-", storageClassName: "", which disables dynamic provisioning. + # If empty or set to null, no storageClassName spec is + # set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). + storageClass: null + +memcachedIndexQueries: + # -- Specifies whether the Memcached index queries cache should be enabled + enabled: false + # -- Number of replicas for memcached-index-queries + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + # -- The name of the PriorityClass for memcached-index-queries pods + priorityClassName: null + # -- Labels for memcached-index-queries pods + podLabels: {} + # -- Annotations for memcached-index-queries pods + podAnnotations: {} + # -- Labels for memcached-index-queries service + serviceLabels: {} + # -- Additional CLI args for memcached-index-queries + extraArgs: + - -I 32m + # -- Environment variables to add to memcached-index-queries pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to memcached-index-queries pods + extraEnvFrom: [] + # -- Resource requests and limits for memcached-index-queries + resources: {} + # -- Containers to add to the memcached-index-queries pods + extraContainers: [] + # -- Grace period to allow memcached-index-queries to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- Affinity for memcached-index-queries pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.memcachedIndexQueriesSelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.memcachedIndexQueriesSelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Pod Disruption Budget maxUnavailable + maxUnavailable: null + # -- Node selector for memcached-index-queries pods + nodeSelector: {} + # -- Tolerations for memcached-index-queries pods + tolerations: [] + persistence: + # -- Enable creating PVCs which will persist cached data through restarts + enabled: false + # -- Size of persistent or memory disk + size: 10Gi + # -- Storage class to be used. + # If defined, storageClassName: . + # If set to "-", storageClassName: "", which disables dynamic provisioning. + # If empty or set to null, no storageClassName spec is + # set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). + storageClass: null + +memcachedIndexWrites: + # -- Specifies whether the Memcached index writes cache should be enabled + enabled: false + # -- Number of replicas for memcached-index-writes + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + # -- The name of the PriorityClass for memcached-index-writes pods + priorityClassName: null + # -- Labels for memcached-index-writes pods + podLabels: {} + # -- Annotations for memcached-index-writes pods + podAnnotations: {} + # -- Labels for memcached-index-writes service + serviceLabels: {} + # -- Additional CLI args for memcached-index-writes + extraArgs: + - -I 32m + # -- Environment variables to add to memcached-index-writes pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to memcached-index-writes pods + extraEnvFrom: [] + # -- Resource requests and limits for memcached-index-writes + resources: {} + # -- Containers to add to the memcached-index-writes pods + extraContainers: [] + # -- Grace period to allow memcached-index-writes to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- Affinity for memcached-index-writes pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "loki.memcachedIndexWritesSelectorLabels" . | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "loki.memcachedIndexWritesSelectorLabels" . | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Pod Disruption Budget maxUnavailable + maxUnavailable: null + # -- Node selector for memcached-index-writes pods + nodeSelector: {} + # -- Tolerations for memcached-index-writes pods + tolerations: [] + persistence: + # -- Enable creating PVCs which will persist cached data through restarts + enabled: false + # -- Size of persistent or memory disk + size: 10Gi + # -- Storage class to be used. + # If defined, storageClassName: . + # If set to "-", storageClassName: "", which disables dynamic provisioning. + # If empty or set to null, no storageClassName spec is + # set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). + storageClass: null + +networkPolicy: + # -- Specifies whether Network Policies should be created + enabled: false + metrics: + # -- Specifies the Pods which are allowed to access the metrics port. + # As this is cross-namespace communication, you also need the namespaceSelector. + podSelector: {} + # -- Specifies the namespaces which are allowed to access the metrics port + namespaceSelector: {} + # -- Specifies specific network CIDRs which are allowed to access the metrics port. + # In case you use namespaceSelector, you also have to specify your kubelet networks here. + # The metrics ports are also used for probes. + cidrs: [] + ingress: + # -- Specifies the Pods which are allowed to access the http port. + # As this is cross-namespace communication, you also need the namespaceSelector. + podSelector: {} + # -- Specifies the namespaces which are allowed to access the http port + namespaceSelector: {} + alertmanager: + # -- Specify the alertmanager port used for alerting + port: 9093 + # -- Specifies the alertmanager Pods. + # As this is cross-namespace communication, you also need the namespaceSelector. + podSelector: {} + # -- Specifies the namespace the alertmanager is running in + namespaceSelector: {} + externalStorage: + # -- Specify the port used for external storage, e.g. AWS S3 + ports: [] + # -- Specifies specific network CIDRs you want to limit access to + cidrs: [] + discovery: + # -- Specify the port used for discovery + port: null + # -- Specifies the Pods labels used for discovery. + # As this is cross-namespace communication, you also need the namespaceSelector. + podSelector: {} + # -- Specifies the namespace the discovery Pods are running in + namespaceSelector: {} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/.helmignore b/observability/lgtm-distributed/charts/mimir-distributed/.helmignore new file mode 100644 index 0000000..e3c5915 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/.helmignore @@ -0,0 +1,7 @@ +.envrc +.gitignore +CHANGELOG.md +ci/ +INTERNAL* +README.md.gotmpl +scripts/ diff --git a/observability/lgtm-distributed/charts/mimir-distributed/Chart.lock b/observability/lgtm-distributed/charts/mimir-distributed/Chart.lock new file mode 100644 index 0000000..79438a8 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/Chart.lock @@ -0,0 +1,12 @@ +dependencies: +- name: minio + repository: https://charts.min.io/ + version: 5.0.14 +- name: grafana-agent-operator + repository: https://grafana.github.io/helm-charts + version: 0.3.19 +- name: rollout-operator + repository: https://grafana.github.io/helm-charts + version: 0.14.0 +digest: sha256:75efdd747392eb84047470b37fb55fc03d99c891cf9cbcf97463278e57e92b39 +generated: "2024-04-02T14:35:36.399712014Z" diff --git a/observability/lgtm-distributed/charts/mimir-distributed/Chart.yaml b/observability/lgtm-distributed/charts/mimir-distributed/Chart.yaml new file mode 100644 index 0000000..c555559 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/Chart.yaml @@ -0,0 +1,24 @@ +apiVersion: v2 +appVersion: 2.12.0 +dependencies: +- alias: minio + condition: minio.enabled + name: minio + repository: https://charts.min.io/ + version: 5.0.14 +- alias: grafana-agent-operator + condition: metaMonitoring.grafanaAgent.installOperator + name: grafana-agent-operator + repository: https://grafana.github.io/helm-charts + version: 0.3.19 +- alias: rollout_operator + condition: rollout_operator.enabled + name: rollout-operator + repository: https://grafana.github.io/helm-charts + version: 0.14.0 +description: Grafana Mimir +home: https://grafana.com/docs/helm-charts/mimir-distributed/latest/ +icon: https://grafana.com/static/img/logos/logo-mimir.svg +kubeVersion: ^1.20.0-0 +name: mimir-distributed +version: 5.3.0 diff --git a/observability/lgtm-distributed/charts/mimir-distributed/README.md b/observability/lgtm-distributed/charts/mimir-distributed/README.md new file mode 100644 index 0000000..e2cf94c --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/README.md @@ -0,0 +1,33 @@ +# Grafana Mimir Helm chart + +Helm chart for deploying [Grafana Mimir](https://grafana.com/docs/mimir/latest/) or optionally [Grafana Enterprise Metrics](https://grafana.com/docs/enterprise-metrics/latest/) to Kubernetes. + +For the full documentation, visit [Grafana mimir-distributed Helm chart documentation](https://grafana.com/docs/helm-charts/mimir-distributed/latest/). + +> **Note:** The documentation version is derived from the Helm chart version which is 5.3.0. + +When upgrading from Helm chart version 4.X, please see [Migrate the Helm chart from version 4.x to 5.0](https://grafana.com/docs/helm-charts/mimir-distributed/latest/migration-guides/migrate-helm-chart-4.x-to-5.0/). +When upgrading from Helm chart version 3.x, please see [Migrate from single zone to zone-aware replication with Helm](https://grafana.com/docs/helm-charts/mimir-distributed/latest/migration-guides/migrate-from-single-zone-with-helm/). +When upgrading from Helm chart version 2.1, please see [Upgrade the Grafana Mimir Helm chart from version 2.1 to 3.0](https://grafana.com/docs/helm-charts/mimir-distributed/latest/migration-guides/migrate-helm-chart-2.x-to-3.0/) as well. + +**IMPORTANT**: Always consult the [CHANGELOG.md](./CHANGELOG.md) file and the deprecation list there to learn about breaking changes that require action during upgrade. + +# mimir-distributed + +![Version: 5.3.0](https://img.shields.io/badge/Version-5.3.0-informational?style=flat-square) ![AppVersion: 2.12.0](https://img.shields.io/badge/AppVersion-2.12.0-informational?style=flat-square) + +Grafana Mimir + +## Requirements + +Kubernetes: `^1.20.0-0` + +| Repository | Name | Version | +|------------|------|---------| +| https://charts.min.io/ | minio(minio) | 5.0.14 | +| https://grafana.github.io/helm-charts | grafana-agent-operator(grafana-agent-operator) | 0.3.19 | +| https://grafana.github.io/helm-charts | rollout_operator(rollout-operator) | 0.14.0 | + +# Contributing and releasing + +Please see the dedicated "[Contributing to Grafana Mimir helm chart](https://github.com/grafana/mimir/tree/main/docs/internal/contributing/contributing-to-helm-chart.md)" page. diff --git a/observability/lgtm-distributed/charts/mimir-distributed/RELEASE.md b/observability/lgtm-distributed/charts/mimir-distributed/RELEASE.md new file mode 100644 index 0000000..4a2dcd5 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/RELEASE.md @@ -0,0 +1,178 @@ +# Releases + +The release processes that follow apply to the Grafana Mimir Helm chart. + +## Schedule + +The release schedule follows the Grafana Mimir and Grafana Enterprise Metrics (GEM) releases so that a new Helm chart release will include both. This usually happens within 2 weeks of the Mimir release. For the Mimir release schedule consult the Mimir [RELEASE.md](../../../../RELEASE.md). + +Security updates of Mimir or GEM will also trigger a Helm chart release. The Helm chart can be released independently of Mimir and GEM, but this is only done if +there's some urgent update needed. + +There are weekly releases with the latest Mimir and GEM build, but they are intended for testing purposes only, not production. Weekly releases are marked with a development version and helm will ignore them unless the `--devel` flag is used on the command line. + +## Before you begin + +One of the following scenarios must apply: + +- Both Mimir and GEM have container images, whose image versions match. The image versions have the same weekly, RC, and final versions. These versions are released to Docker Hub. +- The Mimir and GEM image versions do not match, but there are no breaking changes between them because all of the shared configuration parameters behave the same way. For example, because GEM contains a bugfix, the version of GEM is `2.5.1` and the version of Mimir is `2.5.0`. + +## Release process for a weekly release + +Each weekly release is created automatically, but you need to approve and merge it manually. For an example, see [PR 4600](https://github.com/grafana/mimir/pull/4600). + +[The Chart.yaml file](https://helm.sh/docs/topics/charts/#the-chartyaml-file) requires semantic versioning. + +Weekly releases have the version `x.y.z-weekly.w`, for example `3.1.0-weekly.196`, where `196` represents an incrementing week number. + +> **Note**: You must precede the week number (such as `196`) with a dot (`.`). + +## Release process for a release candidate + +1. Determine the Helm chart version number. + + [The Chart.yaml file](https://helm.sh/docs/topics/charts/#the-chartyaml-file) requires semantic versioning: + + - Release candidates have the version `x.y.z-rc.w`, for example `3.1.0-rc.7`. + + > **Note**: You must precede the release candidate number (such as `7`) with a dot (`.`). + +1. Prepare changelog. + + - Create a PR, whose target is `main`, that updates the [Helm chart changelog](https://github.com/grafana/mimir/blob/main/operations/helm/charts/mimir-distributed/CHANGELOG.md), and move any `## main / unreleased` items under this release’s version. + + > **Note:** If there are any deprecated features that should be removed in this release, then verify that they have been removed, and move their deprecation notices into the section for this release. + + - Have the PR reviewed by a maintainer. + + - Merge the PR upon approval. + +1. Create a release branch. + + - Create (if the branch is not created yet), switch to and push a branch starting from the commit created by the prepare changelog PR and name it `mimir-distributed-release-x.y`. + + For example, `mimir-distributed-release-4.5` for any `4.5.x` release. + + - Push the branch to origin without any commit added. + + - Once the branch is pushed, all changes to `mimir-distributed-release-x.y` branch must be done through PR. + +1. Create a branch from release branch if it hasn't been created yet, to update Mimir/GEM image and helm chart version . + + For example `user/update-mimir-distributed-release-x.y`. + +1. Update versions and links in the `user/update-mimir-distributed-release-x.y` branch. + + - Set the image versions in [values.yaml](https://github.com/grafana/mimir/blob/main/operations/helm/charts/mimir-distributed/values.yaml), as needed: + + - `image.tag` (Mimir) + - `enterprise.image.tag` (GEM) + + > **Note:** Unlike the Mimir image tags, GEM image tags start with `v`. For example, `v2.6.0` instead of `2.6.0`. + + - `smoke_test.image.tag` (Smoke test; usually the same as Mimir) + - `continuous_test.image.tag` (Continuous test; usually the same as Mimir) + + - Set the `version` field, in the [Chart.yaml](https://github.com/grafana/mimir/blob/main/operations/helm/charts/mimir-distributed/Chart.yaml) file, to the desired release candidate version. + + For example, `4.5.0-rc.0`. + + > **Note:** Once this change is merged to `mimir-distributed-x.y` branch, it will trigger the release process GitHub Action. Unless you want to release final release, make sure to append the correct rc version. + + - Set the `appVersion` field, in the [Chart.yaml](https://github.com/grafana/mimir/blob/main/operations/helm/charts/mimir-distributed/Chart.yaml) file, to the version of Mimir that the Helm chart deploys. + + For example, `2.6.0`. + + - Create or update the release notes in `docs/sources/helm-charts/mimir-distributed/release-notes` directory. + + The release notes should refer to the correct Mimir and GEM versions and their specific documentation version. + + > **Note:** This step can be done in a separate PR and shouldn't block release candidate from getting published. + + - Update the Mimir and GEM documentation version parameters in [\_index.md](https://github.com/grafana/mimir/blob/main/docs/sources/helm-charts/mimir-distributed/_index.md) + + The two parameters are `MIMIR_DOCS_VERSION` and `gem_docs_version`. With the exception of the release notes, the Helm chart documentation should refer to the documentation or Mimir and GEM that is actually included in the Helm chart. + + - From the root directory of the repository, run `make doc` to update [README.md](https://github.com/grafana/mimir/blob/main/operations/helm/charts/mimir-distributed/README.md) file. + + - Verify that the links on the [README.md](https://github.com/grafana/mimir/blob/main/operations/helm/charts/mimir-distributed/README.md) are correct. + +1. Open PR to release branch + + - Create PR that contains all the changes we have so far from `user/update-mimir-distributed-release-x.y` branch and make sure that your PR targets the release branch `mimir-distributed-release-x.y`. + + - Have the PR reviewed by a maintainer. + + - Merge the PR upon approval. + +1. Verify that the Helm chart is published + + - Run the following commands: + + `helm repo update && helm search repo grafana/mimir-distributed --devel --version ` + + You might have to wait a few minutes. + + - In a browser, go to [https://grafana.com/docs/helm-charts/mimir-distributed](https://grafana.com/docs/helm-charts/mimir-distributed) and refresh the page. + +1. After the release tag in Git is created, merge the branch back into `main` by following the same procedure as for Mimir releases: [Merging release branch into main](https://github.com/grafana/mimir/blob/main/RELEASE.md#merging-release-branch-into-main). + +1. Backport and additional release candidate. + + - If additional changes need to be added to this release, another release candidate version has to be created. + - Follow [backport process](https://github.com/grafana/mimir/blob/main/RELEASE.md#cherry-picking-changes-into-release-branch) similar with Mimir release to backport changes from main branch. + - Go back to step 5. Update versions and links in the user/update-mimir-distributed-release-x.y branch to update the next release candidate. + +The [release process](https://github.com/grafana/mimir/blob/main/.github/workflows/helm-release.yaml) checks and creates a Git tag formatted as `mimir-distributed-`, for example `mimir-distributed-4.5.0`, on the merge commit created when the PR is merged. To prevent releasing the same version with different content, the release process fails if the tag already exists. The release is published in the [Grafana helm-charts](https://grafana.github.io/helm-charts/) Helm repository. + +## Release process for a final release + +1. Determine the Helm chart version number. + + [The Chart.yaml file](https://helm.sh/docs/topics/charts/#the-chartyaml-file) requires semantic versioning: + + - The final version has the version `x.y.z`, for example `3.1.0`. + - Normally we will proceed the same `x.y.z` version value from the release candidate step. + +1. Create a branch from release branch to update Mimir/GEM image and helm chart version. + + For example `user/update-mimir-distributed-release-x.y-final`. + +1. Optionally finalise release note and update version in the `user/update-mimir-distributed-release-x.y-final` branch. + + - Update and finalize the release notes in `docs/sources/helm-charts/mimir-distributed/release-notes` directory if there has been some changes after release candidate. + + - Set the `version` field, in the [Chart.yaml](https://github.com/grafana/mimir/blob/main/operations/helm/charts/mimir-distributed/Chart.yaml) file, to the desired final release version. + + For example, `4.5.0`. + + > **Note:** Once this change is merged to `mimir-distributed-x.y` branch, it will trigger the release process GitHub Action. + + - There shouldn't be anymore update needed in documentation because that has been done in the release candidate step above. + + - From the root directory of the repository, run `make doc` to update [README.md](https://github.com/grafana/mimir/blob/main/operations/helm/charts/mimir-distributed/README.md) file. + +1. Open PR to release branch + + - Create PR that contains all the changes we have so far from `user/update-mimir-distributed-release-x.y-final` branch and make sure that your PR targets the release branch `mimir-distributed-release-x.y`. + + - Have the PR reviewed by a maintainer. + + - Merge the PR upon approval. + +1. Verify that the Helm chart is published + + - Run the following commands: + + `helm repo update && helm search repo grafana/mimir-distributed --version ` + + You might have to wait a few minutes. + + - In a browser, go to [https://grafana.com/docs/helm-charts/mimir-distributed](https://grafana.com/docs/helm-charts/mimir-distributed) and refresh the page. + +1. After the release tag in Git is created, merge the branch back into `main` by following the same procedure as for Mimir releases: [Merging release branch into main](https://github.com/grafana/mimir/blob/main/RELEASE.md#merging-release-branch-into-main). + +The [release process](https://github.com/grafana/mimir/blob/main/.github/workflows/helm-release.yaml) checks and creates a Git tag formatted as `mimir-distributed-`, for example `mimir-distributed-4.5.0`, on the merge commit created when the PR is merged. To prevent releasing the same version with different content, the release process fails if the tag already exists. The release is published in the [Grafana helm-charts](https://grafana.github.io/helm-charts/) Helm repository. + +When a `mimir-distributed-x.y.z` final version tag is pushed, the Helm chart documentation is [published](https://github.com/grafana/mimir/blob/main/.github/workflows/publish-technical-documentation-release-helm-charts.yml) to [https://grafana.com/docs/helm-charts/mimir-distributed](https://grafana.com/docs/helm-charts/mimir-distributed). diff --git a/observability/lgtm-distributed/charts/mimir-distributed/capped-large.yaml b/observability/lgtm-distributed/charts/mimir-distributed/capped-large.yaml new file mode 100644 index 0000000..a655823 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/capped-large.yaml @@ -0,0 +1,218 @@ +# These values configure the Grafana Mimir or Grafana Enterprise Metrics cluster +# for a more production-ready setup. The setup targets 70% CPU and memory utilization +# so that the cluster has room to grow. The resource requests and limits reflect 100% utilization. +# This is useful when you want to strictly control costs when purchasing GEM through a marketplace subscription for example. +# limits==requests also ensure a "Guaranteed" QoS: https://kubernetes.io/docs/tasks/configure-pod-container/quality-service-pod/. +# Note that setting CPU limits has some known issues: +# https://engineering.indeedblog.com/blog/2019/12/unthrottled-fixing-cpu-limits-in-the-cloud/. +# +# These values are suitable for ingestion of ~10M series and scrape interval of 15s. +# This implies ingestion rate of around 660000 samples per second. +# +# Query requirements can vary dramatically depending on query rate and query +# ranges. The values here satisfy a "usual" query load of around 50 queries per second +# as seen from our production clusters at this scale. +# +# The values in this file also add podAntiAffinity rules for ingesters and store-gateways. +# The rules ensure that the replicas of the same component are not scheduled on the same +# Kubernetes Node. Zone-aware replication is enabled by default on new installation. +# Refer to [Migrate from single zone to zone-aware replication with Helm](https://grafana.com/docs/mimir/latest/migration-guide/migrating-from-single-zone-with-helm) and +# [Zone-Aware Replication](https://grafana.com/docs/mimir/latest/configure/configure-zone-aware-replication/) +# for more information. +# +# MinIO is no longer enabled, and you are encouraged to use your cloud providers +# object storage service such as S3 or GCS. + +alertmanager: + persistentVolume: + enabled: true + replicas: 3 + resources: + limits: + cpu: 1.4 + memory: 1.4Gi + requests: + cpu: 1.4 + memory: 1.4Gi + statefulSet: + enabled: true + +compactor: + persistentVolume: + size: 50Gi + resources: + limits: + cpu: 1.4 + memory: 2.8Gi + requests: + cpu: 1.4 + memory: 2.8Gi + +distributor: + replicas: 12 + resources: + limits: + cpu: 2.8 + memory: 5.7Gi + requests: + cpu: 2.8 + memory: 5.7Gi + +ingester: + persistentVolume: + size: 50Gi + replicas: 27 + resources: + limits: + cpu: 5 + memory: 12Gi + requests: + cpu: 5 + memory: 12Gi + topologySpreadConstraints: {} + affinity: + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchExpressions: + - key: target # support for enterprise.legacyLabels + operator: In + values: + - ingester + topologyKey: 'kubernetes.io/hostname' + + - labelSelector: + matchExpressions: + - key: app.kubernetes.io/component + operator: In + values: + - ingester + topologyKey: 'kubernetes.io/hostname' + zoneAwareReplication: + topologyKey: 'kubernetes.io/hostname' + +admin-cache: + enabled: true + replicas: 2 + +chunks-cache: + enabled: true + replicas: 32 + +index-cache: + enabled: true + replicas: 10 + +metadata-cache: + enabled: true + +results-cache: + enabled: true + replicas: 4 + +minio: + enabled: false + +overrides_exporter: + replicas: 1 + resources: + limits: + cpu: 100m + memory: 128Mi + requests: + cpu: 100m + memory: 128Mi + +querier: + replicas: 4 + resources: + limits: + cpu: 2.8 + memory: 8.5Gi + requests: + cpu: 2.8 + memory: 8.5Gi + +query_frontend: + replicas: 3 + resources: + limits: + cpu: 2.8 + memory: 2.8Gi + requests: + cpu: 2.8 + memory: 2.8Gi + +ruler: + replicas: 3 + resources: + limits: + cpu: 1.4 + memory: 5.7Gi + requests: + cpu: 1.4 + memory: 5.7Gi + +store_gateway: + persistentVolume: + size: 50Gi + replicas: 6 + resources: + limits: + cpu: 1.4 + memory: 8.5Gi + requests: + cpu: 1.4 + memory: 8.5Gi + topologySpreadConstraints: {} + affinity: + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchExpressions: + - key: target # support for enterprise.legacyLabels + operator: In + values: + - store-gateway + topologyKey: 'kubernetes.io/hostname' + + - labelSelector: + matchExpressions: + - key: app.kubernetes.io/component + operator: In + values: + - store-gateway + topologyKey: 'kubernetes.io/hostname' + zoneAwareReplication: + topologyKey: 'kubernetes.io/hostname' + +nginx: + replicas: 3 + resources: + limits: + cpu: 1.4 + memory: 731Mi + requests: + cpu: 1.4 + memory: 731Mi + +# Grafana Enterprise Metrics feature related +admin_api: + replicas: 2 + resources: + limits: + cpu: 200m + memory: 128Mi + requests: + cpu: 200m + memory: 128Mi + +gateway: + replicas: 3 + resources: + limits: + cpu: 1.4 + memory: 731Mi + requests: + cpu: 1.4 + memory: 731Mi diff --git a/observability/lgtm-distributed/charts/mimir-distributed/capped-small.yaml b/observability/lgtm-distributed/charts/mimir-distributed/capped-small.yaml new file mode 100644 index 0000000..69c7559 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/capped-small.yaml @@ -0,0 +1,218 @@ +# These values configure the Grafana Mimir or Grafana Enterprise Metrics cluster +# for a more production-ready setup. The setup targets 70% CPU and memory utilization +# so that the cluster has room to grow. The resource requests and limits reflect 100% utilization. +# This is useful when you want to strictly control costs when purchasing GEM through a marketplace subscription for example. +# limits==requests also ensure a "Guaranteed" QoS: https://kubernetes.io/docs/tasks/configure-pod-container/quality-service-pod/. +# Note that setting CPU limits has some known issues: +# https://engineering.indeedblog.com/blog/2019/12/unthrottled-fixing-cpu-limits-in-the-cloud/. +# +# These values are suitable for ingestion of ~1M series and scrape interval of 15s. +# This implies ingestion rate of around 66000 samples per second. +# +# Query requirements can vary dramatically depending on query rate and query +# ranges. The values here satisfy a "usual" query load of around 5 queries per second +# as seen from our production clusters at this scale. +# +# The values in this file also add podAntiAffinity rules for ingesters and store-gateways. +# The rules ensure that the replicas of the same component are not scheduled on the same +# Kubernetes Node. Zone-aware replication is enabled by default on new installation. +# Refer to [Migrate from single zone to zone-aware replication with Helm](https://grafana.com/docs/mimir/latest/migration-guide/migrating-from-single-zone-with-helm) and +# [Zone-Aware Replication](https://grafana.com/docs/mimir/latest/configure/configure-zone-aware-replication/) +# for more information. +# +# MinIO is no longer enabled, and you are encouraged to use your cloud providers +# object storage service such as S3 or GCS. + +alertmanager: + persistentVolume: + enabled: true + replicas: 2 + resources: + limits: + cpu: 1.4 + memory: 1.4Gi + requests: + cpu: 1.4 + memory: 1.4Gi + statefulSet: + enabled: true + +compactor: + persistentVolume: + size: 20Gi + resources: + limits: + cpu: 1.4 + memory: 2.1Gi + requests: + cpu: 1.4 + memory: 2.1Gi + +distributor: + replicas: 2 + resources: + limits: + cpu: 3.5 + memory: 5.7Gi + requests: + cpu: 3.5 + memory: 5.7Gi + +ingester: + persistentVolume: + size: 50Gi + replicas: 3 + resources: + limits: + cpu: 5 + memory: 12Gi + requests: + cpu: 5 + memory: 12Gi + topologySpreadConstraints: {} + affinity: + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchExpressions: + - key: target # support for enterprise.legacyLabels + operator: In + values: + - ingester + topologyKey: 'kubernetes.io/hostname' + + - labelSelector: + matchExpressions: + - key: app.kubernetes.io/component + operator: In + values: + - ingester + topologyKey: 'kubernetes.io/hostname' + zoneAwareReplication: + topologyKey: 'kubernetes.io/hostname' + +admin-cache: + enabled: true + replicas: 2 + +chunks-cache: + enabled: true + replicas: 2 + +index-cache: + enabled: true + replicas: 3 + +metadata-cache: + enabled: true + +results-cache: + enabled: true + +minio: + enabled: false + +overrides_exporter: + replicas: 1 + resources: + limits: + cpu: 100m + memory: 128Mi + requests: + cpu: 100m + memory: 128Mi + +querier: + replicas: 1 + resources: + limits: + cpu: 2.8 + memory: 5.6Gi + requests: + cpu: 2.8 + memory: 5.6Gi + +query_frontend: + replicas: 1 + resources: + limits: + cpu: 2.8 + memory: 2.8Gi + requests: + cpu: 2.8 + memory: 2.8Gi + +ruler: + replicas: 1 + resources: + limits: + cpu: 1.4 + memory: 2.8Gi + requests: + cpu: 1.4 + memory: 2.8Gi + +store_gateway: + persistentVolume: + size: 10Gi + replicas: 3 + resources: + limits: + cpu: 1.4 + memory: 2.1Gi + requests: + cpu: 1.4 + memory: 2.1Gi + topologySpreadConstraints: {} + affinity: + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchExpressions: + - key: target # support for enterprise.legacyLabels + operator: In + values: + - store-gateway + topologyKey: 'kubernetes.io/hostname' + + - labelSelector: + matchExpressions: + - key: app.kubernetes.io/component + operator: In + values: + - store-gateway + topologyKey: 'kubernetes.io/hostname' + + zoneAwareReplication: + topologyKey: 'kubernetes.io/hostname' + +nginx: + replicas: 1 + resources: + limits: + cpu: 1.4 + memory: 731Mi + requests: + cpu: 1.4 + memory: 731Mi + +# Grafana Enterprise Metrics feature related +admin_api: + replicas: 1 + resources: + limits: + cpu: 200m + memory: 128Mi + requests: + cpu: 200m + memory: 128Mi + +gateway: + replicas: 1 + resources: + limits: + cpu: 1.4 + memory: 731Mi + requests: + cpu: 1.4 + memory: 731Mi diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/.helmignore b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/.helmignore new file mode 100644 index 0000000..50af031 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/.helmignore @@ -0,0 +1,22 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/Chart.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/Chart.yaml new file mode 100644 index 0000000..d0568cb --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/Chart.yaml @@ -0,0 +1,13 @@ +apiVersion: v2 +appVersion: 0.40.3 +description: A Helm chart for Grafana Agent Operator +home: https://grafana.com/docs/agent/v0.40/ +icon: https://raw.githubusercontent.com/grafana/agent/v0.40.3/docs/sources/assets/logo_and_name.png +maintainers: +- email: grafana-agent-team@googlegroups.com + name: Grafana Agent Team +name: grafana-agent-operator +sources: +- https://github.com/grafana/agent/tree/v0.40.3/pkg/operator +type: application +version: 0.3.19 diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/README.md b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/README.md new file mode 100644 index 0000000..7a5187e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/README.md @@ -0,0 +1,78 @@ +# grafana-agent-operator + +![Version: 0.3.19](https://img.shields.io/badge/Version-0.3.19-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 0.40.3](https://img.shields.io/badge/AppVersion-0.40.3-informational?style=flat-square) + +A Helm chart for Grafana Agent Operator + +⚠️ **Please create issues relating to this Helm chart in the [Agent](https://github.com/grafana/agent/issues) repo.** + +## Source Code + +* + +Note that this chart does not provision custom resources like `GrafanaAgent` and `MetricsInstance` (formerly `PrometheusInstance`) or any `*Monitor` resources. + +To learn how to deploy these resources, please see Grafana's [Agent Operator getting started guide](https://grafana.com/docs/agent/latest/operator/getting-started/). + +## CRDs + +The CRDs are synced into this chart manually (for now) from the Grafana Agent [GitHub repo](https://github.com/grafana/agent/tree/main/operations/agent-static-operator/crds). To learn more about how Helm manages CRDs, please see [Custom Resource Definitions](https://helm.sh/docs/chart_best_practices/custom_resource_definitions/) from the Helm docs. + +## Get Repo Info + +```console +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update +``` + +_See [helm repo](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```console +helm install my-release grafana/grafana-agent-operator +``` + +## Uninstalling the Chart + +To uninstall/delete the my-release deployment: + +```console +helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + +## Upgrading an existing Release to a new major version + +A major chart version change (like v1.2.3 -> v2.0.0) indicates that there is an incompatible breaking change needing manual actions. Until this chart's version reaches `v1.0`, there are no promises of backwards compatibility. + +## Values + +| Key | Type | Default | Description | +|-----|------|---------|-------------| +| affinity | object | `{}` | Pod affinity configuration | +| annotations | object | `{}` | Annotations for the Deployment | +| containerSecurityContext | object | `{}` | Container security context (allowPrivilegeEscalation, etc.) | +| extraArgs | list | `[]` | List of additional cli arguments to configure agent-operator (example: `--log.level`) | +| fullnameOverride | string | `""` | Overrides the chart's computed fullname | +| hostAliases | list | `[]` | hostAliases to add | +| image.pullPolicy | string | `"IfNotPresent"` | Image pull policy | +| image.pullSecrets | list | `[]` | Image pull secrets | +| image.registry | string | `"docker.io"` | Image registry | +| image.repository | string | `"grafana/agent-operator"` | Image repo | +| image.tag | string | `"v0.40.3"` | Image tag | +| kubeletService | object | `{"namespace":"default","serviceName":"kubelet"}` | If both are set, Agent Operator will create and maintain a service for scraping kubelets https://grafana.com/docs/agent/latest/operator/getting-started/#monitor-kubelets | +| nameOverride | string | `""` | Overrides the chart's name | +| nodeSelector | object | `{}` | nodeSelector configuration | +| podAnnotations | object | `{}` | Annotations for the Deployment Pods | +| podLabels | object | `{}` | Annotations for the Deployment Pods | +| podSecurityContext | object | `{}` | Pod security context (runAsUser, etc.) | +| rbac.create | bool | `true` | Toggle to create ClusterRole and ClusterRoleBinding | +| rbac.podSecurityPolicyName | string | `""` | Name of a PodSecurityPolicy to use in the ClusterRole. If unset, no PodSecurityPolicy is used. | +| resources | object | `{}` | Resource limits and requests config | +| serviceAccount.create | bool | `true` | Toggle to create ServiceAccount | +| serviceAccount.name | string | `nil` | Service account name | +| tolerations | list | `[]` | Tolerations applied to Pods | diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/README.md.gotmpl b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/README.md.gotmpl new file mode 100644 index 0000000..3dce97a --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/README.md.gotmpl @@ -0,0 +1,52 @@ +{{ template "chart.header" . }} + +{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }} + +{{ template "chart.description" . }} + +⚠️ **Please create issues relating to this Helm chart in the [Agent](https://github.com/grafana/agent/issues) repo.** + +{{ template "chart.sourcesSection" . }} + +{{ template "chart.requirementsSection" . }} + +Note that this chart does not provision custom resources like `GrafanaAgent` and `MetricsInstance` (formerly `PrometheusInstance`) or any `*Monitor` resources. + +To learn how to deploy these resources, please see Grafana's [Agent Operator getting started guide](https://grafana.com/docs/agent/latest/operator/getting-started/). + +## CRDs + +The CRDs are synced into this chart manually (for now) from the Grafana Agent [GitHub repo](https://github.com/grafana/agent/tree/main/operations/agent-static-operator/crds). To learn more about how Helm manages CRDs, please see [Custom Resource Definitions](https://helm.sh/docs/chart_best_practices/custom_resource_definitions/) from the Helm docs. + +## Get Repo Info + +```console +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update +``` + +_See [helm repo](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```console +helm install my-release grafana/grafana-agent-operator +``` + +## Uninstalling the Chart + +To uninstall/delete the my-release deployment: + +```console +helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + +## Upgrading an existing Release to a new major version + +A major chart version change (like v1.2.3 -> v2.0.0) indicates that there is an incompatible breaking change needing manual actions. Until this chart's version reaches `v1.0`, there are no promises of backwards compatibility. + +{{ template "chart.valuesSection" . }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_podmonitors.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_podmonitors.yaml new file mode 100644 index 0000000..153677b --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_podmonitors.yaml @@ -0,0 +1,424 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.9.2 + creationTimestamp: null + name: podmonitors.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + categories: + - prometheus-operator + kind: PodMonitor + listKind: PodMonitorList + plural: podmonitors + shortNames: + - pmon + singular: podmonitor + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + properties: + apiVersion: + type: string + kind: + type: string + metadata: + type: object + spec: + properties: + attachMetadata: + properties: + node: + type: boolean + type: object + jobLabel: + type: string + labelLimit: + format: int64 + type: integer + labelNameLengthLimit: + format: int64 + type: integer + labelValueLengthLimit: + format: int64 + type: integer + namespaceSelector: + properties: + any: + type: boolean + matchNames: + items: + type: string + type: array + type: object + podMetricsEndpoints: + items: + properties: + authorization: + properties: + credentials: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + type: string + type: object + basicAuth: + properties: + password: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + enableHttp2: + type: boolean + filterRunning: + type: boolean + followRedirects: + type: boolean + honorLabels: + type: boolean + honorTimestamps: + type: boolean + interval: + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + metricRelabelings: + items: + properties: + action: + default: replace + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + format: int64 + type: integer + regex: + type: string + replacement: + type: string + separator: + type: string + sourceLabels: + items: + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + type: string + type: object + type: array + oauth2: + properties: + clientId: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + type: object + scopes: + items: + type: string + type: array + tokenUrl: + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + params: + additionalProperties: + items: + type: string + type: array + type: object + path: + type: string + port: + type: string + proxyUrl: + type: string + relabelings: + items: + properties: + action: + default: replace + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + format: int64 + type: integer + regex: + type: string + replacement: + type: string + separator: + type: string + sourceLabels: + items: + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + type: string + type: object + type: array + scheme: + enum: + - http + - https + type: string + scrapeTimeout: + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + targetPort: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + tlsConfig: + properties: + ca: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + type: boolean + keySecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + type: string + type: object + type: object + type: array + podTargetLabels: + items: + type: string + type: array + sampleLimit: + format: int64 + type: integer + selector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + targetLimit: + format: int64 + type: integer + required: + - podMetricsEndpoints + - selector + type: object + required: + - spec + type: object + served: true + storage: true diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_probes.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_probes.yaml new file mode 100644 index 0000000..13fc36f --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_probes.yaml @@ -0,0 +1,458 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.9.2 + creationTimestamp: null + name: probes.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + categories: + - prometheus-operator + kind: Probe + listKind: ProbeList + plural: probes + shortNames: + - prb + singular: probe + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + properties: + apiVersion: + type: string + kind: + type: string + metadata: + type: object + spec: + properties: + authorization: + properties: + credentials: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + type: string + type: object + basicAuth: + properties: + password: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + interval: + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + jobName: + type: string + labelLimit: + format: int64 + type: integer + labelNameLengthLimit: + format: int64 + type: integer + labelValueLengthLimit: + format: int64 + type: integer + metricRelabelings: + items: + properties: + action: + default: replace + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + format: int64 + type: integer + regex: + type: string + replacement: + type: string + separator: + type: string + sourceLabels: + items: + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + type: string + type: object + type: array + module: + type: string + oauth2: + properties: + clientId: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + type: object + scopes: + items: + type: string + type: array + tokenUrl: + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + prober: + properties: + path: + default: /probe + type: string + proxyUrl: + type: string + scheme: + enum: + - http + - https + type: string + url: + type: string + required: + - url + type: object + sampleLimit: + format: int64 + type: integer + scrapeTimeout: + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + targetLimit: + format: int64 + type: integer + targets: + properties: + ingress: + properties: + namespaceSelector: + properties: + any: + type: boolean + matchNames: + items: + type: string + type: array + type: object + relabelingConfigs: + items: + properties: + action: + default: replace + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + format: int64 + type: integer + regex: + type: string + replacement: + type: string + separator: + type: string + sourceLabels: + items: + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + type: string + type: object + type: array + selector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + type: object + staticConfig: + properties: + labels: + additionalProperties: + type: string + type: object + relabelingConfigs: + items: + properties: + action: + default: replace + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + format: int64 + type: integer + regex: + type: string + replacement: + type: string + separator: + type: string + sourceLabels: + items: + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + type: string + type: object + type: array + static: + items: + type: string + type: array + type: object + type: object + tlsConfig: + properties: + ca: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + type: boolean + keySecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + type: string + type: object + type: object + required: + - spec + type: object + served: true + storage: true diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_servicemonitors.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_servicemonitors.yaml new file mode 100644 index 0000000..ff62f8f --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_servicemonitors.yaml @@ -0,0 +1,436 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.9.2 + creationTimestamp: null + name: servicemonitors.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + categories: + - prometheus-operator + kind: ServiceMonitor + listKind: ServiceMonitorList + plural: servicemonitors + shortNames: + - smon + singular: servicemonitor + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + properties: + apiVersion: + type: string + kind: + type: string + metadata: + type: object + spec: + properties: + attachMetadata: + properties: + node: + type: boolean + type: object + endpoints: + items: + properties: + authorization: + properties: + credentials: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + type: string + type: object + basicAuth: + properties: + password: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenFile: + type: string + bearerTokenSecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + enableHttp2: + type: boolean + filterRunning: + type: boolean + followRedirects: + type: boolean + honorLabels: + type: boolean + honorTimestamps: + type: boolean + interval: + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + metricRelabelings: + items: + properties: + action: + default: replace + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + format: int64 + type: integer + regex: + type: string + replacement: + type: string + separator: + type: string + sourceLabels: + items: + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + type: string + type: object + type: array + oauth2: + properties: + clientId: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + type: object + scopes: + items: + type: string + type: array + tokenUrl: + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + params: + additionalProperties: + items: + type: string + type: array + type: object + path: + type: string + port: + type: string + proxyUrl: + type: string + relabelings: + items: + properties: + action: + default: replace + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + format: int64 + type: integer + regex: + type: string + replacement: + type: string + separator: + type: string + sourceLabels: + items: + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + type: string + type: object + type: array + scheme: + enum: + - http + - https + type: string + scrapeTimeout: + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + targetPort: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + tlsConfig: + properties: + ca: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + caFile: + type: string + cert: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + certFile: + type: string + insecureSkipVerify: + type: boolean + keyFile: + type: string + keySecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + type: string + type: object + type: object + type: array + jobLabel: + type: string + labelLimit: + format: int64 + type: integer + labelNameLengthLimit: + format: int64 + type: integer + labelValueLengthLimit: + format: int64 + type: integer + namespaceSelector: + properties: + any: + type: boolean + matchNames: + items: + type: string + type: array + type: object + podTargetLabels: + items: + type: string + type: array + sampleLimit: + format: int64 + type: integer + selector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + targetLabels: + items: + type: string + type: array + targetLimit: + format: int64 + type: integer + required: + - endpoints + - selector + type: object + required: + - spec + type: object + served: true + storage: true diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_grafanaagents.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_grafanaagents.yaml new file mode 100644 index 0000000..4ec31d6 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_grafanaagents.yaml @@ -0,0 +1,3711 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.9.2 + creationTimestamp: null + name: grafanaagents.monitoring.grafana.com +spec: + group: monitoring.grafana.com + names: + categories: + - agent-operator + kind: GrafanaAgent + listKind: GrafanaAgentList + plural: grafanaagents + singular: grafanaagent + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + properties: + apiVersion: + type: string + kind: + type: string + metadata: + type: object + spec: + properties: + affinity: + properties: + nodeAffinity: + properties: + preferredDuringSchedulingIgnoredDuringExecution: + items: + properties: + preference: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + x-kubernetes-map-type: atomic + weight: + format: int32 + type: integer + required: + - preference + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + properties: + nodeSelectorTerms: + items: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + x-kubernetes-map-type: atomic + type: array + required: + - nodeSelectorTerms + type: object + x-kubernetes-map-type: atomic + type: object + podAffinity: + properties: + preferredDuringSchedulingIgnoredDuringExecution: + items: + properties: + podAffinityTerm: + properties: + labelSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + namespaceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + namespaces: + items: + type: string + type: array + topologyKey: + type: string + required: + - topologyKey + type: object + weight: + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + items: + properties: + labelSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + namespaceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + namespaces: + items: + type: string + type: array + topologyKey: + type: string + required: + - topologyKey + type: object + type: array + type: object + podAntiAffinity: + properties: + preferredDuringSchedulingIgnoredDuringExecution: + items: + properties: + podAffinityTerm: + properties: + labelSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + namespaceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + namespaces: + items: + type: string + type: array + topologyKey: + type: string + required: + - topologyKey + type: object + weight: + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + items: + properties: + labelSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + namespaceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + namespaces: + items: + type: string + type: array + topologyKey: + type: string + required: + - topologyKey + type: object + type: array + type: object + type: object + apiServer: + properties: + authorization: + properties: + credentials: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + credentialsFile: + type: string + type: + type: string + type: object + basicAuth: + properties: + password: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerToken: + type: string + bearerTokenFile: + type: string + host: + type: string + tlsConfig: + properties: + ca: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + caFile: + type: string + cert: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + certFile: + type: string + insecureSkipVerify: + type: boolean + keyFile: + type: string + keySecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + type: string + type: object + required: + - host + type: object + configMaps: + items: + type: string + type: array + configReloaderImage: + type: string + configReloaderVersion: + type: string + containers: + items: + properties: + args: + items: + type: string + type: array + command: + items: + type: string + type: array + env: + items: + properties: + name: + type: string + value: + type: string + valueFrom: + properties: + configMapKeyRef: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + fieldRef: + properties: + apiVersion: + type: string + fieldPath: + type: string + required: + - fieldPath + type: object + x-kubernetes-map-type: atomic + resourceFieldRef: + properties: + containerName: + type: string + divisor: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + type: string + required: + - resource + type: object + x-kubernetes-map-type: atomic + secretKeyRef: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + required: + - name + type: object + type: array + envFrom: + items: + properties: + configMapRef: + properties: + name: + type: string + optional: + type: boolean + type: object + x-kubernetes-map-type: atomic + prefix: + type: string + secretRef: + properties: + name: + type: string + optional: + type: boolean + type: object + x-kubernetes-map-type: atomic + type: object + type: array + image: + type: string + imagePullPolicy: + type: string + lifecycle: + properties: + postStart: + properties: + exec: + properties: + command: + items: + type: string + type: array + type: object + httpGet: + properties: + host: + type: string + httpHeaders: + items: + properties: + name: + type: string + value: + type: string + required: + - name + - value + type: object + type: array + path: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + scheme: + type: string + required: + - port + type: object + tcpSocket: + properties: + host: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + properties: + exec: + properties: + command: + items: + type: string + type: array + type: object + httpGet: + properties: + host: + type: string + httpHeaders: + items: + properties: + name: + type: string + value: + type: string + required: + - name + - value + type: object + type: array + path: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + scheme: + type: string + required: + - port + type: object + tcpSocket: + properties: + host: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + properties: + exec: + properties: + command: + items: + type: string + type: array + type: object + failureThreshold: + format: int32 + type: integer + grpc: + properties: + port: + format: int32 + type: integer + service: + type: string + required: + - port + type: object + httpGet: + properties: + host: + type: string + httpHeaders: + items: + properties: + name: + type: string + value: + type: string + required: + - name + - value + type: object + type: array + path: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + scheme: + type: string + required: + - port + type: object + initialDelaySeconds: + format: int32 + type: integer + periodSeconds: + format: int32 + type: integer + successThreshold: + format: int32 + type: integer + tcpSocket: + properties: + host: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + format: int64 + type: integer + timeoutSeconds: + format: int32 + type: integer + type: object + name: + type: string + ports: + items: + properties: + containerPort: + format: int32 + type: integer + hostIP: + type: string + hostPort: + format: int32 + type: integer + name: + type: string + protocol: + default: TCP + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + properties: + exec: + properties: + command: + items: + type: string + type: array + type: object + failureThreshold: + format: int32 + type: integer + grpc: + properties: + port: + format: int32 + type: integer + service: + type: string + required: + - port + type: object + httpGet: + properties: + host: + type: string + httpHeaders: + items: + properties: + name: + type: string + value: + type: string + required: + - name + - value + type: object + type: array + path: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + scheme: + type: string + required: + - port + type: object + initialDelaySeconds: + format: int32 + type: integer + periodSeconds: + format: int32 + type: integer + successThreshold: + format: int32 + type: integer + tcpSocket: + properties: + host: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + format: int64 + type: integer + timeoutSeconds: + format: int32 + type: integer + type: object + resizePolicy: + items: + properties: + resourceName: + type: string + restartPolicy: + type: string + required: + - resourceName + - restartPolicy + type: object + type: array + x-kubernetes-list-type: atomic + resources: + properties: + claims: + items: + properties: + name: + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + type: object + restartPolicy: + type: string + securityContext: + properties: + allowPrivilegeEscalation: + type: boolean + capabilities: + properties: + add: + items: + type: string + type: array + drop: + items: + type: string + type: array + type: object + privileged: + type: boolean + procMount: + type: string + readOnlyRootFilesystem: + type: boolean + runAsGroup: + format: int64 + type: integer + runAsNonRoot: + type: boolean + runAsUser: + format: int64 + type: integer + seLinuxOptions: + properties: + level: + type: string + role: + type: string + type: + type: string + user: + type: string + type: object + seccompProfile: + properties: + localhostProfile: + type: string + type: + type: string + required: + - type + type: object + windowsOptions: + properties: + gmsaCredentialSpec: + type: string + gmsaCredentialSpecName: + type: string + hostProcess: + type: boolean + runAsUserName: + type: string + type: object + type: object + startupProbe: + properties: + exec: + properties: + command: + items: + type: string + type: array + type: object + failureThreshold: + format: int32 + type: integer + grpc: + properties: + port: + format: int32 + type: integer + service: + type: string + required: + - port + type: object + httpGet: + properties: + host: + type: string + httpHeaders: + items: + properties: + name: + type: string + value: + type: string + required: + - name + - value + type: object + type: array + path: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + scheme: + type: string + required: + - port + type: object + initialDelaySeconds: + format: int32 + type: integer + periodSeconds: + format: int32 + type: integer + successThreshold: + format: int32 + type: integer + tcpSocket: + properties: + host: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + format: int64 + type: integer + timeoutSeconds: + format: int32 + type: integer + type: object + stdin: + type: boolean + stdinOnce: + type: boolean + terminationMessagePath: + type: string + terminationMessagePolicy: + type: string + tty: + type: boolean + volumeDevices: + items: + properties: + devicePath: + type: string + name: + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + items: + properties: + mountPath: + type: string + mountPropagation: + type: string + name: + type: string + readOnly: + type: boolean + subPath: + type: string + subPathExpr: + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + type: string + required: + - name + type: object + type: array + disableReporting: + default: false + type: boolean + disableSupportBundle: + default: false + type: boolean + enableConfigReadAPI: + default: false + type: boolean + image: + type: string + imagePullSecrets: + items: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + type: array + initContainers: + items: + properties: + args: + items: + type: string + type: array + command: + items: + type: string + type: array + env: + items: + properties: + name: + type: string + value: + type: string + valueFrom: + properties: + configMapKeyRef: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + fieldRef: + properties: + apiVersion: + type: string + fieldPath: + type: string + required: + - fieldPath + type: object + x-kubernetes-map-type: atomic + resourceFieldRef: + properties: + containerName: + type: string + divisor: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + type: string + required: + - resource + type: object + x-kubernetes-map-type: atomic + secretKeyRef: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + required: + - name + type: object + type: array + envFrom: + items: + properties: + configMapRef: + properties: + name: + type: string + optional: + type: boolean + type: object + x-kubernetes-map-type: atomic + prefix: + type: string + secretRef: + properties: + name: + type: string + optional: + type: boolean + type: object + x-kubernetes-map-type: atomic + type: object + type: array + image: + type: string + imagePullPolicy: + type: string + lifecycle: + properties: + postStart: + properties: + exec: + properties: + command: + items: + type: string + type: array + type: object + httpGet: + properties: + host: + type: string + httpHeaders: + items: + properties: + name: + type: string + value: + type: string + required: + - name + - value + type: object + type: array + path: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + scheme: + type: string + required: + - port + type: object + tcpSocket: + properties: + host: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + properties: + exec: + properties: + command: + items: + type: string + type: array + type: object + httpGet: + properties: + host: + type: string + httpHeaders: + items: + properties: + name: + type: string + value: + type: string + required: + - name + - value + type: object + type: array + path: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + scheme: + type: string + required: + - port + type: object + tcpSocket: + properties: + host: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + properties: + exec: + properties: + command: + items: + type: string + type: array + type: object + failureThreshold: + format: int32 + type: integer + grpc: + properties: + port: + format: int32 + type: integer + service: + type: string + required: + - port + type: object + httpGet: + properties: + host: + type: string + httpHeaders: + items: + properties: + name: + type: string + value: + type: string + required: + - name + - value + type: object + type: array + path: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + scheme: + type: string + required: + - port + type: object + initialDelaySeconds: + format: int32 + type: integer + periodSeconds: + format: int32 + type: integer + successThreshold: + format: int32 + type: integer + tcpSocket: + properties: + host: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + format: int64 + type: integer + timeoutSeconds: + format: int32 + type: integer + type: object + name: + type: string + ports: + items: + properties: + containerPort: + format: int32 + type: integer + hostIP: + type: string + hostPort: + format: int32 + type: integer + name: + type: string + protocol: + default: TCP + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + properties: + exec: + properties: + command: + items: + type: string + type: array + type: object + failureThreshold: + format: int32 + type: integer + grpc: + properties: + port: + format: int32 + type: integer + service: + type: string + required: + - port + type: object + httpGet: + properties: + host: + type: string + httpHeaders: + items: + properties: + name: + type: string + value: + type: string + required: + - name + - value + type: object + type: array + path: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + scheme: + type: string + required: + - port + type: object + initialDelaySeconds: + format: int32 + type: integer + periodSeconds: + format: int32 + type: integer + successThreshold: + format: int32 + type: integer + tcpSocket: + properties: + host: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + format: int64 + type: integer + timeoutSeconds: + format: int32 + type: integer + type: object + resizePolicy: + items: + properties: + resourceName: + type: string + restartPolicy: + type: string + required: + - resourceName + - restartPolicy + type: object + type: array + x-kubernetes-list-type: atomic + resources: + properties: + claims: + items: + properties: + name: + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + type: object + restartPolicy: + type: string + securityContext: + properties: + allowPrivilegeEscalation: + type: boolean + capabilities: + properties: + add: + items: + type: string + type: array + drop: + items: + type: string + type: array + type: object + privileged: + type: boolean + procMount: + type: string + readOnlyRootFilesystem: + type: boolean + runAsGroup: + format: int64 + type: integer + runAsNonRoot: + type: boolean + runAsUser: + format: int64 + type: integer + seLinuxOptions: + properties: + level: + type: string + role: + type: string + type: + type: string + user: + type: string + type: object + seccompProfile: + properties: + localhostProfile: + type: string + type: + type: string + required: + - type + type: object + windowsOptions: + properties: + gmsaCredentialSpec: + type: string + gmsaCredentialSpecName: + type: string + hostProcess: + type: boolean + runAsUserName: + type: string + type: object + type: object + startupProbe: + properties: + exec: + properties: + command: + items: + type: string + type: array + type: object + failureThreshold: + format: int32 + type: integer + grpc: + properties: + port: + format: int32 + type: integer + service: + type: string + required: + - port + type: object + httpGet: + properties: + host: + type: string + httpHeaders: + items: + properties: + name: + type: string + value: + type: string + required: + - name + - value + type: object + type: array + path: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + scheme: + type: string + required: + - port + type: object + initialDelaySeconds: + format: int32 + type: integer + periodSeconds: + format: int32 + type: integer + successThreshold: + format: int32 + type: integer + tcpSocket: + properties: + host: + type: string + port: + anyOf: + - type: integer + - type: string + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + format: int64 + type: integer + timeoutSeconds: + format: int32 + type: integer + type: object + stdin: + type: boolean + stdinOnce: + type: boolean + terminationMessagePath: + type: string + terminationMessagePolicy: + type: string + tty: + type: boolean + volumeDevices: + items: + properties: + devicePath: + type: string + name: + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + items: + properties: + mountPath: + type: string + mountPropagation: + type: string + name: + type: string + readOnly: + type: boolean + subPath: + type: string + subPathExpr: + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + type: string + required: + - name + type: object + type: array + integrations: + properties: + namespaceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + selector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + type: object + logFormat: + type: string + logLevel: + type: string + logs: + properties: + clients: + items: + properties: + backoffConfig: + properties: + maxPeriod: + type: string + maxRetries: + type: integer + minPeriod: + type: string + type: object + basicAuth: + properties: + password: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + batchSize: + type: integer + batchWait: + type: string + bearerToken: + type: string + bearerTokenFile: + type: string + externalLabels: + additionalProperties: + type: string + type: object + oauth2: + properties: + clientId: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + type: object + scopes: + items: + type: string + type: array + tokenUrl: + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyUrl: + type: string + tenantId: + type: string + timeout: + type: string + tlsConfig: + properties: + ca: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + caFile: + type: string + cert: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + certFile: + type: string + insecureSkipVerify: + type: boolean + keyFile: + type: string + keySecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + type: string + type: object + url: + type: string + required: + - url + type: object + type: array + enforcedNamespaceLabel: + type: string + ignoreNamespaceSelectors: + type: boolean + instanceNamespaceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + instanceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + logsExternalLabelName: + type: string + type: object + metrics: + properties: + arbitraryFSAccessThroughSMs: + properties: + deny: + type: boolean + type: object + enforcedNamespaceLabel: + type: string + enforcedSampleLimit: + format: int64 + type: integer + enforcedTargetLimit: + format: int64 + type: integer + externalLabels: + additionalProperties: + type: string + type: object + ignoreNamespaceSelectors: + type: boolean + instanceNamespaceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + instanceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + metricsExternalLabelName: + type: string + overrideHonorLabels: + type: boolean + overrideHonorTimestamps: + type: boolean + remoteWrite: + items: + properties: + basicAuth: + properties: + password: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerToken: + type: string + bearerTokenFile: + type: string + headers: + additionalProperties: + type: string + type: object + metadataConfig: + properties: + send: + type: boolean + sendInterval: + type: string + type: object + name: + type: string + oauth2: + properties: + clientId: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + type: object + scopes: + items: + type: string + type: array + tokenUrl: + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyUrl: + type: string + queueConfig: + properties: + batchSendDeadline: + type: string + capacity: + type: integer + maxBackoff: + type: string + maxRetries: + type: integer + maxSamplesPerSend: + type: integer + maxShards: + type: integer + minBackoff: + type: string + minShards: + type: integer + retryOnRateLimit: + type: boolean + type: object + remoteTimeout: + type: string + sigv4: + properties: + accessKey: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + profile: + type: string + region: + type: string + roleARN: + type: string + secretKey: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + tlsConfig: + properties: + ca: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + caFile: + type: string + cert: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + certFile: + type: string + insecureSkipVerify: + type: boolean + keyFile: + type: string + keySecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + type: string + type: object + url: + type: string + writeRelabelConfigs: + items: + properties: + action: + default: replace + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + format: int64 + type: integer + regex: + type: string + replacement: + type: string + separator: + type: string + sourceLabels: + items: + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + type: string + type: object + type: array + required: + - url + type: object + type: array + replicaExternalLabelName: + type: string + replicas: + format: int32 + type: integer + scrapeInterval: + type: string + scrapeTimeout: + type: string + shards: + format: int32 + type: integer + type: object + nodeSelector: + additionalProperties: + type: string + type: object + paused: + type: boolean + podMetadata: + properties: + annotations: + additionalProperties: + type: string + type: object + labels: + additionalProperties: + type: string + type: object + name: + type: string + type: object + portName: + type: string + priorityClassName: + type: string + resources: + properties: + claims: + items: + properties: + name: + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + type: object + runtimeClassName: + type: string + secrets: + items: + type: string + type: array + securityContext: + properties: + fsGroup: + format: int64 + type: integer + fsGroupChangePolicy: + type: string + runAsGroup: + format: int64 + type: integer + runAsNonRoot: + type: boolean + runAsUser: + format: int64 + type: integer + seLinuxOptions: + properties: + level: + type: string + role: + type: string + type: + type: string + user: + type: string + type: object + seccompProfile: + properties: + localhostProfile: + type: string + type: + type: string + required: + - type + type: object + supplementalGroups: + items: + format: int64 + type: integer + type: array + sysctls: + items: + properties: + name: + type: string + value: + type: string + required: + - name + - value + type: object + type: array + windowsOptions: + properties: + gmsaCredentialSpec: + type: string + gmsaCredentialSpecName: + type: string + hostProcess: + type: boolean + runAsUserName: + type: string + type: object + type: object + serviceAccountName: + type: string + storage: + properties: + disableMountSubPath: + type: boolean + emptyDir: + properties: + medium: + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + ephemeral: + properties: + volumeClaimTemplate: + properties: + metadata: + type: object + spec: + properties: + accessModes: + items: + type: string + type: array + dataSource: + properties: + apiGroup: + type: string + kind: + type: string + name: + type: string + required: + - kind + - name + type: object + x-kubernetes-map-type: atomic + dataSourceRef: + properties: + apiGroup: + type: string + kind: + type: string + name: + type: string + namespace: + type: string + required: + - kind + - name + type: object + resources: + properties: + claims: + items: + properties: + name: + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + type: object + selector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + storageClassName: + type: string + volumeMode: + type: string + volumeName: + type: string + type: object + required: + - spec + type: object + type: object + volumeClaimTemplate: + properties: + apiVersion: + type: string + kind: + type: string + metadata: + properties: + annotations: + additionalProperties: + type: string + type: object + labels: + additionalProperties: + type: string + type: object + name: + type: string + type: object + spec: + properties: + accessModes: + items: + type: string + type: array + dataSource: + properties: + apiGroup: + type: string + kind: + type: string + name: + type: string + required: + - kind + - name + type: object + x-kubernetes-map-type: atomic + dataSourceRef: + properties: + apiGroup: + type: string + kind: + type: string + name: + type: string + namespace: + type: string + required: + - kind + - name + type: object + resources: + properties: + claims: + items: + properties: + name: + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + type: object + selector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + storageClassName: + type: string + volumeMode: + type: string + volumeName: + type: string + type: object + status: + properties: + accessModes: + items: + type: string + type: array + allocatedResourceStatuses: + additionalProperties: + type: string + type: object + x-kubernetes-map-type: granular + allocatedResources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + capacity: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + conditions: + items: + properties: + lastProbeTime: + format: date-time + type: string + lastTransitionTime: + format: date-time + type: string + message: + type: string + reason: + type: string + status: + type: string + type: + type: string + required: + - status + - type + type: object + type: array + phase: + type: string + type: object + type: object + type: object + tolerations: + items: + properties: + effect: + type: string + key: + type: string + operator: + type: string + tolerationSeconds: + format: int64 + type: integer + value: + type: string + type: object + type: array + topologySpreadConstraints: + items: + properties: + labelSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + matchLabelKeys: + items: + type: string + type: array + x-kubernetes-list-type: atomic + maxSkew: + format: int32 + type: integer + minDomains: + format: int32 + type: integer + nodeAffinityPolicy: + type: string + nodeTaintsPolicy: + type: string + topologyKey: + type: string + whenUnsatisfiable: + type: string + required: + - maxSkew + - topologyKey + - whenUnsatisfiable + type: object + type: array + version: + type: string + volumeMounts: + items: + properties: + mountPath: + type: string + mountPropagation: + type: string + name: + type: string + readOnly: + type: boolean + subPath: + type: string + subPathExpr: + type: string + required: + - mountPath + - name + type: object + type: array + volumes: + items: + properties: + awsElasticBlockStore: + properties: + fsType: + type: string + partition: + format: int32 + type: integer + readOnly: + type: boolean + volumeID: + type: string + required: + - volumeID + type: object + azureDisk: + properties: + cachingMode: + type: string + diskName: + type: string + diskURI: + type: string + fsType: + type: string + kind: + type: string + readOnly: + type: boolean + required: + - diskName + - diskURI + type: object + azureFile: + properties: + readOnly: + type: boolean + secretName: + type: string + shareName: + type: string + required: + - secretName + - shareName + type: object + cephfs: + properties: + monitors: + items: + type: string + type: array + path: + type: string + readOnly: + type: boolean + secretFile: + type: string + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + user: + type: string + required: + - monitors + type: object + cinder: + properties: + fsType: + type: string + readOnly: + type: boolean + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + volumeID: + type: string + required: + - volumeID + type: object + configMap: + properties: + defaultMode: + format: int32 + type: integer + items: + items: + properties: + key: + type: string + mode: + format: int32 + type: integer + path: + type: string + required: + - key + - path + type: object + type: array + name: + type: string + optional: + type: boolean + type: object + x-kubernetes-map-type: atomic + csi: + properties: + driver: + type: string + fsType: + type: string + nodePublishSecretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + readOnly: + type: boolean + volumeAttributes: + additionalProperties: + type: string + type: object + required: + - driver + type: object + downwardAPI: + properties: + defaultMode: + format: int32 + type: integer + items: + items: + properties: + fieldRef: + properties: + apiVersion: + type: string + fieldPath: + type: string + required: + - fieldPath + type: object + x-kubernetes-map-type: atomic + mode: + format: int32 + type: integer + path: + type: string + resourceFieldRef: + properties: + containerName: + type: string + divisor: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + type: string + required: + - resource + type: object + x-kubernetes-map-type: atomic + required: + - path + type: object + type: array + type: object + emptyDir: + properties: + medium: + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + ephemeral: + properties: + volumeClaimTemplate: + properties: + metadata: + type: object + spec: + properties: + accessModes: + items: + type: string + type: array + dataSource: + properties: + apiGroup: + type: string + kind: + type: string + name: + type: string + required: + - kind + - name + type: object + x-kubernetes-map-type: atomic + dataSourceRef: + properties: + apiGroup: + type: string + kind: + type: string + name: + type: string + namespace: + type: string + required: + - kind + - name + type: object + resources: + properties: + claims: + items: + properties: + name: + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + type: object + selector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + storageClassName: + type: string + volumeMode: + type: string + volumeName: + type: string + type: object + required: + - spec + type: object + type: object + fc: + properties: + fsType: + type: string + lun: + format: int32 + type: integer + readOnly: + type: boolean + targetWWNs: + items: + type: string + type: array + wwids: + items: + type: string + type: array + type: object + flexVolume: + properties: + driver: + type: string + fsType: + type: string + options: + additionalProperties: + type: string + type: object + readOnly: + type: boolean + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + required: + - driver + type: object + flocker: + properties: + datasetName: + type: string + datasetUUID: + type: string + type: object + gcePersistentDisk: + properties: + fsType: + type: string + partition: + format: int32 + type: integer + pdName: + type: string + readOnly: + type: boolean + required: + - pdName + type: object + gitRepo: + properties: + directory: + type: string + repository: + type: string + revision: + type: string + required: + - repository + type: object + glusterfs: + properties: + endpoints: + type: string + path: + type: string + readOnly: + type: boolean + required: + - endpoints + - path + type: object + hostPath: + properties: + path: + type: string + type: + type: string + required: + - path + type: object + iscsi: + properties: + chapAuthDiscovery: + type: boolean + chapAuthSession: + type: boolean + fsType: + type: string + initiatorName: + type: string + iqn: + type: string + iscsiInterface: + type: string + lun: + format: int32 + type: integer + portals: + items: + type: string + type: array + readOnly: + type: boolean + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + targetPortal: + type: string + required: + - iqn + - lun + - targetPortal + type: object + name: + type: string + nfs: + properties: + path: + type: string + readOnly: + type: boolean + server: + type: string + required: + - path + - server + type: object + persistentVolumeClaim: + properties: + claimName: + type: string + readOnly: + type: boolean + required: + - claimName + type: object + photonPersistentDisk: + properties: + fsType: + type: string + pdID: + type: string + required: + - pdID + type: object + portworxVolume: + properties: + fsType: + type: string + readOnly: + type: boolean + volumeID: + type: string + required: + - volumeID + type: object + projected: + properties: + defaultMode: + format: int32 + type: integer + sources: + items: + properties: + configMap: + properties: + items: + items: + properties: + key: + type: string + mode: + format: int32 + type: integer + path: + type: string + required: + - key + - path + type: object + type: array + name: + type: string + optional: + type: boolean + type: object + x-kubernetes-map-type: atomic + downwardAPI: + properties: + items: + items: + properties: + fieldRef: + properties: + apiVersion: + type: string + fieldPath: + type: string + required: + - fieldPath + type: object + x-kubernetes-map-type: atomic + mode: + format: int32 + type: integer + path: + type: string + resourceFieldRef: + properties: + containerName: + type: string + divisor: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + type: string + required: + - resource + type: object + x-kubernetes-map-type: atomic + required: + - path + type: object + type: array + type: object + secret: + properties: + items: + items: + properties: + key: + type: string + mode: + format: int32 + type: integer + path: + type: string + required: + - key + - path + type: object + type: array + name: + type: string + optional: + type: boolean + type: object + x-kubernetes-map-type: atomic + serviceAccountToken: + properties: + audience: + type: string + expirationSeconds: + format: int64 + type: integer + path: + type: string + required: + - path + type: object + type: object + type: array + type: object + quobyte: + properties: + group: + type: string + readOnly: + type: boolean + registry: + type: string + tenant: + type: string + user: + type: string + volume: + type: string + required: + - registry + - volume + type: object + rbd: + properties: + fsType: + type: string + image: + type: string + keyring: + type: string + monitors: + items: + type: string + type: array + pool: + type: string + readOnly: + type: boolean + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + user: + type: string + required: + - image + - monitors + type: object + scaleIO: + properties: + fsType: + type: string + gateway: + type: string + protectionDomain: + type: string + readOnly: + type: boolean + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + sslEnabled: + type: boolean + storageMode: + type: string + storagePool: + type: string + system: + type: string + volumeName: + type: string + required: + - gateway + - secretRef + - system + type: object + secret: + properties: + defaultMode: + format: int32 + type: integer + items: + items: + properties: + key: + type: string + mode: + format: int32 + type: integer + path: + type: string + required: + - key + - path + type: object + type: array + optional: + type: boolean + secretName: + type: string + type: object + storageos: + properties: + fsType: + type: string + readOnly: + type: boolean + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + volumeName: + type: string + volumeNamespace: + type: string + type: object + vsphereVolume: + properties: + fsType: + type: string + storagePolicyID: + type: string + storagePolicyName: + type: string + volumePath: + type: string + required: + - volumePath + type: object + required: + - name + type: object + type: array + type: object + type: object + served: true + storage: true diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_integrations.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_integrations.yaml new file mode 100644 index 0000000..960b2f7 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_integrations.yaml @@ -0,0 +1,810 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.9.2 + creationTimestamp: null + name: integrations.monitoring.grafana.com +spec: + group: monitoring.grafana.com + names: + categories: + - agent-operator + kind: Integration + listKind: IntegrationList + plural: integrations + singular: integration + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + properties: + apiVersion: + type: string + kind: + type: string + metadata: + type: object + spec: + properties: + config: + type: object + x-kubernetes-preserve-unknown-fields: true + configMaps: + items: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: array + name: + type: string + secrets: + items: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: array + type: + properties: + allNodes: + type: boolean + unique: + type: boolean + type: object + volumeMounts: + items: + properties: + mountPath: + type: string + mountPropagation: + type: string + name: + type: string + readOnly: + type: boolean + subPath: + type: string + subPathExpr: + type: string + required: + - mountPath + - name + type: object + type: array + volumes: + items: + properties: + awsElasticBlockStore: + properties: + fsType: + type: string + partition: + format: int32 + type: integer + readOnly: + type: boolean + volumeID: + type: string + required: + - volumeID + type: object + azureDisk: + properties: + cachingMode: + type: string + diskName: + type: string + diskURI: + type: string + fsType: + type: string + kind: + type: string + readOnly: + type: boolean + required: + - diskName + - diskURI + type: object + azureFile: + properties: + readOnly: + type: boolean + secretName: + type: string + shareName: + type: string + required: + - secretName + - shareName + type: object + cephfs: + properties: + monitors: + items: + type: string + type: array + path: + type: string + readOnly: + type: boolean + secretFile: + type: string + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + user: + type: string + required: + - monitors + type: object + cinder: + properties: + fsType: + type: string + readOnly: + type: boolean + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + volumeID: + type: string + required: + - volumeID + type: object + configMap: + properties: + defaultMode: + format: int32 + type: integer + items: + items: + properties: + key: + type: string + mode: + format: int32 + type: integer + path: + type: string + required: + - key + - path + type: object + type: array + name: + type: string + optional: + type: boolean + type: object + x-kubernetes-map-type: atomic + csi: + properties: + driver: + type: string + fsType: + type: string + nodePublishSecretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + readOnly: + type: boolean + volumeAttributes: + additionalProperties: + type: string + type: object + required: + - driver + type: object + downwardAPI: + properties: + defaultMode: + format: int32 + type: integer + items: + items: + properties: + fieldRef: + properties: + apiVersion: + type: string + fieldPath: + type: string + required: + - fieldPath + type: object + x-kubernetes-map-type: atomic + mode: + format: int32 + type: integer + path: + type: string + resourceFieldRef: + properties: + containerName: + type: string + divisor: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + type: string + required: + - resource + type: object + x-kubernetes-map-type: atomic + required: + - path + type: object + type: array + type: object + emptyDir: + properties: + medium: + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + ephemeral: + properties: + volumeClaimTemplate: + properties: + metadata: + type: object + spec: + properties: + accessModes: + items: + type: string + type: array + dataSource: + properties: + apiGroup: + type: string + kind: + type: string + name: + type: string + required: + - kind + - name + type: object + x-kubernetes-map-type: atomic + dataSourceRef: + properties: + apiGroup: + type: string + kind: + type: string + name: + type: string + namespace: + type: string + required: + - kind + - name + type: object + resources: + properties: + claims: + items: + properties: + name: + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + type: object + selector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + storageClassName: + type: string + volumeMode: + type: string + volumeName: + type: string + type: object + required: + - spec + type: object + type: object + fc: + properties: + fsType: + type: string + lun: + format: int32 + type: integer + readOnly: + type: boolean + targetWWNs: + items: + type: string + type: array + wwids: + items: + type: string + type: array + type: object + flexVolume: + properties: + driver: + type: string + fsType: + type: string + options: + additionalProperties: + type: string + type: object + readOnly: + type: boolean + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + required: + - driver + type: object + flocker: + properties: + datasetName: + type: string + datasetUUID: + type: string + type: object + gcePersistentDisk: + properties: + fsType: + type: string + partition: + format: int32 + type: integer + pdName: + type: string + readOnly: + type: boolean + required: + - pdName + type: object + gitRepo: + properties: + directory: + type: string + repository: + type: string + revision: + type: string + required: + - repository + type: object + glusterfs: + properties: + endpoints: + type: string + path: + type: string + readOnly: + type: boolean + required: + - endpoints + - path + type: object + hostPath: + properties: + path: + type: string + type: + type: string + required: + - path + type: object + iscsi: + properties: + chapAuthDiscovery: + type: boolean + chapAuthSession: + type: boolean + fsType: + type: string + initiatorName: + type: string + iqn: + type: string + iscsiInterface: + type: string + lun: + format: int32 + type: integer + portals: + items: + type: string + type: array + readOnly: + type: boolean + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + targetPortal: + type: string + required: + - iqn + - lun + - targetPortal + type: object + name: + type: string + nfs: + properties: + path: + type: string + readOnly: + type: boolean + server: + type: string + required: + - path + - server + type: object + persistentVolumeClaim: + properties: + claimName: + type: string + readOnly: + type: boolean + required: + - claimName + type: object + photonPersistentDisk: + properties: + fsType: + type: string + pdID: + type: string + required: + - pdID + type: object + portworxVolume: + properties: + fsType: + type: string + readOnly: + type: boolean + volumeID: + type: string + required: + - volumeID + type: object + projected: + properties: + defaultMode: + format: int32 + type: integer + sources: + items: + properties: + configMap: + properties: + items: + items: + properties: + key: + type: string + mode: + format: int32 + type: integer + path: + type: string + required: + - key + - path + type: object + type: array + name: + type: string + optional: + type: boolean + type: object + x-kubernetes-map-type: atomic + downwardAPI: + properties: + items: + items: + properties: + fieldRef: + properties: + apiVersion: + type: string + fieldPath: + type: string + required: + - fieldPath + type: object + x-kubernetes-map-type: atomic + mode: + format: int32 + type: integer + path: + type: string + resourceFieldRef: + properties: + containerName: + type: string + divisor: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + type: string + required: + - resource + type: object + x-kubernetes-map-type: atomic + required: + - path + type: object + type: array + type: object + secret: + properties: + items: + items: + properties: + key: + type: string + mode: + format: int32 + type: integer + path: + type: string + required: + - key + - path + type: object + type: array + name: + type: string + optional: + type: boolean + type: object + x-kubernetes-map-type: atomic + serviceAccountToken: + properties: + audience: + type: string + expirationSeconds: + format: int64 + type: integer + path: + type: string + required: + - path + type: object + type: object + type: array + type: object + quobyte: + properties: + group: + type: string + readOnly: + type: boolean + registry: + type: string + tenant: + type: string + user: + type: string + volume: + type: string + required: + - registry + - volume + type: object + rbd: + properties: + fsType: + type: string + image: + type: string + keyring: + type: string + monitors: + items: + type: string + type: array + pool: + type: string + readOnly: + type: boolean + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + user: + type: string + required: + - image + - monitors + type: object + scaleIO: + properties: + fsType: + type: string + gateway: + type: string + protectionDomain: + type: string + readOnly: + type: boolean + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + sslEnabled: + type: boolean + storageMode: + type: string + storagePool: + type: string + system: + type: string + volumeName: + type: string + required: + - gateway + - secretRef + - system + type: object + secret: + properties: + defaultMode: + format: int32 + type: integer + items: + items: + properties: + key: + type: string + mode: + format: int32 + type: integer + path: + type: string + required: + - key + - path + type: object + type: array + optional: + type: boolean + secretName: + type: string + type: object + storageos: + properties: + fsType: + type: string + readOnly: + type: boolean + secretRef: + properties: + name: + type: string + type: object + x-kubernetes-map-type: atomic + volumeName: + type: string + volumeNamespace: + type: string + type: object + vsphereVolume: + properties: + fsType: + type: string + storagePolicyID: + type: string + storagePolicyName: + type: string + volumePath: + type: string + required: + - volumePath + type: object + required: + - name + type: object + type: array + required: + - config + - name + - type + type: object + type: object + served: true + storage: true diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_logsinstances.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_logsinstances.yaml new file mode 100644 index 0000000..517bb30 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_logsinstances.yaml @@ -0,0 +1,299 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.9.2 + creationTimestamp: null + name: logsinstances.monitoring.grafana.com +spec: + group: monitoring.grafana.com + names: + categories: + - agent-operator + kind: LogsInstance + listKind: LogsInstanceList + plural: logsinstances + singular: logsinstance + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + properties: + apiVersion: + type: string + kind: + type: string + metadata: + type: object + spec: + properties: + additionalScrapeConfigs: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + clients: + items: + properties: + backoffConfig: + properties: + maxPeriod: + type: string + maxRetries: + type: integer + minPeriod: + type: string + type: object + basicAuth: + properties: + password: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + batchSize: + type: integer + batchWait: + type: string + bearerToken: + type: string + bearerTokenFile: + type: string + externalLabels: + additionalProperties: + type: string + type: object + oauth2: + properties: + clientId: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + type: object + scopes: + items: + type: string + type: array + tokenUrl: + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyUrl: + type: string + tenantId: + type: string + timeout: + type: string + tlsConfig: + properties: + ca: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + caFile: + type: string + cert: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + certFile: + type: string + insecureSkipVerify: + type: boolean + keyFile: + type: string + keySecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + type: string + type: object + url: + type: string + required: + - url + type: object + type: array + podLogsNamespaceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + podLogsSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + targetConfig: + properties: + syncPeriod: + type: string + type: object + type: object + type: object + served: true + storage: true diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_metricsinstances.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_metricsinstances.yaml new file mode 100644 index 0000000..610193f --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_metricsinstances.yaml @@ -0,0 +1,495 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.9.2 + creationTimestamp: null + name: metricsinstances.monitoring.grafana.com +spec: + group: monitoring.grafana.com + names: + categories: + - agent-operator + kind: MetricsInstance + listKind: MetricsInstanceList + plural: metricsinstances + singular: metricsinstance + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + properties: + apiVersion: + type: string + kind: + type: string + metadata: + type: object + spec: + properties: + additionalScrapeConfigs: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + maxWALTime: + type: string + minWALTime: + type: string + podMonitorNamespaceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + podMonitorSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + probeNamespaceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + probeSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + remoteFlushDeadline: + type: string + remoteWrite: + items: + properties: + basicAuth: + properties: + password: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerToken: + type: string + bearerTokenFile: + type: string + headers: + additionalProperties: + type: string + type: object + metadataConfig: + properties: + send: + type: boolean + sendInterval: + type: string + type: object + name: + type: string + oauth2: + properties: + clientId: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + type: object + scopes: + items: + type: string + type: array + tokenUrl: + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyUrl: + type: string + queueConfig: + properties: + batchSendDeadline: + type: string + capacity: + type: integer + maxBackoff: + type: string + maxRetries: + type: integer + maxSamplesPerSend: + type: integer + maxShards: + type: integer + minBackoff: + type: string + minShards: + type: integer + retryOnRateLimit: + type: boolean + type: object + remoteTimeout: + type: string + sigv4: + properties: + accessKey: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + profile: + type: string + region: + type: string + roleARN: + type: string + secretKey: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + tlsConfig: + properties: + ca: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + caFile: + type: string + cert: + properties: + configMap: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + certFile: + type: string + insecureSkipVerify: + type: boolean + keyFile: + type: string + keySecret: + properties: + key: + type: string + name: + type: string + optional: + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + type: string + type: object + url: + type: string + writeRelabelConfigs: + items: + properties: + action: + default: replace + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + format: int64 + type: integer + regex: + type: string + replacement: + type: string + separator: + type: string + sourceLabels: + items: + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + type: string + type: object + type: array + required: + - url + type: object + type: array + serviceMonitorNamespaceSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + serviceMonitorSelector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + walTruncateFrequency: + type: string + writeStaleOnShutdown: + type: boolean + type: object + type: object + served: true + storage: true diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_podlogs.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_podlogs.yaml new file mode 100644 index 0000000..f22d051 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_podlogs.yaml @@ -0,0 +1,308 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.9.2 + creationTimestamp: null + name: podlogs.monitoring.grafana.com +spec: + group: monitoring.grafana.com + names: + categories: + - agent-operator + kind: PodLogs + listKind: PodLogsList + plural: podlogs + singular: podlogs + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + properties: + apiVersion: + type: string + kind: + type: string + metadata: + type: object + spec: + properties: + jobLabel: + type: string + namespaceSelector: + properties: + any: + type: boolean + matchNames: + items: + type: string + type: array + type: object + pipelineStages: + items: + properties: + cri: + type: object + docker: + type: object + drop: + properties: + dropCounterReason: + type: string + expression: + type: string + longerThan: + type: string + olderThan: + type: string + source: + type: string + value: + type: string + type: object + json: + properties: + expressions: + additionalProperties: + type: string + type: object + source: + type: string + type: object + labelAllow: + items: + type: string + type: array + labelDrop: + items: + type: string + type: array + labels: + additionalProperties: + type: string + type: object + limit: + properties: + burst: + type: integer + drop: + type: boolean + rate: + type: integer + type: object + match: + properties: + action: + type: string + dropCounterReason: + type: string + pipelineName: + type: string + selector: + type: string + stages: + type: string + required: + - selector + type: object + metrics: + additionalProperties: + properties: + action: + type: string + buckets: + items: + type: string + type: array + countEntryBytes: + type: boolean + description: + type: string + matchAll: + type: boolean + maxIdleDuration: + type: string + prefix: + type: string + source: + type: string + type: + type: string + value: + type: string + required: + - action + - type + type: object + type: object + multiline: + properties: + firstLine: + type: string + maxLines: + type: integer + maxWaitTime: + type: string + required: + - firstLine + type: object + output: + properties: + source: + type: string + required: + - source + type: object + pack: + properties: + ingestTimestamp: + type: boolean + labels: + items: + type: string + type: array + required: + - labels + type: object + regex: + properties: + expression: + type: string + source: + type: string + required: + - expression + type: object + replace: + properties: + expression: + type: string + replace: + type: string + source: + type: string + required: + - expression + type: object + template: + properties: + source: + type: string + template: + type: string + required: + - source + - template + type: object + tenant: + properties: + label: + type: string + source: + type: string + value: + type: string + type: object + timestamp: + properties: + actionOnFailure: + type: string + fallbackFormats: + items: + type: string + type: array + format: + type: string + location: + type: string + source: + type: string + required: + - format + - source + type: object + type: object + type: array + podTargetLabels: + items: + type: string + type: array + relabelings: + items: + properties: + action: + default: replace + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + format: int64 + type: integer + regex: + type: string + replacement: + type: string + separator: + type: string + sourceLabels: + items: + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + type: string + type: object + type: array + selector: + properties: + matchExpressions: + items: + properties: + key: + type: string + operator: + type: string + values: + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + type: object + type: object + x-kubernetes-map-type: atomic + required: + - selector + type: object + type: object + served: true + storage: true diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/_helpers.tpl b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/_helpers.tpl new file mode 100644 index 0000000..f464671 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/_helpers.tpl @@ -0,0 +1,67 @@ +{{/* +Expand the name of the chart. +*/}} +{{- define "ga-operator.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "ga-operator.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default .Chart.Name .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "ga-operator.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "ga-operator.labels" -}} +{{ include "ga-operator.selectorLabels" . }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +app.kubernetes.io/component: operator +helm.sh/chart: {{ include "ga-operator.chart" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +{{- if .Values.customLabels }} +{{ toYaml .Values.customLabels }} +{{- end }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "ga-operator.selectorLabels" -}} +app.kubernetes.io/name: {{ include "ga-operator.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Create the name of the service account to use +*/}} +{{- define "ga-operator.serviceAccountName" -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "ga-operator.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} + diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/operator-clusterrole.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/operator-clusterrole.yaml new file mode 100644 index 0000000..08ad58c --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/operator-clusterrole.yaml @@ -0,0 +1,62 @@ +{{- if .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ include "ga-operator.fullname" . }} + labels: +{{ include "ga-operator.labels" . | indent 4 }} +rules: +- apiGroups: [monitoring.grafana.com] + resources: + - grafanaagents + - metricsinstances + - logsinstances + - podlogs + - integrations + verbs: [get, list, watch] +- apiGroups: [monitoring.grafana.com] + resources: + - grafanaagents/finalizers + - metricsinstances/finalizers + - logsinstances/finalizers + - podlogs/finalizers + - integrations/finalizers + verbs: [get, list, watch, update] +- apiGroups: [monitoring.coreos.com] + resources: + - podmonitors + - probes + - servicemonitors + verbs: [get, list, watch] +- apiGroups: [monitoring.coreos.com] + resources: + - podmonitors/finalizers + - probes/finalizers + - servicemonitors/finalizers + verbs: [get, list, watch, update] +- apiGroups: [""] + resources: + - namespaces + - nodes + verbs: [get, list, watch] +- apiGroups: [""] + resources: + - secrets + - services + - configmaps + - endpoints + verbs: [get, list, watch, create, update, patch, delete] +- apiGroups: ["apps"] + resources: + - statefulsets + - daemonsets + - deployments + verbs: [get, list, watch, create, update, patch, delete] +{{- with .Values.rbac.podSecurityPolicyName }} +- apiGroups: [policy] + resources: + - podsecuritypolicies + verbs: [use] + resourceNames: [ {{ . }} ] +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/operator-clusterrolebinding.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/operator-clusterrolebinding.yaml new file mode 100644 index 0000000..372d310 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/operator-clusterrolebinding.yaml @@ -0,0 +1,17 @@ +{{- if .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "ga-operator.fullname" . }} + labels: +{{ include "ga-operator.labels" . | indent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "ga-operator.fullname" . }} +subjects: +- kind: ServiceAccount + name: {{ template "ga-operator.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} +{{- end -}} + diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/operator-deployment.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/operator-deployment.yaml new file mode 100644 index 0000000..e2c741e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/operator-deployment.yaml @@ -0,0 +1,78 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "ga-operator.fullname" . }} + labels: +{{ include "ga-operator.labels" . | indent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: 1 + selector: + matchLabels: +{{ include "ga-operator.selectorLabels" . | indent 6 }} + template: + metadata: + labels: +{{ include "ga-operator.selectorLabels" . | indent 8 }} +{{- with .Values.podLabels }} +{{- toYaml . | nindent 8 }} +{{- end }} +{{- with .Values.podAnnotations }} + annotations: +{{ toYaml . | indent 8 }} +{{- end }} + spec: + {{- with .Values.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + serviceAccountName: {{ template "ga-operator.serviceAccountName" . }} + {{- with .Values.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: {{ include "ga-operator.name" . }} + image: "{{ .Values.image.registry }}/{{ .Values.image.repository }}:{{ .Values.image.tag }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + {{- with .Values.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 10 }} + {{- end }} + {{- with .Values.resources }} + resources: + {{- toYaml . | nindent 10 }} + {{- end }} + {{- if or (and .Values.kubeletService.namespace .Values.kubeletService.serviceName) (.Values.extraArgs) }} + args: + {{- if and .Values.kubeletService.namespace .Values.kubeletService.serviceName }} + - --kubelet-service={{ .Values.kubeletService.namespace }}/{{ .Values.kubeletService.serviceName }} + {{- end }} + {{- if .Values.extraArgs }} + {{- range .Values.extraArgs }} + - {{ . }} + {{- end }} + {{- end }} + {{- end }} + {{- with .Values.image.pullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/operator-serviceaccount.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/operator-serviceaccount.yaml new file mode 100644 index 0000000..1f9b207 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/operator-serviceaccount.yaml @@ -0,0 +1,10 @@ +{{- if .Values.serviceAccount.create -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ template "ga-operator.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} + labels: +{{ include "ga-operator.labels" . | indent 4 }} +{{- end -}} + diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/tests/test-grafanaagent.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/tests/test-grafanaagent.yaml new file mode 100644 index 0000000..9e9d913 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/templates/tests/test-grafanaagent.yaml @@ -0,0 +1,118 @@ +apiVersion: monitoring.grafana.com/v1alpha1 +kind: GrafanaAgent +metadata: + name: grafana-agent-test + labels: + app: grafana-agent-test + annotations: + "helm.sh/hook": test + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded,hook-failed +spec: + image: "{{ .Values.image.registry }}/grafana/agent:{{ .Values.image.tag }}" + logLevel: info + serviceAccountName: grafana-agent-test-sa + metrics: + instanceSelector: + matchLabels: + agent: grafana-agent-test + +--- + +apiVersion: v1 +kind: ServiceAccount +metadata: + name: grafana-agent-test-sa + annotations: + "helm.sh/hook": test + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded,hook-failed + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: grafana-agent-test-cr + annotations: + "helm.sh/hook": test + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded,hook-failed +rules: +- apiGroups: + - "" + resources: + - nodes + - nodes/proxy + - nodes/metrics + - services + - endpoints + - pods + verbs: + - get + - list + - watch +- apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch +- nonResourceURLs: + - /metrics + - /metrics/cadvisor + verbs: + - get + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: grafana-agent-test-crb + annotations: + "helm.sh/hook": test + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded,hook-failed +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: grafana-agent-test-cr +subjects: +- kind: ServiceAccount + name: grafana-agent-test-sa + namespace: {{ .Release.Namespace }} + +--- + +apiVersion: monitoring.grafana.com/v1alpha1 +kind: MetricsInstance +metadata: + name: primary-test + annotations: + "helm.sh/hook": test + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded,hook-failed + labels: + agent: grafana-agent-test +spec: {} + +--- + +apiVersion: v1 +kind: Pod +metadata: + name: grafana-agent-test-probe + annotations: + "helm.sh/hook": test + "helm.sh/hook-weight": "1" + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded,hook-failed +spec: + containers: + - name: busybox + image: busybox + command: ['wget'] + args: ['grafana-agent-test-operated:8080/-/healthy'] + # Wait for GrafanaAgent CR + initContainers: + - name: sleep + image: busybox + command: ['sleep', '60'] + restartPolicy: Never diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/values.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/values.yaml new file mode 100644 index 0000000..57d3991 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/grafana-agent-operator/values.yaml @@ -0,0 +1,71 @@ +# -- Overrides the chart's name +nameOverride: "" + +# -- Overrides the chart's computed fullname +fullnameOverride: "" + +# -- Annotations for the Deployment +annotations: {} + +# -- Annotations for the Deployment Pods +podAnnotations: {} + +# -- Annotations for the Deployment Pods +podLabels: {} + +# -- Pod security context (runAsUser, etc.) +podSecurityContext: {} + +# -- Container security context (allowPrivilegeEscalation, etc.) +containerSecurityContext: {} + +rbac: + # -- Toggle to create ClusterRole and ClusterRoleBinding + create: true + # -- Name of a PodSecurityPolicy to use in the ClusterRole. If unset, no PodSecurityPolicy is used. + podSecurityPolicyName: '' + +serviceAccount: + # -- Toggle to create ServiceAccount + create: true + # -- Service account name + name: + +image: + # -- Image registry + registry: docker.io + # -- Image repo + repository: grafana/agent-operator + # -- Image tag + tag: v0.40.3 + # -- Image pull policy + pullPolicy: IfNotPresent + # -- Image pull secrets + pullSecrets: [] + +# -- hostAliases to add +hostAliases: [] +# - ip: 1.2.3.4 +# hostnames: +# - domain.tld + +# -- If both are set, Agent Operator will create and maintain a service for scraping kubelets +# https://grafana.com/docs/agent/latest/operator/getting-started/#monitor-kubelets +kubeletService: + namespace: default + serviceName: kubelet + +# -- List of additional cli arguments to configure agent-operator (example: `--log.level`) +extraArgs: [] + +# -- Resource limits and requests config +resources: {} + +# -- nodeSelector configuration +nodeSelector: {} + +# -- Tolerations applied to Pods +tolerations: [] + +# -- Pod affinity configuration +affinity: {} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/.helmignore b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/.helmignore new file mode 100644 index 0000000..a9fe727 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/.helmignore @@ -0,0 +1,23 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj +# OWNERS file for Kubernetes +OWNERS \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/Chart.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/Chart.yaml new file mode 100644 index 0000000..4d64a43 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/Chart.yaml @@ -0,0 +1,18 @@ +apiVersion: v1 +appVersion: RELEASE.2023-09-30T07-02-29Z +description: Multi-Cloud Object Storage +home: https://min.io +icon: https://min.io/resources/img/logo/MINIO_wordmark.png +keywords: +- minio +- storage +- object-storage +- s3 +- cluster +maintainers: +- email: dev@minio.io + name: MinIO, Inc +name: minio +sources: +- https://github.com/minio/minio +version: 5.0.14 diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/README.md b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/README.md new file mode 100644 index 0000000..8ee4de9 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/README.md @@ -0,0 +1,262 @@ +# MinIO Community Helm Chart + +[![Slack](https://slack.min.io/slack?type=svg)](https://slack.min.io) [![license](https://img.shields.io/badge/license-AGPL%20V3-blue)](https://github.com/minio/minio/blob/master/LICENSE) + +MinIO is a High Performance Object Storage released under GNU Affero General Public License v3.0. It is API compatible with Amazon S3 cloud storage service. Use MinIO to build high performance infrastructure for machine learning, analytics and application data workloads. + +| IMPORTANT | +| -------------------------- | +| This Helm chart is community built, maintained, and supported. MinIO does not guarantee support for any given bug, feature request, or update referencing this chart.

MinIO publishes a separate [MinIO Kubernetes Operator and Tenant Helm Chart](https://github.com/minio/operator/tree/master/helm) that is officially maintained and supported. MinIO strongly recommends using the MinIO Kubernetes Operator for production deployments. See [Deploy Operator With Helm](https://min.io/docs/minio/kubernetes/upstream/operations/install-deploy-manage/deploy-operator-helm.html?ref=github) for additional documentation. | + +## Introduction + +This chart bootstraps MinIO Cluster on [Kubernetes](http://kubernetes.io) using the [Helm](https://helm.sh) package manager. + +## Prerequisites + +- Helm cli with Kubernetes cluster configured. +- PV provisioner support in the underlying infrastructure. (We recommend using ) +- Use Kubernetes version v1.19 and later for best experience. + +## Configure MinIO Helm repo + +```bash +helm repo add minio https://charts.min.io/ +``` + +### Installing the Chart + +Install this chart using: + +```bash +helm install --namespace minio --set rootUser=rootuser,rootPassword=rootpass123 --generate-name minio/minio +``` + +The command deploys MinIO on the Kubernetes cluster in the default configuration. The [configuration](#configuration) section lists the parameters that can be configured during installation. + +### Installing the Chart (toy-setup) + +Minimal toy setup for testing purposes can be deployed using: + +```bash +helm install --set resources.requests.memory=512Mi --set replicas=1 --set persistence.enabled=false --set mode=standalone --set rootUser=rootuser,rootPassword=rootpass123 --generate-name minio/minio +``` + +### Upgrading the Chart + +You can use Helm to update MinIO version in a live release. Assuming your release is named as `my-release`, get the values using the command: + +```bash +helm get values my-release > old_values.yaml +``` + +Then change the field `image.tag` in `old_values.yaml` file with MinIO image tag you want to use. Now update the chart using + +```bash +helm upgrade -f old_values.yaml my-release minio/minio +``` + +Default upgrade strategies are specified in the `values.yaml` file. Update these fields if you'd like to use a different strategy. + +### Configuration + +Refer the [Values file](./values.yaml) for all the possible config fields. + +You can specify each parameter using the `--set key=value[,key=value]` argument to `helm install`. For example, + +```bash +helm install --name my-release --set persistence.size=1Ti minio/minio +``` + +The above command deploys MinIO server with a 1Ti backing persistent volume. + +Alternately, you can provide a YAML file that specifies parameter values while installing the chart. For example, + +```bash +helm install --name my-release -f values.yaml minio/minio +``` + +### Persistence + +This chart provisions a PersistentVolumeClaim and mounts corresponding persistent volume to default location `/export`. You'll need physical storage available in the Kubernetes cluster for this to work. If you'd rather use `emptyDir`, disable PersistentVolumeClaim by: + +```bash +helm install --set persistence.enabled=false minio/minio +``` + +> *"An emptyDir volume is first created when a Pod is assigned to a Node, and exists as long as that Pod is running on that node. When a Pod is removed from a node for any reason, the data in the emptyDir is deleted forever."* + +### Existing PersistentVolumeClaim + +If a Persistent Volume Claim already exists, specify it during installation. + +1. Create the PersistentVolume +2. Create the PersistentVolumeClaim +3. Install the chart + +```bash +helm install --set persistence.existingClaim=PVC_NAME minio/minio +``` + +### NetworkPolicy + +To enable network policy for MinIO, +install [a networking plugin that implements the Kubernetes +NetworkPolicy spec](https://kubernetes.io/docs/tasks/administer-cluster/declare-network-policy#before-you-begin), +and set `networkPolicy.enabled` to `true`. + +For Kubernetes v1.5 & v1.6, you must also turn on NetworkPolicy by setting +the DefaultDeny namespace annotation. Note: this will enforce policy for *all* pods in the namespace: + +``` +kubectl annotate namespace default "net.beta.kubernetes.io/network-policy={\"ingress\":{\"isolation\":\"DefaultDeny\"}}" +``` + +With NetworkPolicy enabled, traffic will be limited to just port 9000. + +For more precise policy, set `networkPolicy.allowExternal=true`. This will +only allow pods with the generated client label to connect to MinIO. +This label will be displayed in the output of a successful install. + +### Existing secret + +Instead of having this chart create the secret for you, you can supply a preexisting secret, much +like an existing PersistentVolumeClaim. + +First, create the secret: + +```bash +kubectl create secret generic my-minio-secret --from-literal=rootUser=foobarbaz --from-literal=rootPassword=foobarbazqux +``` + +Then install the chart, specifying that you want to use an existing secret: + +```bash +helm install --set existingSecret=my-minio-secret minio/minio +``` + +The following fields are expected in the secret: + +| .data.\ in Secret | Corresponding variable | Description | Required | +|:------------------------|:-----------------------|:---------------|:---------| +| `rootUser` | `rootUser` | Root user. | yes | +| `rootPassword` | `rootPassword` | Root password. | yes | + +All corresponding variables will be ignored in values file. + +### Configure TLS + +To enable TLS for MinIO containers, acquire TLS certificates from a CA or create self-signed certificates. While creating / acquiring certificates ensure the corresponding domain names are set as per the standard [DNS naming conventions](https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#pod-identity) in a Kubernetes StatefulSet (for a distributed MinIO setup). Then create a secret using + +```bash +kubectl create secret generic tls-ssl-minio --from-file=path/to/private.key --from-file=path/to/public.crt +``` + +Then install the chart, specifying that you want to use the TLS secret: + +```bash +helm install --set tls.enabled=true,tls.certSecret=tls-ssl-minio minio/minio +``` + +### Installing certificates from third party CAs + +MinIO can connect to other servers, including MinIO nodes or other server types such as NATs and Redis. If these servers use certificates that were not registered with a known CA, add trust for these certificates to MinIO Server by bundling these certificates into a Kubernetes secret and providing it to Helm via the `trustedCertsSecret` value. If `.Values.tls.enabled` is `true` and you're installing certificates for third party CAs, remember to include MinIO's own certificate with key `public.crt`, if it also needs to be trusted. + +For instance, given that TLS is enabled and you need to add trust for MinIO's own CA and for the CA of a Keycloak server, a Kubernetes secret can be created from the certificate files using `kubectl`: + +``` +kubectl -n minio create secret generic minio-trusted-certs --from-file=public.crt --from-file=keycloak.crt +``` + +If TLS is not enabled, you would need only the third party CA: + +``` +kubectl -n minio create secret generic minio-trusted-certs --from-file=keycloak.crt +``` + +The name of the generated secret can then be passed to Helm using a values file or the `--set` parameter: + +``` +trustedCertsSecret: "minio-trusted-certs" + +or + +--set trustedCertsSecret=minio-trusted-certs +``` + +### Create buckets after install + +Install the chart, specifying the buckets you want to create after install: + +```bash +helm install --set buckets[0].name=bucket1,buckets[0].policy=none,buckets[0].purge=false minio/minio +``` + +Description of the configuration parameters used above - + +- `buckets[].name` - name of the bucket to create, must be a string with length > 0 +- `buckets[].policy` - can be one of none|download|upload|public +- `buckets[].purge` - purge if bucket exists already + +### Create policies after install + +Install the chart, specifying the policies you want to create after install: + +```bash +helm install --set policies[0].name=mypolicy,policies[0].statements[0].resources[0]='arn:aws:s3:::bucket1',policies[0].statements[0].actions[0]='s3:ListBucket',policies[0].statements[0].actions[1]='s3:GetObject' minio/minio +``` + +Description of the configuration parameters used above - + +- `policies[].name` - name of the policy to create, must be a string with length > 0 +- `policies[].statements[]` - list of statements, includes actions and resources +- `policies[].statements[].resources[]` - list of resources that applies the statement +- `policies[].statements[].actions[]` - list of actions granted + +### Create user after install + +Install the chart, specifying the users you want to create after install: + +```bash +helm install --set users[0].accessKey=accessKey,users[0].secretKey=secretKey,users[0].policy=none,users[1].accessKey=accessKey2,users[1].secretRef=existingSecret,users[1].secretKey=password,users[1].policy=none minio/minio +``` + +Description of the configuration parameters used above - + +- `users[].accessKey` - accessKey of user +- `users[].secretKey` - secretKey of usersecretRef +- `users[].existingSecret` - secret name that contains the secretKey of user +- `users[].existingSecretKey` - data key in existingSecret secret containing the secretKey +- `users[].policy` - name of the policy to assign to user + +### Create service account after install + +Install the chart, specifying the service accounts you want to create after install: + +```bash +helm install --set svcaccts[0].accessKey=accessKey,svcaccts[0].secretKey=secretKey,svcaccts[0].user=parentUser,svcaccts[1].accessKey=accessKey2,svcaccts[1].secretRef=existingSecret,svcaccts[1].secretKey=password,svcaccts[1].user=parentUser2 minio/minio +``` + +Description of the configuration parameters used above - + +- `svcaccts[].accessKey` - accessKey of service account +- `svcaccts[].secretKey` - secretKey of svcacctsecretRef +- `svcaccts[].existingSecret` - secret name that contains the secretKey of service account +- `svcaccts[].existingSecretKey` - data key in existingSecret secret containing the secretKey +- `svcaccts[].user` - name of the parent user to assign to service account + +## Uninstalling the Chart + +Assuming your release is named as `my-release`, delete it using the command: + +```bash +helm delete my-release +``` + +or + +```bash +helm uninstall my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/NOTES.txt b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/NOTES.txt new file mode 100644 index 0000000..7051b1e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/NOTES.txt @@ -0,0 +1,43 @@ +{{- if eq .Values.service.type "ClusterIP" "NodePort" }} +MinIO can be accessed via port {{ .Values.service.port }} on the following DNS name from within your cluster: +{{ template "minio.fullname" . }}.{{ .Release.Namespace }}.svc.cluster.local + +To access MinIO from localhost, run the below commands: + + 1. export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "release={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") + + 2. kubectl port-forward $POD_NAME 9000 --namespace {{ .Release.Namespace }} + +Read more about port forwarding here: http://kubernetes.io/docs/user-guide/kubectl/kubectl_port-forward/ + +You can now access MinIO server on http://localhost:9000. Follow the below steps to connect to MinIO server with mc client: + + 1. Download the MinIO mc client - https://min.io/docs/minio/linux/reference/minio-mc.html#quickstart + + 2. export MC_HOST_{{ template "minio.fullname" . }}-local=http://$(kubectl get secret --namespace {{ .Release.Namespace }} {{ template "minio.secretName" . }} -o jsonpath="{.data.rootUser}" | base64 --decode):$(kubectl get secret --namespace {{ .Release.Namespace }} {{ template "minio.secretName" . }} -o jsonpath="{.data.rootPassword}" | base64 --decode)@localhost:{{ .Values.service.port }} + + 3. mc ls {{ template "minio.fullname" . }}-local + +{{- end }} +{{- if eq .Values.service.type "LoadBalancer" }} +MinIO can be accessed via port {{ .Values.service.port }} on an external IP address. Get the service external IP address by: +kubectl get svc --namespace {{ .Release.Namespace }} -l app={{ template "minio.fullname" . }} + +Note that the public IP may take a couple of minutes to be available. + +You can now access MinIO server on http://:9000. Follow the below steps to connect to MinIO server with mc client: + + 1. Download the MinIO mc client - https://min.io/docs/minio/linux/reference/minio-mc.html#quickstart + + 2. export MC_HOST_{{ template "minio.fullname" . }}-local=http://$(kubectl get secret {{ template "minio.secretName" . }} --namespace {{ .Release.Namespace }} -o jsonpath="{.data.rootUser}" | base64 --decode):$(kubectl get secret {{ template "minio.secretName" . }} -o jsonpath="{.data.rootPassword}" | base64 --decode)@:{{ .Values.service.port }} + + 3. mc ls {{ template "minio.fullname" . }} + +Alternately, you can use your browser or the MinIO SDK to access the server - https://min.io/docs/minio/linux/reference/minio-server/minio-server.html +{{- end }} + +{{ if and (.Values.networkPolicy.enabled) (not .Values.networkPolicy.allowExternal) }} +Note: Since NetworkPolicy is enabled, only pods with label +{{ template "minio.fullname" . }}-client=true" +will be able to connect to this minio cluster. +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_create_bucket.txt b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_create_bucket.txt new file mode 100644 index 0000000..98d9ead --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_create_bucket.txt @@ -0,0 +1,123 @@ +#!/bin/sh +set -e ; # Have script exit in the event of a failed command. + +{{- if .Values.configPathmc }} +MC_CONFIG_DIR="{{ .Values.configPathmc }}" +MC="/usr/bin/mc --insecure --config-dir ${MC_CONFIG_DIR}" +{{- else }} +MC="/usr/bin/mc --insecure" +{{- end }} + +# connectToMinio +# Use a check-sleep-check loop to wait for MinIO service to be available +connectToMinio() { + SCHEME=$1 + ATTEMPTS=0 ; LIMIT=29 ; # Allow 30 attempts + set -e ; # fail if we can't read the keys. + ACCESS=$(cat /config/rootUser) ; SECRET=$(cat /config/rootPassword) ; + set +e ; # The connections to minio are allowed to fail. + echo "Connecting to MinIO server: $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT" ; + MC_COMMAND="${MC} alias set myminio $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT $ACCESS $SECRET" ; + $MC_COMMAND ; + STATUS=$? ; + until [ $STATUS = 0 ] + do + ATTEMPTS=`expr $ATTEMPTS + 1` ; + echo \"Failed attempts: $ATTEMPTS\" ; + if [ $ATTEMPTS -gt $LIMIT ]; then + exit 1 ; + fi ; + sleep 2 ; # 1 second intervals between attempts + $MC_COMMAND ; + STATUS=$? ; + done ; + set -e ; # reset `e` as active + return 0 +} + +# checkBucketExists ($bucket) +# Check if the bucket exists, by using the exit code of `mc ls` +checkBucketExists() { + BUCKET=$1 + CMD=$(${MC} stat myminio/$BUCKET > /dev/null 2>&1) + return $? +} + +# createBucket ($bucket, $policy, $purge) +# Ensure bucket exists, purging if asked to +createBucket() { + BUCKET=$1 + POLICY=$2 + PURGE=$3 + VERSIONING=$4 + OBJECTLOCKING=$5 + + # Purge the bucket, if set & exists + # Since PURGE is user input, check explicitly for `true` + if [ $PURGE = true ]; then + if checkBucketExists $BUCKET ; then + echo "Purging bucket '$BUCKET'." + set +e ; # don't exit if this fails + ${MC} rm -r --force myminio/$BUCKET + set -e ; # reset `e` as active + else + echo "Bucket '$BUCKET' does not exist, skipping purge." + fi + fi + +# Create the bucket if it does not exist and set objectlocking if enabled (NOTE: versioning will be not changed if OBJECTLOCKING is set because it enables versioning to the Buckets created) +if ! checkBucketExists $BUCKET ; then + if [ ! -z $OBJECTLOCKING ] ; then + if [ $OBJECTLOCKING = true ] ; then + echo "Creating bucket with OBJECTLOCKING '$BUCKET'" + ${MC} mb --with-lock myminio/$BUCKET + elif [ $OBJECTLOCKING = false ] ; then + echo "Creating bucket '$BUCKET'" + ${MC} mb myminio/$BUCKET + fi + elif [ -z $OBJECTLOCKING ] ; then + echo "Creating bucket '$BUCKET'" + ${MC} mb myminio/$BUCKET + else + echo "Bucket '$BUCKET' already exists." + fi + fi + + + # set versioning for bucket if objectlocking is disabled or not set + if [ $OBJECTLOCKING = false ] ; then + if [ ! -z $VERSIONING ] ; then + if [ $VERSIONING = true ] ; then + echo "Enabling versioning for '$BUCKET'" + ${MC} version enable myminio/$BUCKET + elif [ $VERSIONING = false ] ; then + echo "Suspending versioning for '$BUCKET'" + ${MC} version suspend myminio/$BUCKET + fi + fi + else + echo "Bucket '$BUCKET' versioning unchanged." + fi + + + # At this point, the bucket should exist, skip checking for existence + # Set policy on the bucket + echo "Setting policy of bucket '$BUCKET' to '$POLICY'." + ${MC} anonymous set $POLICY myminio/$BUCKET +} + +# Try connecting to MinIO instance +{{- if .Values.tls.enabled }} +scheme=https +{{- else }} +scheme=http +{{- end }} +connectToMinio $scheme + +{{ if .Values.buckets }} +{{ $global := . }} +# Create the buckets +{{- range .Values.buckets }} +createBucket {{ tpl .name $global }} {{ .policy | default "none" | quote }} {{ .purge | default false }} {{ .versioning | default false }} {{ .objectlocking | default false }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_create_policy.txt b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_create_policy.txt new file mode 100644 index 0000000..aa58495 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_create_policy.txt @@ -0,0 +1,75 @@ +#!/bin/sh +set -e ; # Have script exit in the event of a failed command. + +{{- if .Values.configPathmc }} +MC_CONFIG_DIR="{{ .Values.configPathmc }}" +MC="/usr/bin/mc --insecure --config-dir ${MC_CONFIG_DIR}" +{{- else }} +MC="/usr/bin/mc --insecure" +{{- end }} + +# connectToMinio +# Use a check-sleep-check loop to wait for MinIO service to be available +connectToMinio() { + SCHEME=$1 + ATTEMPTS=0 ; LIMIT=29 ; # Allow 30 attempts + set -e ; # fail if we can't read the keys. + ACCESS=$(cat /config/rootUser) ; SECRET=$(cat /config/rootPassword) ; + set +e ; # The connections to minio are allowed to fail. + echo "Connecting to MinIO server: $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT" ; + MC_COMMAND="${MC} alias set myminio $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT $ACCESS $SECRET" ; + $MC_COMMAND ; + STATUS=$? ; + until [ $STATUS = 0 ] + do + ATTEMPTS=`expr $ATTEMPTS + 1` ; + echo \"Failed attempts: $ATTEMPTS\" ; + if [ $ATTEMPTS -gt $LIMIT ]; then + exit 1 ; + fi ; + sleep 2 ; # 1 second intervals between attempts + $MC_COMMAND ; + STATUS=$? ; + done ; + set -e ; # reset `e` as active + return 0 +} + +# checkPolicyExists ($policy) +# Check if the policy exists, by using the exit code of `mc admin policy info` +checkPolicyExists() { + POLICY=$1 + CMD=$(${MC} admin policy info myminio $POLICY > /dev/null 2>&1) + return $? +} + +# createPolicy($name, $filename) +createPolicy () { + NAME=$1 + FILENAME=$2 + + # Create the name if it does not exist + echo "Checking policy: $NAME (in /config/$FILENAME.json)" + if ! checkPolicyExists $NAME ; then + echo "Creating policy '$NAME'" + else + echo "Policy '$NAME' already exists." + fi + ${MC} admin policy create myminio $NAME /config/$FILENAME.json + +} + +# Try connecting to MinIO instance +{{- if .Values.tls.enabled }} +scheme=https +{{- else }} +scheme=http +{{- end }} +connectToMinio $scheme + +{{ if .Values.policies }} +# Create the policies +{{- range $idx, $policy := .Values.policies }} +createPolicy {{ $policy.name }} policy_{{ $idx }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_create_svcacct.txt b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_create_svcacct.txt new file mode 100644 index 0000000..59f51b1 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_create_svcacct.txt @@ -0,0 +1,106 @@ +#!/bin/sh +set -e ; # Have script exit in the event of a failed command. + +{{- if .Values.configPathmc }} +MC_CONFIG_DIR="{{ .Values.configPathmc }}" +MC="/usr/bin/mc --insecure --config-dir ${MC_CONFIG_DIR}" +{{- else }} +MC="/usr/bin/mc --insecure" +{{- end }} + +# AccessKey and secretkey credentials file are added to prevent shell execution errors caused by special characters. +# Special characters for example : ',",<,>,{,} +MINIO_ACCESSKEY_SECRETKEY_TMP="/tmp/accessKey_and_secretKey_svcacct_tmp" + +# connectToMinio +# Use a check-sleep-check loop to wait for MinIO service to be available +connectToMinio() { + SCHEME=$1 + ATTEMPTS=0 ; LIMIT=29 ; # Allow 30 attempts + set -e ; # fail if we can't read the keys. + ACCESS=$(cat /config/rootUser) ; SECRET=$(cat /config/rootPassword) ; + set +e ; # The connections to minio are allowed to fail. + echo "Connecting to MinIO server: $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT" ; + MC_COMMAND="${MC} alias set myminio $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT $ACCESS $SECRET" ; + $MC_COMMAND ; + STATUS=$? ; + until [ $STATUS = 0 ] + do + ATTEMPTS=`expr $ATTEMPTS + 1` ; + echo \"Failed attempts: $ATTEMPTS\" ; + if [ $ATTEMPTS -gt $LIMIT ]; then + exit 1 ; + fi ; + sleep 2 ; # 2 second intervals between attempts + $MC_COMMAND ; + STATUS=$? ; + done ; + set -e ; # reset `e` as active + return 0 +} + +# checkSvcacctExists () +# Check if the svcacct exists, by using the exit code of `mc admin user svcacct info` +checkSvcacctExists() { + CMD=$(${MC} admin user svcacct info myminio $(head -1 $MINIO_ACCESSKEY_SECRETKEY_TMP) > /dev/null 2>&1) + return $? +} + +# createSvcacct ($user) +createSvcacct () { + USER=$1 + FILENAME=$2 + #check accessKey_and_secretKey_tmp file + if [[ ! -f $MINIO_ACCESSKEY_SECRETKEY_TMP ]];then + echo "credentials file does not exist" + return 1 + fi + if [[ $(cat $MINIO_ACCESSKEY_SECRETKEY_TMP|wc -l) -ne 2 ]];then + echo "credentials file is invalid" + rm -f $MINIO_ACCESSKEY_SECRETKEY_TMP + return 1 + fi + SVCACCT=$(head -1 $MINIO_ACCESSKEY_SECRETKEY_TMP) + # Create the svcacct if it does not exist + if ! checkSvcacctExists ; then + echo "Creating svcacct '$SVCACCT'" + # Check if policy file is define + if [ -z $FILENAME ]; then + ${MC} admin user svcacct add --access-key $(head -1 $MINIO_ACCESSKEY_SECRETKEY_TMP) --secret-key $(tail -n1 $MINIO_ACCESSKEY_SECRETKEY_TMP) myminio $USER + else + ${MC} admin user svcacct add --access-key $(head -1 $MINIO_ACCESSKEY_SECRETKEY_TMP) --secret-key $(tail -n1 $MINIO_ACCESSKEY_SECRETKEY_TMP) --policy /config/$FILENAME.json myminio $USER + fi + else + echo "Svcacct '$SVCACCT' already exists." + fi + #clean up credentials files. + rm -f $MINIO_ACCESSKEY_SECRETKEY_TMP +} + +# Try connecting to MinIO instance +{{- if .Values.tls.enabled }} +scheme=https +{{- else }} +scheme=http +{{- end }} +connectToMinio $scheme + +{{ if .Values.svcaccts }} +{{ $global := . }} +# Create the svcaccts +{{- range $idx, $svc := .Values.svcaccts }} +echo {{ tpl .accessKey $global }} > $MINIO_ACCESSKEY_SECRETKEY_TMP +{{- if .existingSecret }} +cat /config/secrets-svc/{{ tpl .existingSecret $global }}/{{ tpl .existingSecretKey $global }} >> $MINIO_ACCESSKEY_SECRETKEY_TMP +# Add a new line if it doesn't exist +sed -i '$a\' $MINIO_ACCESSKEY_SECRETKEY_TMP +{{ else }} +echo {{ .secretKey }} >> $MINIO_ACCESSKEY_SECRETKEY_TMP +{{- end }} +{{- if $svc.policy}} +createSvcacct {{ .user }} svc_policy_{{ $idx }} +{{ else }} +createSvcacct {{ .user }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_create_user.txt b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_create_user.txt new file mode 100644 index 0000000..9f2c6a4 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_create_user.txt @@ -0,0 +1,107 @@ +#!/bin/sh +set -e ; # Have script exit in the event of a failed command. + +{{- if .Values.configPathmc }} +MC_CONFIG_DIR="{{ .Values.configPathmc }}" +MC="/usr/bin/mc --insecure --config-dir ${MC_CONFIG_DIR}" +{{- else }} +MC="/usr/bin/mc --insecure" +{{- end }} + +# AccessKey and secretkey credentials file are added to prevent shell execution errors caused by special characters. +# Special characters for example : ',",<,>,{,} +MINIO_ACCESSKEY_SECRETKEY_TMP="/tmp/accessKey_and_secretKey_tmp" + +# connectToMinio +# Use a check-sleep-check loop to wait for MinIO service to be available +connectToMinio() { + SCHEME=$1 + ATTEMPTS=0 ; LIMIT=29 ; # Allow 30 attempts + set -e ; # fail if we can't read the keys. + ACCESS=$(cat /config/rootUser) ; SECRET=$(cat /config/rootPassword) ; + set +e ; # The connections to minio are allowed to fail. + echo "Connecting to MinIO server: $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT" ; + MC_COMMAND="${MC} alias set myminio $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT $ACCESS $SECRET" ; + $MC_COMMAND ; + STATUS=$? ; + until [ $STATUS = 0 ] + do + ATTEMPTS=`expr $ATTEMPTS + 1` ; + echo \"Failed attempts: $ATTEMPTS\" ; + if [ $ATTEMPTS -gt $LIMIT ]; then + exit 1 ; + fi ; + sleep 2 ; # 1 second intervals between attempts + $MC_COMMAND ; + STATUS=$? ; + done ; + set -e ; # reset `e` as active + return 0 +} + +# checkUserExists () +# Check if the user exists, by using the exit code of `mc admin user info` +checkUserExists() { + CMD=$(${MC} admin user info myminio $(head -1 $MINIO_ACCESSKEY_SECRETKEY_TMP) > /dev/null 2>&1) + return $? +} + +# createUser ($policy) +createUser() { + POLICY=$1 + #check accessKey_and_secretKey_tmp file + if [[ ! -f $MINIO_ACCESSKEY_SECRETKEY_TMP ]];then + echo "credentials file does not exist" + return 1 + fi + if [[ $(cat $MINIO_ACCESSKEY_SECRETKEY_TMP|wc -l) -ne 2 ]];then + echo "credentials file is invalid" + rm -f $MINIO_ACCESSKEY_SECRETKEY_TMP + return 1 + fi + USER=$(head -1 $MINIO_ACCESSKEY_SECRETKEY_TMP) + # Create the user if it does not exist + if ! checkUserExists ; then + echo "Creating user '$USER'" + cat $MINIO_ACCESSKEY_SECRETKEY_TMP | ${MC} admin user add myminio + else + echo "User '$USER' already exists." + fi + #clean up credentials files. + rm -f $MINIO_ACCESSKEY_SECRETKEY_TMP + + # set policy for user + if [ ! -z $POLICY -a $POLICY != " " ] ; then + echo "Adding policy '$POLICY' for '$USER'" + set +e ; # policy already attach errors out, allow it. + ${MC} admin policy attach myminio $POLICY --user=$USER + set -e + else + echo "User '$USER' has no policy attached." + fi +} + +# Try connecting to MinIO instance +{{- if .Values.tls.enabled }} +scheme=https +{{- else }} +scheme=http +{{- end }} +connectToMinio $scheme + +{{ if .Values.users }} +{{ $global := . }} +# Create the users +{{- range .Values.users }} +echo {{ tpl .accessKey $global }} > $MINIO_ACCESSKEY_SECRETKEY_TMP +{{- if .existingSecret }} +cat /config/secrets/{{ tpl .existingSecret $global }}/{{ tpl .existingSecretKey $global }} >> $MINIO_ACCESSKEY_SECRETKEY_TMP +# Add a new line if it doesn't exist +sed -i '$a\' $MINIO_ACCESSKEY_SECRETKEY_TMP +createUser {{ .policy }} +{{ else }} +echo {{ .secretKey }} >> $MINIO_ACCESSKEY_SECRETKEY_TMP +createUser {{ .policy }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_custom_command.txt b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_custom_command.txt new file mode 100644 index 0000000..b583a77 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_custom_command.txt @@ -0,0 +1,58 @@ +#!/bin/sh +set -e ; # Have script exit in the event of a failed command. + +{{- if .Values.configPathmc }} +MC_CONFIG_DIR="{{ .Values.configPathmc }}" +MC="/usr/bin/mc --insecure --config-dir ${MC_CONFIG_DIR}" +{{- else }} +MC="/usr/bin/mc --insecure" +{{- end }} + +# connectToMinio +# Use a check-sleep-check loop to wait for MinIO service to be available +connectToMinio() { + SCHEME=$1 + ATTEMPTS=0 ; LIMIT=29 ; # Allow 30 attempts + set -e ; # fail if we can't read the keys. + ACCESS=$(cat /config/rootUser) ; SECRET=$(cat /config/rootPassword) ; + set +e ; # The connections to minio are allowed to fail. + echo "Connecting to MinIO server: $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT" ; + MC_COMMAND="${MC} alias set myminio $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT $ACCESS $SECRET" ; + $MC_COMMAND ; + STATUS=$? ; + until [ $STATUS = 0 ] + do + ATTEMPTS=`expr $ATTEMPTS + 1` ; + echo \"Failed attempts: $ATTEMPTS\" ; + if [ $ATTEMPTS -gt $LIMIT ]; then + exit 1 ; + fi ; + sleep 2 ; # 1 second intervals between attempts + $MC_COMMAND ; + STATUS=$? ; + done ; + set -e ; # reset `e` as active + return 0 +} + +# runCommand ($@) +# Run custom mc command +runCommand() { + ${MC} "$@" + return $? +} + +# Try connecting to MinIO instance +{{- if .Values.tls.enabled }} +scheme=https +{{- else }} +scheme=http +{{- end }} +connectToMinio $scheme + +{{ if .Values.customCommands }} +# Run custom commands +{{- range .Values.customCommands }} +runCommand {{ .command }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_policy.tpl b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_policy.tpl new file mode 100644 index 0000000..8be998e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helper_policy.tpl @@ -0,0 +1,28 @@ +{{- $statements_length := len .statements -}} +{{- $statements_length := sub $statements_length 1 -}} +{ + "Version": "2012-10-17", + "Statement": [ +{{- range $i, $statement := .statements }} + { + "Effect": "{{ $statement.effect | default "Allow" }}", + "Action": [ +"{{ $statement.actions | join "\",\n\"" }}" + ]{{ if $statement.resources }}, + "Resource": [ +"{{ $statement.resources | join "\",\n\"" }}" + ]{{ end }} +{{- if $statement.conditions }} +{{- $condition_len := len $statement.conditions }} +{{- $condition_len := sub $condition_len 1 }} + , + "Condition": { + {{- range $k,$v := $statement.conditions }} + {{- range $operator,$object := $v }} + "{{ $operator }}": { {{ $object }} }{{- if lt $k $condition_len }},{{- end }} + {{- end }}{{- end }} + }{{- end }} + }{{ if lt $i $statements_length }},{{end }} +{{- end }} + ] +} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helpers.tpl b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helpers.tpl new file mode 100644 index 0000000..1cb209e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/_helpers.tpl @@ -0,0 +1,218 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "minio.name" -}} + {{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "minio.fullname" -}} + {{- if .Values.fullnameOverride -}} + {{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} + {{- else -}} + {{- $name := default .Chart.Name .Values.nameOverride -}} + {{- if contains $name .Release.Name -}} + {{- .Release.Name | trunc 63 | trimSuffix "-" -}} + {{- else -}} + {{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} + {{- end -}} + {{- end -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "minio.chart" -}} + {{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for networkpolicy. +*/}} +{{- define "minio.networkPolicy.apiVersion" -}} + {{- if semverCompare ">=1.4-0, <1.7-0" .Capabilities.KubeVersion.Version -}} + {{- print "extensions/v1beta1" -}} + {{- else if semverCompare ">=1.7-0, <1.16-0" .Capabilities.KubeVersion.Version -}} + {{- print "networking.k8s.io/v1beta1" -}} + {{- else if semverCompare "^1.16-0" .Capabilities.KubeVersion.Version -}} + {{- print "networking.k8s.io/v1" -}} + {{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for deployment. +*/}} +{{- define "minio.deployment.apiVersion" -}} + {{- if semverCompare "<1.9-0" .Capabilities.KubeVersion.Version -}} + {{- print "apps/v1beta2" -}} + {{- else -}} + {{- print "apps/v1" -}} + {{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for statefulset. +*/}} +{{- define "minio.statefulset.apiVersion" -}} + {{- if semverCompare "<1.16-0" .Capabilities.KubeVersion.Version -}} + {{- print "apps/v1beta2" -}} + {{- else -}} + {{- print "apps/v1" -}} + {{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "minio.ingress.apiVersion" -}} + {{- if semverCompare "<1.14-0" .Capabilities.KubeVersion.GitVersion -}} + {{- print "extensions/v1beta1" -}} + {{- else if semverCompare "<1.19-0" .Capabilities.KubeVersion.GitVersion -}} + {{- print "networking.k8s.io/v1beta1" -}} + {{- else -}} + {{- print "networking.k8s.io/v1" -}} + {{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for console ingress. +*/}} +{{- define "minio.consoleIngress.apiVersion" -}} + {{- if semverCompare "<1.14-0" .Capabilities.KubeVersion.GitVersion -}} + {{- print "extensions/v1beta1" -}} + {{- else if semverCompare "<1.19-0" .Capabilities.KubeVersion.GitVersion -}} + {{- print "networking.k8s.io/v1beta1" -}} + {{- else -}} + {{- print "networking.k8s.io/v1" -}} + {{- end -}} +{{- end -}} + +{{/* +Determine secret name. +*/}} +{{- define "minio.secretName" -}} + {{- if .Values.existingSecret -}} + {{- .Values.existingSecret }} + {{- else -}} + {{- include "minio.fullname" . -}} + {{- end -}} +{{- end -}} + +{{/* +Determine name for scc role and rolebinding +*/}} +{{- define "minio.sccRoleName" -}} + {{- printf "%s-%s" "scc" (include "minio.fullname" .) | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Properly format optional additional arguments to MinIO binary +*/}} +{{- define "minio.extraArgs" -}} +{{- range .Values.extraArgs -}} +{{ " " }}{{ . }} +{{- end -}} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names +*/}} +{{- define "minio.imagePullSecrets" -}} +{{/* +Helm 2.11 supports the assignment of a value to a variable defined in a different scope, +but Helm 2.9 and 2.10 does not support it, so we need to implement this if-else logic. +Also, we can not use a single if because lazy evaluation is not an option +*/}} +{{- if .Values.global }} +{{- if .Values.global.imagePullSecrets }} +imagePullSecrets: +{{- range .Values.global.imagePullSecrets }} + - name: {{ . }} +{{- end }} +{{- else if .Values.imagePullSecrets }} +imagePullSecrets: + {{ toYaml .Values.imagePullSecrets }} +{{- end -}} +{{- else if .Values.imagePullSecrets }} +imagePullSecrets: + {{ toYaml .Values.imagePullSecrets }} +{{- end -}} +{{- end -}} + +{{/* +Formats volumeMount for MinIO TLS keys and trusted certs +*/}} +{{- define "minio.tlsKeysVolumeMount" -}} +{{- if .Values.tls.enabled }} +- name: cert-secret-volume + mountPath: {{ .Values.certsPath }} +{{- end }} +{{- if or .Values.tls.enabled (ne .Values.trustedCertsSecret "") }} +{{- $casPath := printf "%s/CAs" .Values.certsPath | clean }} +- name: trusted-cert-secret-volume + mountPath: {{ $casPath }} +{{- end }} +{{- end -}} + +{{/* +Formats volume for MinIO TLS keys and trusted certs +*/}} +{{- define "minio.tlsKeysVolume" -}} +{{- if .Values.tls.enabled }} +- name: cert-secret-volume + secret: + secretName: {{ tpl .Values.tls.certSecret $ }} + items: + - key: {{ .Values.tls.publicCrt }} + path: public.crt + - key: {{ .Values.tls.privateKey }} + path: private.key +{{- end }} +{{- if or .Values.tls.enabled (ne .Values.trustedCertsSecret "") }} +{{- $certSecret := eq .Values.trustedCertsSecret "" | ternary .Values.tls.certSecret .Values.trustedCertsSecret }} +{{- $publicCrt := eq .Values.trustedCertsSecret "" | ternary .Values.tls.publicCrt "" }} +- name: trusted-cert-secret-volume + secret: + secretName: {{ $certSecret }} + {{- if ne $publicCrt "" }} + items: + - key: {{ $publicCrt }} + path: public.crt + {{- end }} +{{- end }} +{{- end -}} + +{{/* +Returns the available value for certain key in an existing secret (if it exists), +otherwise it generates a random value. +*/}} +{{- define "minio.getValueFromSecret" }} + {{- $len := (default 16 .Length) | int -}} + {{- $obj := (lookup "v1" "Secret" .Namespace .Name).data -}} + {{- if $obj }} + {{- index $obj .Key | b64dec -}} + {{- else -}} + {{- randAlphaNum $len -}} + {{- end -}} +{{- end }} + +{{- define "minio.root.username" -}} + {{- if .Values.rootUser }} + {{- .Values.rootUser | toString }} + {{- else }} + {{- include "minio.getValueFromSecret" (dict "Namespace" .Release.Namespace "Name" (include "minio.fullname" .) "Length" 20 "Key" "rootUser") }} + {{- end }} +{{- end -}} + +{{- define "minio.root.password" -}} + {{- if .Values.rootPassword }} + {{- .Values.rootPassword | toString }} + {{- else }} + {{- include "minio.getValueFromSecret" (dict "Namespace" .Release.Namespace "Name" (include "minio.fullname" .) "Length" 40 "Key" "rootPassword") }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/configmap.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/configmap.yaml new file mode 100644 index 0000000..47f64cc --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/configmap.yaml @@ -0,0 +1,32 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +data: + initialize: |- + {{- include (print $.Template.BasePath "/_helper_create_bucket.txt") . | nindent 4 }} + add-user: |- + {{- include (print $.Template.BasePath "/_helper_create_user.txt") . | nindent 4 }} + add-policy: |- + {{- include (print $.Template.BasePath "/_helper_create_policy.txt") . | nindent 4 }} + {{- range $idx, $policy := .Values.policies }} + # Policy: {{ $policy.name }} + policy_{{ $idx }}.json: |- + {{- include (print $.Template.BasePath "/_helper_policy.tpl") . | nindent 4 }} + {{ end }} + {{- range $idx, $svc := .Values.svcaccts }} + {{- if $svc.policy }} + # SVC: {{ $svc.accessKey }} + svc_policy_{{ $idx }}.json: |- + {{- include (print $.Template.BasePath "/_helper_policy.tpl") .policy | nindent 4 }} + {{- end }} + {{- end }} + add-svcacct: |- + {{- include (print $.Template.BasePath "/_helper_create_svcacct.txt") . | nindent 4 }} + custom-command: |- + {{- include (print $.Template.BasePath "/_helper_custom_command.txt") . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/console-ingress.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/console-ingress.yaml new file mode 100644 index 0000000..79a2b1b --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/console-ingress.yaml @@ -0,0 +1,55 @@ +{{- if .Values.consoleIngress.enabled -}} +{{- $fullName := printf "%s-console" (include "minio.fullname" .) -}} +{{- $servicePort := .Values.consoleService.port -}} +{{- $ingressPath := .Values.consoleIngress.path -}} +apiVersion: {{ template "minio.consoleIngress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ $fullName }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + {{- with .Values.consoleIngress.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.consoleIngress.annotations }} + annotations: {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if .Values.consoleIngress.ingressClassName }} + ingressClassName: {{ .Values.consoleIngress.ingressClassName }} + {{- end }} + {{- if .Values.consoleIngress.tls }} + tls: + {{- range .Values.consoleIngress.tls }} + - hosts: + {{- range .hosts }} + - {{ . | quote }} + {{- end }} + secretName: {{ .secretName }} + {{- end }} + {{- end }} + rules: + {{- range .Values.consoleIngress.hosts }} + - http: + paths: + - path: {{ $ingressPath }} + {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }} + pathType: Prefix + backend: + service: + name: {{ $fullName }} + port: + number: {{ $servicePort }} + {{- else }} + backend: + serviceName: {{ $fullName }} + servicePort: {{ $servicePort }} + {{- end }} + {{- if . }} + host: {{ tpl . $ | quote }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/console-service.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/console-service.yaml new file mode 100644 index 0000000..2bbe7e3 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/console-service.yaml @@ -0,0 +1,43 @@ +{{ $scheme := .Values.tls.enabled | ternary "https" "http" }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "minio.fullname" . }}-console + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + {{- if .Values.consoleService.annotations }} + annotations: {{- toYaml .Values.consoleService.annotations | nindent 4 }} + {{- end }} +spec: + {{- if (or (eq .Values.consoleService.type "ClusterIP" "") (empty .Values.consoleService.type)) }} + type: ClusterIP + {{- if not (empty .Values.consoleService.clusterIP) }} + clusterIP: {{ .Values.consoleService.clusterIP }} + {{- end }} + {{- else if eq .Values.consoleService.type "LoadBalancer" }} + type: {{ .Values.consoleService.type }} + loadBalancerIP: {{ default "" .Values.consoleService.loadBalancerIP }} + {{- else }} + type: {{ .Values.consoleService.type }} + {{- end }} + ports: + - name: {{ $scheme }} + port: {{ .Values.consoleService.port }} + protocol: TCP + {{- if (and (eq .Values.consoleService.type "NodePort") ( .Values.consoleService.nodePort)) }} + nodePort: {{ .Values.consoleService.nodePort }} + {{- else }} + targetPort: {{ .Values.minioConsolePort }} + {{- end }} + {{- if .Values.consoleService.externalIPs }} + externalIPs: + {{- range $i , $ip := .Values.consoleService.externalIPs }} + - {{ $ip }} + {{- end }} + {{- end }} + selector: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/deployment.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/deployment.yaml new file mode 100644 index 0000000..da62973 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/deployment.yaml @@ -0,0 +1,202 @@ +{{- if eq .Values.mode "standalone" }} +{{ $scheme := .Values.tls.enabled | ternary "https" "http" }} +{{ $bucketRoot := or ($.Values.bucketRoot) ($.Values.mountPath) }} +apiVersion: {{ template "minio.deployment.apiVersion" . }} +kind: Deployment +metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + {{- if .Values.additionalLabels }} + {{- toYaml .Values.additionalLabels | nindent 4 }} + {{- end }} + {{- if .Values.additionalAnnotations }} + annotations: {{- toYaml .Values.additionalAnnotations | nindent 4 }} + {{- end }} +spec: + strategy: + type: {{ .Values.deploymentUpdate.type }} + {{- if eq .Values.deploymentUpdate.type "RollingUpdate" }} + rollingUpdate: + maxSurge: {{ .Values.deploymentUpdate.maxSurge }} + maxUnavailable: {{ .Values.deploymentUpdate.maxUnavailable }} + {{- end }} + replicas: 1 + selector: + matchLabels: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} + template: + metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} + {{- if .Values.podLabels }} + {{- toYaml .Values.podLabels | nindent 8 }} + {{- end }} + annotations: + {{- if not .Values.ignoreChartChecksums }} + checksum/secrets: {{ include (print $.Template.BasePath "/secrets.yaml") . | sha256sum }} + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + {{- end }} + {{- if .Values.podAnnotations }} + {{- toYaml .Values.podAnnotations | trimSuffix "\n" | nindent 8 }} + {{- end }} + spec: + {{- if .Values.priorityClassName }} + priorityClassName: "{{ .Values.priorityClassName }}" + {{- end }} + {{- if .Values.runtimeClassName }} + runtimeClassName: "{{ .Values.runtimeClassName }}" + {{- end }} + {{- if and .Values.securityContext.enabled .Values.persistence.enabled }} + securityContext: + runAsUser: {{ .Values.securityContext.runAsUser }} + runAsGroup: {{ .Values.securityContext.runAsGroup }} + fsGroup: {{ .Values.securityContext.fsGroup }} + {{- if and (ge .Capabilities.KubeVersion.Major "1") (ge .Capabilities.KubeVersion.Minor "20") }} + fsGroupChangePolicy: {{ .Values.securityContext.fsGroupChangePolicy }} + {{- end }} + {{- end }} + {{ if .Values.serviceAccount.create }} + serviceAccountName: {{ .Values.serviceAccount.name }} + {{- end }} + containers: + - name: {{ .Chart.Name }} + image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + command: + - "/bin/sh" + - "-ce" + - "/usr/bin/docker-entrypoint.sh minio server {{ $bucketRoot }} -S {{ .Values.certsPath }} --address :{{ .Values.minioAPIPort }} --console-address :{{ .Values.minioConsolePort }} {{- template "minio.extraArgs" . }}" + volumeMounts: + - name: minio-user + mountPath: "/tmp/credentials" + readOnly: true + - name: export + mountPath: {{ .Values.mountPath }} + {{- if and .Values.persistence.enabled .Values.persistence.subPath }} + subPath: "{{ .Values.persistence.subPath }}" + {{- end }} + {{- if .Values.extraSecret }} + - name: extra-secret + mountPath: "/tmp/minio-config-env" + {{- end }} + {{- include "minio.tlsKeysVolumeMount" . | indent 12 }} + {{- if .Values.extraVolumeMounts }} + {{- toYaml .Values.extraVolumeMounts | nindent 12 }} + {{- end }} + ports: + - name: {{ $scheme }} + containerPort: {{ .Values.minioAPIPort }} + - name: {{ $scheme }}-console + containerPort: {{ .Values.minioConsolePort }} + env: + - name: MINIO_ROOT_USER + valueFrom: + secretKeyRef: + name: {{ template "minio.secretName" . }} + key: rootUser + - name: MINIO_ROOT_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "minio.secretName" . }} + key: rootPassword + {{- if .Values.extraSecret }} + - name: MINIO_CONFIG_ENV_FILE + value: "/tmp/minio-config-env/config.env" + {{- end }} + {{- if .Values.metrics.serviceMonitor.public }} + - name: MINIO_PROMETHEUS_AUTH_TYPE + value: "public" + {{- end }} + {{- if .Values.oidc.enabled }} + - name: MINIO_IDENTITY_OPENID_CONFIG_URL + value: {{ .Values.oidc.configUrl }} + - name: MINIO_IDENTITY_OPENID_CLIENT_ID + value: {{ .Values.oidc.clientId }} + - name: MINIO_IDENTITY_OPENID_CLIENT_SECRET + {{- if and .Values.oidc.existingClientSecretName .Values.oidc.existingClientSecretKey }} + valueFrom: + secretKeyRef: + name: {{ .Values.oidc.existingClientSecretName }} + key: {{ .Values.oidc.existingClientSecretKey }} + {{- else }} + value: {{ .Values.oidc.clientSecret }} + {{- end }} + - name: MINIO_IDENTITY_OPENID_CLAIM_NAME + value: {{ .Values.oidc.claimName }} + - name: MINIO_IDENTITY_OPENID_CLAIM_PREFIX + value: {{ .Values.oidc.claimPrefix }} + - name: MINIO_IDENTITY_OPENID_SCOPES + value: {{ .Values.oidc.scopes }} + - name: MINIO_IDENTITY_OPENID_COMMENT + value: {{ .Values.oidc.comment }} + {{- end }} + {{- if .Values.etcd.endpoints }} + - name: MINIO_ETCD_ENDPOINTS + value: {{ join "," .Values.etcd.endpoints | quote }} + {{- if .Values.etcd.clientCert }} + - name: MINIO_ETCD_CLIENT_CERT + value: "/tmp/credentials/etcd_client_cert.pem" + {{- end }} + {{- if .Values.etcd.clientCertKey }} + - name: MINIO_ETCD_CLIENT_CERT_KEY + value: "/tmp/credentials/etcd_client_cert_key.pem" + {{- end }} + {{- if .Values.etcd.pathPrefix }} + - name: MINIO_ETCD_PATH_PREFIX + value: {{ .Values.etcd.pathPrefix }} + {{- end }} + {{- if .Values.etcd.corednsPathPrefix }} + - name: MINIO_ETCD_COREDNS_PATH + value: {{ .Values.etcd.corednsPathPrefix }} + {{- end }} + {{- end }} + {{- range $key, $val := .Values.environment }} + - name: {{ $key }} + value: {{ tpl $val $ | quote }} + {{- end }} + resources: {{- toYaml .Values.resources | nindent 12 }} + {{- with .Values.extraContainers }} + {{- if eq (typeOf .) "string" }} + {{- tpl . $ | nindent 8 }} + {{- else }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.nodeSelector }} + nodeSelector: {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "minio.imagePullSecrets" . | indent 6 }} + {{- with .Values.affinity }} + affinity: {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: export + {{- if .Values.persistence.enabled }} + persistentVolumeClaim: + claimName: {{ .Values.persistence.existingClaim | default (include "minio.fullname" .) }} + {{- else }} + emptyDir: {} + {{- end }} + {{- if .Values.extraSecret }} + - name: extra-secret + secret: + secretName: {{ .Values.extraSecret }} + {{- end }} + - name: minio-user + secret: + secretName: {{ template "minio.secretName" . }} + {{- include "minio.tlsKeysVolume" . | indent 8 }} + {{- if .Values.extraVolumes }} + {{ toYaml .Values.extraVolumes | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/ingress.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/ingress.yaml new file mode 100644 index 0000000..1a564c6 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/ingress.yaml @@ -0,0 +1,55 @@ +{{- if .Values.ingress.enabled -}} +{{- $fullName := include "minio.fullname" . -}} +{{- $servicePort := .Values.service.port -}} +{{- $ingressPath := .Values.ingress.path -}} +apiVersion: {{ template "minio.ingress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ $fullName }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + {{- with .Values.ingress.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.ingress.annotations }} + annotations: {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if .Values.ingress.ingressClassName }} + ingressClassName: {{ .Values.ingress.ingressClassName }} + {{- end }} + {{- if .Values.ingress.tls }} + tls: + {{- range .Values.ingress.tls }} + - hosts: + {{- range .hosts }} + - {{ . | quote }} + {{- end }} + secretName: {{ .secretName }} + {{- end }} + {{- end }} + rules: + {{- range .Values.ingress.hosts }} + - http: + paths: + - path: {{ $ingressPath }} + {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }} + pathType: Prefix + backend: + service: + name: {{ $fullName }} + port: + number: {{ $servicePort }} + {{- else }} + backend: + serviceName: {{ $fullName }} + servicePort: {{ $servicePort }} + {{- end }} + {{- if . }} + host: {{ tpl . $ | quote }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/networkpolicy.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/networkpolicy.yaml new file mode 100644 index 0000000..7ebc2aa --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/networkpolicy.yaml @@ -0,0 +1,26 @@ +{{- if .Values.networkPolicy.enabled }} +kind: NetworkPolicy +apiVersion: {{ template "minio.networkPolicy.apiVersion" . }} +metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +spec: + podSelector: + matchLabels: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} + ingress: + - ports: + - port: {{ .Values.minioAPIPort }} + - port: {{ .Values.minioConsolePort }} + {{- if not .Values.networkPolicy.allowExternal }} + from: + - podSelector: + matchLabels: + {{ template "minio.name" . }}-client: "true" + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/poddisruptionbudget.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/poddisruptionbudget.yaml new file mode 100644 index 0000000..a5f90a0 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/poddisruptionbudget.yaml @@ -0,0 +1,17 @@ +{{- if .Values.podDisruptionBudget.enabled }} +{{- if .Capabilities.APIVersions.Has "policy/v1beta1/PodDisruptionBudget" }} +apiVersion: policy/v1beta1 +{{- else }} +apiVersion: policy/v1 +{{- end }} +kind: PodDisruptionBudget +metadata: + name: minio + labels: + app: {{ template "minio.name" . }} +spec: + maxUnavailable: {{ .Values.podDisruptionBudget.maxUnavailable }} + selector: + matchLabels: + app: {{ template "minio.name" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/post-job.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/post-job.yaml new file mode 100644 index 0000000..5feb783 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/post-job.yaml @@ -0,0 +1,255 @@ +{{- if or .Values.buckets .Values.users .Values.policies .Values.customCommands .Values.svcaccts }} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ template "minio.fullname" . }}-post-job + labels: + app: {{ template "minio.name" . }}-post-job + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + annotations: + "helm.sh/hook": post-install,post-upgrade + "helm.sh/hook-delete-policy": hook-succeeded,before-hook-creation + {{- with .Values.postJob.annotations }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + template: + metadata: + labels: + app: {{ template "minio.name" . }}-job + release: {{ .Release.Name }} + {{- if .Values.podLabels }} + {{- toYaml .Values.podLabels | nindent 8 }} + {{- end }} + {{- if .Values.postJob.podAnnotations }} + annotations: {{- toYaml .Values.postJob.podAnnotations | nindent 8 }} + {{- end }} + spec: + restartPolicy: OnFailure + {{- include "minio.imagePullSecrets" . | indent 6 }} + {{- if .Values.nodeSelector }} + nodeSelector: {{- toYaml .Values.postJob.nodeSelector | nindent 8 }} + {{- end }} + {{- with .Values.postJob.affinity }} + affinity: {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.postJob.tolerations }} + tolerations: {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.postJob.securityContext.enabled }} + securityContext: + runAsUser: {{ .Values.postJob.securityContext.runAsUser }} + runAsGroup: {{ .Values.postJob.securityContext.runAsGroup }} + fsGroup: {{ .Values.postJob.securityContext.fsGroup }} + {{- end }} + volumes: + - name: etc-path + emptyDir: {} + - name: tmp + emptyDir: {} + - name: minio-configuration + projected: + sources: + - configMap: + name: {{ template "minio.fullname" . }} + - secret: + name: {{ template "minio.secretName" . }} + {{- range (concat .Values.users (default (list) .Values.svcaccts)) }} + {{- if .existingSecret }} + - secret: + name: {{ tpl .existingSecret $ }} + items: + - key: {{ .existingSecretKey }} + path: secrets/{{ tpl .existingSecret $ }}/{{ tpl .existingSecretKey $ }} + {{- end }} + {{- end }} + {{- range ( default list .Values.svcaccts ) }} + {{- if .existingSecret }} + - secret: + name: {{ tpl .existingSecret $ }} + items: + - key: {{ .existingSecretKey }} + path: secrets-svc/{{ tpl .existingSecret $ }}/{{ tpl .existingSecretKey $ }} + {{- end }} + {{- end }} + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + secret: + secretName: {{ .Values.tls.certSecret }} + items: + - key: {{ .Values.tls.publicCrt }} + path: CAs/public.crt + {{- end }} + {{- if .Values.serviceAccount.create }} + serviceAccountName: {{ .Values.serviceAccount.name }} + {{- end }} + {{- if .Values.policies }} + initContainers: + - name: minio-make-policy + image: "{{ .Values.mcImage.repository }}:{{ .Values.mcImage.tag }}" + {{- if .Values.makePolicyJob.securityContext.enabled }} + securityContext: + runAsUser: {{ .Values.makePolicyJob.securityContext.runAsUser }} + runAsGroup: {{ .Values.makePolicyJob.securityContext.runAsGroup }} + {{- end }} + imagePullPolicy: {{ .Values.mcImage.pullPolicy }} + {{- if .Values.makePolicyJob.exitCommand }} + command: [ "/bin/sh", "-c" ] + args: [ "/bin/sh /config/add-policy; EV=$?; {{ .Values.makePolicyJob.exitCommand }} && exit $EV" ] + {{- else }} + command: [ "/bin/sh", "/config/add-policy" ] + {{- end }} + env: + - name: MINIO_ENDPOINT + value: {{ template "minio.fullname" . }} + - name: MINIO_PORT + value: {{ .Values.service.port | quote }} + volumeMounts: + - name: etc-path + mountPath: /etc/minio/mc + - name: tmp + mountPath: /tmp + - name: minio-configuration + mountPath: /config + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + mountPath: {{ .Values.configPathmc }}certs + {{- end }} + resources: {{- toYaml .Values.makePolicyJob.resources | nindent 12 }} + {{- end }} + containers: + {{- if .Values.buckets }} + - name: minio-make-bucket + image: "{{ .Values.mcImage.repository }}:{{ .Values.mcImage.tag }}" + {{- if .Values.makeBucketJob.securityContext.enabled }} + securityContext: + runAsUser: {{ .Values.makeBucketJob.securityContext.runAsUser }} + runAsGroup: {{ .Values.makeBucketJob.securityContext.runAsGroup }} + {{- end }} + imagePullPolicy: {{ .Values.mcImage.pullPolicy }} + {{- if .Values.makeBucketJob.exitCommand }} + command: [ "/bin/sh", "-c" ] + args: [ "/bin/sh /config/initialize; EV=$?; {{ .Values.makeBucketJob.exitCommand }} && exit $EV" ] + {{- else }} + command: [ "/bin/sh", "/config/initialize" ] + {{- end }} + env: + - name: MINIO_ENDPOINT + value: {{ template "minio.fullname" . }} + - name: MINIO_PORT + value: {{ .Values.service.port | quote }} + volumeMounts: + - name: etc-path + mountPath: /etc/minio/mc + - name: tmp + mountPath: /tmp + - name: minio-configuration + mountPath: /config + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + mountPath: {{ .Values.configPathmc }}certs + {{- end }} + resources: {{- toYaml .Values.makeBucketJob.resources | nindent 12 }} + {{- end }} + {{- if .Values.users }} + - name: minio-make-user + image: "{{ .Values.mcImage.repository }}:{{ .Values.mcImage.tag }}" + {{- if .Values.makeUserJob.securityContext.enabled }} + securityContext: + runAsUser: {{ .Values.makeUserJob.securityContext.runAsUser }} + runAsGroup: {{ .Values.makeUserJob.securityContext.runAsGroup }} + {{- end }} + imagePullPolicy: {{ .Values.mcImage.pullPolicy }} + {{- if .Values.makeUserJob.exitCommand }} + command: [ "/bin/sh", "-c" ] + args: [ "/bin/sh /config/add-user; EV=$?; {{ .Values.makeUserJob.exitCommand }} && exit $EV" ] + {{- else }} + command: [ "/bin/sh", "/config/add-user" ] + {{- end }} + env: + - name: MINIO_ENDPOINT + value: {{ template "minio.fullname" . }} + - name: MINIO_PORT + value: {{ .Values.service.port | quote }} + volumeMounts: + - name: etc-path + mountPath: /etc/minio/mc + - name: tmp + mountPath: /tmp + - name: minio-configuration + mountPath: /config + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + mountPath: {{ .Values.configPathmc }}certs + {{- end }} + resources: {{- toYaml .Values.makeUserJob.resources | nindent 12 }} + {{- end }} + {{- if .Values.customCommands }} + - name: minio-custom-command + image: "{{ .Values.mcImage.repository }}:{{ .Values.mcImage.tag }}" + {{- if .Values.customCommandJob.securityContext.enabled }} + securityContext: + runAsUser: {{ .Values.customCommandJob.securityContext.runAsUser }} + runAsGroup: {{ .Values.customCommandJob.securityContext.runAsGroup }} + {{- end }} + imagePullPolicy: {{ .Values.mcImage.pullPolicy }} + {{- if .Values.customCommandJob.exitCommand }} + command: [ "/bin/sh", "-c" ] + args: [ "/bin/sh /config/custom-command; EV=$?; {{ .Values.customCommandJob.exitCommand }} && exit $EV" ] + {{- else }} + command: [ "/bin/sh", "/config/custom-command" ] + {{- end }} + env: + - name: MINIO_ENDPOINT + value: {{ template "minio.fullname" . }} + - name: MINIO_PORT + value: {{ .Values.service.port | quote }} + volumeMounts: + - name: etc-path + mountPath: /etc/minio/mc + - name: tmp + mountPath: /tmp + - name: minio-configuration + mountPath: /config + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + mountPath: {{ .Values.configPathmc }}certs + {{- end }} + resources: {{- toYaml .Values.customCommandJob.resources | nindent 12 }} + {{- end }} + {{- if .Values.svcaccts }} + - name: minio-make-svcacct + image: "{{ .Values.mcImage.repository }}:{{ .Values.mcImage.tag }}" + {{- if .Values.makeServiceAccountJob.securityContext.enabled }} + securityContext: + runAsUser: {{ .Values.makeServiceAccountJob.securityContext.runAsUser }} + runAsGroup: {{ .Values.makeServiceAccountJob.securityContext.runAsGroup }} + {{- end }} + imagePullPolicy: {{ .Values.mcImage.pullPolicy }} + {{- if .Values.makeServiceAccountJob.exitCommand }} + command: [ "/bin/sh", "-c" ] + args: ["/bin/sh /config/add-svcacct; EV=$?; {{ .Values.makeServiceAccountJob.exitCommand }} && exit $EV" ] + {{- else }} + command: ["/bin/sh", "/config/add-svcacct"] + {{- end }} + env: + - name: MINIO_ENDPOINT + value: {{ template "minio.fullname" . }} + - name: MINIO_PORT + value: {{ .Values.service.port | quote }} + volumeMounts: + - name: etc-path + mountPath: /etc/minio/mc + - name: tmp + mountPath: /tmp + - name: minio-configuration + mountPath: /config + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + mountPath: {{ .Values.configPathmc }}certs + {{- end }} + resources: {{- toYaml .Values.makeServiceAccountJob.resources | nindent 12 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/pvc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/pvc.yaml new file mode 100644 index 0000000..60f5267 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/pvc.yaml @@ -0,0 +1,32 @@ +{{- if eq .Values.mode "standalone" }} +{{- if and .Values.persistence.enabled (not .Values.persistence.existingClaim) }} +apiVersion: v1 +kind: PersistentVolumeClaim +metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + {{- if .Values.persistence.annotations }} + annotations: {{- toYaml .Values.persistence.annotations | nindent 4 }} + {{- end }} +spec: + accessModes: + - {{ .Values.persistence.accessMode | quote }} + resources: + requests: + storage: {{ .Values.persistence.size | quote }} + {{- if .Values.persistence.storageClass }} + {{- if (eq "-" .Values.persistence.storageClass) }} + storageClassName: "" + {{- else }} + storageClassName: "{{ .Values.persistence.storageClass }}" + {{- end }} + {{- end }} + {{- if .Values.persistence.volumeName }} + volumeName: "{{ .Values.persistence.volumeName }}" + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/secrets.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/secrets.yaml new file mode 100644 index 0000000..476c3da --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/secrets.yaml @@ -0,0 +1,21 @@ +{{- if not .Values.existingSecret }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ template "minio.secretName" . }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +type: Opaque +data: + rootUser: {{ include "minio.root.username" . | b64enc | quote }} + rootPassword: {{ include "minio.root.password" . | b64enc | quote }} + {{- if .Values.etcd.clientCert }} + etcd_client.crt: {{ .Values.etcd.clientCert | toString | b64enc | quote }} + {{- end }} + {{- if .Values.etcd.clientCertKey }} + etcd_client.key: {{ .Values.etcd.clientCertKey | toString | b64enc | quote }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/securitycontextconstraints.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/securitycontextconstraints.yaml new file mode 100644 index 0000000..4bac7e3 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/securitycontextconstraints.yaml @@ -0,0 +1,45 @@ +{{- if and .Values.securityContext.enabled .Values.persistence.enabled (.Capabilities.APIVersions.Has "security.openshift.io/v1") }} +apiVersion: security.openshift.io/v1 +kind: SecurityContextConstraints +metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +allowHostDirVolumePlugin: false +allowHostIPC: false +allowHostNetwork: false +allowHostPID: false +allowHostPorts: false +allowPrivilegeEscalation: true +allowPrivilegedContainer: false +allowedCapabilities: [] +readOnlyRootFilesystem: false +defaultAddCapabilities: [] +requiredDropCapabilities: +- KILL +- MKNOD +- SETUID +- SETGID +fsGroup: + type: MustRunAs + ranges: + - max: {{ .Values.securityContext.fsGroup }} + min: {{ .Values.securityContext.fsGroup }} +runAsUser: + type: MustRunAs + uid: {{ .Values.securityContext.runAsUser }} +seLinuxContext: + type: MustRunAs +supplementalGroups: + type: RunAsAny +volumes: +- configMap +- downwardAPI +- emptyDir +- persistentVolumeClaim +- projected +- secret +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/service.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/service.yaml new file mode 100644 index 0000000..ba1f3fe --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/service.yaml @@ -0,0 +1,44 @@ +{{ $scheme := .Values.tls.enabled | ternary "https" "http" }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + monitoring: "true" + {{- if .Values.service.annotations }} + annotations: {{- toYaml .Values.service.annotations | nindent 4 }} + {{- end }} +spec: + {{- if (or (eq .Values.service.type "ClusterIP" "") (empty .Values.service.type)) }} + type: ClusterIP + {{- if not (empty .Values.service.clusterIP) }} + clusterIP: {{ .Values.service.clusterIP }} + {{- end }} + {{- else if eq .Values.service.type "LoadBalancer" }} + type: {{ .Values.service.type }} + loadBalancerIP: {{ default "" .Values.service.loadBalancerIP }} + {{- else }} + type: {{ .Values.service.type }} + {{- end }} + ports: + - name: {{ $scheme }} + port: {{ .Values.service.port }} + protocol: TCP + {{- if (and (eq .Values.service.type "NodePort") ( .Values.service.nodePort)) }} + nodePort: {{ .Values.service.nodePort }} + {{- else }} + targetPort: {{ .Values.minioAPIPort }} + {{- end }} + {{- if .Values.service.externalIPs }} + externalIPs: + {{- range $i , $ip := .Values.service.externalIPs }} + - {{ $ip }} + {{- end }} + {{- end }} + selector: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/serviceaccount.yaml new file mode 100644 index 0000000..0784015 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/serviceaccount.yaml @@ -0,0 +1,6 @@ +{{- if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ .Values.serviceAccount.name | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/servicemonitor.yaml new file mode 100644 index 0000000..f875a85 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/servicemonitor.yaml @@ -0,0 +1,112 @@ +{{- if and .Values.metrics.serviceMonitor.enabled .Values.metrics.serviceMonitor.includeNode }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "minio.fullname" . }} + {{- if .Values.metrics.serviceMonitor.namespace }} + namespace: {{ .Values.metrics.serviceMonitor.namespace }} + {{- end }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + {{- if .Values.metrics.serviceMonitor.additionalLabels }} + {{- toYaml .Values.metrics.serviceMonitor.additionalLabels | nindent 4 }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.annotations }} + annotations: {{- toYaml .Values.metrics.serviceMonitor.annotations | nindent 4 }} + {{- end }} +spec: + endpoints: + {{- if .Values.tls.enabled }} + - port: https + scheme: https + tlsConfig: + ca: + secret: + name: {{ .Values.tls.certSecret }} + key: {{ .Values.tls.publicCrt }} + serverName: {{ template "minio.fullname" . }} + {{- else }} + - port: http + scheme: http + {{- end }} + path: /minio/v2/metrics/node + {{- if .Values.metrics.serviceMonitor.interval }} + interval: {{ .Values.metrics.serviceMonitor.interval }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.metrics.serviceMonitor.scrapeTimeout }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.relabelConfigs }} + {{- toYaml .Values.metrics.serviceMonitor.relabelConfigs | nindent 6 }} + {{- end }} + {{- if not .Values.metrics.serviceMonitor.public }} + bearerTokenSecret: + name: {{ template "minio.fullname" . }}-prometheus + key: token + {{- end }} + namespaceSelector: + matchNames: + - {{ .Release.Namespace | quote }} + selector: + matchLabels: + app: {{ include "minio.name" . }} + release: {{ .Release.Name }} + monitoring: "true" +{{- end }} +{{- if .Values.metrics.serviceMonitor.enabled }} +--- +apiVersion: monitoring.coreos.com/v1 +kind: Probe +metadata: + name: {{ template "minio.fullname" . }}-cluster + {{- if .Values.metrics.serviceMonitor.namespace }} + namespace: {{ .Values.metrics.serviceMonitor.namespace }} + {{- end }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + {{- if .Values.metrics.serviceMonitor.additionalLabels }} + {{- toYaml .Values.metrics.serviceMonitor.additionalLabels | nindent 4 }} + {{- end }} +spec: + jobName: {{ template "minio.fullname" . }} + {{- if .Values.tls.enabled }} + tlsConfig: + ca: + secret: + name: {{ .Values.tls.certSecret }} + key: {{ .Values.tls.publicCrt }} + serverName: {{ template "minio.fullname" . }} + {{- end }} + prober: + url: {{ template "minio.fullname" . }}.{{ .Release.Namespace }}:{{ .Values.service.port }} + path: /minio/v2/metrics/cluster + {{- if .Values.tls.enabled }} + scheme: https + {{- else }} + scheme: http + {{- end }} + {{- if .Values.metrics.serviceMonitor.relabelConfigsCluster }} + {{- toYaml .Values.metrics.serviceMonitor.relabelConfigsCluster | nindent 2 }} + {{- end }} + targets: + staticConfig: + static: + - {{ template "minio.fullname" . }}.{{ .Release.Namespace }} + {{- if not .Values.metrics.serviceMonitor.public }} + {{- if .Values.metrics.serviceMonitor.interval }} + interval: {{ .Values.metrics.serviceMonitor.interval }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.metrics.serviceMonitor.scrapeTimeout }} + {{- end }} + bearerTokenSecret: + name: {{ template "minio.fullname" . }}-prometheus + key: token + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/statefulset.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/statefulset.yaml new file mode 100644 index 0000000..c95cba2 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/templates/statefulset.yaml @@ -0,0 +1,252 @@ +{{- if eq .Values.mode "distributed" }} +{{ $poolCount := .Values.pools | int }} +{{ $nodeCount := .Values.replicas | int }} +{{ $replicas := mul $poolCount $nodeCount }} +{{ $drivesPerNode := .Values.drivesPerNode | int }} +{{ $scheme := .Values.tls.enabled | ternary "https" "http" }} +{{ $mountPath := .Values.mountPath }} +{{ $bucketRoot := or ($.Values.bucketRoot) ($.Values.mountPath) }} +{{ $subPath := .Values.persistence.subPath }} +{{ $penabled := .Values.persistence.enabled }} +{{ $accessMode := .Values.persistence.accessMode }} +{{ $storageClass := .Values.persistence.storageClass }} +{{ $psize := .Values.persistence.size }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "minio.fullname" . }}-svc + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +spec: + publishNotReadyAddresses: true + clusterIP: None + ports: + - name: {{ $scheme }} + port: {{ .Values.service.port }} + protocol: TCP + targetPort: {{ .Values.minioAPIPort }} + selector: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} +--- +apiVersion: {{ template "minio.statefulset.apiVersion" . }} +kind: StatefulSet +metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + {{- if .Values.additionalLabels }} + {{- toYaml .Values.additionalLabels | nindent 4 }} + {{- end }} + {{- if .Values.additionalAnnotations }} + annotations: {{- toYaml .Values.additionalAnnotations | nindent 4 }} + {{- end }} +spec: + updateStrategy: + type: {{ .Values.statefulSetUpdate.updateStrategy }} + podManagementPolicy: "Parallel" + serviceName: {{ template "minio.fullname" . }}-svc + replicas: {{ $replicas }} + selector: + matchLabels: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} + template: + metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} + {{- if .Values.podLabels }} + {{- toYaml .Values.podLabels | nindent 8 }} + {{- end }} + annotations: + {{- if not .Values.ignoreChartChecksums }} + checksum/secrets: {{ include (print $.Template.BasePath "/secrets.yaml") . | sha256sum }} + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + {{- end }} + {{- if .Values.podAnnotations }} + {{- toYaml .Values.podAnnotations | nindent 8 }} + {{- end }} + spec: + {{- if .Values.priorityClassName }} + priorityClassName: "{{ .Values.priorityClassName }}" + {{- end }} + {{- if .Values.runtimeClassName }} + runtimeClassName: "{{ .Values.runtimeClassName }}" + {{- end }} + {{- if and .Values.securityContext.enabled .Values.persistence.enabled }} + securityContext: + runAsUser: {{ .Values.securityContext.runAsUser }} + runAsGroup: {{ .Values.securityContext.runAsGroup }} + fsGroup: {{ .Values.securityContext.fsGroup }} + {{- if and (ge .Capabilities.KubeVersion.Major "1") (ge .Capabilities.KubeVersion.Minor "20") }} + fsGroupChangePolicy: {{ .Values.securityContext.fsGroupChangePolicy }} + {{- end }} + {{- end }} + {{- if .Values.serviceAccount.create }} + serviceAccountName: {{ .Values.serviceAccount.name }} + {{- end }} + containers: + - name: {{ .Chart.Name }} + image: {{ .Values.image.repository }}:{{ .Values.image.tag }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + command: [ + "/bin/sh", + "-ce", + "/usr/bin/docker-entrypoint.sh minio server {{- range $i := until $poolCount }}{{ $factor := mul $i $nodeCount }}{{ $endIndex := add $factor $nodeCount }}{{ $beginIndex := mul $i $nodeCount }} {{ $scheme }}://{{ template `minio.fullname` $ }}-{{ `{` }}{{ $beginIndex }}...{{ sub $endIndex 1 }}{{ `}`}}.{{ template `minio.fullname` $ }}-svc.{{ $.Release.Namespace }}.svc.{{ $.Values.clusterDomain }}{{if (gt $drivesPerNode 1)}}{{ $bucketRoot }}-{{ `{` }}0...{{ sub $drivesPerNode 1 }}{{ `}` }}{{ else }}{{ $bucketRoot }}{{end }}{{- end }} -S {{ .Values.certsPath }} --address :{{ .Values.minioAPIPort }} --console-address :{{ .Values.minioConsolePort }} {{- template `minio.extraArgs` . }}" + ] + volumeMounts: + {{- if $penabled }} + {{- if (gt $drivesPerNode 1) }} + {{- range $i := until $drivesPerNode }} + - name: export-{{ $i }} + mountPath: {{ $mountPath }}-{{ $i }} + {{- if and $penabled $subPath }} + subPath: {{ $subPath }} + {{- end }} + {{- end }} + {{- else }} + - name: export + mountPath: {{ $mountPath }} + {{- if and $penabled $subPath }} + subPath: {{ $subPath }} + {{- end }} + {{- end }} + {{- end }} + {{- if .Values.extraSecret }} + - name: extra-secret + mountPath: "/tmp/minio-config-env" + {{- end }} + {{- include "minio.tlsKeysVolumeMount" . | indent 12 }} + {{- if .Values.extraVolumeMounts }} + {{- toYaml .Values.extraVolumeMounts | nindent 12 }} + {{- end }} + ports: + - name: {{ $scheme }} + containerPort: {{ .Values.minioAPIPort }} + - name: {{ $scheme }}-console + containerPort: {{ .Values.minioConsolePort }} + env: + - name: MINIO_ROOT_USER + valueFrom: + secretKeyRef: + name: {{ template "minio.secretName" . }} + key: rootUser + - name: MINIO_ROOT_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "minio.secretName" . }} + key: rootPassword + {{- if .Values.extraSecret }} + - name: MINIO_CONFIG_ENV_FILE + value: "/tmp/minio-config-env/config.env" + {{- end }} + {{- if .Values.metrics.serviceMonitor.public }} + - name: MINIO_PROMETHEUS_AUTH_TYPE + value: "public" + {{- end }} + {{- if .Values.oidc.enabled }} + - name: MINIO_IDENTITY_OPENID_CONFIG_URL + value: {{ .Values.oidc.configUrl }} + - name: MINIO_IDENTITY_OPENID_CLIENT_ID + value: {{ .Values.oidc.clientId }} + - name: MINIO_IDENTITY_OPENID_CLIENT_SECRET + {{- if and .Values.oidc.existingClientSecretName .Values.oidc.existingClientSecretKey }} + valueFrom: + secretKeyRef: + name: {{ .Values.oidc.existingClientSecretName }} + key: {{ .Values.oidc.existingClientSecretKey }} + {{- else }} + value: {{ .Values.oidc.clientSecret }} + {{- end }} + - name: MINIO_IDENTITY_OPENID_CLAIM_NAME + value: {{ .Values.oidc.claimName }} + - name: MINIO_IDENTITY_OPENID_CLAIM_PREFIX + value: {{ .Values.oidc.claimPrefix }} + - name: MINIO_IDENTITY_OPENID_SCOPES + value: {{ .Values.oidc.scopes }} + - name: MINIO_IDENTITY_OPENID_COMMENT + value: {{ .Values.oidc.comment }} + {{- end }} + {{- range $key, $val := .Values.environment }} + - name: {{ $key }} + value: {{ tpl $val $ | quote }} + {{- end }} + resources: {{- toYaml .Values.resources | nindent 12 }} + {{- with .Values.extraContainers }} + {{- if eq (typeOf .) "string" }} + {{- tpl . $ | nindent 8 }} + {{- else }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.nodeSelector }} + nodeSelector: {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "minio.imagePullSecrets" . | indent 6 }} + {{- with .Values.affinity }} + affinity: {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: {{- toYaml . | nindent 8 }} + {{- end }} + {{- if and (gt $replicas 1) (ge .Capabilities.KubeVersion.Major "1") (ge .Capabilities.KubeVersion.Minor "19") }} + {{- with .Values.topologySpreadConstraints }} + topologySpreadConstraints: {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + volumes: + - name: minio-user + secret: + secretName: {{ template "minio.secretName" . }} + {{- if .Values.extraSecret }} + - name: extra-secret + secret: + secretName: {{ .Values.extraSecret }} + {{- end }} + {{- include "minio.tlsKeysVolume" . | indent 8 }} + {{- if .Values.extraVolumes }} + {{- toYaml .Values.extraVolumes | nindent 8 }} + {{- end }} + {{- if .Values.persistence.enabled }} + volumeClaimTemplates: + {{- if gt $drivesPerNode 1 }} + {{- range $diskId := until $drivesPerNode}} + - metadata: + name: export-{{ $diskId }} + {{- if $.Values.persistence.annotations }} + annotations: {{- toYaml $.Values.persistence.annotations | nindent 10 }} + {{- end }} + spec: + accessModes: [ {{ $accessMode | quote }} ] + {{- if $storageClass }} + storageClassName: {{ $storageClass }} + {{- end }} + resources: + requests: + storage: {{ $psize }} + {{- end }} + {{- else }} + - metadata: + name: export + {{- if $.Values.persistence.annotations }} + annotations: {{- toYaml $.Values.persistence.annotations | nindent 10 }} + {{- end }} + spec: + accessModes: [ {{ $accessMode | quote }} ] + {{- if $storageClass }} + storageClassName: {{ $storageClass }} + {{- end }} + resources: + requests: + storage: {{ $psize }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/values.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/values.yaml new file mode 100644 index 0000000..2bb9b62 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/minio/values.yaml @@ -0,0 +1,546 @@ +## Provide a name in place of minio for `app:` labels +## +nameOverride: "" + +## Provide a name to substitute for the full names of resources +## +fullnameOverride: "" + +## set kubernetes cluster domain where minio is running +## +clusterDomain: cluster.local + +## Set default image, imageTag, and imagePullPolicy. mode is used to indicate the +## +image: + repository: quay.io/minio/minio + tag: RELEASE.2023-09-30T07-02-29Z + pullPolicy: IfNotPresent + +imagePullSecrets: [] +# - name: "image-pull-secret" + +## Set default image, imageTag, and imagePullPolicy for the `mc` (the minio +## client used to create a default bucket). +## +mcImage: + repository: quay.io/minio/mc + tag: RELEASE.2023-09-29T16-41-22Z + pullPolicy: IfNotPresent + +## minio mode, i.e. standalone or distributed +mode: distributed ## other supported values are "standalone" + +## Additional labels to include with deployment or statefulset +additionalLabels: {} + +## Additional annotations to include with deployment or statefulset +additionalAnnotations: {} + +## Typically the deployment/statefulset includes checksums of secrets/config, +## So that when these change on a subsequent helm install, the deployment/statefulset +## is restarted. This can result in unnecessary restarts under GitOps tooling such as +## flux, so set to "true" to disable this behaviour. +ignoreChartChecksums: false + +## Additional arguments to pass to minio binary +extraArgs: [] + +## Additional volumes to minio container +extraVolumes: [] + +## Additional volumeMounts to minio container +extraVolumeMounts: [] + +## Additional sidecar containers +extraContainers: [] + +## Internal port number for MinIO S3 API container +## Change service.port to change external port number +minioAPIPort: "9000" + +## Internal port number for MinIO Browser Console container +## Change consoleService.port to change external port number +minioConsolePort: "9001" + +## Update strategy for Deployments +deploymentUpdate: + type: RollingUpdate + maxUnavailable: 0 + maxSurge: 100% + +## Update strategy for StatefulSets +statefulSetUpdate: + updateStrategy: RollingUpdate + +## Pod priority settings +## ref: https://kubernetes.io/docs/concepts/configuration/pod-priority-preemption/ +## +priorityClassName: "" + +## Pod runtime class name +## ref https://kubernetes.io/docs/concepts/containers/runtime-class/ +## +runtimeClassName: "" + +## Set default rootUser, rootPassword +## AccessKey and secretKey is generated when not set +## Distributed MinIO ref: https://min.io/docs/minio/linux/operations/install-deploy-manage/deploy-minio-multi-node-multi-drive.html +## +rootUser: "" +rootPassword: "" + +## Use existing Secret that store following variables: +## +## | Chart var | .data. in Secret | +## |:----------------------|:-------------------------| +## | rootUser | rootUser | +## | rootPassword | rootPassword | +## +## All mentioned variables will be ignored in values file. +## .data.rootUser and .data.rootPassword are mandatory, +## others depend on enabled status of corresponding sections. +existingSecret: "" + +## Directory on the MinIO pof +certsPath: "/etc/minio/certs/" +configPathmc: "/etc/minio/mc/" + +## Path where PV would be mounted on the MinIO Pod +mountPath: "/export" +## Override the root directory which the minio server should serve from. +## If left empty, it defaults to the value of {{ .Values.mountPath }} +## If defined, it must be a sub-directory of the path specified in {{ .Values.mountPath }} +## +bucketRoot: "" + +# Number of drives attached to a node +drivesPerNode: 1 +# Number of MinIO containers running +replicas: 16 +# Number of expanded MinIO clusters +pools: 1 + +## TLS Settings for MinIO +tls: + enabled: false + ## Create a secret with private.key and public.crt files and pass that here. Ref: https://github.com/minio/minio/tree/master/docs/tls/kubernetes#2-create-kubernetes-secret + certSecret: "" + publicCrt: public.crt + privateKey: private.key + +## Trusted Certificates Settings for MinIO. Ref: https://min.io/docs/minio/linux/operations/network-encryption.html#third-party-certificate-authorities +## Bundle multiple trusted certificates into one secret and pass that here. Ref: https://github.com/minio/minio/tree/master/docs/tls/kubernetes#2-create-kubernetes-secret +## When using self-signed certificates, remember to include MinIO's own certificate in the bundle with key public.crt. +## If certSecret is left empty and tls is enabled, this chart installs the public certificate from .Values.tls.certSecret. +trustedCertsSecret: "" + +## Enable persistence using Persistent Volume Claims +## ref: http://kubernetes.io/docs/user-guide/persistent-volumes/ +## +persistence: + enabled: true + annotations: {} + + ## A manually managed Persistent Volume and Claim + ## Requires persistence.enabled: true + ## If defined, PVC must be created manually before volume will be bound + existingClaim: "" + + ## minio data Persistent Volume Storage Class + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is + ## set, choosing the default provisioner. (gp2 on AWS, standard on + ## GKE, AWS & OpenStack) + ## + ## Storage class of PV to bind. By default it looks for standard storage class. + ## If the PV uses a different storage class, specify that here. + storageClass: "" + volumeName: "" + accessMode: ReadWriteOnce + size: 500Gi + + ## If subPath is set mount a sub folder of a volume instead of the root of the volume. + ## This is especially handy for volume plugins that don't natively support sub mounting (like glusterfs). + ## + subPath: "" + +## Expose the MinIO service to be accessed from outside the cluster (LoadBalancer service). +## or access it from within the cluster (ClusterIP service). Set the service type and the port to serve it. +## ref: http://kubernetes.io/docs/user-guide/services/ +## +service: + type: ClusterIP + clusterIP: ~ + port: "9000" + nodePort: 32000 + loadBalancerIP: ~ + externalIPs: [] + annotations: {} + +## Configure Ingress based on the documentation here: https://kubernetes.io/docs/concepts/services-networking/ingress/ +## + +ingress: + enabled: false + ingressClassName: ~ + labels: {} + # node-role.kubernetes.io/ingress: platform + annotations: {} + # kubernetes.io/ingress.class: nginx + # kubernetes.io/tls-acme: "true" + # kubernetes.io/ingress.allow-http: "false" + # kubernetes.io/ingress.global-static-ip-name: "" + # nginx.ingress.kubernetes.io/secure-backends: "true" + # nginx.ingress.kubernetes.io/backend-protocol: "HTTPS" + # nginx.ingress.kubernetes.io/whitelist-source-range: 0.0.0.0/0 + path: / + hosts: + - minio-example.local + tls: [] + # - secretName: chart-example-tls + # hosts: + # - chart-example.local + +consoleService: + type: ClusterIP + clusterIP: ~ + port: "9001" + nodePort: 32001 + loadBalancerIP: ~ + externalIPs: [] + annotations: {} + +consoleIngress: + enabled: false + ingressClassName: ~ + labels: {} + # node-role.kubernetes.io/ingress: platform + annotations: {} + # kubernetes.io/ingress.class: nginx + # kubernetes.io/tls-acme: "true" + # kubernetes.io/ingress.allow-http: "false" + # kubernetes.io/ingress.global-static-ip-name: "" + # nginx.ingress.kubernetes.io/secure-backends: "true" + # nginx.ingress.kubernetes.io/backend-protocol: "HTTPS" + # nginx.ingress.kubernetes.io/whitelist-source-range: 0.0.0.0/0 + path: / + hosts: + - console.minio-example.local + tls: [] + # - secretName: chart-example-tls + # hosts: + # - chart-example.local + +## Node labels for pod assignment +## Ref: https://kubernetes.io/docs/user-guide/node-selection/ +## +nodeSelector: {} +tolerations: [] +affinity: {} +topologySpreadConstraints: [] + +## Add stateful containers to have security context, if enabled MinIO will run as this +## user and group NOTE: securityContext is only enabled if persistence.enabled=true +securityContext: + enabled: true + runAsUser: 1000 + runAsGroup: 1000 + fsGroup: 1000 + fsGroupChangePolicy: "OnRootMismatch" + +# Additational pod annotations +podAnnotations: {} + +# Additional pod labels +podLabels: {} + +## Configure resource requests and limits +## ref: http://kubernetes.io/docs/user-guide/compute-resources/ +## +resources: + requests: + memory: 16Gi + +## List of policies to be created after minio install +## +## In addition to default policies [readonly|readwrite|writeonly|consoleAdmin|diagnostics] +## you can define additional policies with custom supported actions and resources +policies: [] +## writeexamplepolicy policy grants creation or deletion of buckets with name +## starting with example. In addition, grants objects write permissions on buckets starting with +## example. +# - name: writeexamplepolicy +# statements: +# - effect: Allow # this is the default +# resources: +# - 'arn:aws:s3:::example*/*' +# actions: +# - "s3:AbortMultipartUpload" +# - "s3:GetObject" +# - "s3:DeleteObject" +# - "s3:PutObject" +# - "s3:ListMultipartUploadParts" +# - resources: +# - 'arn:aws:s3:::example*' +# actions: +# - "s3:CreateBucket" +# - "s3:DeleteBucket" +# - "s3:GetBucketLocation" +# - "s3:ListBucket" +# - "s3:ListBucketMultipartUploads" +## readonlyexamplepolicy policy grants access to buckets with name starting with example. +## In addition, grants objects read permissions on buckets starting with example. +# - name: readonlyexamplepolicy +# statements: +# - resources: +# - 'arn:aws:s3:::example*/*' +# actions: +# - "s3:GetObject" +# - resources: +# - 'arn:aws:s3:::example*' +# actions: +# - "s3:GetBucketLocation" +# - "s3:ListBucket" +# - "s3:ListBucketMultipartUploads" +## conditionsexample policy creates all access to example bucket with aws:username="johndoe" and source ip range 10.0.0.0/8 and 192.168.0.0/24 only +# - name: conditionsexample +# statements: +# - resources: +# - 'arn:aws:s3:::example/*' +# actions: +# - 's3:*' +# conditions: +# - StringEquals: '"aws:username": "johndoe"' +# - IpAddress: | +# "aws:SourceIp": [ +# "10.0.0.0/8", +# "192.168.0.0/24" +# ] +# +## Additional Annotations for the Kubernetes Job makePolicyJob +makePolicyJob: + securityContext: + enabled: false + runAsUser: 1000 + runAsGroup: 1000 + resources: + requests: + memory: 128Mi + # Command to run after the main command on exit + exitCommand: "" + +## List of users to be created after minio install +## +users: + ## Username, password and policy to be assigned to the user + ## Default policies are [readonly|readwrite|writeonly|consoleAdmin|diagnostics] + ## Add new policies as explained here https://min.io/docs/minio/kubernetes/upstream/administration/identity-access-management.html#access-management + ## NOTE: this will fail if LDAP is enabled in your MinIO deployment + ## make sure to disable this if you are using LDAP. + - accessKey: console + secretKey: console123 + policy: consoleAdmin + # Or you can refer to specific secret + #- accessKey: externalSecret + # existingSecret: my-secret + # existingSecretKey: password + # policy: readonly + +## Additional Annotations for the Kubernetes Job makeUserJob +makeUserJob: + securityContext: + enabled: false + runAsUser: 1000 + runAsGroup: 1000 + resources: + requests: + memory: 128Mi + # Command to run after the main command on exit + exitCommand: "" + +## List of service accounts to be created after minio install +## +svcaccts: [] + ## accessKey, secretKey and parent user to be assigned to the service accounts + ## Add new service accounts as explained here https://min.io/docs/minio/kubernetes/upstream/administration/identity-access-management/minio-user-management.html#service-accounts + # - accessKey: console-svcacct + # secretKey: console123 + # user: console + ## Or you can refer to specific secret + # - accessKey: externalSecret + # existingSecret: my-secret + # existingSecretKey: password + # user: console + ## You also can pass custom policy + # - accessKey: console-svcacct + # secretKey: console123 + # user: console + # policy: + # statements: + # - resources: + # - 'arn:aws:s3:::example*/*' + # actions: + # - "s3:AbortMultipartUpload" + # - "s3:GetObject" + # - "s3:DeleteObject" + # - "s3:PutObject" + # - "s3:ListMultipartUploadParts" + +makeServiceAccountJob: + securityContext: + enabled: false + runAsUser: 1000 + runAsGroup: 1000 + resources: + requests: + memory: 128Mi + # Command to run after the main command on exit + exitCommand: "" + +## List of buckets to be created after minio install +## +buckets: [] + # # Name of the bucket + # - name: bucket1 + # # Policy to be set on the + # # bucket [none|download|upload|public] + # policy: none + # # Purge if bucket exists already + # purge: false + # # set versioning for + # # bucket [true|false] + # versioning: false + # # set objectlocking for + # # bucket [true|false] NOTE: versioning is enabled by default if you use locking + # objectlocking: false + # - name: bucket2 + # policy: none + # purge: false + # versioning: true + # # set objectlocking for + # # bucket [true|false] NOTE: versioning is enabled by default if you use locking + # objectlocking: false + +## Additional Annotations for the Kubernetes Job makeBucketJob +makeBucketJob: + securityContext: + enabled: false + runAsUser: 1000 + runAsGroup: 1000 + resources: + requests: + memory: 128Mi + # Command to run after the main command on exit + exitCommand: "" + +## List of command to run after minio install +## NOTE: the mc command TARGET is always "myminio" +customCommands: + # - command: "admin policy attach myminio consoleAdmin --group='cn=ops,cn=groups,dc=example,dc=com'" + +## Additional Annotations for the Kubernetes Job customCommandJob +customCommandJob: + securityContext: + enabled: false + runAsUser: 1000 + runAsGroup: 1000 + resources: + requests: + memory: 128Mi + # Command to run after the main command on exit + exitCommand: "" + +## Merge jobs +postJob: + podAnnotations: {} + annotations: {} + securityContext: + enabled: false + runAsUser: 1000 + runAsGroup: 1000 + fsGroup: 1000 + nodeSelector: {} + tolerations: [] + affinity: {} + +## Use this field to add environment variables relevant to MinIO server. These fields will be passed on to MinIO container(s) +## when Chart is deployed +environment: + ## Please refer for comprehensive list https://min.io/docs/minio/linux/reference/minio-server/minio-server.html + ## MINIO_SUBNET_LICENSE: "License key obtained from https://subnet.min.io" + ## MINIO_BROWSER: "off" + +## The name of a secret in the same kubernetes namespace which contain secret values +## This can be useful for LDAP password, etc +## The key in the secret must be 'config.env' +## +extraSecret: ~ + +## OpenID Identity Management +## The following section documents environment variables for enabling external identity management using an OpenID Connect (OIDC)-compatible provider. +## See https://min.io/docs/minio/linux/operations/external-iam/configure-openid-external-identity-management.html for a tutorial on using these variables. +oidc: + enabled: false + configUrl: "https://identity-provider-url/.well-known/openid-configuration" + clientId: "minio" + clientSecret: "" + # Provide existing client secret from the Kubernetes Secret resource, existing secret will have priority over `clientSecret` + existingClientSecretName: "" + existingClientSecretKey: "" + claimName: "policy" + scopes: "openid,profile,email" + redirectUri: "https://console-endpoint-url/oauth_callback" + # Can leave empty + claimPrefix: "" + comment: "" + +networkPolicy: + enabled: false + allowExternal: true + +## PodDisruptionBudget settings +## ref: https://kubernetes.io/docs/concepts/workloads/pods/disruptions/ +## +podDisruptionBudget: + enabled: false + maxUnavailable: 1 + +## Specify the service account to use for the MinIO pods. If 'create' is set to 'false' +## and 'name' is left unspecified, the account 'default' will be used. +serviceAccount: + create: true + ## The name of the service account to use. If 'create' is 'true', a service account with that name + ## will be created. + name: "minio-sa" + +metrics: + serviceMonitor: + enabled: false + # scrape each node/pod individually for additional metrics + includeNode: false + public: true + additionalLabels: {} + annotations: {} + # for node metrics + relabelConfigs: {} + # for cluster metrics + relabelConfigsCluster: {} + # metricRelabelings: + # - regex: (server|pod) + # action: labeldrop + namespace: ~ + # Scrape interval, for example `interval: 30s` + interval: ~ + # Scrape timeout, for example `scrapeTimeout: 10s` + scrapeTimeout: ~ + +## ETCD settings: https://github.com/minio/minio/blob/master/docs/sts/etcd.md +## Define endpoints to enable this section. +etcd: + endpoints: [] + pathPrefix: "" + corednsPathPrefix: "" + clientCert: "" + clientCertKey: "" diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/.helmignore b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/.helmignore new file mode 100644 index 0000000..0e8a0eb --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/.helmignore @@ -0,0 +1,23 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*.orig +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/Chart.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/Chart.yaml new file mode 100644 index 0000000..90e0133 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/Chart.yaml @@ -0,0 +1,8 @@ +apiVersion: v2 +appVersion: v0.13.0 +description: Grafana rollout-operator +home: https://github.com/grafana/rollout-operator +kubeVersion: ^1.10.0-0 +name: rollout-operator +type: application +version: 0.14.0 diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/README.md b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/README.md new file mode 100644 index 0000000..f0de8ef --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/README.md @@ -0,0 +1,71 @@ +# Grafana rollout-operator Helm Chart + +Helm chart for deploying [Grafana rollout-operator](https://github.com/grafana/rollout-operator) to Kubernetes. + +# rollout-operator + +![Version: 0.14.0](https://img.shields.io/badge/Version-0.14.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: v0.13.0](https://img.shields.io/badge/AppVersion-v0.13.0-informational?style=flat-square) + +Grafana rollout-operator + +## Requirements + +Kubernetes: `^1.10.0-0` + +## Installation + +This section describes various use cases for installation, upgrade and migration from different systems and versions. + +### Preparation + +These are the common tasks to perform before any of the use cases. + +```bash +# Add the repository +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update +``` + +### Installation of Grafana Rollout Operator + +```bash +helm install -n grafana/rollout-operator +``` + +The Grafana rollout-operator should be installed in the same namespace as the statefulsets it is operating upon. +It is not a highly available application and runs as a single pod. + +## Values + +| Key | Type | Default | Description | +|-----|------|---------|-------------| +| affinity | object | `{}` | | +| fullnameOverride | string | `""` | | +| hostAliases | list | `[]` | hostAliases to add | +| image.pullPolicy | string | `"IfNotPresent"` | | +| image.repository | string | `"grafana/rollout-operator"` | | +| image.tag | string | `""` | Overrides the image tag whose default is the chart appVersion. | +| imagePullSecrets | list | `[]` | | +| minReadySeconds | int | `10` | | +| nameOverride | string | `""` | | +| nodeSelector | object | `{}` | | +| podAnnotations | object | `{}` | Pod Annotations | +| podLabels | object | `{}` | Pod (extra) Labels | +| podSecurityContext | object | `{}` | | +| priorityClassName | string | `""` | | +| resources.limits.memory | string | `"200Mi"` | | +| resources.requests.cpu | string | `"100m"` | | +| resources.requests.memory | string | `"100Mi"` | | +| securityContext | object | `{}` | | +| serviceAccount.annotations | object | `{}` | Annotations to add to the service account | +| serviceAccount.create | bool | `true` | Specifies whether a service account should be created | +| serviceAccount.name | string | `""` | The name of the service account to use. If not set and create is true, a name is generated using the fullname template | +| serviceMonitor.annotations | object | `{}` | ServiceMonitor annotations | +| serviceMonitor.enabled | bool | `false` | Create ServiceMonitor to scrape metrics for Prometheus | +| serviceMonitor.interval | string | `nil` | ServiceMonitor scrape interval | +| serviceMonitor.labels | object | `{}` | Additional ServiceMonitor labels | +| serviceMonitor.namespace | string | `nil` | Alternative namespace for ServiceMonitor resources | +| serviceMonitor.namespaceSelector | object | `{}` | Namespace selector for ServiceMonitor resources | +| serviceMonitor.relabelings | list | `[]` | ServiceMonitor relabel configs to apply to samples before scraping https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig | +| serviceMonitor.scrapeTimeout | string | `nil` | ServiceMonitor scrape timeout in Go duration format (e.g. 15s) | +| tolerations | list | `[]` | | diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/README.md.gotmpl b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/README.md.gotmpl new file mode 100644 index 0000000..0ac2d47 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/README.md.gotmpl @@ -0,0 +1,38 @@ +# Grafana rollout-operator Helm Chart + +Helm chart for deploying [Grafana rollout-operator]({{ template "chart.homepage" . }}) to Kubernetes. + +{{ template "chart.header" . }} + +{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }} + +{{ template "chart.description" . }} + +{{ template "chart.sourcesSection" . }} + +{{ template "chart.requirementsSection" . }} + +## Installation + +This section describes various use cases for installation, upgrade and migration from different systems and versions. + +### Preparation + +These are the common tasks to perform before any of the use cases. + +```bash +# Add the repository +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update +``` + +### Installation of Grafana Rollout Operator + +```bash +helm install -n grafana/rollout-operator +``` + +The Grafana rollout-operator should be installed in the same namespace as the statefulsets it is operating upon. +It is not a highly available application and runs as a single pod. + +{{ template "chart.valuesSection" . }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/NOTES.txt b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/NOTES.txt new file mode 100644 index 0000000..a76e5ba --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/NOTES.txt @@ -0,0 +1,10 @@ +Repo : {{ .Chart.Home }} + +Validation: + +Check the logs of the pod and ensure messages for reconcilliation of the statefulsets are present. +``` +kubectl logs -n {{ .Release.Namespace }} -l {{ include "cli.labels" . }} +``` +Example log line: +level=debug ts=2022-04-20T13:59:52.783051541Z msg="reconciling StatefulSet" statefulset=mimir-store-gateway-zone-a diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/_helpers.tpl b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/_helpers.tpl new file mode 100644 index 0000000..bf3553a --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/_helpers.tpl @@ -0,0 +1,79 @@ +{{/* +Expand the name of the chart. +*/}} +{{- define "rollout-operator.name" -}} +{{- default (include "rollout-operator.chartName" .) .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "rollout-operator.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default (include "rollout-operator.chartName" .) .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Recalculate the chart name, because it may be sub-chart included as rollout_operator, +and _ is not valid in resource names. +*/}} +{{- define "rollout-operator.chartName" -}} +{{- print .Chart.Name | replace "_" "-" -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "rollout-operator.chart" -}} +{{- printf "%s-%s" (include "rollout-operator.chartName" .) .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "rollout-operator.labels" -}} +helm.sh/chart: {{ include "rollout-operator.chart" . }} +{{ include "rollout-operator.selectorLabels" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "rollout-operator.selectorLabels" -}} +app.kubernetes.io/name: {{ include "rollout-operator.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Create the name of the service account to use +*/}} +{{- define "rollout-operator.serviceAccountName" -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "rollout-operator.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} + + +{{- define "cli.labels" -}} +{{- $list := list -}} +{{- range $k, $v := ( include "rollout-operator.selectorLabels" . | fromYaml ) -}} +{{- $list = append $list (printf "%s=%s" $k $v) -}} +{{- end -}} +{{ join "," $list }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/deployment.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/deployment.yaml new file mode 100644 index 0000000..d35b866 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/deployment.yaml @@ -0,0 +1,74 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "rollout-operator.fullname" . }} + labels: + {{- include "rollout-operator.labels" . | nindent 4 }} +spec: + replicas: 1 + minReadySeconds: {{ .Values.minReadySeconds }} + selector: + matchLabels: + {{- include "rollout-operator.selectorLabels" . | nindent 6 }} + strategy: + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + template: + metadata: + {{- with .Values.podAnnotations }} + annotations: + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "rollout-operator.selectorLabels" . | nindent 8 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- with .Values.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "rollout-operator.serviceAccountName" . }} + securityContext: + {{- toYaml .Values.podSecurityContext | nindent 8 }} + containers: + - name: rollout-operator + securityContext: + {{- toYaml .Values.securityContext | nindent 12 }} + image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - -kubernetes.namespace={{ .Release.Namespace }} + ports: + - name: http-metrics + containerPort: 8001 + protocol: TCP + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 5 + timeoutSeconds: 1 + resources: + {{- toYaml .Values.resources | nindent 12 }} + {{- with .Values.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/role.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/role.yaml new file mode 100644 index 0000000..210c456 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/role.yaml @@ -0,0 +1,28 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ include "rollout-operator.fullname" . }} +rules: +- apiGroups: + - "" + resources: + - pods + verbs: + - list + - get + - watch + - delete +- apiGroups: + - apps + resources: + - statefulsets + verbs: + - list + - get + - watch +- apiGroups: + - apps + resources: + - statefulsets/status + verbs: + - update diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/rolebinding.yaml new file mode 100644 index 0000000..24fcd72 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/rolebinding.yaml @@ -0,0 +1,11 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "rollout-operator.fullname" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "rollout-operator.fullname" . }} +subjects: +- kind: ServiceAccount + name: {{ include "rollout-operator.serviceAccountName" . }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/service.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/service.yaml new file mode 100644 index 0000000..60ce5b1 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/service.yaml @@ -0,0 +1,18 @@ +{{- if .Values.serviceMonitor.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "rollout-operator.fullname" . }} + labels: + {{- include "rollout-operator.labels" . | nindent 4 }} +spec: + type: ClusterIP + clusterIP: None + ports: + - port: 8001 + targetPort: http-metrics + protocol: TCP + name: http-metrics + selector: + {{- include "rollout-operator.selectorLabels" . | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/serviceaccount.yaml new file mode 100644 index 0000000..37698a4 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/serviceaccount.yaml @@ -0,0 +1,12 @@ +{{- if .Values.serviceAccount.create -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "rollout-operator.serviceAccountName" . }} + labels: + {{- include "rollout-operator.labels" . | nindent 4 }} + {{- with .Values.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/servicemonitor.yaml new file mode 100644 index 0000000..7810843 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/templates/servicemonitor.yaml @@ -0,0 +1,36 @@ +{{- if .Values.serviceMonitor.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "rollout-operator.fullname" . }} + {{- with .Values.serviceMonitor.namespace }} + namespace: {{ . }} + {{- end }} + labels: + {{- include "rollout-operator.labels" . | nindent 4 }} + {{- with .Values.serviceMonitor.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .Values.serviceMonitor.namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "rollout-operator.selectorLabels" . | nindent 6 }} + endpoints: + - port: http-metrics + {{- with .Values.serviceMonitor.interval }} + interval: {{ . }} + {{- end }} + {{- with .Values.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + relabelings: + {{- with .Values.serviceMonitor.relabelings }} + {{- toYaml . | nindent 8 }} + {{- end }} + scheme: http +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/values.yaml b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/values.yaml new file mode 100644 index 0000000..66f9486 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/charts/rollout-operator/values.yaml @@ -0,0 +1,83 @@ +# Default values for rollout-operator. +# This is a YAML-formatted file. +# Declare variables to be passed into your templates. + +image: + repository: grafana/rollout-operator + pullPolicy: IfNotPresent + # -- Overrides the image tag whose default is the chart appVersion. + tag: "" + +imagePullSecrets: [] + +# -- hostAliases to add +hostAliases: [] +# - ip: 1.2.3.4 +# hostnames: +# - domain.tld + +nameOverride: "" +fullnameOverride: "" + +serviceAccount: + # -- Specifies whether a service account should be created + create: true + # -- Annotations to add to the service account + annotations: {} + # -- The name of the service account to use. + # If not set and create is true, a name is generated using the fullname template + name: "" + +# -- Pod Annotations +podAnnotations: {} + +# -- Pod (extra) Labels +podLabels: {} + +podSecurityContext: {} + # fsGroup: 2000 + +securityContext: {} + # capabilities: + # drop: + # - ALL + # readOnlyRootFilesystem: true + # runAsNonRoot: true + # runAsUser: 1000 + +resources: + limits: + # cpu: "1" + memory: 200Mi + requests: + cpu: 100m + memory: 100Mi + +minReadySeconds: 10 + +nodeSelector: {} + +tolerations: [] + +affinity: {} + +priorityClassName: "" + +serviceMonitor: + # -- Create ServiceMonitor to scrape metrics for Prometheus + enabled: false + # -- Alternative namespace for ServiceMonitor resources + namespace: null + # -- Namespace selector for ServiceMonitor resources + namespaceSelector: {} + # -- ServiceMonitor annotations + annotations: {} + # -- Additional ServiceMonitor labels + labels: {} + # -- ServiceMonitor scrape interval + interval: null + # -- ServiceMonitor scrape timeout in Go duration format (e.g. 15s) + scrapeTimeout: null + # -- ServiceMonitor relabel configs to apply to samples before scraping + # https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig + relabelings: [] diff --git a/observability/lgtm-distributed/charts/mimir-distributed/large.yaml b/observability/lgtm-distributed/charts/mimir-distributed/large.yaml new file mode 100644 index 0000000..ac9ba73 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/large.yaml @@ -0,0 +1,209 @@ +# These values configure the Grafana Mimir or Grafana Enterprise Metrics cluster +# for a more production-ready setup. The setup targets 70% CPU and memory utilization +# so that the cluster has room to grow. The resource requests reflect 70% utilization +# and the limits reflect 100% utilization. The values do not set CPU limits, +# because CPU limits have caused severe issues elsewhere, so we don't apply any in our helm chart: +# see https://engineering.indeedblog.com/blog/2019/12/unthrottled-fixing-cpu-limits-in-the-cloud/ +# If you require CPU limits for billing purposes see capped-large.yaml +# +# These values are suitable for ingestion of ~10M series and scrape interval of 15s. +# This implies ingestion rate of around 660000 samples per second. +# +# Query requirements can vary dramatically depending on query rate and query +# ranges. The values here satisfy a "usual" query load of around 50 queries per second +# as seen from our production clusters at this scale. +# +# The values in this file also add podAntiAffinity rules for ingesters and store-gateways. +# The rules ensure that the replicas of the same component are not scheduled on the same +# Kubernetes Node. Zone-aware replication is enabled by default on new installation. +# Refer to [Migrate from single zone to zone-aware replication with Helm](https://grafana.com/docs/mimir/latest/migration-guide/migrating-from-single-zone-with-helm) and +# [Zone-Aware Replication](https://grafana.com/docs/mimir/latest/configure/configure-zone-aware-replication/) +# for more information. +# +# MinIO is no longer enabled, and you are encouraged to use your cloud providers +# object storage service such as S3 or GCS. + +alertmanager: + persistentVolume: + enabled: true + replicas: 3 + resources: + limits: + memory: 1.4Gi + requests: + cpu: 1 + memory: 1Gi + statefulSet: + enabled: true + +compactor: + persistentVolume: + size: 50Gi + resources: + limits: + memory: 2.8Gi + requests: + cpu: 1 + memory: 2Gi + +distributor: + replicas: 12 + resources: + limits: + memory: 5.7Gi + requests: + cpu: 2 + memory: 4Gi + +ingester: + persistentVolume: + size: 50Gi + replicas: 27 + resources: + limits: + memory: 12Gi + requests: + cpu: 3.5 + memory: 8Gi + topologySpreadConstraints: {} + affinity: + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchExpressions: + - key: target # support for enterprise.legacyLabels + operator: In + values: + - ingester + topologyKey: 'kubernetes.io/hostname' + + - labelSelector: + matchExpressions: + - key: app.kubernetes.io/component + operator: In + values: + - ingester + topologyKey: 'kubernetes.io/hostname' + + zoneAwareReplication: + topologyKey: 'kubernetes.io/hostname' + +admin-cache: + enabled: true + replicas: 2 + +chunks-cache: + enabled: true + replicas: 4 + +index-cache: + enabled: true + replicas: 4 + +metadata-cache: + enabled: true + +results-cache: + enabled: true + replicas: 4 + allocatedMemory: 1024 + +minio: + enabled: false + +overrides_exporter: + replicas: 1 + resources: + limits: + memory: 128Mi + requests: + cpu: 100m + memory: 128Mi + +querier: + replicas: 4 + resources: + limits: + memory: 8.5Gi + requests: + cpu: 2 + memory: 6Gi + +query_frontend: + replicas: 3 + resources: + limits: + memory: 2.8Gi + requests: + cpu: 2 + memory: 2Gi + +ruler: + replicas: 3 + resources: + limits: + memory: 5.7Gi + requests: + cpu: 1 + memory: 4Gi + +store_gateway: + persistentVolume: + size: 50Gi + replicas: 6 + resources: + limits: + memory: 8.5Gi + requests: + cpu: 1 + memory: 6Gi + topologySpreadConstraints: {} + affinity: + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchExpressions: + - key: target # support for enterprise.legacyLabels + operator: In + values: + - store-gateway + topologyKey: 'kubernetes.io/hostname' + + - labelSelector: + matchExpressions: + - key: app.kubernetes.io/component + operator: In + values: + - store-gateway + topologyKey: 'kubernetes.io/hostname' + + zoneAwareReplication: + topologyKey: 'kubernetes.io/hostname' + +nginx: + replicas: 3 + resources: + limits: + memory: 731Mi + requests: + cpu: 1 + memory: 512Mi + +# Grafana Enterprise Metrics feature related +admin_api: + replicas: 2 + resources: + limits: + memory: 128Mi + requests: + cpu: 100m + memory: 64Mi + +gateway: + replicas: 3 + resources: + limits: + memory: 731Mi + requests: + cpu: 1 + memory: 512Mi diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/alerts.yaml b/observability/lgtm-distributed/charts/mimir-distributed/mixins/alerts.yaml new file mode 100644 index 0000000..ef05886 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/alerts.yaml @@ -0,0 +1,1061 @@ +groups: +- name: mimir_alerts + rules: + - alert: MimirIngesterUnhealthy + annotations: + message: Mimir cluster {{ $labels.cluster }}/{{ $labels.namespace }} has {{ + printf "%f" $value }} unhealthy ingester(s). + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterunhealthy + expr: | + min by (cluster, namespace) (cortex_ring_members{state="Unhealthy", name="ingester"}) > 0 + for: 15m + labels: + severity: critical + - alert: MimirRequestErrors + annotations: + message: | + The route {{ $labels.route }} in {{ $labels.cluster }}/{{ $labels.namespace }} is experiencing {{ printf "%.2f" $value }}% errors. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirrequesterrors + expr: | + 100 * sum by (cluster, namespace, job, route) (rate(cortex_request_duration_seconds_count{status_code=~"5..",route!~"ready|debug_pprof"}[1m])) + / + sum by (cluster, namespace, job, route) (rate(cortex_request_duration_seconds_count{route!~"ready|debug_pprof"}[1m])) + > 1 + for: 15m + labels: + severity: critical + - alert: MimirRequestLatency + annotations: + message: | + {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirrequestlatency + expr: | + cluster_namespace_job_route:cortex_request_duration_seconds:99quantile{route!~"metrics|/frontend.Frontend/Process|ready|/schedulerpb.SchedulerForFrontend/FrontendLoop|/schedulerpb.SchedulerForQuerier/QuerierLoop|debug_pprof"} + > + 2.5 + for: 15m + labels: + severity: warning + - alert: MimirInconsistentRuntimeConfig + annotations: + message: | + An inconsistent runtime config file is used across cluster {{ $labels.cluster }}/{{ $labels.namespace }}. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirinconsistentruntimeconfig + expr: | + count(count by(cluster, namespace, job, sha256) (cortex_runtime_config_hash)) without(sha256) > 1 + for: 1h + labels: + severity: critical + - alert: MimirBadRuntimeConfig + annotations: + message: | + {{ $labels.job }} failed to reload runtime config. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirbadruntimeconfig + expr: | + # The metric value is reset to 0 on error while reloading the config at runtime. + cortex_runtime_config_last_reload_successful == 0 + for: 5m + labels: + severity: critical + - alert: MimirFrontendQueriesStuck + annotations: + message: | + There are {{ $value }} queued up queries in {{ $labels.cluster }}/{{ $labels.namespace }} {{ $labels.job }}. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirfrontendqueriesstuck + expr: | + sum by (cluster, namespace, job) (min_over_time(cortex_query_frontend_queue_length[1m])) > 0 + for: 5m + labels: + severity: critical + - alert: MimirSchedulerQueriesStuck + annotations: + message: | + There are {{ $value }} queued up queries in {{ $labels.cluster }}/{{ $labels.namespace }} {{ $labels.job }}. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirschedulerqueriesstuck + expr: | + sum by (cluster, namespace, job) (min_over_time(cortex_query_scheduler_queue_length[1m])) > 0 + for: 7m + labels: + severity: critical + - alert: MimirCacheRequestErrors + annotations: + message: | + The cache {{ $labels.name }} used by Mimir {{ $labels.cluster }}/{{ $labels.namespace }} is experiencing {{ printf "%.2f" $value }}% errors for {{ $labels.operation }} operation. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimircacherequesterrors + expr: | + ( + sum by(cluster, namespace, name, operation) ( + rate(thanos_memcached_operation_failures_total[1m]) + or + rate(thanos_cache_operation_failures_total[1m]) + ) + / + sum by(cluster, namespace, name, operation) ( + rate(thanos_memcached_operations_total[1m]) + or + rate(thanos_cache_operations_total[1m]) + ) + ) * 100 > 5 + for: 5m + labels: + severity: warning + - alert: MimirIngesterRestarts + annotations: + message: Mimir {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has restarted {{ printf "%.2f" $value }} times in the last 30 mins. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterrestarts + expr: | + ( + sum by(cluster, namespace, pod) ( + increase(kube_pod_container_status_restarts_total{container=~"(ingester|mimir-write)"}[30m]) + ) + >= 2 + ) + and + ( + count by(cluster, namespace, pod) (cortex_build_info) > 0 + ) + labels: + severity: warning + - alert: MimirKVStoreFailure + annotations: + message: | + Mimir {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace }} is failing to talk to the KV store {{ $labels.kv_name }}. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirkvstorefailure + expr: | + ( + sum by(cluster, namespace, pod, status_code, kv_name) (rate(cortex_kv_request_duration_seconds_count{status_code!~"2.+"}[1m])) + / + sum by(cluster, namespace, pod, status_code, kv_name) (rate(cortex_kv_request_duration_seconds_count[1m])) + ) + # We want to get alerted only in case there's a constant failure. + == 1 + for: 5m + labels: + severity: critical + - alert: MimirMemoryMapAreasTooHigh + annotations: + message: '{{ $labels.job }}/{{ $labels.pod }} has a number of mmap-ed areas + close to the limit.' + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirmemorymapareastoohigh + expr: | + process_memory_map_areas{job=~".*/(ingester.*|cortex|mimir|mimir-write.*|store-gateway.*|cortex|mimir|mimir-backend.*)"} / process_memory_map_areas_limit{job=~".*/(ingester.*|cortex|mimir|mimir-write.*|store-gateway.*|cortex|mimir|mimir-backend.*)"} > 0.8 + for: 5m + labels: + severity: critical + - alert: MimirIngesterInstanceHasNoTenants + annotations: + message: Mimir ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has no tenants assigned. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterinstancehasnotenants + expr: | + (min by(cluster, namespace, pod) (cortex_ingester_memory_users) == 0) + and on (cluster, namespace) + # Only if there are more time-series than would be expected due to continuous testing load + ( + sum by(cluster, namespace) (cortex_ingester_memory_series) + / + max by(cluster, namespace) (cortex_distributor_replication_factor) + ) > 100000 + for: 1h + labels: + severity: warning + - alert: MimirRulerInstanceHasNoRuleGroups + annotations: + message: Mimir ruler {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has no rule groups assigned. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirrulerinstancehasnorulegroups + expr: | + # Alert on ruler instances in microservices mode that have no rule groups assigned, + min by(cluster, namespace, pod) (cortex_ruler_managers_total{pod=~"(.*mimir-)?ruler.*"}) == 0 + # but only if other ruler instances of the same cell do have rule groups assigned + and on (cluster, namespace) + (max by(cluster, namespace) (cortex_ruler_managers_total) > 0) + # and there are more than two instances overall + and on (cluster, namespace) + (count by (cluster, namespace) (cortex_ruler_managers_total) > 2) + for: 1h + labels: + severity: warning + - alert: MimirIngestedDataTooFarInTheFuture + annotations: + message: Mimir ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has ingested samples with timestamps more than 1h in the future. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesteddatatoofarinthefuture + expr: | + max by(cluster, namespace, pod) ( + cortex_ingester_tsdb_head_max_timestamp_seconds - time() + and + cortex_ingester_tsdb_head_max_timestamp_seconds > 0 + ) > 60*60 + for: 5m + labels: + severity: warning + - alert: MimirStoreGatewayTooManyFailedOperations + annotations: + message: Mimir store-gateway {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} is experiencing {{ $value | humanizePercentage }} errors while doing {{ + $labels.operation }} on the object storage. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirstoregatewaytoomanyfailedoperations + expr: | + sum by(cluster, namespace, operation) (rate(thanos_objstore_bucket_operation_failures_total{component="store-gateway"}[1m])) > 0 + for: 5m + labels: + severity: warning + - alert: MimirRingMembersMismatch + annotations: + message: | + Number of members in Mimir ingester hash ring does not match the expected number in {{ $labels.cluster }}/{{ $labels.namespace }}. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirringmembersmismatch + expr: | + ( + avg by(cluster, namespace) (sum by(cluster, namespace, pod) (cortex_ring_members{name="ingester",job=~".*/(ingester.*|cortex|mimir|mimir-write.*)"})) + != sum by(cluster, namespace) (up{job=~".*/(ingester.*|cortex|mimir|mimir-write.*)"}) + ) + and + ( + count by(cluster, namespace) (cortex_build_info) > 0 + ) + for: 15m + labels: + component: ingester + severity: warning +- name: mimir_instance_limits_alerts + rules: + - alert: MimirIngesterReachingSeriesLimit + annotations: + message: | + Ingester {{ $labels.job }}/{{ $labels.pod }} has reached {{ $value | humanizePercentage }} of its series limit. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterreachingserieslimit + expr: | + ( + (cortex_ingester_memory_series / ignoring(limit) cortex_ingester_instance_limits{limit="max_series"}) + and ignoring (limit) + (cortex_ingester_instance_limits{limit="max_series"} > 0) + ) > 0.8 + for: 3h + labels: + severity: warning + - alert: MimirIngesterReachingSeriesLimit + annotations: + message: | + Ingester {{ $labels.job }}/{{ $labels.pod }} has reached {{ $value | humanizePercentage }} of its series limit. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterreachingserieslimit + expr: | + ( + (cortex_ingester_memory_series / ignoring(limit) cortex_ingester_instance_limits{limit="max_series"}) + and ignoring (limit) + (cortex_ingester_instance_limits{limit="max_series"} > 0) + ) > 0.9 + for: 5m + labels: + severity: critical + - alert: MimirIngesterReachingTenantsLimit + annotations: + message: | + Ingester {{ $labels.job }}/{{ $labels.pod }} has reached {{ $value | humanizePercentage }} of its tenant limit. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterreachingtenantslimit + expr: | + ( + (cortex_ingester_memory_users / ignoring(limit) cortex_ingester_instance_limits{limit="max_tenants"}) + and ignoring (limit) + (cortex_ingester_instance_limits{limit="max_tenants"} > 0) + ) > 0.7 + for: 5m + labels: + severity: warning + - alert: MimirIngesterReachingTenantsLimit + annotations: + message: | + Ingester {{ $labels.job }}/{{ $labels.pod }} has reached {{ $value | humanizePercentage }} of its tenant limit. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterreachingtenantslimit + expr: | + ( + (cortex_ingester_memory_users / ignoring(limit) cortex_ingester_instance_limits{limit="max_tenants"}) + and ignoring (limit) + (cortex_ingester_instance_limits{limit="max_tenants"} > 0) + ) > 0.8 + for: 5m + labels: + severity: critical + - alert: MimirReachingTCPConnectionsLimit + annotations: + message: | + Mimir instance {{ $labels.job }}/{{ $labels.pod }} has reached {{ $value | humanizePercentage }} of its TCP connections limit for {{ $labels.protocol }} protocol. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirreachingtcpconnectionslimit + expr: | + cortex_tcp_connections / cortex_tcp_connections_limit > 0.8 and + cortex_tcp_connections_limit > 0 + for: 5m + labels: + severity: critical + - alert: MimirDistributorReachingInflightPushRequestLimit + annotations: + message: | + Distributor {{ $labels.job }}/{{ $labels.pod }} has reached {{ $value | humanizePercentage }} of its inflight push request limit. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirdistributorreachinginflightpushrequestlimit + expr: | + ( + (cortex_distributor_inflight_push_requests / ignoring(limit) cortex_distributor_instance_limits{limit="max_inflight_push_requests"}) + and ignoring (limit) + (cortex_distributor_instance_limits{limit="max_inflight_push_requests"} > 0) + ) > 0.8 + for: 5m + labels: + severity: critical +- name: mimir-rollout-alerts + rules: + - alert: MimirRolloutStuck + annotations: + message: | + The {{ $labels.rollout_group }} rollout is stuck in {{ $labels.cluster }}/{{ $labels.namespace }}. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirrolloutstuck + expr: | + ( + max without (revision) ( + sum without(statefulset) (label_replace(kube_statefulset_status_current_revision, "rollout_group", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?")) + unless + sum without(statefulset) (label_replace(kube_statefulset_status_update_revision, "rollout_group", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?")) + ) + * + ( + sum without(statefulset) (label_replace(kube_statefulset_replicas, "rollout_group", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?")) + != + sum without(statefulset) (label_replace(kube_statefulset_status_replicas_updated, "rollout_group", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?")) + ) + ) and ( + changes(sum without(statefulset) (label_replace(kube_statefulset_status_replicas_updated, "rollout_group", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?"))[15m:1m]) + == + 0 + ) + * on(cluster, namespace) group_left max by(cluster, namespace) (cortex_build_info) + for: 30m + labels: + severity: warning + workload_type: statefulset + - alert: MimirRolloutStuck + annotations: + message: | + The {{ $labels.rollout_group }} rollout is stuck in {{ $labels.cluster }}/{{ $labels.namespace }}. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirrolloutstuck + expr: | + ( + sum without(deployment) (label_replace(kube_deployment_spec_replicas, "rollout_group", "$1", "deployment", "(.*?)(?:-zone-[a-z])?")) + != + sum without(deployment) (label_replace(kube_deployment_status_replicas_updated, "rollout_group", "$1", "deployment", "(.*?)(?:-zone-[a-z])?")) + ) and ( + changes(sum without(deployment) (label_replace(kube_deployment_status_replicas_updated, "rollout_group", "$1", "deployment", "(.*?)(?:-zone-[a-z])?"))[15m:1m]) + == + 0 + ) + * on(cluster, namespace) group_left max by(cluster, namespace) (cortex_build_info) + for: 30m + labels: + severity: warning + workload_type: deployment + - alert: RolloutOperatorNotReconciling + annotations: + message: | + Rollout operator is not reconciling the rollout group {{ $labels.rollout_group }} in {{ $labels.cluster }}/{{ $labels.namespace }}. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#rolloutoperatornotreconciling + expr: | + max by(cluster, namespace, rollout_group) (time() - rollout_operator_last_successful_group_reconcile_timestamp_seconds) > 600 + for: 5m + labels: + severity: critical +- name: mimir-provisioning + rules: + - alert: MimirAllocatingTooMuchMemory + annotations: + message: | + Instance {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace }} is using too much memory. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirallocatingtoomuchmemory + expr: | + ( + # We use RSS instead of working set memory because of the ingester's extensive usage of mmap. + # See: https://github.com/grafana/mimir/issues/2466 + container_memory_rss{container=~"(ingester|mimir-write|mimir-backend)"} + / + ( container_spec_memory_limit_bytes{container=~"(ingester|mimir-write|mimir-backend)"} > 0 ) + ) + # Match only Mimir namespaces. + * on(cluster, namespace) group_left max by(cluster, namespace) (cortex_build_info) + > 0.65 + for: 15m + labels: + severity: warning + - alert: MimirAllocatingTooMuchMemory + annotations: + message: | + Instance {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace }} is using too much memory. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirallocatingtoomuchmemory + expr: | + ( + # We use RSS instead of working set memory because of the ingester's extensive usage of mmap. + # See: https://github.com/grafana/mimir/issues/2466 + container_memory_rss{container=~"(ingester|mimir-write|mimir-backend)"} + / + ( container_spec_memory_limit_bytes{container=~"(ingester|mimir-write|mimir-backend)"} > 0 ) + ) + # Match only Mimir namespaces. + * on(cluster, namespace) group_left max by(cluster, namespace) (cortex_build_info) + > 0.8 + for: 15m + labels: + severity: critical +- name: ruler_alerts + rules: + - alert: MimirRulerTooManyFailedPushes + annotations: + message: | + Mimir Ruler {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace }} is experiencing {{ printf "%.2f" $value }}% write (push) errors. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirrulertoomanyfailedpushes + expr: | + 100 * ( + sum by (cluster, namespace, pod) (rate(cortex_ruler_write_requests_failed_total[1m])) + / + sum by (cluster, namespace, pod) (rate(cortex_ruler_write_requests_total[1m])) + ) > 1 + for: 5m + labels: + severity: critical + - alert: MimirRulerTooManyFailedQueries + annotations: + message: | + Mimir Ruler {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace }} is experiencing {{ printf "%.2f" $value }}% errors while evaluating rules. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirrulertoomanyfailedqueries + expr: | + 100 * ( + sum by (cluster, namespace, pod) (rate(cortex_ruler_queries_failed_total[1m])) + / + sum by (cluster, namespace, pod) (rate(cortex_ruler_queries_total[1m])) + ) > 1 + for: 5m + labels: + severity: critical + - alert: MimirRulerMissedEvaluations + annotations: + message: | + Mimir Ruler {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace }} is experiencing {{ printf "%.2f" $value }}% missed iterations for the rule group {{ $labels.rule_group }}. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirrulermissedevaluations + expr: | + 100 * ( + sum by (cluster, namespace, pod, rule_group) (rate(cortex_prometheus_rule_group_iterations_missed_total[1m])) + / + sum by (cluster, namespace, pod, rule_group) (rate(cortex_prometheus_rule_group_iterations_total[1m])) + ) > 1 + for: 5m + labels: + severity: warning + - alert: MimirRulerFailedRingCheck + annotations: + message: | + Mimir Rulers in {{ $labels.cluster }}/{{ $labels.namespace }} are experiencing errors when checking the ring for rule group ownership. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirrulerfailedringcheck + expr: | + sum by (cluster, namespace, job) (rate(cortex_ruler_ring_check_errors_total[1m])) + > 0 + for: 5m + labels: + severity: critical + - alert: MimirRulerRemoteEvaluationFailing + annotations: + message: | + Mimir rulers in {{ $labels.cluster }}/{{ $labels.namespace }} are failing to perform {{ printf "%.2f" $value }}% of remote evaluations through the ruler-query-frontend. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirrulerremoteevaluationfailing + expr: | + 100 * ( + sum by (cluster, namespace) (rate(cortex_request_duration_seconds_count{route="/httpgrpc.HTTP/Handle", status_code=~"5..", job=~".*/(ruler-query-frontend.*)"}[5m])) + / + sum by (cluster, namespace) (rate(cortex_request_duration_seconds_count{route="/httpgrpc.HTTP/Handle", job=~".*/(ruler-query-frontend.*)"}[5m])) + ) > 1 + for: 5m + labels: + severity: warning +- name: gossip_alerts + rules: + - alert: MimirGossipMembersTooHigh + annotations: + message: One or more Mimir instances in {{ $labels.cluster }}/{{ $labels.namespace + }} consistently sees a higher than expected number of gossip members. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirgossipmemberstoohigh + expr: | + max by (cluster, namespace) (memberlist_client_cluster_members_count) + > + (sum by (cluster, namespace) (up{job=~".+/(admin-api|alertmanager|compactor.*|distributor.*|ingester.*|querier.*|ruler|ruler-querier.*|store-gateway.*|cortex|mimir|mimir-write.*|mimir-read.*|mimir-backend.*)"}) + 10) + for: 20m + labels: + severity: warning + - alert: MimirGossipMembersTooLow + annotations: + message: One or more Mimir instances in {{ $labels.cluster }}/{{ $labels.namespace + }} consistently sees a lower than expected number of gossip members. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirgossipmemberstoolow + expr: | + min by (cluster, namespace) (memberlist_client_cluster_members_count) + < + (sum by (cluster, namespace) (up{job=~".+/(admin-api|alertmanager|compactor.*|distributor.*|ingester.*|querier.*|ruler|ruler-querier.*|store-gateway.*|cortex|mimir|mimir-write.*|mimir-read.*|mimir-backend.*)"}) * 0.5) + for: 20m + labels: + severity: warning +- name: etcd_alerts + rules: + - alert: EtcdAllocatingTooMuchMemory + annotations: + message: | + Too much memory being used by {{ $labels.namespace }}/{{ $labels.pod }} - bump memory limit. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#etcdallocatingtoomuchmemory + expr: | + ( + container_memory_working_set_bytes{container="etcd"} + / + ( container_spec_memory_limit_bytes{container="etcd"} > 0 ) + ) > 0.65 + for: 15m + labels: + severity: warning + - alert: EtcdAllocatingTooMuchMemory + annotations: + message: | + Too much memory being used by {{ $labels.namespace }}/{{ $labels.pod }} - bump memory limit. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#etcdallocatingtoomuchmemory + expr: | + ( + container_memory_working_set_bytes{container="etcd"} + / + ( container_spec_memory_limit_bytes{container="etcd"} > 0 ) + ) > 0.8 + for: 15m + labels: + severity: critical +- name: alertmanager_alerts + rules: + - alert: MimirAlertmanagerSyncConfigsFailing + annotations: + message: | + Mimir Alertmanager {{ $labels.job }}/{{ $labels.pod }} is failing to read tenant configurations from storage. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiralertmanagersyncconfigsfailing + expr: | + rate(cortex_alertmanager_sync_configs_failed_total[5m]) > 0 + for: 30m + labels: + severity: critical + - alert: MimirAlertmanagerRingCheckFailing + annotations: + message: | + Mimir Alertmanager {{ $labels.job }}/{{ $labels.pod }} is unable to check tenants ownership via the ring. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiralertmanagerringcheckfailing + expr: | + rate(cortex_alertmanager_ring_check_errors_total[2m]) > 0 + for: 10m + labels: + severity: critical + - alert: MimirAlertmanagerPartialStateMergeFailing + annotations: + message: | + Mimir Alertmanager {{ $labels.job }}/{{ $labels.pod }} is failing to merge partial state changes received from a replica. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiralertmanagerpartialstatemergefailing + expr: | + rate(cortex_alertmanager_partial_state_merges_failed_total[2m]) > 0 + for: 10m + labels: + severity: critical + - alert: MimirAlertmanagerReplicationFailing + annotations: + message: | + Mimir Alertmanager {{ $labels.job }}/{{ $labels.pod }} is failing to replicating partial state to its replicas. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiralertmanagerreplicationfailing + expr: | + rate(cortex_alertmanager_state_replication_failed_total[2m]) > 0 + for: 10m + labels: + severity: critical + - alert: MimirAlertmanagerPersistStateFailing + annotations: + message: | + Mimir Alertmanager {{ $labels.job }}/{{ $labels.pod }} is unable to persist full state snaphots to remote storage. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiralertmanagerpersiststatefailing + expr: | + rate(cortex_alertmanager_state_persist_failed_total[15m]) > 0 + for: 1h + labels: + severity: critical + - alert: MimirAlertmanagerInitialSyncFailed + annotations: + message: | + Mimir Alertmanager {{ $labels.job }}/{{ $labels.pod }} was unable to obtain some initial state when starting up. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiralertmanagerinitialsyncfailed + expr: | + increase(cortex_alertmanager_state_initial_sync_completed_total{outcome="failed"}[1m]) > 0 + labels: + severity: critical + - alert: MimirAlertmanagerAllocatingTooMuchMemory + annotations: + message: | + Alertmanager {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace }} is using too much memory. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiralertmanagerallocatingtoomuchmemory + expr: | + (container_memory_working_set_bytes{container="alertmanager"} / container_spec_memory_limit_bytes{container="alertmanager"}) > 0.80 + and + (container_spec_memory_limit_bytes{container="alertmanager"} > 0) + for: 15m + labels: + severity: warning + - alert: MimirAlertmanagerAllocatingTooMuchMemory + annotations: + message: | + Alertmanager {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace }} is using too much memory. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiralertmanagerallocatingtoomuchmemory + expr: | + (container_memory_working_set_bytes{container="alertmanager"} / container_spec_memory_limit_bytes{container="alertmanager"}) > 0.90 + and + (container_spec_memory_limit_bytes{container="alertmanager"} > 0) + for: 15m + labels: + severity: critical + - alert: MimirAlertmanagerInstanceHasNoTenants + annotations: + message: Mimir alertmanager {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} owns no tenants. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiralertmanagerinstancehasnotenants + expr: | + # Alert on alertmanager instances in microservices mode that own no tenants, + min by(cluster, namespace, pod) (cortex_alertmanager_tenants_owned{pod=~"(.*mimir-)?alertmanager.*"}) == 0 + # but only if other instances of the same cell do have tenants assigned. + and on (cluster, namespace) + max by(cluster, namespace) (cortex_alertmanager_tenants_owned) > 0 + for: 1h + labels: + severity: warning +- name: mimir_blocks_alerts + rules: + - alert: MimirIngesterHasNotShippedBlocks + annotations: + message: Mimir Ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has not shipped any block in the last 4 hours. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterhasnotshippedblocks + expr: | + (min by(cluster, namespace, pod) (time() - cortex_ingester_shipper_last_successful_upload_timestamp_seconds) > 60 * 60 * 4) + and + (max by(cluster, namespace, pod) (cortex_ingester_shipper_last_successful_upload_timestamp_seconds) > 0) + and + # Only if the ingester has ingested samples over the last 4h. + (max by(cluster, namespace, pod) (max_over_time(cluster_namespace_pod:cortex_ingester_ingested_samples_total:rate1m[4h])) > 0) + and + # Only if the ingester was ingesting samples 4h ago. This protects against the case where the ingester replica + # had ingested samples in the past, then no traffic was received for a long period and then it starts + # receiving samples again. Without this check, the alert would fire as soon as it gets back receiving + # samples, while the a block shipping is expected within the next 4h. + (max by(cluster, namespace, pod) (max_over_time(cluster_namespace_pod:cortex_ingester_ingested_samples_total:rate1m[1h] offset 4h)) > 0) + for: 15m + labels: + severity: critical + - alert: MimirIngesterHasNotShippedBlocksSinceStart + annotations: + message: Mimir Ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has not shipped any block in the last 4 hours. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterhasnotshippedblockssincestart + expr: | + (max by(cluster, namespace, pod) (cortex_ingester_shipper_last_successful_upload_timestamp_seconds) == 0) + and + (max by(cluster, namespace, pod) (max_over_time(cluster_namespace_pod:cortex_ingester_ingested_samples_total:rate1m[4h])) > 0) + for: 4h + labels: + severity: critical + - alert: MimirIngesterHasUnshippedBlocks + annotations: + message: Mimir Ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has compacted a block {{ $value | humanizeDuration }} ago but it hasn't + been successfully uploaded to the storage yet. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterhasunshippedblocks + expr: | + (time() - cortex_ingester_oldest_unshipped_block_timestamp_seconds > 3600) + and + (cortex_ingester_oldest_unshipped_block_timestamp_seconds > 0) + for: 15m + labels: + severity: critical + - alert: MimirIngesterTSDBHeadCompactionFailed + annotations: + message: Mimir Ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} is failing to compact TSDB head. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringestertsdbheadcompactionfailed + expr: | + rate(cortex_ingester_tsdb_compactions_failed_total[5m]) > 0 + for: 15m + labels: + severity: critical + - alert: MimirIngesterTSDBHeadTruncationFailed + annotations: + message: Mimir Ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} is failing to truncate TSDB head. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringestertsdbheadtruncationfailed + expr: | + rate(cortex_ingester_tsdb_head_truncations_failed_total[5m]) > 0 + labels: + severity: critical + - alert: MimirIngesterTSDBCheckpointCreationFailed + annotations: + message: Mimir Ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} is failing to create TSDB checkpoint. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringestertsdbcheckpointcreationfailed + expr: | + rate(cortex_ingester_tsdb_checkpoint_creations_failed_total[5m]) > 0 + labels: + severity: critical + - alert: MimirIngesterTSDBCheckpointDeletionFailed + annotations: + message: Mimir Ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} is failing to delete TSDB checkpoint. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringestertsdbcheckpointdeletionfailed + expr: | + rate(cortex_ingester_tsdb_checkpoint_deletions_failed_total[5m]) > 0 + labels: + severity: critical + - alert: MimirIngesterTSDBWALTruncationFailed + annotations: + message: Mimir Ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} is failing to truncate TSDB WAL. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringestertsdbwaltruncationfailed + expr: | + rate(cortex_ingester_tsdb_wal_truncations_failed_total[5m]) > 0 + labels: + severity: warning + - alert: MimirIngesterTSDBWALCorrupted + annotations: + message: Mimir Ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} got a corrupted TSDB WAL. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringestertsdbwalcorrupted + expr: | + # alert when there are more than one corruptions + count by (cluster, namespace) (rate(cortex_ingester_tsdb_wal_corruptions_total[5m]) > 0) > 1 + and + # and there is only one zone + count by (cluster, namespace) (group by (cluster, namespace, job) (cortex_ingester_tsdb_wal_corruptions_total)) == 1 + labels: + deployment: single-zone + severity: critical + - alert: MimirIngesterTSDBWALCorrupted + annotations: + message: Mimir Ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} got a corrupted TSDB WAL. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringestertsdbwalcorrupted + expr: | + # alert when there are more than one corruptions + count by (cluster, namespace) (sum by (cluster, namespace, job) (rate(cortex_ingester_tsdb_wal_corruptions_total[5m]) > 0)) > 1 + and + # and there are multiple zones + count by (cluster, namespace) (group by (cluster, namespace, job) (cortex_ingester_tsdb_wal_corruptions_total)) > 1 + labels: + deployment: multi-zone + severity: critical + - alert: MimirIngesterTSDBWALWritesFailed + annotations: + message: Mimir Ingester {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} is failing to write to TSDB WAL. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringestertsdbwalwritesfailed + expr: | + rate(cortex_ingester_tsdb_wal_writes_failed_total[1m]) > 0 + for: 3m + labels: + severity: critical + - alert: MimirStoreGatewayHasNotSyncTheBucket + annotations: + message: Mimir store-gateway {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has not successfully synched the bucket since {{ $value | humanizeDuration + }}. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirstoregatewayhasnotsyncthebucket + expr: | + (time() - cortex_bucket_stores_blocks_last_successful_sync_timestamp_seconds{component="store-gateway"} > 60 * 30) + and + cortex_bucket_stores_blocks_last_successful_sync_timestamp_seconds{component="store-gateway"} > 0 + for: 5m + labels: + severity: critical + - alert: MimirStoreGatewayNoSyncedTenants + annotations: + message: Mimir store-gateway {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} is not syncing any blocks for any tenant. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirstoregatewaynosyncedtenants + expr: | + min by(cluster, namespace, pod) (cortex_bucket_stores_tenants_synced{component="store-gateway"}) == 0 + for: 1h + labels: + severity: warning + - alert: MimirBucketIndexNotUpdated + annotations: + message: Mimir bucket index for tenant {{ $labels.user }} in {{ $labels.cluster + }}/{{ $labels.namespace }} has not been updated since {{ $value | humanizeDuration + }}. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirbucketindexnotupdated + expr: | + min by(cluster, namespace, user) (time() - cortex_bucket_index_last_successful_update_timestamp_seconds) > 7200 + labels: + severity: critical +- name: mimir_compactor_alerts + rules: + - alert: MimirCompactorHasNotSuccessfullyCleanedUpBlocks + annotations: + message: Mimir Compactor {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has not successfully cleaned up blocks in the last 6 hours. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimircompactorhasnotsuccessfullycleanedupblocks + expr: | + # The "last successful run" metric is updated even if the compactor owns no tenants, + # so this alert correctly doesn't fire if compactor has nothing to do. + (time() - cortex_compactor_block_cleanup_last_successful_run_timestamp_seconds > 60 * 60 * 6) + for: 1h + labels: + severity: critical + - alert: MimirCompactorHasNotSuccessfullyRunCompaction + annotations: + message: Mimir Compactor {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has not run compaction in the last 24 hours. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimircompactorhasnotsuccessfullyruncompaction + expr: | + # The "last successful run" metric is updated even if the compactor owns no tenants, + # so this alert correctly doesn't fire if compactor has nothing to do. + (time() - cortex_compactor_last_successful_run_timestamp_seconds > 60 * 60 * 24) + and + (cortex_compactor_last_successful_run_timestamp_seconds > 0) + for: 1h + labels: + reason: in-last-24h + severity: critical + - alert: MimirCompactorHasNotSuccessfullyRunCompaction + annotations: + message: Mimir Compactor {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has not run compaction in the last 24 hours. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimircompactorhasnotsuccessfullyruncompaction + expr: | + # The "last successful run" metric is updated even if the compactor owns no tenants, + # so this alert correctly doesn't fire if compactor has nothing to do. + cortex_compactor_last_successful_run_timestamp_seconds == 0 + for: 24h + labels: + reason: since-startup + severity: critical + - alert: MimirCompactorHasNotSuccessfullyRunCompaction + annotations: + message: Mimir Compactor {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} failed to run 2 consecutive compactions. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimircompactorhasnotsuccessfullyruncompaction + expr: | + increase(cortex_compactor_runs_failed_total{reason!="shutdown"}[2h]) >= 2 + labels: + reason: consecutive-failures + severity: critical + - alert: MimirCompactorHasNotUploadedBlocks + annotations: + message: Mimir Compactor {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has not uploaded any block in the last 24 hours. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimircompactorhasnotuploadedblocks + expr: | + (time() - (max by(cluster, namespace, pod) (thanos_objstore_bucket_last_successful_upload_time{component="compactor"})) > 60 * 60 * 24) + and + (max by(cluster, namespace, pod) (thanos_objstore_bucket_last_successful_upload_time{component="compactor"}) > 0) + and + # Only if some compactions have started. We don't want to fire this alert if the compactor has nothing to do + # (e.g. there are more replicas than required because running as part of mimir-backend). + (sum by(cluster, namespace, pod) (rate(cortex_compactor_group_compaction_runs_started_total[24h])) > 0) + for: 15m + labels: + severity: critical + time_period: 24h + - alert: MimirCompactorHasNotUploadedBlocks + annotations: + message: Mimir Compactor {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has not uploaded any block since its start. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimircompactorhasnotuploadedblocks + expr: | + (max by(cluster, namespace, pod) (thanos_objstore_bucket_last_successful_upload_time{component="compactor"}) == 0) + and + # Only if some compactions have started. We don't want to fire this alert if the compactor has nothing to do + # (e.g. there are more replicas than required because running as part of mimir-backend). + (sum by(cluster, namespace, pod) (rate(cortex_compactor_group_compaction_runs_started_total[24h])) > 0) + for: 24h + labels: + severity: critical + time_period: since-start + - alert: MimirCompactorSkippedUnhealthyBlocks + annotations: + message: Mimir Compactor {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has found and ignored unhealthy blocks. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimircompactorskippedunhealthyblocks + expr: | + increase(cortex_compactor_blocks_marked_for_no_compaction_total[5m]) > 0 + for: 1m + labels: + severity: warning + - alert: MimirCompactorSkippedUnhealthyBlocks + annotations: + message: Mimir Compactor {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} has found and ignored unhealthy blocks. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimircompactorskippedunhealthyblocks + expr: | + increase(cortex_compactor_blocks_marked_for_no_compaction_total[5m]) > 1 + for: 30m + labels: + severity: critical +- name: mimir_autoscaling + rules: + - alert: MimirAutoscalerNotActive + annotations: + message: The Horizontal Pod Autoscaler (HPA) {{ $labels.horizontalpodautoscaler + }} in {{ $labels.namespace }} is not active. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirautoscalernotactive + expr: | + ( + label_replace(( + kube_horizontalpodautoscaler_status_condition{condition="ScalingActive",status="false"} + # Match only Mimir namespaces. + * on(cluster, namespace) group_left max by(cluster, namespace) (cortex_build_info) + # Add "metric" label. + + on(cluster, namespace, horizontalpodautoscaler) group_right label_replace(kube_horizontalpodautoscaler_spec_target_metric*0, "metric", "$1", "metric_name", "(.+)") + > 0), + "scaledObject", "$1", "horizontalpodautoscaler", "keda-hpa-(.*)" + ) + ) + # Alert only if the scaling metric exists and is > 0. If the KEDA ScaledObject is configured to scale down 0, + # then HPA ScalingActive may be false when expected to run 0 replicas. In this case, the scaling metric exported + # by KEDA could not exist at all or being exposed with a value of 0. + and on (cluster, namespace, metric, scaledObject) + (label_replace(keda_scaler_metrics_value, "namespace", "$0", "exported_namespace", ".+") > 0) + for: 1h + labels: + severity: critical + - alert: MimirAutoscalerKedaFailing + annotations: + message: The Keda ScaledObject {{ $labels.scaledObject }} in {{ $labels.namespace + }} is experiencing errors. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirautoscalerkedafailing + expr: | + ( + # Find KEDA scalers reporting errors. + label_replace(rate(keda_scaler_errors[5m]), "namespace", "$1", "exported_namespace", "(.*)") + # Match only Mimir namespaces. + * on(cluster, namespace) group_left max by(cluster, namespace) (cortex_build_info) + ) + > 0 + for: 1h + labels: + severity: critical +- name: mimir_ingest_storage_alerts + rules: + - alert: MimirIngesterLastConsumedOffsetCommitFailed + annotations: + message: Mimir {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} is failing to commit the last consumed offset. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterlastconsumedoffsetcommitfailed + expr: | + sum by(cluster, namespace, pod) (rate(cortex_ingest_storage_reader_offset_commit_failures_total[5m])) + / + sum by(cluster, namespace, pod) (rate(cortex_ingest_storage_reader_offset_commit_requests_total[5m])) + > 0.2 + for: 15m + labels: + severity: critical + - alert: MimirIngesterFailedToReadRecordsFromKafka + annotations: + message: Mimir {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} is failing to read records from Kafka. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterfailedtoreadrecordsfromkafka + expr: | + sum by(cluster, namespace, pod, node_id) (rate(cortex_ingest_storage_reader_read_errors_total[1m])) + > 0 + for: 5m + labels: + severity: critical + - alert: MimirIngesterKafkaFetchErrorsRateTooHigh + annotations: + message: Mimir {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} is receiving fetch errors when reading records from Kafka. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterkafkafetcherrorsratetoohigh + expr: | + sum by (cluster, namespace, pod) (rate (cortex_ingest_storage_reader_fetch_errors_total[5m])) + / + sum by (cluster, namespace, pod) (rate (cortex_ingest_storage_reader_fetches_total[5m])) + > 0.1 + for: 15m + labels: + severity: critical + - alert: MimirStartingIngesterKafkaReceiveDelayIncreasing + annotations: + message: Mimir {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} in "starting" phase is not reducing consumption lag of write requests read + from Kafka. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirstartingingesterkafkareceivedelayincreasing + expr: | + deriv(( + sum by (cluster, namespace, pod) (rate(cortex_ingest_storage_reader_receive_delay_seconds_sum{phase="starting"}[1m])) + / + sum by (cluster, namespace, pod) (rate(cortex_ingest_storage_reader_receive_delay_seconds_count{phase="starting"}[1m])) + )[5m:1m]) > 0 + for: 5m + labels: + severity: warning + - alert: MimirRunningIngesterReceiveDelayTooHigh + annotations: + message: Mimir {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} in "running" phase is too far behind in its consumption of write requests + from Kafka. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimirrunningingesterreceivedelaytoohigh + expr: | + ( + sum by (cluster, namespace, pod) (rate(cortex_ingest_storage_reader_receive_delay_seconds_sum{phase="running"}[1m])) + / + sum by (cluster, namespace, pod) (rate(cortex_ingest_storage_reader_receive_delay_seconds_count{phase="running"}[1m])) + ) > (10 * 60) + for: 5m + labels: + severity: critical + - alert: MimirIngesterFailsToProcessRecordsFromKafka + annotations: + message: Mimir {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} fails to consume write requests read from Kafka due to internal errors. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterfailstoprocessrecordsfromkafka + expr: | + sum by (cluster, namespace, pod) (rate(cortex_ingest_storage_reader_records_failed_total{cause="server"}[1m])) > 0 + for: 5m + labels: + severity: critical + - alert: MimirIngesterFailsEnforceStrongConsistencyOnReadPath + annotations: + message: Mimir {{ $labels.pod }} in {{ $labels.cluster }}/{{ $labels.namespace + }} fails to enforce strong-consistency on read-path. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimiringesterfailsenforcestrongconsistencyonreadpath + expr: | + sum by (cluster, namespace, pod) (rate(cortex_ingest_storage_strong_consistency_failures_total[1m])) > 0 + for: 5m + labels: + severity: critical +- name: mimir_continuous_test + rules: + - alert: MimirContinuousTestNotRunningOnWrites + annotations: + message: Mimir continuous test {{ $labels.test }} in {{ $labels.cluster }}/{{ + $labels.namespace }} is not effectively running because writes are failing. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimircontinuoustestnotrunningonwrites + expr: | + sum by(cluster, namespace, test) (rate(mimir_continuous_test_writes_failed_total[5m])) > 0 + for: 1h + labels: + severity: warning + - alert: MimirContinuousTestNotRunningOnReads + annotations: + message: Mimir continuous test {{ $labels.test }} in {{ $labels.cluster }}/{{ + $labels.namespace }} is not effectively running because queries are failing. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimircontinuoustestnotrunningonreads + expr: | + sum by(cluster, namespace, test) (rate(mimir_continuous_test_queries_failed_total[5m])) > 0 + for: 1h + labels: + severity: warning + - alert: MimirContinuousTestFailed + annotations: + message: Mimir continuous test {{ $labels.test }} in {{ $labels.cluster }}/{{ + $labels.namespace }} failed when asserting query results. + runbook_url: https://grafana.com/docs/mimir/latest/operators-guide/mimir-runbooks/#mimircontinuoustestfailed + expr: | + sum by(cluster, namespace, test) (rate(mimir_continuous_test_query_result_checks_failed_total[10m])) > 0 + labels: + severity: warning diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-alertmanager-resources.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-alertmanager-resources.json new file mode 100644 index 0000000..18d924e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-alertmanager-resources.json @@ -0,0 +1,697 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"alertmanager\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alertmanager", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?alertmanager.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?alertmanager.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_written_bytes_total[$__rate_interval]\n )\n)\n+\nignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"alertmanager\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "title": "Disk writes", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_read_bytes_total[$__rate_interval]\n )\n) + ignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"alertmanager\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "title": "Disk reads", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 12, + "targets": [ + { + "expr": "max by(persistentvolumeclaim) (\n kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n kube_persistentvolumeclaim_labels{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n label_name=~\"(alertmanager).*\"\n }\n)\n", + "format": "time_series", + "legendFormat": "{{persistentvolumeclaim}}", + "legendLink": null + } + ], + "title": "Disk space utilization", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Alertmanager resources", + "uid": "a6883fb22799ac74479c7db872451092", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-alertmanager.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-alertmanager.json new file mode 100644 index 0000000..92596ba --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-alertmanager.json @@ -0,0 +1,2444 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_job_pod:cortex_alertmanager_alerts:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Total alerts", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_job_pod:cortex_alertmanager_silences:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Total silences", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max(cortex_alertmanager_tenants_discovered{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Tenants", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "QPS", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})) * 1e3", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", route=~\"/alertmanagerpb.Alertmanager/HandleRequest\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alertmanager Distributor", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 12, + "targets": [ + { + "expr": "sum(cluster_job:cortex_alertmanager_alerts_received_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "APS", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alerts received", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 12, + "targets": [ + { + "expr": "cortex_alertmanager_dispatcher_aggregation_groups{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "per pod Active Aggregation Groups", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alerts grouping", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "NPS", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "(\nsum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)\n-\nsum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)\n) > 0\nor on () vector(0)\n", + "format": "time_series", + "legendFormat": "success - {{ integration }}", + "legendLink": null + }, + { + "expr": "sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}) by(integration)", + "format": "time_series", + "legendFormat": "failed - {{ integration }}", + "legendLink": null + } + ], + "title": "NPS by integration", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_alertmanager_notification_latency_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_alertmanager_notification_latency_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_alertmanager_notification_latency_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_alertmanager_notification_latency_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alert notifications", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Operations / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\"}[$__rate_interval])) >= 0", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Error rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 13, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"attributes\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Attributes", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"exists\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Exists", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alertmanager Configuration Object Store (Alertmanager accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 15, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Get", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 16, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"get_range\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: GetRange", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 17, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Upload", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 18, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"alertmanager-storage\",operation=\"delete\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Delete", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 19, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (cortex_alertmanager_tenants_owned{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Per pod tenants", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 20, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (cluster_job_pod:cortex_alertmanager_alerts:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Per pod alerts", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 21, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (cluster_job_pod:cortex_alertmanager_silences:sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Per pod silences", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Replication", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 22, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(cortex_alertmanager_sync_configs_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_sync_configs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_alertmanager_sync_configs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Syncs/sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 23, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(reason) (rate(cortex_alertmanager_sync_configs_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{reason}}", + "legendLink": null + } + ], + "title": "Syncs/sec (by reason)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 24, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum (rate(cortex_alertmanager_ring_check_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "errors", + "legendLink": null + } + ], + "title": "Ring check errors/sec", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Tenant configuration sync", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 25, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(outcome) (rate(cortex_alertmanager_state_initial_sync_completed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "interval": "1m", + "legendFormat": "{{outcome}}", + "legendLink": null + } + ], + "title": "Initial syncs /sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 26, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "interval": "1m", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "interval": "1m", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_alertmanager_state_initial_sync_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "interval": "1m", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Initial sync duration", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 27, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(cortex_alertmanager_state_fetch_replica_state_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "interval": "1m", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_alertmanager_state_fetch_replica_state_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "interval": "1m", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Fetch state from other alertmanagers /sec", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Sharding initial state sync", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 28, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(cluster_job:cortex_alertmanager_state_replication_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Replicate state to other alertmanagers /sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 29, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n-\nsum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Merge state from other alertmanagers /sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 30, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(cortex_alertmanager_state_persist_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_alertmanager_state_persist_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_alertmanager_state_persist_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Persist state to remote storage /sec", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Sharding runtime state sync", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Alertmanager", + "uid": "b0d38d318bbddd80476246d4930f9e55", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-compactor-resources.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-compactor-resources.json new file mode 100644 index 0000000..3ca6721 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-compactor-resources.json @@ -0,0 +1,810 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU and memory", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "max by(pod) (container_memory_rss{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (RSS)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"compactor\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?compactor.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?compactor.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_written_bytes_total[$__rate_interval]\n )\n)\n+\nignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"compactor\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "title": "Disk writes", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_read_bytes_total[$__rate_interval]\n )\n) + ignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"compactor\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "title": "Disk reads", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(persistentvolumeclaim) (\n kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n kube_persistentvolumeclaim_labels{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n label_name=~\"(compactor).*\"\n }\n)\n", + "format": "time_series", + "legendFormat": "{{persistentvolumeclaim}}", + "legendLink": null + } + ], + "title": "Disk space utilization", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Compactor resources", + "uid": "09a5c49e9cdb2f2b24c6d184574a07fd", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-compactor.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-compactor.json new file mode 100644 index 0000000..7a80a90 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-compactor.json @@ -0,0 +1,2161 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Per-instance runs\nNumber of times a compactor instance triggers a compaction across all tenants that it manages.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "bars", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ops" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "completed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "started" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#34CCEB", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_compactor_runs_started_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "started", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_compactor_runs_completed_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "completed", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_compactor_runs_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Per-instance runs / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Tenants compaction progress\nIn a multi-tenant cluster, display the progress of tenants that are compacted while compaction is running.\n\n", + "fieldConfig": { + "defaults": { + "max": 1, + "noValue": 1, + "unit": "percentunit" + } + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "(\n cortex_compactor_tenants_processing_succeeded{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"} +\n cortex_compactor_tenants_processing_failed{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"} +\n cortex_compactor_tenants_skipped{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}\n)\n/\ncortex_compactor_tenants_discovered{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"} > 0\n", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Tenants compaction progress", + "type": "timeseries" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Longest time since last successful run\nDisplays the amount of time since the most recent successful execution\nof the compactor.\nThe value shown will be for the compactor replica that has the longest time since its\nlast successful run.\nThe table to the right shows a summary for all compactor replicas.\n\nIf there is no time value, one of the following messages might appear:\n\n- If you see \"No compactor data\" in this panel, that means that no compactors are active yet.\n\n- If you see \"No successful runs\" in this panel, that means that compactors are active, but none\n of them were successfully executed yet.\n\nThese might be expected - for example, if you just recently restarted your compactors,\nthey might not have had a chance to complete their first compaction run.\nHowever, if these messages persist, you should check the health of your compactors.\n\n", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "No compactor data", + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Last run" + }, + "properties": [ + { + "id": "custom.width", + "value": 74 + }, + { + "id": "mappings", + "value": [ + { + "options": { + "from": "-Infinity", + "result": { + "color": "text", + "text": "No successful runs since startup yet" + }, + "to": 0 + }, + "type": "range" + } + ] + }, + { + "id": "color", + "value": { + "mode": "thresholds" + } + }, + { + "id": "thresholds", + "value": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "yellow", + "value": 7200 + }, + { + "color": "orange", + "value": 21600 + }, + { + "color": "red", + "value": 43200 + } + ] + } + } + ] + } + ] + }, + "fill": 1, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "reduceOptions": { + "calcs": [ + "first" + ], + "fields": "/^Last run$/", + "values": false + }, + "textMode": "value" + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(pod)\n(\n (time() * (max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h]) !=bool 0))\n -\n max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h])\n)\n", + "format": "table", + "instant": true, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Longest time since last successful run", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transformations": [ + { + "id": "organize", + "options": { + "renameByName": { + "Value": "Last run", + "pod": "Compactor" + } + } + }, + { + "id": "sortBy", + "options": { + "sort": [ + { + "desc": true, + "field": "Last run" + } + ] + } + } + ], + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "description": "### Last successful run per-compactor replica\nDisplays the compactor replicas, and for each, shows how long it has been since\nits last successful compaction run.\n\nThe value in the status column is based on how long it has been since the last successful compaction.\n\n- Okay: less than 2 hours\n- Delayed: more than 2 hours\n- Late: more than 6 hours\n- Very late: more than 12 hours\n\nIf the status of any compactor replicas are *Late* or *Very late*, check their health.\n\n", + "fieldConfig": { + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Status" + }, + "properties": [ + { + "id": "custom.displayMode", + "value": "color-background" + }, + { + "id": "mappings", + "value": [ + { + "options": { + "from": "-Infinity", + "result": { + "color": "transparent", + "text": "N/A" + }, + "to": 0 + }, + "type": "range" + }, + { + "options": { + "from": 0, + "result": { + "color": "green", + "text": "Ok" + }, + "to": 7200 + }, + "type": "range" + }, + { + "options": { + "from": 7200, + "result": { + "color": "yellow", + "text": "Delayed" + }, + "to": 21600 + }, + "type": "range" + }, + { + "options": { + "from": 21600, + "result": { + "color": "orange", + "text": "Late" + }, + "to": 43200 + }, + "type": "range" + }, + { + "options": { + "from": 43200, + "result": { + "color": "red", + "text": "Very late" + }, + "to": "Infinity" + }, + "type": "range" + }, + { + "options": { + "match": "null+nan", + "result": { + "color": "transparent", + "text": "Unknown" + } + }, + "type": "special" + } + ] + }, + { + "id": "custom.width", + "value": 86 + }, + { + "id": "custom.align", + "value": "center" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Last run" + }, + "properties": [ + { + "id": "unit", + "value": "s" + }, + { + "id": "custom.width", + "value": 74 + }, + { + "id": "mappings", + "value": [ + { + "options": { + "from": "-Infinity", + "result": { + "text": "Never" + }, + "to": 0 + }, + "type": "range" + } + ] + } + ] + } + ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "max by(pod)\n(\n (time() * (max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h]) !=bool 0))\n -\n max_over_time(cortex_compactor_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[1h])\n)\n", + "format": "table", + "instant": true, + "legendFormat": "Last run", + "legendLink": null + } + ], + "title": "Last successful run per-compactor replica", + "transformations": [ + { + "id": "organize", + "options": { + "renameByName": { + "Value": "Last run", + "pod": "Compactor" + } + } + }, + { + "id": "sortBy", + "options": { + "sort": [ + { + "desc": true, + "field": "Last run" + } + ] + } + }, + { + "id": "calculateField", + "options": { + "alias": "One", + "binary": { + "left": "Last run", + "operator": "/", + "right": "Last run" + }, + "mode": "binary", + "replaceFields": false + } + }, + { + "id": "calculateField", + "options": { + "alias": "Status", + "binary": { + "left": "Last run", + "operator": "*", + "right": "One" + }, + "mode": "binary", + "replaceFields": false + } + }, + { + "id": "filterFieldsByName", + "options": { + "include": { + "names": [ + "Compactor", + "Last run", + "Status" + ] + } + } + } + ], + "type": "table" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Summary", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Estimated Compaction Jobs\nEstimated number of compaction jobs based on latest version of bucket index. Ingesters upload new blocks every 2 hours (shortly after 01:00 UTC, 03:00 UTC, 05:00 UTC, etc.),\nand compactors should process all of them within 2h interval. If this graph regularly goes to zero (or close to zero) in 2 hour intervals, then compaction works as designed.\n\nMetric with number of compaction jobs is computed from blocks in bucket index, which is updated regularly. Metric doesn't change between bucket index updates, even if\nthere were compaction jobs finished in this time. When computing compaction jobs, only jobs that can be executed at given moment are counted. There can be more\njobs, but if they are blocked, they are not counted in the metric. For example if there is a split compaction job pending for some time range, no merge job\ncovering the same time range can run. In this case only split compaction job is counted toward the metric, but merge job isn't.\n\nIn other words, computed number of compaction jobs is the minimum number of compaction jobs based on latest version of bucket index.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(cortex_bucket_index_estimated_compaction_jobs{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}) and (sum(rate(cortex_bucket_index_estimated_compaction_jobs_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) == 0)", + "format": "time_series", + "legendFormat": "Jobs", + "legendLink": null + } + ], + "title": "Estimated Compaction Jobs", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### TSDB compactions / sec\nRate of TSDB compactions. Single TSDB compaction takes one or more input blocks and produces one or more (during \"split\" phase) output blocks.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ops" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(prometheus_tsdb_compactions_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "compactions", + "legendLink": null + } + ], + "title": "TSDB compactions / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### TSDB compaction duration\nDisplay the amount of time that it has taken to run a single TSDB compaction.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(prometheus_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(prometheus_tsdb_compaction_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(prometheus_tsdb_compaction_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "TSDB compaction duration", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "avg(max by(user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + } + ], + "title": "Average blocks / tenant", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Tenants with largest number of blocks\nThe 10 tenants with the largest number of blocks.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "topk(10, max by(user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}))", + "format": "time_series", + "legendFormat": "{{user}}", + "legendLink": null + } + ], + "title": "Tenants with largest number of blocks", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ops" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(rate(cortex_compactor_blocks_marked_for_deletion_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "blocks", + "legendLink": null + } + ], + "title": "Blocks marked for deletion / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ops" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(rate(cortex_compactor_blocks_cleaned_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_compactor_block_cleanup_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Blocks deletions / sec", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Garbage collector", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ops" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(rate(cortex_compactor_meta_syncs_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_compactor_meta_sync_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_compactor_meta_sync_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Metadata syncs / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 13, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_compactor_meta_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_compactor_meta_sync_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_compactor_meta_sync_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_compactor_meta_sync_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Metadata sync duration", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Metadata sync", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Operations / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 15, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\"}[$__rate_interval])) >= 0", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Error rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 16, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"attributes\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Attributes", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 17, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"exists\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Exists", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Object Store", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 18, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Get", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 19, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"get_range\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: GetRange", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 20, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Upload", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 21, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"compactor\",operation=\"delete\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Delete", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 22, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 23, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", kv_name=~\".+\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Key-value store for compactors ring", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Compactor", + "uid": "1b3443aea86db629e6efdb7d05c53823", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-config.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-config.json new file mode 100644 index 0000000..069ce8d --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-config.json @@ -0,0 +1,258 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "instances" + }, + "overrides": [ ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 12, + "targets": [ + { + "expr": "count(cortex_config_hash{cluster=~\"$cluster\", namespace=~\"$namespace\"}) by (sha256)", + "format": "time_series", + "legendFormat": "sha256:{{sha256}}", + "legendLink": null + } + ], + "title": "Startup config file hashes", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Startup config file", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "instances" + }, + "overrides": [ ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 12, + "targets": [ + { + "expr": "count(cortex_runtime_config_hash{cluster=~\"$cluster\", namespace=~\"$namespace\"}) by (sha256)", + "format": "time_series", + "legendFormat": "sha256:{{sha256}}", + "legendLink": null + } + ], + "title": "Runtime config file hashes", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Runtime config file", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Config", + "uid": "5d9d0b4724c0f80d68467088ec61e003", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-object-store.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-object-store.json new file mode 100644 index 0000000..456b849 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-object-store.json @@ -0,0 +1,822 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(component) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{component}}", + "legendLink": null + } + ], + "title": "RPS / component", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(component) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) / sum by(component) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) >= 0", + "format": "time_series", + "legendFormat": "{{component}}", + "legendLink": null + } + ], + "title": "Error rate / component", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Components", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "RPS / operation", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) >= 0", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Error rate / operation", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Operations", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Op: Get", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"get_range\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Op: GetRange", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"exists\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Op: Exists", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"attributes\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Op: Attributes", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Op: Upload", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",operation=\"delete\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Op: Delete", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Object Store", + "uid": "e1324ee2a434f4158c00a9ee279d3292", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-overrides.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-overrides.json new file mode 100644 index 0000000..708e1b2 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-overrides.json @@ -0,0 +1,266 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "${datasource}", + "id": 1, + "span": 12, + "targets": [ + { + "expr": "max by(limit_name) (cortex_limits_defaults{cluster=~\"$cluster\",namespace=~\"$namespace\"})", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Defaults", + "transformations": [ + { + "id": "labelsToFields", + "options": { } + }, + { + "id": "merge", + "options": { } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true + }, + "indexByName": { + "Value": 1, + "limit_name": 0 + } + } + }, + { + "id": "sortBy", + "options": { + "fields": { }, + "sort": [ + { + "field": "limit_name" + } + ] + } + } + ], + "type": "table" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "${datasource}", + "id": 2, + "span": 12, + "targets": [ + { + "expr": "max by(user, limit_name) (cortex_limits_overrides{cluster=~\"$cluster\",namespace=~\"$namespace\",user=~\"${tenant_id}\"})", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Per-tenant overrides", + "transformations": [ + { + "id": "labelsToFields", + "options": { + "mode": "columns", + "valueLabel": "limit_name" + } + }, + { + "id": "merge", + "options": { } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true + }, + "indexByName": { + "user": 0 + } + } + } + ], + "type": "table" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "current": { + "selected": true, + "text": ".*", + "value": ".*" + }, + "hide": 0, + "label": "Tenant ID", + "name": "tenant_id", + "options": [ + { + "selected": true, + "text": ".*", + "value": ".*" + } + ], + "query": ".*", + "type": "textbox" + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Overrides", + "uid": "1e2c358600ac53f09faea133f811b5bb", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-overview-networking.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-overview-networking.json new file mode 100644 index 0000000..451d487 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-overview-networking.json @@ -0,0 +1,820 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Writes", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Reads", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Backend", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Overview networking", + "uid": "e15c71d372cc541367a088f10d9fcd92", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-overview-resources.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-overview-resources.json new file mode 100644 index 0000000..b5b33b8 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-overview-resources.json @@ -0,0 +1,922 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor|ingester|mimir-write\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor|ingester|mimir-write\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor|ingester|mimir-write\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Writes", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_written_bytes_total[$__rate_interval]\n )\n)\n+\nignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"distributor|ingester|mimir-write\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "title": "Disk writes", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_read_bytes_total[$__rate_interval]\n )\n) + ignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"distributor|ingester|mimir-write\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "title": "Disk reads", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(persistentvolumeclaim) (\n kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n kube_persistentvolumeclaim_labels{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n label_name=~\"(distributor|ingester|mimir-write).*\"\n }\n)\n", + "format": "time_series", + "legendFormat": "{{persistentvolumeclaim}}", + "legendLink": null + } + ], + "title": "Disk space utilization", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Reads", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Backend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 13, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_written_bytes_total[$__rate_interval]\n )\n)\n+\nignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "title": "Disk writes", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_read_bytes_total[$__rate_interval]\n )\n) + ignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "title": "Disk reads", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 15, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(persistentvolumeclaim) (\n kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n kube_persistentvolumeclaim_labels{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n label_name=~\"(query-scheduler|ruler-query-scheduler|ruler|store-gateway|compactor|alertmanager|overrides-exporter|mimir-backend).*\"\n }\n)\n", + "format": "time_series", + "legendFormat": "{{persistentvolumeclaim}}", + "legendLink": null + } + ], + "title": "Disk space utilization", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Overview resources", + "uid": "a9b92d3c4d1af325d872a9e9a7083d71", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-overview.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-overview.json new file mode 100644 index 0000000..1f16a96 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-overview.json @@ -0,0 +1,1600 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "content": "The 'Status' panel shows an overview on the cluster health over the time.\nTo investigate failures, see a specific dashboard:\n\n- Writes\n- Reads\n- Rule evaluations\n- Alerting notifications\n- Object storage\n", + "datasource": null, + "description": "", + "id": 1, + "mode": "markdown", + "span": 3, + "title": "", + "transparent": true, + "type": "text" + }, + { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "#7EB26D", + "value": null + }, + { + "color": "#EAB839", + "value": 0.01 + }, + { + "color": "#E24D42", + "value": 0.050000000000000003 + } + ] + } + } + }, + "id": 2, + "options": { + "showValue": "never" + }, + "span": 6, + "targets": [ + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": false, + "expr": "(\n # gRPC errors are not tracked as 5xx but \"error\".\n sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"5.*|error\"}[$__rate_interval]))\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n", + "instant": false, + "legendFormat": "Writes", + "range": true + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": false, + "expr": "(\n sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"5.*\"}[$__rate_interval]))\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n", + "instant": false, + "legendFormat": "Reads", + "range": true + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": false, + "expr": "(\n (\n sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n +\n # Consider missed evaluations as failures.\n sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n )\n or\n # Handle the case no failure has been tracked yet.\n vector(0)\n)\n/\nsum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "instant": false, + "legendFormat": "Rule evaluations", + "range": true + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": false, + "expr": "(\n # Failed notifications from ruler to Alertmanager (handling the case the ruler metrics are missing).\n ((sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n) or vector(0))\n +\n # Failed notifications from Alertmanager to receivers (handling the case the alertmanager metrics are missing).\n ((sum(cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n) or vector(0))\n)\n/\n(\n # Total notifications from ruler to Alertmanager (handling the case the ruler metrics are missing).\n ((sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n) or vector(0))\n +\n # Total notifications from Alertmanager to receivers (handling the case the alertmanager metrics are missing).\n ((sum(cluster_job_integration:cortex_alertmanager_notifications_total:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\"})\n) or vector(0))\n)\n", + "instant": false, + "legendFormat": "Alerting notifications", + "range": true + }, + { + "datasource": { + "uid": "$datasource" + }, + "exemplar": false, + "expr": "sum(rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))\n/\nsum(rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))\n", + "instant": false, + "legendFormat": "Object storage", + "range": true + } + ], + "title": "Status", + "type": "state-timeline" + }, + { + "id": 3, + "options": { + "alertInstanceLabelFilter": "cluster=~\"$cluster\", namespace=~\"$namespace\"", + "alertName": "Mimir", + "dashboardAlerts": false, + "maxItems": 100, + "sortOrder": 3, + "stateFilter": { + "error": true, + "firing": true, + "noData": false, + "normal": false, + "pending": false + } + }, + "span": 3, + "title": "Firing alerts", + "type": "alertlist" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Mimir cluster health", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "content": "These panels show an overview on the write path. \nTo examine the write path in detail, see a specific dashboard:\n\n- Writes\n- Writes resources\n- Writes networking\n- Overview resources\n- Overview networking\n", + "datasource": null, + "description": "", + "id": 4, + "mode": "markdown", + "span": 3, + "title": "", + "transparent": true, + "type": "text" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Write requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Write latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "cps" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(cluster_namespace_job:cortex_distributor_received_samples:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "legendFormat": "samples / sec", + "legendLink": null + }, + { + "expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "legendFormat": "exemplars / sec", + "legendLink": null + } + ], + "title": "Ingestion / sec", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Writes", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "content": "These panels show an overview on the read path. \nTo examine the read path in detail, see a specific dashboard:\n\n- Reads\n- Reads resources\n- Reads networking\n- Overview resources\n- Overview networking\n- Queries\n- Compactor\n", + "datasource": null, + "description": "", + "id": 8, + "mode": "markdown", + "span": 3, + "title": "", + "transparent": true, + "type": "text" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Read requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Read latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byRegexp", + "options": "/.*_api_v1_query($|[^_])/" + }, + "properties": [ + { + "id": "displayName", + "value": "instant queries" + }, + { + "id": "color", + "value": { + "fixedColor": "#429D48", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/.*_api_v1_query_range($|[^_])/" + }, + "properties": [ + { + "id": "displayName", + "value": "range queries" + }, + { + "id": "color", + "value": { + "fixedColor": "#F1C731", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/.*_api_v1_labels($|[^_])/" + }, + "properties": [ + { + "id": "displayName", + "value": "\"label names\" queries" + }, + { + "id": "color", + "value": { + "fixedColor": "#2A66CF", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/.*_api_v1_label_name_values($|[^_])/" + }, + "properties": [ + { + "id": "displayName", + "value": "\"label values\" queries" + }, + { + "id": "color", + "value": { + "fixedColor": "#9E44C1", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/.*_api_v1_series($|[^_])/" + }, + "properties": [ + { + "id": "displayName", + "value": "series queries" + }, + { + "id": "color", + "value": { + "fixedColor": "#FFAB57", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/.*_api_v1_read($|[^_])/" + }, + "properties": [ + { + "id": "displayName", + "value": "remote read queries" + }, + { + "id": "color", + "value": { + "fixedColor": "#C79424", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/.*_api_v1_metadata($|[^_])/" + }, + "properties": [ + { + "id": "displayName", + "value": "metadata queries" + }, + { + "id": "color", + "value": { + "fixedColor": "#84D586", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/.*_api_v1_query_exemplars($|[^_])/" + }, + "properties": [ + { + "id": "displayName", + "value": "exemplar queries" + }, + { + "id": "color", + "value": { + "fixedColor": "#A1C4FC", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/.*_api_v1_cardinality_active_series($|[^_])/" + }, + "properties": [ + { + "id": "displayName", + "value": "\"active series\" queries" + }, + { + "id": "color", + "value": { + "fixedColor": "#C788DE", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/.*_api_v1_cardinality_label_names($|[^_])/" + }, + "properties": [ + { + "id": "displayName", + "value": "\"label name cardinality\" queries" + }, + { + "id": "color", + "value": { + "fixedColor": "#3F6833", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/.*_api_v1_cardinality_label_values($|[^_])/" + }, + "properties": [ + { + "id": "displayName", + "value": "\"label value cardinality\" queries" + }, + { + "id": "color", + "value": { + "fixedColor": "#447EBC", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by (route) (rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)(_api_v1_query|_api_v1_query_range|_api_v1_labels|_api_v1_label_name_values|_api_v1_series|_api_v1_read|_api_v1_metadata|_api_v1_query_exemplars|_api_v1_cardinality_active_series|_api_v1_cardinality_label_names|_api_v1_cardinality_label_values)\"}[$__rate_interval]))", + "format": "time_series", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_.*\",route!~\"(prometheus|api_prom)(_api_v1_query|_api_v1_query_range|_api_v1_labels|_api_v1_label_name_values|_api_v1_series|_api_v1_read|_api_v1_metadata|_api_v1_query_exemplars|_api_v1_cardinality_active_series|_api_v1_cardinality_label_names|_api_v1_cardinality_label_values)\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "other", + "legendLink": null + } + ], + "title": "Queries / sec", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Reads", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "content": "These panels show an overview on the recording and alerting rules evaluation.\nTo examine the rules evaluation and alerts notifications in detail, see a specific dashboard:\n\n- Ruler\n- Alertmanager\n- Alertmanager resources\n- Overview resources\n- Overview networking\n", + "datasource": null, + "description": "", + "id": 12, + "mode": "markdown", + "span": 3, + "title": "", + "transparent": true, + "type": "text" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 13, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "success", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "missed", + "legendLink": null + } + ], + "title": "Rule evaluations / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "average", + "legendLink": null + } + ], + "title": "Rule evaluations latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 15, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n -\nsum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Alerting notifications sent to Alertmanager / sec", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Recording and alerting rules", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "content": "These panels show an overview on the long-term storage (object storage).\nTo examine the storage in detail, see a specific dashboard:\n\n- Object store\n- Compactor\n", + "datasource": null, + "description": "", + "id": 16, + "mode": "markdown", + "span": 3, + "title": "", + "transparent": true, + "type": "text" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 17, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))\n-\nsum(rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ ] + }, + "id": 18, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "seriesOverrides": [ + { + "alias": "attributes", + "color": "#429D48" + }, + { + "alias": "delete", + "color": "#F1C731" + }, + { + "alias": "exists", + "color": "#2A66CF" + }, + { + "alias": "get", + "color": "#9E44C1" + }, + { + "alias": "get_range", + "color": "#FFAB57" + }, + { + "alias": "iter", + "color": "#C79424" + }, + { + "alias": "upload", + "color": "#84D586" + } + ], + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Operations / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 19, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(max by(user) (max_over_time(cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[15m])))", + "format": "time_series", + "legendFormat": "blocks", + "legendLink": null + } + ], + "title": "Total number of blocks in the storage", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Long-term storage (object storage)", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Overview", + "uid": "ffcd83628d7d4b5a03d1cafd159e6c9c", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-queries.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-queries.json new file mode 100644 index 0000000..940ef79 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-queries.json @@ -0,0 +1,2535 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 1, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_query_frontend_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_frontend_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Queue duration", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 2, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_query_frontend_retries_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_query_frontend_retries_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Retries", + "type": "timeseries", + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (cortex_query_frontend_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Queue length (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": "0", + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(user) (cortex_query_frontend_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}) > 0", + "format": "time_series", + "legendFormat": "{{user}}", + "legendLink": null + } + ], + "title": "Queue length (per user)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_query_scheduler_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Queue duration", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (cortex_query_scheduler_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Queue length (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": "0", + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(user) (cortex_query_scheduler_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}) > 0", + "format": "time_series", + "legendFormat": "{{user}}", + "legendLink": null + } + ], + "title": "Queue length (per user)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-scheduler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Intervals per query\nThe average number of split queries (partitioned by time) executed a single input query.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(cortex_frontend_split_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / sum(rate(cortex_frontend_query_range_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", method=\"split_by_interval_and_results_cache\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "splitting rate", + "legendLink": null + } + ], + "title": "Intervals per query", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "# Query the new metric introduced in Mimir 2.10.\n(\n sum by(request_type) (rate(cortex_frontend_query_result_cache_hits_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n /\n sum by(request_type) (rate(cortex_frontend_query_result_cache_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n)\n# Otherwise fallback to the previous general-purpose metrics.\nor\n(\n label_replace(\n # Query metrics before and after dskit cache refactor.\n sum (\n rate(thanos_cache_memcached_hits_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_hits_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n )\n /\n sum (\n rate(thanos_cache_memcached_requests_total{name=~\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_requests_total{name=~\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n ),\n \"request_type\", \"query_range\", \"\", \"\")\n)\n", + "format": "time_series", + "legendFormat": "{{request_type}}", + "legendLink": null + } + ], + "title": "Query results cache hit ratio", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Query results cache skipped\nThe % of queries whose results could not be cached.\nIt is tracked for each split query when the splitting by interval is enabled.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(cortex_frontend_query_result_cache_skipped_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (reason) /\nignoring (reason) group_left sum(rate(cortex_frontend_query_result_cache_attempted_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "{{reason}}", + "legendLink": null + } + ], + "title": "Query results cache skipped", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend - query splitting and results cache", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Sharded queries ratio\nThe % of queries that have been successfully rewritten and executed in a shardable way.\nThis panel only takes into account the type of queries that are supported by query sharding (eg. range queries).\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(rate(cortex_frontend_query_sharding_rewrites_succeeded_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) /\nsum(rate(cortex_frontend_query_sharding_rewrites_attempted_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "sharded queries ratio", + "legendLink": null + } + ], + "title": "Sharded queries ratio", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Number of sharded queries per query\nThe number of sharded queries that have been executed for a single input query. It only tracks queries that\nhave been successfully rewritten in a shardable way.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_frontend_sharded_queries_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_frontend_sharded_queries_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_frontend_sharded_queries_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_frontend_sharded_queries_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Number of sharded queries per query", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend - query sharding", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 13, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_series_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_series_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1 * sum(cluster_job:cortex_ingester_queried_series_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_series_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Series per query", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_samples_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_samples_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1 * sum(cluster_job:cortex_ingester_queried_samples_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_samples_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Samples per query", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 15, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})) * 1", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1 * sum(cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}) / sum(cluster_job:cortex_ingester_queried_exemplars_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Exemplars per query", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 16, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_querier_storegateway_instances_hit_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_instances_hit_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Number of store-gateways hit per query", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 17, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_querier_storegateway_refetches_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_refetches_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Refetches of missing blocks per query", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "description": "### Consistency checks failed\nRate of queries that had to run with consistency checks and those checks failed. A failed consistency check means that some of at least one block which had to be queried wasn't present in any of the store-gateways.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Failure Rate" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 18, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_querier_blocks_consistency_checks_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / sum(rate(cortex_querier_blocks_consistency_checks_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Failure Rate", + "legendLink": null + } + ], + "title": "Consistency checks failed", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Rejected queries\nThe proportion of all queries received by queriers that were rejected for some reason.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 19, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by (reason) (rate(cortex_querier_queries_rejected_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) / ignoring (reason) group_left sum(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_query(_range)?\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{reason}}", + "legendLink": null + } + ], + "title": "Rejected queries", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 20, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"})", + "format": "time_series", + "legendFormat": "Max", + "legendLink": null + }, + { + "expr": "min(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"})", + "format": "time_series", + "legendFormat": "Min", + "legendLink": null + }, + { + "expr": "avg(cortex_bucket_index_loaded{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"})", + "format": "time_series", + "legendFormat": "Average", + "legendLink": null + } + ], + "title": "Bucket indexes loaded (per querier)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 21, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(cortex_bucket_index_loads_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_index_load_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_bucket_index_load_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Bucket indexes load / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 22, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_index_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_index_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_bucket_index_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_index_load_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Bucket indexes load latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ops" + }, + "overrides": [ ] + }, + "id": 23, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(cortex_bucket_store_series_blocks_queried_sum{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "blocks", + "legendLink": null + } + ], + "title": "Blocks queried / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "binBps" + }, + "overrides": [ ] + }, + "id": 24, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(data_type) (\n # Exclude \"chunks refetched\".\n rate(cortex_bucket_store_series_data_size_fetched_bytes_sum{component=\"store-gateway\", stage!=\"refetched\", cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n)\n", + "format": "time_series", + "legendFormat": "{{data_type}}", + "legendLink": null + } + ], + "title": "Data fetched / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "binBps" + }, + "overrides": [ ] + }, + "id": 25, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(data_type) (\n # Exclude \"chunks processed\" to only count \"chunks returned\", other than postings and series.\n rate(cortex_bucket_store_series_data_size_touched_bytes_sum{component=\"store-gateway\", stage!=\"processed\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n)\n", + "format": "time_series", + "legendFormat": "{{data_type}}", + "legendLink": null + } + ], + "title": "Data touched / sec", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Store-gateway", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 26, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(stage) (rate(cortex_bucket_store_series_request_stage_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum by(stage) (rate(cortex_bucket_store_series_request_stage_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "{{stage}}", + "legendLink": null + } + ], + "title": "Series request average latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 27, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by(stage, le) (rate(cortex_bucket_store_series_request_stage_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])))\n", + "format": "time_series", + "legendFormat": "{{stage}}", + "legendLink": null + } + ], + "title": "Series request 99th percentile latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Series batch preloading efficiency\nThis panel shows the % of time reduced by preloading, for Series() requests which have been\nsplit to 2+ batches. If a Series() request is served within a single batch, then preloading\nis not triggered, and thus not counted in this measurement.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 28, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "# Clamping min to 0 because if preloading not useful at all, then the actual value we get is\n# slightly negative because of the small overhead introduced by preloading.\nclamp_min(1 - (\n sum(rate(cortex_bucket_store_series_batch_preloading_wait_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\n sum(rate(cortex_bucket_store_series_batch_preloading_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n), 0)\n", + "format": "time_series", + "legendFormat": "% of time reduced by preloading", + "legendLink": null + } + ], + "title": "Series batch preloading efficiency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Blocks currently owned\nThis panel shows the number of blocks owned by each store-gateway replica.\nFor each owned block, the store-gateway keeps its index-header on disk, and\neventually loaded in memory (if index-header lazy loading is disabled, or lazy loading\nis enabled and the index-header was loaded).\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 29, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "cortex_bucket_store_blocks_loaded{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Blocks currently owned", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 30, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(cortex_bucket_store_block_loads_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_store_block_load_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_bucket_store_block_load_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Blocks loaded / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 31, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(cortex_bucket_store_block_drops_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) - sum(rate(cortex_bucket_store_block_drop_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_bucket_store_block_drop_failures_total{component=\"store-gateway\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Blocks dropped / sec", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 32, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "cortex_bucket_store_indexheader_lazy_load_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"} - cortex_bucket_store_indexheader_lazy_unload_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Lazy loaded index-headers", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 33, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_store_indexheader_lazy_load_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Index-header lazy load duration", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "description": "### Index-header lazy load gate latency\nTime spent waiting for a turn to load an index header. This time is not included in \"Index-header lazy load duration.\"\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 34, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_bucket_stores_gate_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_bucket_stores_gate_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_bucket_stores_gate_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_bucket_stores_gate_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",gate=\"index_header\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Index-header lazy load gate latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 35, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(cortex_bucket_store_series_hash_cache_hits_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_bucket_store_series_hash_cache_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "hit ratio", + "legendLink": null + } + ], + "title": "Series hash cache hit ratio", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 36, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(thanos_store_index_cache_hits_total{item_type=\"ExpandedPostings\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(thanos_store_index_cache_requests_total{item_type=\"ExpandedPostings\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "hit ratio", + "legendLink": null + } + ], + "title": "ExpandedPostings cache hit ratio", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 37, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(cortex_cache_memory_hits_total{name=\"chunks-attributes-cache\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_cache_memory_requests_total{name=\"chunks-attributes-cache\",cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "hit ratio", + "legendLink": null + } + ], + "title": "Chunks attributes in-memory cache hit ratio", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Queries", + "uid": "b3abe8d5c040395cc36615cb4334c92d", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-reads-networking.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-reads-networking.json new file mode 100644 index 0000000..1bab7d0 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-reads-networking.json @@ -0,0 +1,1504 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read).*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Summary", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-frontend.*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?query-scheduler.*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-scheduler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 13, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 15, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 16, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?querier.*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 17, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 18, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 19, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 20, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?store-gateway.*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Store-gateway", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 21, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 22, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 23, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 24, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler.*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Reads networking", + "uid": "54b2a0a4748b3bd1aefa92ce5559a1c2", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-reads-resources.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-reads-resources.json new file mode 100644 index 0000000..2e8f82f --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-reads-resources.json @@ -0,0 +1,2449 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend|querier|ruler-query-frontend|ruler-querier|mimir-read\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Summary", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-frontend\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"query-scheduler\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-scheduler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"querier\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 13, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 15, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "max by(pod) (container_memory_rss{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (RSS)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 16, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 17, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Rules", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 18, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 19, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 20, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 21, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 22, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Store-gateway", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 23, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "max by(pod) (container_memory_rss{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (RSS)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 24, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"store-gateway\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 25, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_written_bytes_total[$__rate_interval]\n )\n)\n+\nignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"store-gateway\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "title": "Disk writes", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 26, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_read_bytes_total[$__rate_interval]\n )\n) + ignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"store-gateway\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "title": "Disk reads", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 27, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(persistentvolumeclaim) (\n kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n kube_persistentvolumeclaim_labels{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n label_name=~\"(store-gateway).*\"\n }\n)\n", + "format": "time_series", + "legendFormat": "{{persistentvolumeclaim}}", + "legendLink": null + } + ], + "title": "Disk space utilization", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Reads resources", + "uid": "cc86fd5aa9301c6528986572ad974db9", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-reads.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-reads.json new file mode 100644 index 0000000..ddc9af1 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-reads.json @@ -0,0 +1,4737 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "175px", + "panels": [ + { + "content": "

\n This dashboard shows health metrics for the read path.\n It is broken into sections for each service on the read path, and organized by the order in which the read request flows.\n
\n Incoming queries travel from the gateway → query frontend → query scheduler → querier → ingester and/or store-gateway (depending on the time range of the query).\n
\n For each service, there are 3 panels showing (1) requests per second to that service, (2) average, median, and p99 latency of requests to that service, and (3) p99 latency of requests to each instance of that service.\n

\n

\n The dashboard also shows metrics for the 4 optional caches that can be deployed:\n the query results cache, the metadata cache, the chunks cache, and the index cache.\n
\n These panels will show “no data” if the caches are not deployed.\n

\n

\n Lastly, it also includes metrics for how the ingester and store-gateway interact with object storage.\n

\n", + "datasource": null, + "description": "", + "id": 1, + "mode": "markdown", + "span": 12, + "title": "", + "transparent": true, + "type": "text" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Reads dashboard description", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Instant queries per second\nRate of instant queries per second being made to the system.\nIncludes both queries made to the /prometheus API as\nwell as queries from the ruler.\n\n", + "fill": 1, + "format": "reqps", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n rate(\n cortex_request_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",\n route=~\"(prometheus|api_prom)_api_v1_query\"\n }[$__rate_interval]\n )\n or\n rate(\n cortex_prometheus_rule_evaluations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Instant queries / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Range queries per second\nRate of range queries per second being made to\nMimir via the /prometheus API.\n\n", + "fill": 1, + "format": "reqps", + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_query_range\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Range queries / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### \"Label names\" queries per second\nRate of \"label names\" endpoint queries per second being made to\nMimir via the /prometheus API.\n\n", + "fill": 1, + "format": "reqps", + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_labels\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Label names queries / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### \"Label values\" queries per second\nRate of specific \"label values\" endpoint queries per second being made to\nMimir via the /prometheus API.\n\n", + "fill": 1, + "format": "reqps", + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_label_name_values\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Label values queries / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Series queries per second\nRate of series queries per second being made to\nMimir via the /prometheus API.\n\n", + "fill": 1, + "format": "reqps", + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\",route=~\"(prometheus|api_prom)_api_v1_series\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Series queries / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))", + "format": "time_series", + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-frontend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Requests / sec\n

\n The query scheduler is an optional service that moves\n the internal queue from the query-frontend into a\n separate component.\n If this service is not deployed,\n these panels will show \"No data.\"\n

\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Latency (Time in Queue)\n

\n The query scheduler is an optional service that moves\n the internal queue from the query-frontend into a\n separate component.\n If this service is not deployed,\n these panels will show \"No data.\"\n

\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_query_scheduler_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency (Time in Queue)", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "description": "### Queue length\n

\n The query scheduler is an optional service that moves\n the internal queue from the query-frontend into a\n separate component.\n If this service is not deployed,\n these panels will show \"No data.\"\n

\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "queries" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "sum(min_over_time(cortex_query_scheduler_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__interval]))", + "format": "time_series", + "legendFormat": "Queue length", + "legendLink": null + } + ], + "title": "Queue length", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-scheduler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### 99th Percentile Latency by Queue Dimension\n

\n The query scheduler can optionally create subqueues\n in order to enforce round-robin query queuing fairness\n across additional queue dimensions beyond the default.\n\n By default, query queuing fairness is only applied by tenant ID.\n Queries without additional queue dimensions are labeled 'none'.\n

\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 13, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "label_replace(histogram_quantile(0.99, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) by (le, additional_queue_dimensions)) * 1e3, \"additional_queue_dimensions\", \"none\", \"additional_queue_dimensions\", \"^$\")\n", + "format": "time_series", + "legendFormat": "99th Percentile: {{ additional_queue_dimensions }}", + "refId": "A" + } + ], + "title": "99th Percentile Latency by Queue Dimension", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### 50th Percentile Latency by Queue Dimension\n

\n The query scheduler can optionally create subqueues\n in order to enforce round-robin query queuing fairness\n across additional queue dimensions beyond the default.\n\n By default, query queuing fairness is only applied by tenant ID.\n Queries without additional queue dimensions are labeled 'none'.\n

\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "label_replace(histogram_quantile(0.50, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) by (le, additional_queue_dimensions)) * 1e3, \"additional_queue_dimensions\", \"none\", \"additional_queue_dimensions\", \"^$\")\n", + "format": "time_series", + "legendFormat": "50th Percentile: {{ additional_queue_dimensions }}", + "refId": "A" + } + ], + "title": "50th Percentile Latency by Queue Dimension", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Average Latency by Queue Dimension\n

\n The query scheduler can optionally create subqueues\n in order to enforce round-robin query queuing fairness\n across additional queue dimensions beyond the default.\n\n By default, query queuing fairness is only applied by tenant ID.\n Queries without additional queue dimensions are labeled 'none'.\n

\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 15, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "label_replace(sum(rate(cortex_query_scheduler_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) by (additional_queue_dimensions) * 1e3 / sum(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\"}[$__rate_interval])) by (additional_queue_dimensions), \"additional_queue_dimensions\", \"none\", \"additional_queue_dimensions\", \"^$\")\n", + "format": "time_series", + "legendFormat": "Average: {{ additional_queue_dimensions }}", + "refId": "C" + } + ], + "title": "Average Latency by Queue Dimension", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query-scheduler Latency (Time in Queue) Breakout by Additional Queue Dimensions", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ops" + }, + "overrides": [ ] + }, + "id": 16, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum (\n rate(thanos_memcached_operations_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{name=\"frontend-cache\", cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\"}[$__rate_interval])\n)\n", + "format": "time_series", + "legendFormat": "Requests/s", + "legendLink": null + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 17, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", name=\"frontend-cache\"}[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Cache – query results", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 18, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 19, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 20, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_querier_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))", + "format": "time_series", + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 21, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",route=~\"/cortex.Ingester/(QueryStream|QueryExemplars|LabelValues|LabelNames|UserStats|AllUserStats|MetricsForLabelMatchers|MetricsMetadata|LabelNamesAndValues|LabelValuesCardinality|ActiveSeries)\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 22, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/(QueryStream|QueryExemplars|LabelValues|LabelNames|UserStats|AllUserStats|MetricsForLabelMatchers|MetricsMetadata|LabelNamesAndValues|LabelValuesCardinality|ActiveSeries)\"})) * 1e3", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/(QueryStream|QueryExemplars|LabelValues|LabelNames|UserStats|AllUserStats|MetricsForLabelMatchers|MetricsMetadata|LabelNamesAndValues|LabelValuesCardinality|ActiveSeries)\"})) * 1e3", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/(QueryStream|QueryExemplars|LabelValues|LabelNames|UserStats|AllUserStats|MetricsForLabelMatchers|MetricsMetadata|LabelNamesAndValues|LabelValuesCardinality|ActiveSeries)\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/(QueryStream|QueryExemplars|LabelValues|LabelNames|UserStats|AllUserStats|MetricsForLabelMatchers|MetricsMetadata|LabelNamesAndValues|LabelValuesCardinality|ActiveSeries)\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 23, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=~\"/cortex.Ingester/(QueryStream|QueryExemplars|LabelValues|LabelNames|UserStats|AllUserStats|MetricsForLabelMatchers|MetricsMetadata|LabelNamesAndValues|LabelValuesCardinality|ActiveSeries)\"}[$__rate_interval])))", + "format": "time_series", + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 24, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",route=~\"/gatewaypb.StoreGateway/.*\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 25, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})) * 1e3", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})) * 1e3", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 26, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", route=~\"/gatewaypb.StoreGateway/.*\"}[$__rate_interval])))", + "format": "time_series", + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Store-gateway", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Replicas\nThe maximum, and current number of querier replicas.\nPlease note that the current number of replicas can still show 1 replica even when scaled to 0.\nSince HPA never reports 0 replicas, the query will report 0 only if the HPA is not active.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byRegexp", + "options": "/Max .+/" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/Current .+/" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/Min .+/" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 27, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by (scaletargetref_name) (\n kube_horizontalpodautoscaler_spec_max_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"}\n # Add the scaletargetref_name label which is more readable than \"kube-hpa-...\"\n + on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"}\n)\n", + "format": "time_series", + "legendFormat": "Max {{ scaletargetref_name }}", + "legendLink": null + }, + { + "expr": "max by (scaletargetref_name) (\n kube_horizontalpodautoscaler_status_current_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"}\n # HPA doesn't go to 0 replicas, so we multiply by 0 if the HPA is not active.\n * on (cluster, namespace, horizontalpodautoscaler)\n kube_horizontalpodautoscaler_status_condition{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\", condition=\"ScalingActive\", status=\"true\"}\n # Add the scaletargetref_name label which is more readable than \"kube-hpa-...\"\n + on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"}\n)\n", + "format": "time_series", + "legendFormat": "Current {{ scaletargetref_name }}", + "legendLink": null + }, + { + "expr": "max by (scaletargetref_name) (\n kube_horizontalpodautoscaler_spec_min_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"}\n # Add the scaletargetref_name label which is more readable than \"kube-hpa-...\"\n + on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"}\n)\n", + "format": "time_series", + "legendFormat": "Min {{ scaletargetref_name }}", + "legendLink": null + } + ], + "title": "Replicas", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Scaling metric (desired replicas)\nThis panel shows the result scaling metric exposed by KEDA divided by the target/threshold used.\nIt should represent the desired number of replicas, ignoring the min/max constraints which are applied later.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 28, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (scaler) (\n label_replace(\n keda_scaler_metrics_value{cluster=~\"$cluster\", exported_namespace=~\"$namespace\"},\n \"namespace\", \"$1\", \"exported_namespace\", \"(.*)\"\n )\n /\n on(cluster, namespace, scaledObject, metric) group_left\n label_replace(label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"},\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n ), \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\")\n)\n", + "format": "time_series", + "legendFormat": "{{ scaler }}", + "legendLink": null + } + ], + "title": "Scaling metric (desired replicas)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Autoscaler failures rate\nThe rate of failures in the KEDA custom metrics API server. Whenever an error occurs, the KEDA custom\nmetrics server is unable to query the scaling metric from Prometheus so the autoscaler woudln't work properly.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 29, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(cluster, namespace, scaler, metric, scaledObject) (\n label_replace(\n rate(keda_scaler_errors[$__rate_interval]),\n \"namespace\", \"$1\", \"exported_namespace\", \"(.+)\"\n )\n) +\non(cluster, namespace, metric, scaledObject) group_left\nlabel_replace(\n label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-querier\"} * 0,\n \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\"\n ),\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n", + "format": "time_series", + "legendFormat": "{{scaler}} failures", + "legendLink": null + } + ], + "title": "Autoscaler failures rate", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Querier - autoscaling", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 30, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 31, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\", kv_name=~\"store-gateway\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Store-gateway – key-value store for store-gateways ring", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ops" + }, + "overrides": [ ] + }, + "id": 32, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(operation) (\n # Backwards compatibility\n rate(\n thanos_memcached_operations_total{\n component=\"store-gateway\",\n name=\"index-cache\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n or ignoring(backend)\n rate(\n thanos_cache_operations_total{\n component=\"store-gateway\",\n name=\"index-cache\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 33, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"index-cache\"\n}\n[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency (getmulti)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Hit ratio\nEven if you do not set up memcached for the blocks index cache, you will still see data in this panel because the store-gateway by default has an\nin-memory blocks index cache.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 34, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(item_type) (\n rate(\n thanos_store_index_cache_hits_total{\n component=\"store-gateway\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n/\nsum by(item_type) (\n rate(\n thanos_store_index_cache_requests_total{\n component=\"store-gateway\",\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\"\n }[$__rate_interval]\n )\n)\n", + "format": "time_series", + "legendFormat": "{{item_type}}", + "legendLink": null + } + ], + "title": "Hit ratio", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memcached – block index cache (store-gateway accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ops" + }, + "overrides": [ ] + }, + "id": 35, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 36, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n}\n[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency (getmulti)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 37, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"chunks-cache\"\n }[$__rate_interval])\n)\n", + "format": "time_series", + "legendFormat": "items", + "legendLink": null + } + ], + "title": "Hit ratio", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memcached – chunks cache (store-gateway accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ops" + }, + "overrides": [ ] + }, + "id": 38, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 39, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n operation=\"getmulti\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency (getmulti)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 40, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((store-gateway.*|cortex|mimir|mimir-backend.*))\",\n component=\"store-gateway\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n", + "format": "time_series", + "legendFormat": "items", + "legendLink": null + } + ], + "title": "Hit ratio", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memcached – metadata cache (store-gateway accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ops" + }, + "overrides": [ ] + }, + "id": 41, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(operation) (\n # Backwards compatibility\n rate(thanos_memcached_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or ignoring(backend)\n rate(thanos_cache_operations_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 42, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_bucket{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) by (le)) * 1e3\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_sum{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n) * 1e3\n/\nsum(\n # Backwards compatibility\n rate(thanos_memcached_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n or\n rate(thanos_cache_operation_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n operation=\"getmulti\",\n component=\"querier\",\n name=\"metadata-cache\"\n}\n[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency (getmulti)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 43, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(\n # Backwards compatibility\n rate(thanos_cache_memcached_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_hits_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n/\nsum(\n # Backwards compatibility\n rate(thanos_cache_memcached_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n or\n rate(thanos_cache_requests_total{\n cluster=~\"$cluster\", job=~\"($namespace)/((querier.*|cortex|mimir|mimir-read.*))\",\n component=\"querier\",\n name=\"metadata-cache\"\n }[$__rate_interval])\n)\n", + "format": "time_series", + "legendFormat": "items", + "legendLink": null + } + ], + "title": "Hit ratio", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memcached – metadata cache (querier accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ ] + }, + "id": 44, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Operations / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 45, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\"}[$__rate_interval])) >= 0", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Error rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 46, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"attributes\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Attributes", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 47, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"exists\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Exists", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Blocks object store (store-gateway accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 48, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Get", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 49, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"get_range\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: GetRange", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 50, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Upload", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 51, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"store-gateway\",operation=\"delete\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Delete", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ ] + }, + "id": 52, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Operations / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 53, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\"}[$__rate_interval])) >= 0", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Error rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 54, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"attributes\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Attributes", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 55, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"exists\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Exists", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Blocks object store (querier accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 56, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Get", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 57, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"get_range\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: GetRange", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 58, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Upload", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 59, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"querier\",operation=\"delete\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Delete", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Reads", + "uid": "e327503188913dc38ad571c647eef643", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-remote-ruler-reads-networking.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-remote-ruler-reads-networking.json new file mode 100644 index 0000000..28c919f --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-remote-ruler-reads-networking.json @@ -0,0 +1,1048 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(ruler-query-frontend|ruler-query-scheduler|ruler-querier).*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(ruler-query-frontend|ruler-query-scheduler|ruler-querier).*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(ruler-query-frontend|ruler-query-scheduler|ruler-querier).*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(ruler-query-frontend|ruler-query-scheduler|ruler-querier).*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(ruler-query-frontend|ruler-query-scheduler|ruler-querier).*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(ruler-query-frontend|ruler-query-scheduler|ruler-querier).*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(ruler-query-frontend|ruler-query-scheduler|ruler-querier).*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Summary", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-frontend.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-frontend.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-frontend.*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-frontend.*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-frontend.*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-frontend.*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-frontend.*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler-query-frontend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-scheduler.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-scheduler.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-scheduler.*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-scheduler.*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-scheduler.*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-scheduler.*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-query-scheduler.*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler-query-scheduler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 13, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-querier.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-querier.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 15, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-querier.*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-querier.*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 16, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-querier.*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-querier.*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ruler-querier.*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler-querier", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Remote ruler reads networking", + "uid": "9e8cfff65f91632f8a25981c6fe44bc9", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-remote-ruler-reads-resources.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-remote-ruler-reads-resources.json new file mode 100644 index 0000000..c079baa --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-remote-ruler-reads-resources.json @@ -0,0 +1,982 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-frontend\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler-query-frontend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-query-scheduler\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler-query-scheduler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ruler-querier\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler-querier", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Remote ruler reads resources", + "uid": "1940f6ef765a506a171faa2056c956c3", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-remote-ruler-reads.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-remote-ruler-reads.json new file mode 100644 index 0000000..3b509ef --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-remote-ruler-reads.json @@ -0,0 +1,1683 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "175px", + "panels": [ + { + "content": "

\n This dashboard shows health metrics for the ruler read path when remote operational mode is enabled.\n It is broken into sections for each service on the ruler read path, and organized by the order in which the read request flows.\n
\n For each service, there are three panels showing (1) requests per second to that service, (2) average, median, and p99 latency of requests to that service, and (3) p99 latency of requests to each instance of that service.\n

\n", + "datasource": null, + "description": "", + "id": 1, + "mode": "markdown", + "span": 12, + "title": "", + "transparent": true, + "type": "text" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Remote ruler reads dashboard description", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Evaluations per second\nRate of rule expressions evaluated per second.\n\n", + "fill": 1, + "format": "reqps", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n rate(\n cortex_request_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\",\n route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"\n }[$__rate_interval]\n )\n)\n", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Evaluations / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 4, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"})) * 1e3", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"})) * 1e3", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"}[$__rate_interval])))", + "format": "time_series", + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler-query-frontend", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Requests / sec\n

\n The query scheduler is an optional service that moves\n the internal queue from the query-frontend into a\n separate component.\n If this service is not deployed,\n these panels will show \"No data.\"\n

\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Latency (Time in Queue)\n

\n The query scheduler is an optional service that moves\n the internal queue from the query-frontend into a\n separate component.\n If this service is not deployed,\n these panels will show \"No data.\"\n

\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_query_scheduler_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency (Time in Queue)", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "description": "### Queue length\n

\n The query scheduler is an optional service that moves\n the internal queue from the query-frontend into a\n separate component.\n If this service is not deployed,\n these panels will show \"No data.\"\n

\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "queries" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "sum(min_over_time(cortex_query_scheduler_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__interval]))", + "format": "time_series", + "legendFormat": "Queue length", + "legendLink": null + } + ], + "title": "Queue length", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler-query-scheduler", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### 99th Percentile Latency by Queue Dimension\n

\n The query scheduler can optionally create subqueues\n in order to enforce round-robin query queuing fairness\n across additional queue dimensions beyond the default.\n\n By default, query queuing fairness is only applied by tenant ID.\n Queries without additional queue dimensions are labeled 'none'.\n

\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "label_replace(histogram_quantile(0.99, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (le, additional_queue_dimensions)) * 1e3, \"additional_queue_dimensions\", \"none\", \"additional_queue_dimensions\", \"^$\")\n", + "format": "time_series", + "legendFormat": "99th Percentile: {{ additional_queue_dimensions }}", + "refId": "A" + } + ], + "title": "99th Percentile Latency by Queue Dimension", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### 50th Percentile Latency by Queue Dimension\n

\n The query scheduler can optionally create subqueues\n in order to enforce round-robin query queuing fairness\n across additional queue dimensions beyond the default.\n\n By default, query queuing fairness is only applied by tenant ID.\n Queries without additional queue dimensions are labeled 'none'.\n

\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "label_replace(histogram_quantile(0.50, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (le, additional_queue_dimensions)) * 1e3, \"additional_queue_dimensions\", \"none\", \"additional_queue_dimensions\", \"^$\")\n", + "format": "time_series", + "legendFormat": "50th Percentile: {{ additional_queue_dimensions }}", + "refId": "A" + } + ], + "title": "50th Percentile Latency by Queue Dimension", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Average Latency by Queue Dimension\n

\n The query scheduler can optionally create subqueues\n in order to enforce round-robin query queuing fairness\n across additional queue dimensions beyond the default.\n\n By default, query queuing fairness is only applied by tenant ID.\n Queries without additional queue dimensions are labeled 'none'.\n

\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "label_replace(sum(rate(cortex_query_scheduler_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (additional_queue_dimensions) * 1e3 / sum(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (additional_queue_dimensions), \"additional_queue_dimensions\", \"none\", \"additional_queue_dimensions\", \"^$\")\n", + "format": "time_series", + "legendFormat": "Average: {{ additional_queue_dimensions }}", + "refId": "C" + } + ], + "title": "Average Latency by Queue Dimension", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler-query-scheduler Latency (Time in Queue) Breakout by Additional Queue Dimensions", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 13, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_querier_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))", + "format": "time_series", + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler-querier", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Replicas\nThe maximum and current number of ruler-querier replicas.\nNote: The current number of replicas can still show 1 replica even when scaled to 0.\nBecause HPA never reports 0 replicas, the query will report 0 only if the HPA is not active.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byRegexp", + "options": "/Max .+/" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/Current .+/" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/Min .+/" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 15, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "max by (scaletargetref_name) (\n kube_horizontalpodautoscaler_spec_max_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n # Add the scaletargetref_name label for readability\n + on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n)\n", + "format": "time_series", + "legendFormat": "Max {{ scaletargetref_name }}", + "legendLink": null + }, + { + "expr": "max by (scaletargetref_name) (\n kube_horizontalpodautoscaler_status_current_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n # HPA doesn't go to 0 replicas, so we multiply by 0 if the HPA is not active\n * on (cluster, namespace, horizontalpodautoscaler)\n kube_horizontalpodautoscaler_status_condition{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\", condition=\"ScalingActive\", status=\"true\"}\n # Add the scaletargetref_name label for readability\n + on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n)\n", + "format": "time_series", + "legendFormat": "Current {{ scaletargetref_name }}", + "legendLink": null + }, + { + "expr": "max by (scaletargetref_name) (\n kube_horizontalpodautoscaler_spec_min_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n # Add the scaletargetref_name label for readability\n + on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n)\n", + "format": "time_series", + "legendFormat": "Min {{ scaletargetref_name }}", + "legendLink": null + } + ], + "title": "Replicas", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Autoscaler failures rate\nThe rate of failures in the KEDA custom metrics API server. Whenever an error occurs, the KEDA custom\nmetrics server is unable to query the scaling metric from Prometheus so the autoscaler woudln't work properly.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 16, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(cluster, namespace, scaler, metric, scaledObject) (\n label_replace(\n rate(keda_scaler_errors[$__rate_interval]),\n \"namespace\", \"$1\", \"exported_namespace\", \"(.+)\"\n )\n) +\non(cluster, namespace, metric, scaledObject) group_left\nlabel_replace(\n label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"} * 0,\n \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\"\n ),\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n", + "format": "time_series", + "legendFormat": "{{scaler}} failures", + "legendLink": null + } + ], + "title": "Autoscaler failures rate", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler-querier - autoscaling", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Scaling metric (CPU): Desired replicas\nThis panel shows the scaling metric exposed by KEDA divided by the target/threshold used.\nIt should represent the desired number of replicas, ignoring the min/max constraints applied later.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 17, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (scaler) (\n label_replace(\n keda_scaler_metrics_value{cluster=~\"$cluster\", exported_namespace=~\"$namespace\", scaler=~\".*cpu.*\"},\n \"namespace\", \"$1\", \"exported_namespace\", \"(.*)\"\n )\n /\n on(cluster, namespace, scaledObject, metric) group_left label_replace(\n label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"},\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n ),\n \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\"\n )\n)\n", + "format": "time_series", + "legendFormat": "{{ scaler }}", + "legendLink": null + } + ], + "title": "Scaling metric (CPU): Desired replicas", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Scaling metric (memory): Desired replicas\nThis panel shows the scaling metric exposed by KEDA divided by the target/threshold used.\nIt should represent the desired number of replicas, ignoring the min/max constraints applied later.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 18, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (scaler) (\n label_replace(\n keda_scaler_metrics_value{cluster=~\"$cluster\", exported_namespace=~\"$namespace\", scaler=~\".*memory.*\"},\n \"namespace\", \"$1\", \"exported_namespace\", \"(.*)\"\n )\n /\n on(cluster, namespace, scaledObject, metric) group_left label_replace(\n label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"},\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n ),\n \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\"\n )\n)\n", + "format": "time_series", + "legendFormat": "{{ scaler }}", + "legendLink": null + } + ], + "title": "Scaling metric (memory): Desired replicas", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Scaling metric (in-flight queries): Desired replicas\nThis panel shows the scaling metric exposed by KEDA divided by the target/threshold used.\nIt should represent the desired number of replicas, ignoring the min/max constraints applied later.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 19, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (scaler) (\n label_replace(\n keda_scaler_metrics_value{cluster=~\"$cluster\", exported_namespace=~\"$namespace\", scaler=~\".*queries.*\"},\n \"namespace\", \"$1\", \"exported_namespace\", \"(.*)\"\n )\n /\n on(cluster, namespace, scaledObject, metric) group_left label_replace(\n label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"},\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n ),\n \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\"\n )\n)\n", + "format": "time_series", + "legendFormat": "{{ scaler }}", + "legendLink": null + } + ], + "title": "Scaling metric (in-flight queries): Desired replicas", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Remote ruler reads", + "uid": "f103238f7f5ab2f1345ce650cbfbfe2f", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-rollout-progress.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-rollout-progress.json new file mode 100644 index 0000000..734a630 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-rollout-progress.json @@ -0,0 +1,1404 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "fillOpacity": 80, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 1, + "scaleDistribution": { + "type": "linear" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [ ], + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Ready" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "green", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Updated" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "blue", + "mode": "fixed" + } + } + ] + } + ] + }, + "gridPos": { + "h": 13, + "w": 10, + "x": 0, + "y": 0 + }, + "id": 1, + "links": [ ], + "options": { + "barRadius": 0, + "barWidth": 0.96999999999999997, + "fullHighlight": false, + "groupWidth": 0.69999999999999996, + "legend": { + "calcs": [ ], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "orientation": "horizontal", + "showValue": "auto", + "stacking": "none", + "tooltip": { + "mode": "multi", + "sort": "none" + }, + "xField": "Workload", + "xTickLabelRotation": 0, + "xTickLabelSpacing": 0 + }, + "targets": [ + { + "expr": "(\n sum by (workload) (\n label_replace(label_replace(label_replace(\n kube_deployment_status_replicas_updated{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n or\n kube_statefulset_status_replicas_updated{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n , \"workload\", \"$1\", \"deployment\", \"(.+)\"), \"workload\", \"$1\", \"statefulset\", \"(.+)\"), \"workload\", \"$1\", \"workload\", \"(.*?)(?:-zone-[a-z])?\")\n )\n /\n sum by (workload) (\n label_replace(label_replace(label_replace(\n kube_deployment_status_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n or\n kube_statefulset_status_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n , \"workload\", \"$1\", \"deployment\", \"(.+)\"), \"workload\", \"$1\", \"statefulset\", \"(.+)\"), \"workload\", \"$1\", \"workload\", \"(.*?)(?:-zone-[a-z])?\")\n )\n) and (\n sum by (workload) (\n label_replace(label_replace(label_replace(\n kube_deployment_status_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n or\n kube_statefulset_status_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n , \"workload\", \"$1\", \"deployment\", \"(.+)\"), \"workload\", \"$1\", \"statefulset\", \"(.+)\"), \"workload\", \"$1\", \"workload\", \"(.*?)(?:-zone-[a-z])?\")\n )\n > 0\n)\n", + "format": "table", + "instant": true, + "intervalFactor": null, + "legendFormat": "__auto", + "legendLink": null, + "step": null + }, + { + "expr": "(\n sum by (workload) (\n label_replace(label_replace(label_replace(\n kube_deployment_status_replicas_ready{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n or\n kube_statefulset_status_replicas_ready{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n , \"workload\", \"$1\", \"deployment\", \"(.+)\"), \"workload\", \"$1\", \"statefulset\", \"(.+)\"), \"workload\", \"$1\", \"workload\", \"(.*?)(?:-zone-[a-z])?\")\n )\n /\n sum by (workload) (\n label_replace(label_replace(label_replace(\n kube_deployment_status_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n or\n kube_statefulset_status_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n , \"workload\", \"$1\", \"deployment\", \"(.+)\"), \"workload\", \"$1\", \"statefulset\", \"(.+)\"), \"workload\", \"$1\", \"workload\", \"(.*?)(?:-zone-[a-z])?\")\n )\n) and (\n sum by (workload) (\n label_replace(label_replace(label_replace(\n kube_deployment_status_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n or\n kube_statefulset_status_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n , \"workload\", \"$1\", \"deployment\", \"(.+)\"), \"workload\", \"$1\", \"statefulset\", \"(.+)\"), \"workload\", \"$1\", \"workload\", \"(.*?)(?:-zone-[a-z])?\")\n )\n > 0\n)\n", + "format": "table", + "instant": true, + "intervalFactor": null, + "legendFormat": "__auto", + "legendLink": null, + "step": null + } + ], + "title": "Rollout progress", + "transformations": [ + { + "id": "joinByField", + "options": { + "byField": "workload", + "mode": "outer" + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Time 1": true, + "Time 2": true + }, + "renameByName": { + "Value #A": "Updated", + "Value #B": "Ready", + "workload": "Workload" + } + } + }, + { + "id": "sortBy", + "options": { + "sort": [ + { + "field": "Workload" + } + ] + } + } + ], + "type": "barchart" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 2, + "x": 10, + "y": 0 + }, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"2.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Writes - 2xx", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 0.20000000000000001 + }, + { + "color": "red", + "value": 0.5 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 2, + "x": 12, + "y": 0 + }, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"4.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Writes - 4xx", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 0.01 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 2, + "x": 14, + "y": 0 + }, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\",status_code=~\"5.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Writes - 5xx", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 0.20000000000000001 + }, + { + "color": "red", + "value": 0.5 + } + ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 8, + "x": 16, + "y": 0 + }, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Writes 99th latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 2, + "x": 10, + "y": 4 + }, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"2.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Reads - 2xx", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 0.01 + }, + { + "color": "red", + "value": 0.050000000000000003 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 2, + "x": 12, + "y": 4 + }, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"4.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Reads - 4xx", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 0.01 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 2, + "x": 14, + "y": 4 + }, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\",status_code=~\"5.+\"}[$__rate_interval])) /\nsum(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Reads - 5xx", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 1, + "noValue": "", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 1 + }, + { + "color": "red", + "value": 2.5 + } + ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 4, + "w": 8, + "x": 16, + "y": 4 + }, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))\n", + "format": null, + "instant": false, + "interval": "", + "intervalFactor": null, + "legendFormat": "", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Reads 99th latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 0, + "noValue": "All healthy", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "orange", + "value": 1 + }, + { + "color": "red", + "value": 2 + } + ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "fill": 1, + "gridPos": { + "h": 3, + "w": 10, + "x": 0, + "y": 13 + }, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "text": { + "titleSize": 14, + "valueSize": 14 + }, + "textMode": "value_and_name" + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "kube_deployment_status_replicas_unavailable{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n> 0\n", + "format": null, + "instant": true, + "interval": "", + "intervalFactor": null, + "legendFormat": "{{deployment}}", + "legendLink": null, + "step": null + }, + { + "expr": "kube_statefulset_status_replicas_current{cluster=~\"$cluster\", namespace=~\"$namespace\"} -\nkube_statefulset_status_replicas_ready {cluster=~\"$cluster\", namespace=~\"$namespace\"}\n> 0\n", + "format": null, + "instant": true, + "interval": "", + "intervalFactor": null, + "legendFormat": "{{statefulset}}", + "legendLink": null, + "step": null + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Unhealthy pods", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "stat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "overrides": [ + { + "matcher": { + "id": "byRegexp", + "options": "r.*" + }, + "properties": [ + { + "id": "custom.align", + "value": "center" + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 6, + "x": 10, + "y": 8 + }, + "id": 11, + "targets": [ + { + "expr": "count by(container, version) (\n label_replace(\n kube_pod_container_info{cluster=~\"$cluster\", namespace=~\"$namespace\"},\n \"version\", \"$1\", \"image\", \".*:(.*)\"\n )\n)\n", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Pods count per version", + "transformations": [ + { + "id": "labelsToFields", + "options": { + "valueLabel": "version" + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true + }, + "indexByName": { + "Time": 0, + "container": 1 + } + } + }, + { + "id": "sortBy", + "options": { + "fields": { }, + "sort": [ + { + "field": "container" + } + ] + } + } + ], + "type": "table" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "fillOpacity": 10 + }, + "unit": "percentunit" + } + }, + "gridPos": { + "h": 8, + "w": 8, + "x": 16, + "y": 8 + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "targets": [ + { + "expr": "1 - (\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"} offset 24h))[1h:])\n /\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"api_(v1|prom)_push|otlp_v1_metrics\"}))[1h:])\n)\n", + "format": "time_series", + "legendFormat": "writes", + "legendLink": null + }, + { + "expr": "1 - (\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"} offset 24h))[1h:])\n /\n avg_over_time(histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}))[1h:])\n)\n", + "format": "time_series", + "legendFormat": "reads", + "legendLink": null + } + ], + "title": "Latency vs 24h ago", + "type": "timeseries" + } + ], + "refresh": "10s", + "rows": null, + "schemaVersion": 27, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Rollout progress", + "uid": "7f0b5567d543a1698e695b530eb7f5de", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-ruler.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-ruler.json new file mode 100644 index 0000000..ea91503 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-ruler.json @@ -0,0 +1,2617 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cortex_ruler_managers_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Active configurations", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"})", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Total rules", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Read from ingesters - QPS\nNote: Even while operating in Remote ruler mode you will still see values for this panel.\n\nThis is because the metrics are inclusive of intermediate services and are showing the requests that ultimately reach the ingesters.\n\nFor a more detailed view of the read path when using remote ruler mode, see the Remote ruler reads dashboard.\n\n", + "fill": 1, + "format": "reqps", + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Read from ingesters - QPS", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "reqps", + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Write to ingesters - QPS", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n-\nsum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "success", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "missed", + "legendLink": null + } + ], + "title": "Evaluations per second", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "average", + "legendLink": null + } + ], + "title": "Latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rule evaluations global", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "QPS", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_ingester_client_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", operation=\"/cortex.Ingester/Push\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Writes (ingesters)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "QPS", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_client_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_ingester_client_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_client_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*|ruler-querier.*))\", operation=\"/cortex.Ingester/QueryStream\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Reads (ingesters)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", kv_name=~\"ruler\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler - key-value store for rulers ring", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 13, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_instances_hit_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_querier_storegateway_instances_hit_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_instances_hit_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Number of store-gateways hit per query", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_querier_storegateway_refetches_per_query_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) by (le)) * 1", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_querier_storegateway_refetches_per_query_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) * 1 / sum(rate(cortex_querier_storegateway_refetches_per_query_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Refetches of missing blocks per query", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "description": "### Consistency checks failed\nRate of queries that had to run with consistency checks and those checks failed. A failed consistency check means that some of at least one block which had to be queried wasn't present in any of the store-gateways.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Failures / sec" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 15, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(rate(cortex_querier_blocks_consistency_checks_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) / sum(rate(cortex_querier_blocks_consistency_checks_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Failures / sec", + "legendLink": null + } + ], + "title": "Consistency checks failed", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler - blocks storage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 16, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(user) (rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]) > 0)\n> 0\n", + "format": "time_series", + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "title": "Delivery errors", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 17, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(user) (rate(cortex_prometheus_notifications_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_notifications_queue_capacity{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0\n", + "format": "time_series", + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "title": "Queue length", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 18, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (user) (increase(cortex_prometheus_notifications_dropped_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0\n", + "format": "time_series", + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "title": "Dropped", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Notifications", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 19, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(user) (rate(cortex_prometheus_rule_group_iterations_missed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0", + "format": "time_series", + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "title": "Missed iterations", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 20, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "rate(cortex_prometheus_rule_group_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n /\nrate(cortex_prometheus_rule_group_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])\n", + "format": "time_series", + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "title": "Latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 21, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(rule_group) (rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) > 0", + "format": "time_series", + "legendFormat": "{{ rule_group }}", + "legendLink": null + } + ], + "title": "Failures", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Group evaluations", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 22, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 12, + "targets": [ + { + "expr": "sum by(user) (rate(cortex_prometheus_rule_evaluation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n /\nsum by(user) (rate(cortex_prometheus_rule_evaluation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}[$__rate_interval]))\n", + "format": "time_series", + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "title": "Latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rule evaluation per user", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ ] + }, + "id": 23, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Operations / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 1, + "min": 0, + "noValue": "0", + "unit": "percentunit" + } + }, + "id": 24, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(operation) (rate(thanos_objstore_bucket_operation_failures_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\"}[$__rate_interval])) / sum by(operation) (rate(thanos_objstore_bucket_operations_total{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\"}[$__rate_interval])) >= 0", + "format": "time_series", + "legendFormat": "{{operation}}", + "legendLink": null + } + ], + "title": "Error rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 25, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"attributes\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"attributes\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"attributes\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Attributes", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 26, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"exists\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"exists\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"exists\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Exists", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ruler configuration object store (ruler accesses)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 27, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Get", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 28, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get_range\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get_range\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"get_range\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: GetRange", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 29, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Upload", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 30, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"delete\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"delete\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\",component=\"ruler-storage\",operation=\"delete\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency of op: Delete", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Ruler", + "uid": "631e15d5d85afb2ca8e35d62984eeaa0", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-scaling.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-scaling.json new file mode 100644 index 0000000..b7b6182 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-scaling.json @@ -0,0 +1,361 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "200px", + "panels": [ + { + "id": 1, + "options": { + "content": "This dashboard identifies scaling-related issues by suggesting services that you might want to scale up.\nThe table that follows contains a suggested number of replicas and the reason why.\nIf the system is failing and depending on the reason, try scaling up to the specified number.\nThe specified numbers are intended as helpful guidelines when things go wrong, rather than prescriptive guidelines.\n\nReasons:\n- **sample_rate**: There are not enough replicas to handle the\n sample rate. Applies to distributor and ingesters.\n- **active_series**: There are not enough replicas\n to handle the number of active series. Applies to ingesters.\n- **cpu_usage**: There are not enough replicas\n based on the CPU usage of the jobs vs the resource requests.\n Applies to all jobs.\n- **memory_usage**: There are not enough replicas based on the memory\n usage vs the resource requests. Applies to all jobs.\n- **active_series_limits**: There are not enough replicas to hold 60% of the\n sum of all the per tenant series limits.\n- **sample_rate_limits**: There are not enough replicas to handle 60% of the\n sum of all the per tenant rate limits.\n", + "mode": "markdown" + }, + "span": 12, + "title": "", + "type": "text" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Service scaling", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "400px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 0, + "desc": false + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Required Replicas", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "Cluster", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "__name__", + "thresholds": [ ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Cluster", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "cluster", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "Service", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "deployment", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "namespace", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "Reason", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "reason", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sort_desc(\n cluster_namespace_deployment_reason:required_replicas:count{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n > ignoring(reason) group_left\n cluster_namespace_deployment:actual_replicas:count{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\n", + "format": "table", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Workload-based scaling", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Scaling", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Scaling", + "uid": "64bbad83507b7289b514725658e10352", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-slow-queries.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-slow-queries.json new file mode 100644 index 0000000..240205b --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-slow-queries.json @@ -0,0 +1,1463 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap duration_seconds(response_time) [$__auto]) by ()", + "format": "time_series", + "legendFormat": "p99", + "legendLink": null + }, + { + "expr": "quantile_over_time(0.5, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap duration_seconds(response_time) [$__auto]) by ()", + "format": "time_series", + "legendFormat": "p50", + "legendLink": null + } + ], + "title": "Response time", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap fetched_series_count[$__auto]) by ()", + "format": "time_series", + "legendFormat": "p99", + "legendLink": null + }, + { + "expr": "quantile_over_time(0.5, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap fetched_series_count[$__auto]) by ()", + "format": "time_series", + "legendFormat": "p50", + "legendLink": null + } + ], + "title": "Fetched series", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap fetched_chunk_bytes[$__auto]) by ()", + "format": "time_series", + "legendFormat": "p99", + "legendLink": null + }, + { + "expr": "quantile_over_time(0.5, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap fetched_chunk_bytes[$__auto]) by ()", + "format": "time_series", + "legendFormat": "p50", + "legendLink": null + } + ], + "title": "Fetched chunks", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap response_size_bytes[$__auto]) by ()", + "format": "time_series", + "legendFormat": "p99", + "legendLink": null + }, + { + "expr": "quantile_over_time(0.5, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap response_size_bytes[$__auto]) by ()", + "format": "time_series", + "legendFormat": "p50", + "legendLink": null + } + ], + "title": "Response size", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap duration_seconds(length) [$__auto]) by ()", + "format": "time_series", + "legendFormat": "p99", + "legendLink": null + }, + { + "expr": "quantile_over_time(0.5, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap duration_seconds(length) [$__auto]) by ()", + "format": "time_series", + "legendFormat": "p50", + "legendLink": null + } + ], + "title": "Time span", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "description": "### Query wall time\nSeconds per second spent by queriers evaluating queries.\nThis is roughly the product of the number of subqueries for a query and how long they took.\nIn increase in this metric means that queries take more resources from the query path to evaluate.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap query_wall_time_seconds [$__auto]) by ()", + "format": "time_series", + "legendFormat": "p99", + "legendLink": null + }, + { + "expr": "quantile_over_time(0.5, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap query_wall_time_seconds [$__auto]) by ()", + "format": "time_series", + "legendFormat": "p50", + "legendLink": null + } + ], + "title": "Query wall time", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Across tenants", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "topk(10, quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap duration_seconds(response_time) [$__auto]) by (user))", + "format": "time_series", + "legendFormat": "{{user}}", + "legendLink": null + } + ], + "title": "P99 response time", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "topk(10, quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap fetched_series_count[$__auto]) by (user))", + "format": "time_series", + "legendFormat": "{{user}}", + "legendLink": null + } + ], + "title": "P99 fetched series", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "topk(10, quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap fetched_chunk_bytes[$__auto]) by (user))", + "format": "time_series", + "legendFormat": "{{user}}", + "legendLink": null + } + ], + "title": "P99 fetched chunks", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "topk(10, quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap response_size_bytes[$__auto]) by (user))", + "format": "time_series", + "legendFormat": "{{user}}", + "legendLink": null + } + ], + "title": "P99 response size", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "topk(10, quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap duration_seconds(length) [$__auto]) by (user))", + "format": "time_series", + "legendFormat": "{{user}}", + "legendLink": null + } + ], + "title": "P99 time span", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "description": "### Query wall time\nSeconds per second spent by queriers evaluating queries.\nThis is roughly the product of the number of subqueries for a query and how long they took.\nIn increase in this metric means that queries take more resources from the query path to evaluate.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "topk(10, quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap query_wall_time_seconds [$__auto]) by (user))", + "format": "time_series", + "legendFormat": "{{user}}", + "legendLink": null + } + ], + "title": "P99 query wall time", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Top 10 tenants", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 13, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "topk(10, quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap duration_seconds(response_time) [$__auto]) by (user_agent))", + "format": "time_series", + "legendFormat": "{{user_agent}}", + "legendLink": null + } + ], + "title": "P99 response time", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "topk(10, quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap fetched_series_count[$__auto]) by (user_agent))", + "format": "time_series", + "legendFormat": "{{user_agent}}", + "legendLink": null + } + ], + "title": "P99 fetched series", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 15, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "topk(10, quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap fetched_chunk_bytes[$__auto]) by (user_agent))", + "format": "time_series", + "legendFormat": "{{user_agent}}", + "legendLink": null + } + ], + "title": "P99 fetched chunks", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 16, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "topk(10, quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap response_size_bytes[$__auto]) by (user_agent))", + "format": "time_series", + "legendFormat": "{{user_agent}}", + "legendLink": null + } + ], + "title": "P99 response size", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 17, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "topk(10, quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap duration_seconds(length) [$__auto]) by (user_agent))", + "format": "time_series", + "legendFormat": "{{user_agent}}", + "legendLink": null + } + ], + "title": "P99 time span", + "type": "timeseries" + }, + { + "datasource": "${loki_datasource}", + "description": "### Query wall time\nSeconds per second spent by queriers evaluating queries.\nThis is roughly the product of the number of subqueries for a query and how long they took.\nIn increase in this metric means that queries take more resources from the query path to evaluate.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 18, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 2, + "targets": [ + { + "expr": "topk(10, quantile_over_time(0.99, {cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | unwrap query_wall_time_seconds [$__auto]) by (user_agent))", + "format": "time_series", + "legendFormat": "{{user_agent}}", + "legendLink": null + } + ], + "title": "P99 query wall time", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Top 10 User-Agents", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "${loki_datasource}", + "fieldConfig": { + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "fetched_chunk_bytes" + }, + "properties": [ + { + "id": "unit", + "value": "bytes" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "fetched_index_bytes" + }, + "properties": [ + { + "id": "unit", + "value": "bytes" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "response_size_bytes" + }, + "properties": [ + { + "id": "unit", + "value": "bytes" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "results_cache_hit_bytes" + }, + "properties": [ + { + "id": "unit", + "value": "bytes" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "results_cache_miss_bytes" + }, + "properties": [ + { + "id": "unit", + "value": "bytes" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "estimated_series_count" + }, + "properties": [ + { + "id": "unit", + "value": "short" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "fetched_chunks_count" + }, + "properties": [ + { + "id": "unit", + "value": "short" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "fetched_series_count" + }, + "properties": [ + { + "id": "unit", + "value": "short" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Time span" + }, + "properties": [ + { + "id": "unit", + "value": "s" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Duration" + }, + "properties": [ + { + "id": "unit", + "value": "s" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Step" + }, + "properties": [ + { + "id": "unit", + "value": "s" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "queue_time_seconds" + }, + "properties": [ + { + "id": "unit", + "value": "s" + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "query_wall_time_seconds" + }, + "properties": [ + { + "id": "unit", + "value": "s" + } + ] + } + ] + }, + "height": "500px", + "id": 19, + "span": 12, + "targets": [ + { + "expr": "{cluster=~\"$cluster\",namespace=~\"$namespace\",name=~\"query-frontend.*\"} |= \"query stats\" != \"/api/v1/read\" | logfmt | user=~\"${tenant_id}\" | user_agent=~\"${user_agent}\" | response_time > ${min_duration} | label_format response_time_seconds=\"{{ if .response_time }} {{ duration .response_time }} {{ end }}\",param_step_seconds=\"{{ if .param_step }} {{ div .param_step 1000 }} {{ end }}\",length_seconds=\"{{ if .length }} {{ duration .length }} {{ end }}\"", + "instant": false, + "legendFormat": "", + "range": true, + "refId": "A" + } + ], + "title": "Slow queries", + "transformations": [ + { + "id": "extractFields", + "options": { + "source": "labels" + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Line": true, + "Time": true, + "caller": true, + "cluster": true, + "component": true, + "container": true, + "gossip_ring_member": true, + "host": true, + "id": true, + "job": true, + "labels": true, + "length": true, + "level": true, + "line": true, + "method": true, + "msg": true, + "name": true, + "namespace": true, + "param_step": true, + "path": true, + "pod": true, + "pod_template_hash": true, + "response_time": true, + "stream": true, + "traceID": true, + "tsNs": true + }, + "indexByName": { + "err": 10, + "length_seconds": 3, + "param_end": 5, + "param_query": 8, + "param_start": 4, + "param_step_seconds": 7, + "param_time": 6, + "response_time_seconds": 9, + "status": 1, + "ts": 0, + "user": 2 + }, + "renameByName": { + "err": "Error", + "length_seconds": "Time span", + "param_end": "End", + "param_query": "Query", + "param_start": "Start", + "param_step_seconds": "Step", + "param_time": "Time (instant query)", + "response_time_seconds": "Duration", + "ts": "Completion date", + "user": "Tenant ID" + } + } + }, + { + "id": "convertFieldType", + "options": { + "conversions": [ + { + "destinationType": "number", + "targetField": "sharded_queries" + }, + { + "destinationType": "number", + "targetField": "split_queries" + }, + { + "destinationType": "number", + "targetField": "fetched_chunk_bytes" + }, + { + "destinationType": "number", + "targetField": "fetched_index_bytes" + }, + { + "destinationType": "number", + "targetField": "response_size_bytes" + }, + { + "destinationType": "number", + "targetField": "results_cache_hit_bytes" + }, + { + "destinationType": "number", + "targetField": "results_cache_miss_bytes" + }, + { + "destinationType": "number", + "targetField": "estimated_series_count" + }, + { + "destinationType": "number", + "targetField": "fetched_chunks_count" + }, + { + "destinationType": "number", + "targetField": "fetched_series_count" + }, + { + "destinationType": "number", + "targetField": "Time span" + }, + { + "destinationType": "number", + "targetField": "Duration" + }, + { + "destinationType": "number", + "targetField": "Step" + }, + { + "destinationType": "number", + "targetField": "queue_time_seconds" + }, + { + "destinationType": "number", + "targetField": "query_wall_time_seconds" + } + ] + } + } + ], + "type": "table" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "hide": 0, + "includeAll": false, + "label": "Loki data source", + "multi": false, + "name": "loki_datasource", + "query": "loki", + "type": "datasource" + }, + { + "current": { + "selected": true, + "text": "5s", + "value": "5s" + }, + "hide": 0, + "label": "Min duration", + "name": "min_duration", + "options": [ + { + "selected": true, + "text": "5s", + "value": "5s" + } + ], + "query": "5s", + "type": "textbox" + }, + { + "current": { + "selected": true, + "text": ".*", + "value": ".*" + }, + "hide": 0, + "label": "Tenant ID", + "name": "tenant_id", + "options": [ + { + "selected": true, + "text": ".*", + "value": ".*" + } + ], + "query": ".*", + "type": "textbox" + }, + { + "current": { + "selected": true, + "text": ".*", + "value": ".*" + }, + "hide": 0, + "label": "User-Agent HTTP Header", + "name": "user_agent", + "options": [ + { + "selected": true, + "text": ".*", + "value": ".*" + } + ], + "query": ".*", + "type": "textbox" + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Slow queries", + "uid": "6089e1ce1e678788f46312a0a1e647e6", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-tenants.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-tenants.json new file mode 100644 index 0000000..257327d --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-tenants.json @@ -0,0 +1,2661 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "25px", + "panels": [ + { + "content": "

\n This dashboard shows various metrics detailed by tenant (user) selected above.\n

\n", + "datasource": null, + "description": "", + "id": 1, + "mode": "markdown", + "span": 12, + "title": "", + "transparent": true, + "type": "text" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Tenants dashboard description", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### All series\nNumber of active, in-memory, and owned series per user, and active series matching custom trackers (in parenthesis).\nNote that these counts include all series regardless of the type of data (counter, gauge, native histogram, etc.).\nNote that active series matching custom trackers are included in the total active series count.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum(\n (\n cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n - cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "legendFormat": "in-memory", + "legendLink": null + }, + { + "expr": "max(cortex_limits_overrides{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"max_global_series_per_user\", user=\"$user\"})\nor\nmax(cortex_limits_defaults{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"max_global_series_per_user\"})\n", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "sum(\n cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "legendFormat": "active", + "legendLink": null + }, + { + "expr": "sum(\n cortex_ingester_owned_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "legendFormat": "owned", + "legendLink": null + }, + { + "expr": "sum by (name) (\n cortex_ingester_active_series_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n) > 0\n", + "format": "time_series", + "legendFormat": "active ({{ name }})", + "legendLink": null + } + ], + "title": "All series", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### In-memory series per ingester\nLocal tenant series limit and number of in-memory series per ingester.\nBecause series can be unevenly distributed across ingesters, ingesters may hit the local limit at different times.\nNote that in-memory series may exceed the local limit if limiting based on owned series is enabled.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byRegexp", + "options": "/local limit .+/" + }, + "properties": [ + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + }, + { + "id": "color", + "value": { + "fixedColor": "yellow", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "min by (job) (cortex_ingester_local_limits{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", limit=\"max_global_series_per_user\", user=\"$user\"})\n", + "format": "time_series", + "legendFormat": "local limit ({{job}})", + "legendLink": null + }, + { + "expr": "cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n- cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "In-memory series per ingester", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Owned series per ingester\nLocal tenant series limit and number of owned series per ingester.\nBecause series can be unevenly distributed across ingesters, ingesters may hit the local limit at different times.\nOwned series are the subset of an ingester's in-memory series that currently map to it in the ring\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byRegexp", + "options": "/local limit .+/" + }, + "properties": [ + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + }, + { + "id": "color", + "value": { + "fixedColor": "yellow", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "min by (job) (cortex_ingester_local_limits{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", limit=\"max_global_series_per_user\", user=\"$user\"})\n", + "format": "time_series", + "legendFormat": "local limit ({{job}})", + "legendLink": null + }, + { + "expr": "cortex_ingester_owned_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Owned series per ingester", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Tenant series counts", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Series with exemplars\nNumber of series with exemplars currently in storage.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(\n cortex_ingester_tsdb_exemplar_series_with_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "legendFormat": "series", + "legendLink": null + } + ], + "title": "Series with exemplars", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Oldest exemplar age\nThe age of the oldest exemplar stored in circular storage.\nUseful to check for what time range the current exemplar buffer limit allows.\nThis usually means the max age for all exemplars for a typical setup.\nThis is not true though if one of the series timestamp is in future compared to rest series.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "time() - min(cortex_ingester_tsdb_exemplar_last_exemplars_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"} > 0)", + "format": "time_series", + "legendFormat": "age", + "legendLink": null + } + ], + "title": "Oldest exemplar age", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Native histogram series\nNumber of active native histogram series per user, and active native histogram series matching custom trackers (in parenthesis).\nNote that active series matching custom trackers are included in the total active series count.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(\n cortex_ingester_active_native_histogram_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "legendFormat": "active", + "legendLink": null + }, + { + "expr": "sum by (name) (\n cortex_ingester_active_native_histogram_series_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n) > 0\n", + "format": "time_series", + "legendFormat": "active ({{ name }})", + "legendLink": null + } + ], + "title": "Native histogram series", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Total number of buckets used by native histogram series\nTotal number of buckets in active native histogram series per user, and total active native histogram buckets matching custom trackers (in parenthesis).\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(\n cortex_ingester_active_native_histogram_buckets{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "legendFormat": "buckets", + "legendLink": null + }, + { + "expr": "sum by (name) (\n cortex_ingester_active_native_histogram_buckets_custom_tracker{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n) > 0\n", + "format": "time_series", + "legendFormat": "buckets ({{ name }})", + "legendLink": null + } + ], + "title": "Total number of buckets used by native histogram series", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Exemplars and native histograms", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Distributor requests incoming rate\nThe rate of requests that have come in to the distributor, including rejected requests.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_requests_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "rate", + "legendLink": null + } + ], + "title": "Distributor requests incoming rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Distributor requests received (accepted) rate\nThe rate of received requests, excluding rejected requests.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_received_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "rate", + "legendLink": null + }, + { + "expr": "max(cortex_limits_overrides{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"request_rate\", user=\"$user\"})\nor\nmax(cortex_limits_defaults{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"request_rate\"})\n", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "Distributor requests received (accepted) rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Newest seen sample age\nThe age of the newest received sample seen in the distributors.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "time() - max(cortex_distributor_latest_seen_sample_timestamp_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", user=\"$user\"} > 0)", + "format": "time_series", + "legendFormat": "age", + "legendLink": null + } + ], + "title": "Newest seen sample age", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Distributor discarded requests rate\nThe rate of each request's discarding reason.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by (reason) (rate(cortex_discarded_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{ reason }}", + "legendLink": null + } + ], + "title": "Distributor discarded requests rate", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor ingestion requests", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Distributor samples incoming rate\nThe rate of samples that have come in to the distributor, including rejected or deduped exemplars.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 13, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_samples_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "rate", + "legendLink": null + } + ], + "title": "Distributor samples incoming rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Distributor samples received (accepted) rate\nThe rate of received samples, excluding rejected and deduped samples.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "rate", + "legendLink": null + }, + { + "expr": "max(cortex_limits_overrides{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"ingestion_rate\", user=\"$user\"})\nor\nmax(cortex_limits_defaults{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"ingestion_rate\"})\n", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "Distributor samples received (accepted) rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Distributor deduplicated/non-HA\nThe rate of deduplicated samples and the rate of received samples for a user that has HA tracking turned on, but the sample didn't contain both HA labels.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 15, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_deduped_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "deduplicated", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_distributor_non_ha_samples_received_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "non-HA", + "legendLink": null + } + ], + "title": "Distributor deduplicated/non-HA", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Distributor and ingester discarded samples rate\nThe rate of each sample's discarding reason.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 16, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by (reason) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{ reason }} (distributor)", + "legendLink": null + }, + { + "expr": "sum by (reason) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{ reason }} (ingester)", + "legendLink": null + } + ], + "title": "Distributor and ingester discarded samples rate", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Samples ingestion funnel", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Distributor exemplars incoming rate\nThe rate of exemplars that have come in to the distributor, including rejected or deduped exemplars.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 17, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_exemplars_in_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "rate", + "legendLink": null + } + ], + "title": "Distributor exemplars incoming rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Distributor exemplars received (accepted) rate\nThe rate of received exemplars, excluding rejected and deduped exemplars.\nThis number can be sensibly lower than incoming rate because we dedupe the HA sent exemplars, and then reject based on time.\nSee discarded rate for reasons why exemplars are being discarded.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 18, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_distributor_received_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "rate", + "legendLink": null + } + ], + "title": "Distributor exemplars received (accepted) rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Distributor discarded exemplars rate\nThe rate of each exmplars' discarding reason.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 19, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by (reason) (rate(cortex_discarded_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{ reason }}", + "legendLink": null + } + ], + "title": "Distributor discarded exemplars rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Ingester appended exemplars rate\nTotal number of exemplars appended in the ingesters.\nThis can be lower than ingested exemplars rate since TSDB does not append the same exemplar twice, and those can be frequent.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 20, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(\n rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"}[$__rate_interval])\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "legendFormat": "rate", + "legendLink": null + } + ], + "title": "Ingester appended exemplars rate", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Exemplars ingestion funnel", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Symbol table size for loaded blocks\nSize of symbol table in memory for loaded blocks, averaged by ingester.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 21, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (job) (cortex_ingester_tsdb_symbol_table_size_bytes{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"})", + "format": "time_series", + "legendFormat": "{{ job }}", + "legendLink": null + } + ], + "title": "Symbol table size for loaded blocks", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Space used by local blocks\nThe number of bytes that are currently used for local storage by all blocks.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 22, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (job) (cortex_ingester_tsdb_storage_blocks_bytes{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", user=\"$user\"})", + "format": "time_series", + "legendFormat": "{{ job }}", + "legendLink": null + } + ], + "title": "Space used by local blocks", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingesters' storage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Number of groups\nTotal number of rule groups for a tenant.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 23, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "count(sum by (rule_group) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))", + "format": "time_series", + "legendFormat": "groups", + "legendLink": null + }, + { + "expr": "max(cortex_limits_overrides{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"ruler_max_rule_groups_per_tenant\", user=\"$user\"})\nor\nmax(cortex_limits_defaults{cluster=~\"$cluster\", job=~\"($namespace)/((overrides-exporter|mimir-backend.*))\", limit_name=\"ruler_max_rule_groups_per_tenant\"})\n", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "Number of groups", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Number of rules\nTotal number of rules for a tenant.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 24, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"})", + "format": "time_series", + "legendFormat": "rules", + "legendLink": null + } + ], + "title": "Number of rules", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 25, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_prometheus_rule_evaluations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "rate", + "legendLink": null + } + ], + "title": "Total evaluations rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 26, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by (rule_group) (rate(cortex_prometheus_rule_evaluation_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval])) > 0", + "format": "time_series", + "legendFormat": "{{ rule_group }}", + "legendLink": null + } + ], + "title": "Failed evaluations rate", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rules", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 27, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "rules", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (rule_group) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))", + "format": "table", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit biggest groups", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 28, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "seconds", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (rule_group) (cortex_prometheus_rule_group_last_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}))", + "format": "table", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit slowest groups (last evaluation)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Top rules", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 29, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(rate(cortex_prometheus_notifications_sent_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "rate", + "legendLink": null + } + ], + "title": "Sent notifications rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "rate" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 30, + "links": [ ], + "options": { + "legend": { + "showLegend": false + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(rate(cortex_prometheus_notifications_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "rate", + "legendLink": null + } + ], + "title": "Failed notifications rate", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Notifications", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 31, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (user) (cortex_alertmanager_alerts{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", user=\"$user\"})", + "format": "time_series", + "legendFormat": "alerts", + "legendLink": null + }, + { + "expr": "sum by (user) (cortex_alertmanager_silences{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", user=\"$user\"})", + "format": "time_series", + "legendFormat": "silences", + "legendLink": null + } + ], + "title": "Alerts", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 32, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "(\nsum(rate(cortex_alertmanager_notifications_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))\n-\non() (sum(rate(cortex_alertmanager_notifications_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval])) or on () vector(0))\n) > 0\n", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_alertmanager_notifications_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "NPS", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 33, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "(\nsum(rate(cortex_alertmanager_notifications_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval])) by(integration)\n-\n(sum(rate(cortex_alertmanager_notifications_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval])) by(integration) or\n (sum(rate(cortex_alertmanager_notifications_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval])) by(integration) * 0)\n)) > 0\n", + "format": "time_series", + "legendFormat": "success - {{ integration }}", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_alertmanager_notifications_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((alertmanager|cortex|mimir|mimir-backend.*))\", user=\"$user\"}[$__rate_interval])) by(integration)", + "format": "time_series", + "legendFormat": "failed - {{ integration }}", + "legendLink": null + } + ], + "title": "NPS by integration", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alertmanager", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 34, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(rate(cortex_query_frontend_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((query-frontend.*|cortex|mimir|mimir-read.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Queries / Sec", + "legendLink": null + } + ], + "title": "Rate of Read Requests - query-frontend", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 35, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(cortex_query_scheduler_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((query-scheduler.*|mimir-backend.*))\", user=\"$user\"})", + "format": "time_series", + "legendFormat": "Queue Length", + "legendLink": null + } + ], + "title": "Number of Queries Queued - query-scheduler", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Read Path - Queries (User)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 36, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(rate(cortex_query_frontend_queries_total{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", user=\"$user\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Queries / Sec", + "legendLink": null + } + ], + "title": "Rate of Read Requests - ruler-query-frontend", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 37, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(cortex_query_scheduler_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\", user=\"$user\"})", + "format": "time_series", + "legendFormat": "Queue Length", + "legendLink": null + } + ], + "title": "Number of Queries Queued - ruler-query-scheduler", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Read Path - Queries (Ruler)", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Estimated Compaction Jobs\nEstimated number of compaction jobs for selected user, based on latest version of bucket index. When user sends data, ingesters upload new user blocks every 2 hours\n(shortly after 01:00 UTC, 03:00 UTC, 05:00 UTC, etc.), and compactors should process all of the blocks within 2h interval.\nIf this graph regularly goes to zero (or close to zero) in 2 hour intervals, then compaction for this user works correctly.\n\nDepending on the configuration, there are two types of jobs: `split` jobs and `merge` jobs. Split jobs will only show up when user is configured with positive number of `compactor_split_and_merge_shards`.\nValues for split and merge jobs are stacked.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 50, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 38, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (type) (cortex_bucket_index_estimated_compaction_jobs{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", user=\"$user\"})\nand ignoring(type)\n(sum(rate(cortex_bucket_index_estimated_compaction_jobs_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) == 0)\n", + "format": "time_series", + "legendFormat": "{{ job }}", + "legendLink": null + } + ], + "title": "Estimated Compaction Jobs", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Number of blocks\nNumber of blocks stored in long-term storage for this user.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 39, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "max by (user) (cortex_bucket_blocks_count{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\", user=\"$user\"})\n", + "format": "time_series", + "legendFormat": "{{ job }}", + "legendLink": null + } + ], + "title": "Blocks", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Compactions", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "user", + "multi": false, + "name": "user", + "options": [ ], + "query": "label_values(cortex_ingester_active_series{cluster=~\"$cluster\", namespace=~\"$namespace\"}, user)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "current": { + "selected": true, + "text": "10", + "value": "10" + }, + "hide": 0, + "includeAll": false, + "multi": false, + "name": "limit", + "options": [ + { + "selected": true, + "text": "10", + "value": "10" + }, + { + "selected": false, + "text": "50", + "value": "50" + }, + { + "selected": false, + "text": "100", + "value": "100" + }, + { + "selected": false, + "text": "500", + "value": "500" + }, + { + "selected": false, + "text": "1000", + "value": "1000" + } + ], + "type": "custom" + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Tenants", + "uid": "35fa247ce651ba189debf33d7ae41611", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-top-tenants.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-top-tenants.json new file mode 100644 index 0000000..1d50197 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-top-tenants.json @@ -0,0 +1,1639 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "25px", + "panels": [ + { + "content": "

\n This dashboard shows the top tenants based on multiple selection criterias.\n Rows are collapsed by default to avoid querying all of them.\n Use the templating variable \"limit\" above to select the amount of users to be shown.\n

\n", + "datasource": null, + "description": "", + "id": 1, + "mode": "markdown", + "span": 12, + "title": "", + "transparent": true, + "type": "text" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Top tenants dashboard description", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "series", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "user", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "user", + "thresholds": [ ], + "type": "number", + "unit": "string" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit,\n sum by (user) (\n cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n )\n)\n", + "format": "table", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by active series", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By active series", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "series", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "user", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "user", + "thresholds": [ ], + "type": "number", + "unit": "string" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"} )\n)\n)", + "format": "table", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by in-memory series (series created - series removed)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By in-memory series", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 12, + "targets": [ + { + "expr": "sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} )\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"} )\n)\n\nand\ntopk($limit, sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ end())\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ end())\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"} @ end())\n)\n - sum by (user) (\n (\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_created_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ start())\n -\n sum by (user, cluster, namespace) (cortex_ingester_memory_series_removed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"} @ start())\n )\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"} @ start())\n)\n)\n", + "format": "time_series", + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "title": "Top $limit users by in-memory series (series created - series removed) that grew the most between query range start and query range end", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By in-memory series growth", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "samples/s", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "user", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "user", + "thresholds": [ ], + "type": "number", + "unit": "string" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"}[5m])))", + "format": "table", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by received samples rate in last 5m", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By samples rate", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 12, + "targets": [ + { + "expr": "sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\nand\ntopk($limit,\n sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ end()))\n -\n sum by (user) (rate(cortex_distributor_received_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ start()))\n)\n", + "format": "time_series", + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "title": "Top $limit users by received samples rate that grew the most between query range start and query range end", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By samples rate growth", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "samples/s", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "user", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "user", + "thresholds": [ ], + "type": "number", + "unit": "string" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor.*|cortex|mimir|mimir-write.*))\"}[5m])))", + "format": "table", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by discarded samples rate in last 5m", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By discarded samples rate", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 12, + "targets": [ + { + "expr": "sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\nand\ntopk($limit,\n sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ end()))\n -\n sum by (user) (rate(cortex_discarded_samples_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*|distributor.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval] @ start()))\n)\n", + "format": "time_series", + "legendFormat": "{{ user }}", + "legendLink": null + } + ], + "title": "Top $limit users by discarded samples rate that grew the most between query range start and query range end", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By discarded samples rate growth", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "series", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "user", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "user", + "thresholds": [ ], + "type": "number", + "unit": "string" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit,\n sum by (user) (\n cortex_ingester_tsdb_exemplar_series_with_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n )\n)\n", + "format": "table", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by series with exemplars", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By series with exemplars", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "exemplars/s", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "user", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "user", + "thresholds": [ ], + "type": "number", + "unit": "string" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (user) (rate(cortex_distributor_received_exemplars_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"}[5m])))", + "format": "table", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by received exemplars rate in last 5m", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By exemplars rate", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 11, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 3, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "rules", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "user", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "user", + "thresholds": [ ], + "type": "number", + "unit": "string" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (rule_group, user) (cortex_prometheus_rule_group_rules{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}))", + "format": "table", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit biggest groups", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By rule group size", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 12, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 3, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "seconds", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "user", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "user", + "thresholds": [ ], + "type": "number", + "unit": "string" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit, sum by (rule_group, user) (cortex_prometheus_rule_group_last_duration_seconds{cluster=~\"$cluster\", job=~\"($namespace)/((ruler|cortex|mimir|mimir-backend.*))\"}))", + "format": "table", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit slowest groups (last evaluation)", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By rule group evaluation time", + "titleSize": "h6" + }, + { + "collapse": true, + "height": "250px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 13, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "sort": { + "col": 2, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Compaction Jobs", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "short" + }, + { + "alias": "user", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "user", + "thresholds": [ ], + "type": "number", + "unit": "string" + }, + { + "alias": "", + "colorMode": null, + "colors": [ ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "topk($limit,\n sum by (user) (cortex_bucket_index_estimated_compaction_jobs{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"})\n and ignoring(user)\n (sum(rate(cortex_bucket_index_estimated_compaction_jobs_errors_total{cluster=~\"$cluster\", job=~\"($namespace)/((compactor.*|cortex|mimir|mimir-backend.*))\"}[$__rate_interval])) == 0)\n)\n", + "format": "table", + "instant": true, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $limit users by estimated compaction jobs from bucket-index", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "By estimated compaction jobs from bucket-index", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "current": { + "selected": true, + "text": "10", + "value": "10" + }, + "hide": 0, + "includeAll": false, + "multi": false, + "name": "limit", + "options": [ + { + "selected": true, + "text": "10", + "value": "10" + }, + { + "selected": false, + "text": "50", + "value": "50" + }, + { + "selected": false, + "text": "100", + "value": "100" + } + ], + "type": "custom" + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Top tenants", + "uid": "bc6e12d4fe540e4a1785b9d3ca0ffdd9", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-writes-networking.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-writes-networking.json new file mode 100644 index 0000000..5a757f8 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-writes-networking.json @@ -0,0 +1,820 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?(distributor|ingester|mimir-write).*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Summary", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?distributor.*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_receive_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Receive bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(pod) (rate(container_network_transmit_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Transmit bandwidth", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"})", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(cortex_inflight_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"})", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + } + ], + "title": "Inflight requests (per pod)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "avg(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"}))", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + }, + { + "expr": "max(sum by(pod) (cortex_tcp_connections{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"}))", + "format": "time_series", + "legendFormat": "highest", + "legendLink": null + }, + { + "expr": "min(cortex_tcp_connections_limit{cluster=~\"$cluster\", namespace=~\"$namespace\",pod=~\"(.*mimir-)?ingester.*\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + } + ], + "title": "TCP connections (per pod)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Writes networking", + "uid": "978c1cb452585c96697a238eaac7fe2d", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-writes-resources.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-writes-resources.json new file mode 100644 index 0000000..503a6b8 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-writes-resources.json @@ -0,0 +1,1186 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 1, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor|ingester|mimir-write\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 2, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor|ingester|mimir-write\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 3, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor|ingester|mimir-write\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Summary", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 4, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 5, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 6, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"distributor\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (cortex_ingester_memory_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "In-memory series", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 8, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\",resource=\"cpu\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "CPU", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_rss{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (RSS)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "request" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#FFC000", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E02F44", + "mode": "fixed" + } + }, + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + }, + { + "expr": "min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"} > 0)", + "format": "time_series", + "legendFormat": "limit", + "legendLink": null + }, + { + "expr": "min(kube_pod_container_resource_requests{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\",resource=\"memory\"})", + "format": "time_series", + "legendFormat": "request", + "legendLink": null + } + ], + "title": "Memory (workingset)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "bytes" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\",container=~\"ingester\"})", + "format": "time_series", + "legendFormat": "{{pod}}", + "legendLink": null + } + ], + "title": "Memory (go heap inuse)", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_written_bytes_total[$__rate_interval]\n )\n)\n+\nignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"ingester\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "title": "Disk writes", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "Bps" + }, + "overrides": [ ] + }, + "id": 13, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by(instance, pod, device) (\n rate(\n node_disk_read_bytes_total[$__rate_interval]\n )\n) + ignoring(pod) group_right() (\n label_replace(\n count by(\n instance,\n pod,\n device\n )\n (\n container_fs_writes_bytes_total{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n container=~\"ingester\",\n device!~\".*sda.*\"\n }\n ),\n \"device\",\n \"$1\",\n \"device\",\n \"/dev/(.*)\"\n ) * 0\n)\n\n", + "format": "time_series", + "legendFormat": "{{pod}} - {{device}}", + "legendLink": null + } + ], + "title": "Disk reads", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "custom": { + "fillOpacity": 0 + }, + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "percentunit" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "max by(persistentvolumeclaim) (\n kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} /\n kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}\n)\nand\ncount by(persistentvolumeclaim) (\n kube_persistentvolumeclaim_labels{\n cluster=~\"$cluster\", namespace=~\"$namespace\",\n label_name=~\"(ingester).*\"\n }\n)\n", + "format": "time_series", + "legendFormat": "{{persistentvolumeclaim}}", + "legendLink": null + } + ], + "title": "Disk space utilization", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "prod", + "value": "prod" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Writes resources", + "uid": "bc9160e50b52e89e0e49c840fea3d379", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-writes.json b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-writes.json new file mode 100644 index 0000000..c91b1b0 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/dashboards/mimir-writes.json @@ -0,0 +1,3253 @@ +{ + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "8.0.0" + } + ], + "annotations": { + "list": [ ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "links": [ + { + "asDropdown": true, + "icon": "external link", + "includeVars": true, + "keepTime": true, + "tags": [ + "mimir" + ], + "targetBlank": false, + "title": "Mimir dashboards", + "type": "dashboards" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "125px", + "panels": [ + { + "content": "

\n This dashboard shows various health metrics for the write path.\n It is broken into sections for each service on the write path,\n and organized by the order in which the write request flows.\n
\n Incoming metrics data travels from the gateway → distributor → ingester.\n
\n For each service, there are 3 panels showing\n (1) requests per second to that service,\n (2) average, median, and p99 latency of requests to that service, and\n (3) p99 latency of requests to each instance of that service.\n

\n

\n It also includes metrics for the key-value (KV) stores used to manage\n the high-availability tracker and the ingesters.\n

\n", + "datasource": null, + "description": "", + "id": 1, + "mode": "markdown", + "span": 12, + "title": "", + "transparent": true, + "type": "text" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Writes dashboard description", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_namespace_job:cortex_distributor_received_samples:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Samples / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Exemplars / sec\nThe total number of received exemplars by the distributors, excluding rejected and deduped exemplars, but not necessarily ingested by the ingesters.\n\n", + "fill": 1, + "format": "short", + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Exemplars / sec", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### In-memory series\nThe number of series not yet flushed to object storage that are held in ingester memory.\n\n", + "fill": 1, + "format": "short", + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cortex_ingester_memory_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n/ on(cluster, namespace) group_left\nmax by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"}))\n", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "In-memory series", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "### Exemplars in ingesters\nNumber of TSDB exemplars currently in ingesters' storage.\n\n", + "fill": 1, + "format": "short", + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cortex_ingester_tsdb_exemplar_exemplars_in_storage{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n/ on(cluster, namespace) group_left\nmax by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"}))\n", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Exemplars in ingesters", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "short", + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "count(count by(user) (cortex_ingester_active_series{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}))", + "format": "time_series", + "instant": true, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Tenants", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Requests / sec\nThe rate of successful, failed and rejected requests to distributor.\nRejected requests are requests that distributor fails to handle because of distributor instance limits.\nWhen distributor is configured to use \"early\" request rejection, then rejected requests are NOT included in other metrics.\nWhen distributor is not configured to use \"early\" request rejection, then rejected requests are also counted as \"errors\".\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 7, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 8, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})) * 1e3", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 9, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", route=~\"/distributor.Distributor/Push|/httpgrpc.*|api_(v1|prom)_push|otlp_v1_metrics\"}[$__rate_interval])))", + "format": "time_series", + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Requests / sec\nThe rate of successful, failed and rejected requests to ingester.\nRejected requests are requests that ingester fails to handle because of ingester instance limits (ingester-max-inflight-push-requests, ingester-max-inflight-push-requests-bytes, ingester-max-ingestion-rate).\nWhen ingester is configured to use \"early\" request rejection, then rejected requests are NOT included in other metrics.\nWhen ingester is not configured to use \"early\" request rejection, then rejected requests are also counted as \"errors\".\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 10, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",route=\"/cortex.Ingester/Push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 11, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 4, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})) * 1e3", + "format": "time_series", + "legendFormat": "99th percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})) * 1e3", + "format": "time_series", + "legendFormat": "50th percentile", + "refId": "B" + }, + { + "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"})", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 0, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 12, + "links": [ ], + "options": { + "legend": { + "displayMode": "hidden", + "showLegend": false + }, + "tooltip": { + "mode": "multi", + "sort": "desc" + } + }, + "span": 4, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", route=\"/cortex.Ingester/Push\"}[$__rate_interval])))", + "format": "time_series", + "legendFormat": "", + "legendLink": null + } + ], + "title": "Per pod p99 latency", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Replicas\nThe maximum and current number of distributor replicas.\nNote: The current number of replicas can still show 1 replica even when scaled to 0.\nBecause HPA never reports 0 replicas, the query will report 0 only if the HPA is not active.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byRegexp", + "options": "/Max .+/" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/Current .+/" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + } + ] + }, + { + "matcher": { + "id": "byRegexp", + "options": "/Min .+/" + }, + "properties": [ + { + "id": "custom.fillOpacity", + "value": 0 + }, + { + "id": "custom.lineStyle", + "value": { + "fill": "dash" + } + } + ] + } + ] + }, + "id": 13, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "max by (scaletargetref_name) (\n kube_horizontalpodautoscaler_spec_max_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"}\n # Add the scaletargetref_name label for readability\n + on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"}\n)\n", + "format": "time_series", + "legendFormat": "Max {{ scaletargetref_name }}", + "legendLink": null + }, + { + "expr": "max by (scaletargetref_name) (\n kube_horizontalpodautoscaler_status_current_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"}\n # HPA doesn't go to 0 replicas, so we multiply by 0 if the HPA is not active\n * on (cluster, namespace, horizontalpodautoscaler)\n kube_horizontalpodautoscaler_status_condition{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\", condition=\"ScalingActive\", status=\"true\"}\n # Add the scaletargetref_name label for readability\n + on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"}\n)\n", + "format": "time_series", + "legendFormat": "Current {{ scaletargetref_name }}", + "legendLink": null + }, + { + "expr": "max by (scaletargetref_name) (\n kube_horizontalpodautoscaler_spec_min_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"}\n # Add the scaletargetref_name label for readability\n + on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"}\n)\n", + "format": "time_series", + "legendFormat": "Min {{ scaletargetref_name }}", + "legendLink": null + } + ], + "title": "Replicas", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Scaling metric (CPU): Desired replicas\nThis panel shows the scaling metric exposed by KEDA divided by the target/threshold used.\nIt should represent the desired number of replicas, ignoring the min/max constraints applied later.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 14, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by (scaler) (\n label_replace(\n keda_scaler_metrics_value{cluster=~\"$cluster\", exported_namespace=~\"$namespace\", scaler=~\".*cpu.*\"},\n \"namespace\", \"$1\", \"exported_namespace\", \"(.*)\"\n )\n /\n on(cluster, namespace, scaledObject, metric) group_left label_replace(\n label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"},\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n ),\n \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\"\n )\n)\n", + "format": "time_series", + "legendFormat": "{{ scaler }}", + "legendLink": null + } + ], + "title": "Scaling metric (CPU): Desired replicas", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Scaling metric (memory): Desired replicas\nThis panel shows the scaling metric exposed by KEDA divided by the target/threshold used.\nIt should represent the desired number of replicas, ignoring the min/max constraints applied later.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 15, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by (scaler) (\n label_replace(\n keda_scaler_metrics_value{cluster=~\"$cluster\", exported_namespace=~\"$namespace\", scaler=~\".*memory.*\"},\n \"namespace\", \"$1\", \"exported_namespace\", \"(.*)\"\n )\n /\n on(cluster, namespace, scaledObject, metric) group_left label_replace(\n label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"},\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n ),\n \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\"\n )\n)\n", + "format": "time_series", + "legendFormat": "{{ scaler }}", + "legendLink": null + } + ], + "title": "Scaling metric (memory): Desired replicas", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Autoscaler failures rate\nThe rate of failures in the KEDA custom metrics API server. Whenever an error occurs, the KEDA custom\nmetrics server is unable to query the scaling metric from Prometheus so the autoscaler woudln't work properly.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ ] + }, + "id": 16, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum by(cluster, namespace, scaler, metric, scaledObject) (\n label_replace(\n rate(keda_scaler_errors[$__rate_interval]),\n \"namespace\", \"$1\", \"exported_namespace\", \"(.+)\"\n )\n) +\non(cluster, namespace, metric, scaledObject) group_left\nlabel_replace(\n label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-distributor\"} * 0,\n \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\"\n ),\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n", + "format": "time_series", + "legendFormat": "{{scaler}} failures", + "legendLink": null + } + ], + "title": "Autoscaler failures rate", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor - autoscaling", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 17, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 18, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-hatracker\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor - key-value store for high-availability (HA) deduplication", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 19, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 20, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\", kv_name=~\"distributor-(lifecycler|ring)\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Distributor - key-value store for distributors ring", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "1xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EAB839", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "2xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "3xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#6ED0E0", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "4xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#EF843C", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "5xx" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "OK" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "cancel" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#A9A9A9", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "error" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "success" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 21, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "format": "time_series", + "legendFormat": "{{status}}", + "refId": "A" + } + ], + "title": "Requests / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 22, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_kv_request_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_kv_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\", kv_name=~\"ingester-.*\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester - key-value store for the ingesters ring", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Uploaded blocks / sec\nThe rate of blocks being uploaded from the ingesters\nto object storage.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 23, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_shipper_uploads_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_shipper_upload_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_ingester_shipper_upload_failures_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Uploaded blocks / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Upload latency\nThe average, median (50th percentile), and 99th percentile time\nthe ingesters take to upload blocks to object storage.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 24, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(thanos_objstore_bucket_operation_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(thanos_objstore_bucket_operation_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval])) * 1e3 / sum(rate(thanos_objstore_bucket_operation_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\",component=\"ingester\",operation=\"upload\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Upload latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester - shipper", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Compactions per second\nIngesters maintain a local TSDB per-tenant on disk. Each TSDB maintains a head block for each\nactive time series; these blocks get periodically compacted (by default, every 2h).\nThis panel shows the rate of compaction operations across all TSDBs on all ingesters.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 25, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_tsdb_compactions_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_ingester_tsdb_compactions_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Compactions / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Compaction latency\nThe average, median (50th percentile), and 99th percentile time ingesters take to compact TSDB head blocks\non the local filesystem.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ms" + }, + "overrides": [ ] + }, + "id": 26, + "links": [ ], + "nullPointMode": "null as zero", + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50, sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) by (le)) * 1e3", + "format": "time_series", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "expr": "sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_ingester_tsdb_compaction_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "Average", + "refId": "C" + } + ], + "title": "Compactions latency", + "type": "timeseries", + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester - TSDB head", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### WAL truncations per second\nThe WAL is truncated each time a new TSDB block is written. This panel measures the rate of\ntruncations.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 27, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_tsdb_wal_truncations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_tsdb_wal_truncations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_ingester_tsdb_wal_truncations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "WAL truncations / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Checkpoints created per second\nCheckpoints are created as part of the WAL truncation process.\nThis metric measures the rate of checkpoint creation.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "failed" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "successful" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#7EB26D", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 28, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_tsdb_checkpoint_creations_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) - sum(rate(cortex_ingester_tsdb_checkpoint_creations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "successful", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_ingester_tsdb_checkpoint_creations_failed_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "failed", + "legendLink": null + } + ], + "title": "Checkpoints created / sec", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### WAL truncations latency (including checkpointing)\nAverage time taken to perform a full WAL truncation,\nincluding the time taken for the checkpointing to complete.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "noValue": "0", + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "s" + }, + "overrides": [ ] + }, + "id": 29, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_tsdb_wal_truncate_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))\n/\nsum(rate(cortex_ingester_tsdb_wal_truncate_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval])) >= 0\n", + "format": "time_series", + "legendFormat": "avg", + "legendLink": null + } + ], + "title": "WAL truncations latency (includes checkpointing)", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 100, + "lineWidth": 0, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + } + }, + "min": 0, + "noValue": "0", + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ops" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "WAL" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E24D42", + "mode": "fixed" + } + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "mmap-ed chunks" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#E28A42", + "mode": "fixed" + } + } + ] + } + ] + }, + "id": 30, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(rate(cortex_ingester_tsdb_wal_corruptions_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "WAL", + "legendLink": null + }, + { + "expr": "sum(rate(cortex_ingester_tsdb_mmap_chunk_corruptions_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "mmap-ed chunks", + "legendLink": null + } + ], + "title": "Corruptions / sec", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Ingester - TSDB write ahead log (WAL)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "description": "### Distributor exemplars incoming rate\nThe rate of exemplars that have come in to the distributor, including rejected or deduped exemplars.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ex/s" + }, + "overrides": [ ] + }, + "id": 31, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(cluster_namespace_job:cortex_distributor_exemplars_in:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "legendFormat": "incoming exemplars", + "legendLink": null + } + ], + "title": "Distributor exemplars incoming rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Distributor exemplars received rate\nThe rate of received exemplars, excluding rejected and deduped exemplars.\nThis number can be sensibly lower than incoming rate because we dedupe the HA sent exemplars, and then reject based on time, see `cortex_discarded_exemplars_total` for specific reasons rates.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ex/s" + }, + "overrides": [ ] + }, + "id": 32, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(cluster_namespace_job:cortex_distributor_received_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})", + "format": "time_series", + "legendFormat": "received exemplars", + "legendLink": null + } + ], + "title": "Distributor exemplars received rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Ingester ingested exemplars rate\nThe rate of exemplars ingested in the ingesters.\nEvery exemplar is sent to the replication factor number of ingesters, so the sum of rates from all ingesters is divided by the replication factor.\nThis ingested exemplars rate should match the distributor's received exemplars rate.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ex/s" + }, + "overrides": [ ] + }, + "id": 33, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(\n cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "legendFormat": "ingested exemplars", + "legendLink": null + } + ], + "title": "Ingester ingested exemplars rate", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "description": "### Ingester appended exemplars rate\nThe rate of exemplars appended in the ingesters.\nThis can be lower than ingested exemplars rate since TSDB does not append the same exemplar twice, and those can be frequent.\n\n", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "ex/s" + }, + "overrides": [ ] + }, + "id": 34, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 3, + "targets": [ + { + "expr": "sum(\n cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}\n / on(cluster, namespace) group_left\n max by (cluster, namespace) (cortex_distributor_replication_factor{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"})\n)\n", + "format": "time_series", + "legendFormat": "appended exemplars", + "legendLink": null + } + ], + "title": "Ingester appended exemplars rate", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Exemplars", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ ] + }, + "id": 35, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (reason) (rate(cortex_distributor_instance_rejected_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((distributor.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{reason}}", + "legendLink": null + } + ], + "title": "Rejected distributor requests", + "type": "timeseries" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "drawStyle": "line", + "fillOpacity": 1, + "lineWidth": 1, + "pointSize": 5, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + } + }, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ ] + }, + "unit": "reqps" + }, + "overrides": [ ] + }, + "id": 36, + "links": [ ], + "options": { + "legend": { + "showLegend": true + }, + "tooltip": { + "mode": "single", + "sort": "none" + } + }, + "span": 6, + "targets": [ + { + "expr": "sum by (reason) (rate(cortex_ingester_instance_rejected_requests_total{cluster=~\"$cluster\", job=~\"($namespace)/((ingester.*|cortex|mimir|mimir-write.*))\"}[$__rate_interval]))", + "format": "time_series", + "legendFormat": "{{reason}}", + "legendLink": null + } + ], + "title": "Rejected ingester requests", + "type": "timeseries" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Instance Limits", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "mimir" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(cortex_build_info, cluster)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "namespace", + "multi": true, + "name": "namespace", + "options": [ ], + "query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Mimir / Writes", + "uid": "8280707b8f16e7b87b840fc1cc92d4c5", + "version": 0 + } \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/mixins/rules.yaml b/observability/lgtm-distributed/charts/mimir-distributed/mixins/rules.yaml new file mode 100644 index 0000000..bd28aa9 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/mixins/rules.yaml @@ -0,0 +1,521 @@ +groups: +- name: mimir_api_1 + rules: + - expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_request_duration_seconds:99quantile + - expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_request_duration_seconds:50quantile + - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job) / sum(rate(cortex_request_duration_seconds_count[1m])) + by (cluster, job) + record: cluster_job:cortex_request_duration_seconds:avg + - expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job) + record: cluster_job:cortex_request_duration_seconds_bucket:sum_rate + - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job) + record: cluster_job:cortex_request_duration_seconds_sum:sum_rate + - expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job) + record: cluster_job:cortex_request_duration_seconds_count:sum_rate + - expr: sum(rate(cortex_request_duration_seconds[1m])) by (cluster, job) + record: cluster_job:cortex_request_duration_seconds:sum_rate +- name: mimir_api_2 + rules: + - expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m])) + by (le, cluster, job, route)) + record: cluster_job_route:cortex_request_duration_seconds:99quantile + - expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m])) + by (le, cluster, job, route)) + record: cluster_job_route:cortex_request_duration_seconds:50quantile + - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job, route) + / sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job, route) + record: cluster_job_route:cortex_request_duration_seconds:avg + - expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job, + route) + record: cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate + - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job, route) + record: cluster_job_route:cortex_request_duration_seconds_sum:sum_rate + - expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job, route) + record: cluster_job_route:cortex_request_duration_seconds_count:sum_rate + - expr: sum(rate(cortex_request_duration_seconds[1m])) by (cluster, job, route) + record: cluster_job_route:cortex_request_duration_seconds:sum_rate +- name: mimir_api_3 + rules: + - expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m])) + by (le, cluster, namespace, job, route)) + record: cluster_namespace_job_route:cortex_request_duration_seconds:99quantile + - expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m])) + by (le, cluster, namespace, job, route)) + record: cluster_namespace_job_route:cortex_request_duration_seconds:50quantile + - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, namespace, + job, route) / sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, + namespace, job, route) + record: cluster_namespace_job_route:cortex_request_duration_seconds:avg + - expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, namespace, + job, route) + record: cluster_namespace_job_route:cortex_request_duration_seconds_bucket:sum_rate + - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, namespace, + job, route) + record: cluster_namespace_job_route:cortex_request_duration_seconds_sum:sum_rate + - expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, namespace, + job, route) + record: cluster_namespace_job_route:cortex_request_duration_seconds_count:sum_rate + - expr: sum(rate(cortex_request_duration_seconds[1m])) by (cluster, namespace, job, + route) + record: cluster_namespace_job_route:cortex_request_duration_seconds:sum_rate +- name: mimir_querier_api + rules: + - expr: histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_querier_request_duration_seconds:99quantile + - expr: histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_querier_request_duration_seconds:50quantile + - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster, + job) / sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster, + job) + record: cluster_job:cortex_querier_request_duration_seconds:avg + - expr: sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster, + job) + record: cluster_job:cortex_querier_request_duration_seconds_bucket:sum_rate + - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster, + job) + record: cluster_job:cortex_querier_request_duration_seconds_sum:sum_rate + - expr: sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster, + job) + record: cluster_job:cortex_querier_request_duration_seconds_count:sum_rate + - expr: histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) + by (le, cluster, job, route)) + record: cluster_job_route:cortex_querier_request_duration_seconds:99quantile + - expr: histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) + by (le, cluster, job, route)) + record: cluster_job_route:cortex_querier_request_duration_seconds:50quantile + - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster, + job, route) / sum(rate(cortex_querier_request_duration_seconds_count[1m])) by + (cluster, job, route) + record: cluster_job_route:cortex_querier_request_duration_seconds:avg + - expr: sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster, + job, route) + record: cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate + - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster, + job, route) + record: cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate + - expr: sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster, + job, route) + record: cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate + - expr: histogram_quantile(0.99, sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) + by (le, cluster, namespace, job, route)) + record: cluster_namespace_job_route:cortex_querier_request_duration_seconds:99quantile + - expr: histogram_quantile(0.50, sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) + by (le, cluster, namespace, job, route)) + record: cluster_namespace_job_route:cortex_querier_request_duration_seconds:50quantile + - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster, + namespace, job, route) / sum(rate(cortex_querier_request_duration_seconds_count[1m])) + by (cluster, namespace, job, route) + record: cluster_namespace_job_route:cortex_querier_request_duration_seconds:avg + - expr: sum(rate(cortex_querier_request_duration_seconds_bucket[1m])) by (le, cluster, + namespace, job, route) + record: cluster_namespace_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate + - expr: sum(rate(cortex_querier_request_duration_seconds_sum[1m])) by (cluster, + namespace, job, route) + record: cluster_namespace_job_route:cortex_querier_request_duration_seconds_sum:sum_rate + - expr: sum(rate(cortex_querier_request_duration_seconds_count[1m])) by (cluster, + namespace, job, route) + record: cluster_namespace_job_route:cortex_querier_request_duration_seconds_count:sum_rate +- name: mimir_storage + rules: + - expr: histogram_quantile(0.99, sum(rate(cortex_kv_request_duration_seconds_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_kv_request_duration_seconds:99quantile + - expr: histogram_quantile(0.50, sum(rate(cortex_kv_request_duration_seconds_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_kv_request_duration_seconds:50quantile + - expr: sum(rate(cortex_kv_request_duration_seconds_sum[1m])) by (cluster, job) + / sum(rate(cortex_kv_request_duration_seconds_count[1m])) by (cluster, job) + record: cluster_job:cortex_kv_request_duration_seconds:avg + - expr: sum(rate(cortex_kv_request_duration_seconds_bucket[1m])) by (le, cluster, + job) + record: cluster_job:cortex_kv_request_duration_seconds_bucket:sum_rate + - expr: sum(rate(cortex_kv_request_duration_seconds_sum[1m])) by (cluster, job) + record: cluster_job:cortex_kv_request_duration_seconds_sum:sum_rate + - expr: sum(rate(cortex_kv_request_duration_seconds_count[1m])) by (cluster, job) + record: cluster_job:cortex_kv_request_duration_seconds_count:sum_rate +- name: mimir_queries + rules: + - expr: histogram_quantile(0.99, sum(rate(cortex_query_frontend_retries_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_query_frontend_retries:99quantile + - expr: histogram_quantile(0.50, sum(rate(cortex_query_frontend_retries_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_query_frontend_retries:50quantile + - expr: sum(rate(cortex_query_frontend_retries_sum[1m])) by (cluster, job) / sum(rate(cortex_query_frontend_retries_count[1m])) + by (cluster, job) + record: cluster_job:cortex_query_frontend_retries:avg + - expr: sum(rate(cortex_query_frontend_retries_bucket[1m])) by (le, cluster, job) + record: cluster_job:cortex_query_frontend_retries_bucket:sum_rate + - expr: sum(rate(cortex_query_frontend_retries_sum[1m])) by (cluster, job) + record: cluster_job:cortex_query_frontend_retries_sum:sum_rate + - expr: sum(rate(cortex_query_frontend_retries_count[1m])) by (cluster, job) + record: cluster_job:cortex_query_frontend_retries_count:sum_rate + - expr: histogram_quantile(0.99, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_query_frontend_queue_duration_seconds:99quantile + - expr: histogram_quantile(0.50, sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_query_frontend_queue_duration_seconds:50quantile + - expr: sum(rate(cortex_query_frontend_queue_duration_seconds_sum[1m])) by (cluster, + job) / sum(rate(cortex_query_frontend_queue_duration_seconds_count[1m])) by + (cluster, job) + record: cluster_job:cortex_query_frontend_queue_duration_seconds:avg + - expr: sum(rate(cortex_query_frontend_queue_duration_seconds_bucket[1m])) by (le, + cluster, job) + record: cluster_job:cortex_query_frontend_queue_duration_seconds_bucket:sum_rate + - expr: sum(rate(cortex_query_frontend_queue_duration_seconds_sum[1m])) by (cluster, + job) + record: cluster_job:cortex_query_frontend_queue_duration_seconds_sum:sum_rate + - expr: sum(rate(cortex_query_frontend_queue_duration_seconds_count[1m])) by (cluster, + job) + record: cluster_job:cortex_query_frontend_queue_duration_seconds_count:sum_rate +- name: mimir_ingester_queries + rules: + - expr: histogram_quantile(0.99, sum(rate(cortex_ingester_queried_series_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_ingester_queried_series:99quantile + - expr: histogram_quantile(0.50, sum(rate(cortex_ingester_queried_series_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_ingester_queried_series:50quantile + - expr: sum(rate(cortex_ingester_queried_series_sum[1m])) by (cluster, job) / sum(rate(cortex_ingester_queried_series_count[1m])) + by (cluster, job) + record: cluster_job:cortex_ingester_queried_series:avg + - expr: sum(rate(cortex_ingester_queried_series_bucket[1m])) by (le, cluster, job) + record: cluster_job:cortex_ingester_queried_series_bucket:sum_rate + - expr: sum(rate(cortex_ingester_queried_series_sum[1m])) by (cluster, job) + record: cluster_job:cortex_ingester_queried_series_sum:sum_rate + - expr: sum(rate(cortex_ingester_queried_series_count[1m])) by (cluster, job) + record: cluster_job:cortex_ingester_queried_series_count:sum_rate + - expr: histogram_quantile(0.99, sum(rate(cortex_ingester_queried_samples_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_ingester_queried_samples:99quantile + - expr: histogram_quantile(0.50, sum(rate(cortex_ingester_queried_samples_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_ingester_queried_samples:50quantile + - expr: sum(rate(cortex_ingester_queried_samples_sum[1m])) by (cluster, job) / sum(rate(cortex_ingester_queried_samples_count[1m])) + by (cluster, job) + record: cluster_job:cortex_ingester_queried_samples:avg + - expr: sum(rate(cortex_ingester_queried_samples_bucket[1m])) by (le, cluster, job) + record: cluster_job:cortex_ingester_queried_samples_bucket:sum_rate + - expr: sum(rate(cortex_ingester_queried_samples_sum[1m])) by (cluster, job) + record: cluster_job:cortex_ingester_queried_samples_sum:sum_rate + - expr: sum(rate(cortex_ingester_queried_samples_count[1m])) by (cluster, job) + record: cluster_job:cortex_ingester_queried_samples_count:sum_rate + - expr: histogram_quantile(0.99, sum(rate(cortex_ingester_queried_exemplars_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_ingester_queried_exemplars:99quantile + - expr: histogram_quantile(0.50, sum(rate(cortex_ingester_queried_exemplars_bucket[1m])) + by (le, cluster, job)) + record: cluster_job:cortex_ingester_queried_exemplars:50quantile + - expr: sum(rate(cortex_ingester_queried_exemplars_sum[1m])) by (cluster, job) / + sum(rate(cortex_ingester_queried_exemplars_count[1m])) by (cluster, job) + record: cluster_job:cortex_ingester_queried_exemplars:avg + - expr: sum(rate(cortex_ingester_queried_exemplars_bucket[1m])) by (le, cluster, + job) + record: cluster_job:cortex_ingester_queried_exemplars_bucket:sum_rate + - expr: sum(rate(cortex_ingester_queried_exemplars_sum[1m])) by (cluster, job) + record: cluster_job:cortex_ingester_queried_exemplars_sum:sum_rate + - expr: sum(rate(cortex_ingester_queried_exemplars_count[1m])) by (cluster, job) + record: cluster_job:cortex_ingester_queried_exemplars_count:sum_rate +- name: mimir_received_samples + rules: + - expr: | + sum by (cluster, namespace, job) (rate(cortex_distributor_received_samples_total[5m])) + record: cluster_namespace_job:cortex_distributor_received_samples:rate5m +- name: mimir_exemplars_in + rules: + - expr: | + sum by (cluster, namespace, job) (rate(cortex_distributor_exemplars_in_total[5m])) + record: cluster_namespace_job:cortex_distributor_exemplars_in:rate5m +- name: mimir_received_exemplars + rules: + - expr: | + sum by (cluster, namespace, job) (rate(cortex_distributor_received_exemplars_total[5m])) + record: cluster_namespace_job:cortex_distributor_received_exemplars:rate5m +- name: mimir_exemplars_ingested + rules: + - expr: | + sum by (cluster, namespace, job) (rate(cortex_ingester_ingested_exemplars_total[5m])) + record: cluster_namespace_job:cortex_ingester_ingested_exemplars:rate5m +- name: mimir_exemplars_appended + rules: + - expr: | + sum by (cluster, namespace, job) (rate(cortex_ingester_tsdb_exemplar_exemplars_appended_total[5m])) + record: cluster_namespace_job:cortex_ingester_tsdb_exemplar_exemplars_appended:rate5m +- name: mimir_scaling_rules + rules: + - expr: | + # Convenience rule to get the number of replicas for both a deployment and a statefulset. + # Multi-zone deployments are grouped together removing the "zone-X" suffix. + sum by (cluster, namespace, deployment) ( + label_replace( + kube_deployment_spec_replicas, + # The question mark in "(.*?)" is used to make it non-greedy, otherwise it + # always matches everything and the (optional) zone is not removed. + "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?" + ) + ) + or + sum by (cluster, namespace, deployment) ( + label_replace(kube_statefulset_replicas, "deployment", "$1", "statefulset", "(.*?)(?:-zone-[a-z])?") + ) + record: cluster_namespace_deployment:actual_replicas:count + - expr: | + ceil( + quantile_over_time(0.99, + sum by (cluster, namespace) ( + cluster_namespace_job:cortex_distributor_received_samples:rate5m + )[24h:] + ) + / 240000 + ) + labels: + deployment: distributor + reason: sample_rate + record: cluster_namespace_deployment_reason:required_replicas:count + - expr: | + ceil( + sum by (cluster, namespace) (cortex_limits_overrides{limit_name="ingestion_rate"}) + * 0.59999999999999998 / 240000 + ) + labels: + deployment: distributor + reason: sample_rate_limits + record: cluster_namespace_deployment_reason:required_replicas:count + - expr: | + ceil( + quantile_over_time(0.99, + sum by (cluster, namespace) ( + cluster_namespace_job:cortex_distributor_received_samples:rate5m + )[24h:] + ) + * 3 / 80000 + ) + labels: + deployment: ingester + reason: sample_rate + record: cluster_namespace_deployment_reason:required_replicas:count + - expr: | + ceil( + quantile_over_time(0.99, + sum by(cluster, namespace) ( + cortex_ingester_memory_series + )[24h:] + ) + / 1500000 + ) + labels: + deployment: ingester + reason: active_series + record: cluster_namespace_deployment_reason:required_replicas:count + - expr: | + ceil( + sum by (cluster, namespace) (cortex_limits_overrides{limit_name="max_global_series_per_user"}) + * 3 * 0.59999999999999998 / 1500000 + ) + labels: + deployment: ingester + reason: active_series_limits + record: cluster_namespace_deployment_reason:required_replicas:count + - expr: | + ceil( + sum by (cluster, namespace) (cortex_limits_overrides{limit_name="ingestion_rate"}) + * 0.59999999999999998 / 80000 + ) + labels: + deployment: ingester + reason: sample_rate_limits + record: cluster_namespace_deployment_reason:required_replicas:count + - expr: | + ceil( + (sum by (cluster, namespace) ( + cortex_ingester_tsdb_storage_blocks_bytes{job=~".+/ingester.*"} + ) / 4) + / + avg by (cluster, namespace) ( + memcached_limit_bytes{job=~".+/memcached"} + ) + ) + labels: + deployment: memcached + reason: active_series + record: cluster_namespace_deployment_reason:required_replicas:count + - expr: | + sum by (cluster, namespace, deployment) ( + label_replace( + label_replace( + sum by (cluster, namespace, pod)(rate(container_cpu_usage_seconds_total[1m])), + "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))" + ), + # The question mark in "(.*?)" is used to make it non-greedy, otherwise it + # always matches everything and the (optional) zone is not removed. + "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?" + ) + ) + record: cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate + - expr: | + # Convenience rule to get the CPU request for both a deployment and a statefulset. + # Multi-zone deployments are grouped together removing the "zone-X" suffix. + # This recording rule is made compatible with the breaking changes introduced in kube-state-metrics v2 + # that remove resource metrics, ref: + # - https://github.com/kubernetes/kube-state-metrics/blob/master/CHANGELOG.md#v200-alpha--2020-09-16 + # - https://github.com/kubernetes/kube-state-metrics/pull/1004 + # + # This is the old expression, compatible with kube-state-metrics < v2.0.0, + # where kube_pod_container_resource_requests_cpu_cores was removed: + ( + sum by (cluster, namespace, deployment) ( + label_replace( + label_replace( + kube_pod_container_resource_requests_cpu_cores, + "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))" + ), + # The question mark in "(.*?)" is used to make it non-greedy, otherwise it + # always matches everything and the (optional) zone is not removed. + "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?" + ) + ) + ) + or + # This expression is compatible with kube-state-metrics >= v1.4.0, + # where kube_pod_container_resource_requests was introduced. + ( + sum by (cluster, namespace, deployment) ( + label_replace( + label_replace( + kube_pod_container_resource_requests{resource="cpu"}, + "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))" + ), + # The question mark in "(.*?)" is used to make it non-greedy, otherwise it + # always matches everything and the (optional) zone is not removed. + "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?" + ) + ) + ) + record: cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum + - expr: | + # Jobs should be sized to their CPU usage. + # We do this by comparing 99th percentile usage over the last 24hrs to + # their current provisioned #replicas and resource requests. + ceil( + cluster_namespace_deployment:actual_replicas:count + * + quantile_over_time(0.99, cluster_namespace_deployment:container_cpu_usage_seconds_total:sum_rate[24h]) + / + cluster_namespace_deployment:kube_pod_container_resource_requests_cpu_cores:sum + ) + labels: + reason: cpu_usage + record: cluster_namespace_deployment_reason:required_replicas:count + - expr: | + # Convenience rule to get the Memory utilization for both a deployment and a statefulset. + # Multi-zone deployments are grouped together removing the "zone-X" suffix. + sum by (cluster, namespace, deployment) ( + label_replace( + label_replace( + container_memory_usage_bytes{image!=""}, + "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))" + ), + # The question mark in "(.*?)" is used to make it non-greedy, otherwise it + # always matches everything and the (optional) zone is not removed. + "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?" + ) + ) + record: cluster_namespace_deployment:container_memory_usage_bytes:sum + - expr: | + # Convenience rule to get the Memory request for both a deployment and a statefulset. + # Multi-zone deployments are grouped together removing the "zone-X" suffix. + # This recording rule is made compatible with the breaking changes introduced in kube-state-metrics v2 + # that remove resource metrics, ref: + # - https://github.com/kubernetes/kube-state-metrics/blob/master/CHANGELOG.md#v200-alpha--2020-09-16 + # - https://github.com/kubernetes/kube-state-metrics/pull/1004 + # + # This is the old expression, compatible with kube-state-metrics < v2.0.0, + # where kube_pod_container_resource_requests_memory_bytes was removed: + ( + sum by (cluster, namespace, deployment) ( + label_replace( + label_replace( + kube_pod_container_resource_requests_memory_bytes, + "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))" + ), + # The question mark in "(.*?)" is used to make it non-greedy, otherwise it + # always matches everything and the (optional) zone is not removed. + "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?" + ) + ) + ) + or + # This expression is compatible with kube-state-metrics >= v1.4.0, + # where kube_pod_container_resource_requests was introduced. + ( + sum by (cluster, namespace, deployment) ( + label_replace( + label_replace( + kube_pod_container_resource_requests{resource="memory"}, + "deployment", "$1", "pod", "(.*)-(?:([0-9]+)|([a-z0-9]+)-([a-z0-9]+))" + ), + # The question mark in "(.*?)" is used to make it non-greedy, otherwise it + # always matches everything and the (optional) zone is not removed. + "deployment", "$1", "deployment", "(.*?)(?:-zone-[a-z])?" + ) + ) + ) + record: cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum + - expr: | + # Jobs should be sized to their Memory usage. + # We do this by comparing 99th percentile usage over the last 24hrs to + # their current provisioned #replicas and resource requests. + ceil( + cluster_namespace_deployment:actual_replicas:count + * + quantile_over_time(0.99, cluster_namespace_deployment:container_memory_usage_bytes:sum[24h]) + / + cluster_namespace_deployment:kube_pod_container_resource_requests_memory_bytes:sum + ) + labels: + reason: memory_usage + record: cluster_namespace_deployment_reason:required_replicas:count +- name: mimir_alertmanager_rules + rules: + - expr: | + sum by (cluster, job, pod) (cortex_alertmanager_alerts) + record: cluster_job_pod:cortex_alertmanager_alerts:sum + - expr: | + sum by (cluster, job, pod) (cortex_alertmanager_silences) + record: cluster_job_pod:cortex_alertmanager_silences:sum + - expr: | + sum by (cluster, job) (rate(cortex_alertmanager_alerts_received_total[5m])) + record: cluster_job:cortex_alertmanager_alerts_received_total:rate5m + - expr: | + sum by (cluster, job) (rate(cortex_alertmanager_alerts_invalid_total[5m])) + record: cluster_job:cortex_alertmanager_alerts_invalid_total:rate5m + - expr: | + sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_total[5m])) + record: cluster_job_integration:cortex_alertmanager_notifications_total:rate5m + - expr: | + sum by (cluster, job, integration) (rate(cortex_alertmanager_notifications_failed_total[5m])) + record: cluster_job_integration:cortex_alertmanager_notifications_failed_total:rate5m + - expr: | + sum by (cluster, job) (rate(cortex_alertmanager_state_replication_total[5m])) + record: cluster_job:cortex_alertmanager_state_replication_total:rate5m + - expr: | + sum by (cluster, job) (rate(cortex_alertmanager_state_replication_failed_total[5m])) + record: cluster_job:cortex_alertmanager_state_replication_failed_total:rate5m + - expr: | + sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_total[5m])) + record: cluster_job:cortex_alertmanager_partial_state_merges_total:rate5m + - expr: | + sum by (cluster, job) (rate(cortex_alertmanager_partial_state_merges_failed_total[5m])) + record: cluster_job:cortex_alertmanager_partial_state_merges_failed_total:rate5m +- name: mimir_ingester_rules + rules: + - expr: | + sum by(cluster, namespace, pod) (rate(cortex_ingester_ingested_samples_total[1m])) + record: cluster_namespace_pod:cortex_ingester_ingested_samples_total:rate1m diff --git a/observability/lgtm-distributed/charts/mimir-distributed/small.yaml b/observability/lgtm-distributed/charts/mimir-distributed/small.yaml new file mode 100644 index 0000000..771b9db --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/small.yaml @@ -0,0 +1,207 @@ +# These values configure the Grafana Mimir or Grafana Enterprise Metrics cluster +# for a more production-ready setup. The setup targets 70% CPU and memory utilization +# so that the cluster has room to grow. The resource requests reflect 70% utilization +# and the limits reflect 100% utilization. The values do not set CPU limits, +# because CPU limits have caused severe issues elsewhere, so we don't apply any in our helm chart: +# see https://engineering.indeedblog.com/blog/2019/12/unthrottled-fixing-cpu-limits-in-the-cloud/ +# If you require CPU limits for billing purposes see capped-small.yaml +# +# These values are suitable for ingestion of ~1M series and scrape interval of 15s. +# This implies ingestion rate of around 66000 samples per second. +# +# Query requirements can vary dramatically depending on query rate and query +# ranges. The values here satisfy a "usual" query load of around 5 queries per second +# as seen from our production clusters at this scale. +# +# The values in this file also add podAntiAffinity rules for ingesters and store-gateways. +# The rules ensure that the replicas of the same component are not scheduled on the same +# Kubernetes Node. Zone-aware replication is enabled by default on new installation. +# Refer to [Migrate from single zone to zone-aware replication with Helm](https://grafana.com/docs/mimir/latest/migration-guide/migrating-from-single-zone-with-helm) and +# [Zone-Aware Replication](https://grafana.com/docs/mimir/latest/configure/configure-zone-aware-replication/) +# for more information. +# +# MinIO is no longer enabled, and you are encouraged to use your cloud providers +# object storage service such as S3 or GCS. + +alertmanager: + persistentVolume: + enabled: true + replicas: 2 + resources: + limits: + memory: 1.4Gi + requests: + cpu: 1 + memory: 1Gi + statefulSet: + enabled: true + +compactor: + persistentVolume: + size: 20Gi + resources: + limits: + memory: 2.1Gi + requests: + cpu: 1 + memory: 1.5Gi + +distributor: + replicas: 2 + resources: + limits: + memory: 5.7Gi + requests: + cpu: 2 + memory: 4Gi + +ingester: + persistentVolume: + size: 50Gi + replicas: 3 + resources: + limits: + memory: 12Gi + requests: + cpu: 3.5 + memory: 8Gi + topologySpreadConstraints: {} + affinity: + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchExpressions: + - key: target # support for enterprise.legacyLabels + operator: In + values: + - ingester + topologyKey: 'kubernetes.io/hostname' + + - labelSelector: + matchExpressions: + - key: app.kubernetes.io/component + operator: In + values: + - ingester + topologyKey: 'kubernetes.io/hostname' + + zoneAwareReplication: + topologyKey: 'kubernetes.io/hostname' + +admin-cache: + enabled: true + replicas: 2 + +chunks-cache: + enabled: true + replicas: 2 + +index-cache: + enabled: true + replicas: 3 + +metadata-cache: + enabled: true + +results-cache: + enabled: true + replicas: 2 + +minio: + enabled: false + +overrides_exporter: + replicas: 1 + resources: + limits: + memory: 128Mi + requests: + cpu: 100m + memory: 128Mi + +querier: + replicas: 1 + resources: + limits: + memory: 5.6Gi + requests: + cpu: 2 + memory: 4Gi + +query_frontend: + replicas: 1 + resources: + limits: + memory: 2.8Gi + requests: + cpu: 2 + memory: 2Gi + +ruler: + replicas: 1 + resources: + limits: + memory: 2.8Gi + requests: + cpu: 1 + memory: 2Gi + +store_gateway: + persistentVolume: + size: 10Gi + replicas: 3 + resources: + limits: + memory: 2.1Gi + requests: + cpu: 1 + memory: 1.5Gi + topologySpreadConstraints: {} + affinity: + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchExpressions: + - key: target # support for enterprise.legacyLabels + operator: In + values: + - store-gateway + topologyKey: 'kubernetes.io/hostname' + + - labelSelector: + matchExpressions: + - key: app.kubernetes.io/component + operator: In + values: + - store-gateway + topologyKey: 'kubernetes.io/hostname' + zoneAwareReplication: + topologyKey: 'kubernetes.io/hostname' + +nginx: + replicas: 1 + resources: + limits: + memory: 731Mi + requests: + cpu: 1 + memory: 512Mi + +# Grafana Enterprise Metrics feature related +admin_api: + replicas: 1 + resources: + limits: + memory: 128Mi + requests: + cpu: 100m + memory: 64Mi + +gateway: + replicas: 1 + resources: + limits: + memory: 731Mi + requests: + cpu: 1 + memory: 512Mi diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/NOTES.txt b/observability/lgtm-distributed/charts/mimir-distributed/templates/NOTES.txt new file mode 100644 index 0000000..b5e585f --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/NOTES.txt @@ -0,0 +1,36 @@ +{{ if .Values.enterprise.enabled }} +Welcome to Grafana Enterprise Metrics! +{{- else }} +Welcome to Grafana Mimir! +{{- end }} +{{- $gateway := .Values.nginx }} +{{- if eq (include "mimir.gateway.isEnabled" .) "true" }} +{{- $gateway = .Values.gateway }} +{{- end }} +Remote write endpoints for Prometheus or Grafana Agent: +{{ with $gateway.ingress -}} +{{- if .enabled -}} +From outside the cluster via ingress: +{{ range .hosts }} http{{ if .tls }}s{{ end }}://{{ .host }}/api/v1/push +{{ end }} +{{- else -}} +Ingress is not enabled, see the {{ if eq (include "mimir.gateway.isEnabled" $) "true" }}gateway{{ else }}nginx{{ end }}.ingress values. +{{- end -}} +{{- end }} +From inside the cluster: + {{ include "mimir.remoteWriteUrl.inCluster" $ }} + +Read address, Grafana data source (Prometheus) URL: +{{ with $gateway.ingress -}} +{{- if .enabled -}} +From outside the cluster via ingress: +{{ range .hosts }} http{{ if .tls }}s{{ end }}://{{ .host }}{{ template "mimir.prometheusHttpPrefix" $ }} +{{ end }} +{{- else -}} +Ingress is not enabled, see the {{ if eq (include "mimir.gateway.isEnabled" $) "true" }}gateway{{ else }}nginx{{ end }}.ingress values. +{{- end -}} +{{- end }} +From inside the cluster: + {{ include "mimir.gatewayUrl" $ }}{{ template "mimir.prometheusHttpPrefix" $ }} + +**IMPORTANT**: Always consult CHANGELOG.md file at https://github.com/grafana/mimir/blob/main/operations/helm/charts/mimir-distributed/CHANGELOG.md and the deprecation list there to learn about breaking changes that require action during upgrade. diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/_config-render.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/_config-render.tpl new file mode 100644 index 0000000..447421b --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/_config-render.tpl @@ -0,0 +1 @@ +{{- tpl .Values.mimir.config . -}} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/_helpers.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/_helpers.tpl new file mode 100644 index 0000000..ba0000e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/_helpers.tpl @@ -0,0 +1,699 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "mimir.name" -}} +{{- default ( include "mimir.infixName" . ) .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "mimir.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default ( include "mimir.infixName" . ) .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Calculate the infix for naming +*/}} +{{- define "mimir.infixName" -}} +{{- if and .Values.enterprise.enabled .Values.enterprise.legacyLabels -}}enterprise-metrics{{- else -}}mimir{{- end -}} +{{- end -}} + +{{/* +Calculate the gateway url +*/}} +{{- define "mimir.gatewayUrl" -}} +{{- if eq (include "mimir.gateway.isEnabled" . ) "true" -}} +http://{{ include "mimir.gateway.service.name" . }}.{{ .Release.Namespace }}.svc:{{ .Values.gateway.service.port | default (include "mimir.serverHttpListenPort" . ) }} +{{- else -}} +http://{{ template "mimir.fullname" . }}-nginx.{{ .Release.Namespace }}.svc:{{ .Values.nginx.service.port }} +{{- end -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "mimir.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Calculate image name based on whether enterprise features are requested +*/}} +{{- define "mimir.imageReference" -}} +{{- if .Values.enterprise.enabled -}}{{ .Values.enterprise.image.repository }}:{{ .Values.enterprise.image.tag }}{{- else -}}{{ .Values.image.repository }}:{{ .Values.image.tag }}{{- end -}} +{{- end -}} + +{{/* +For compatibility and to support upgrade from enterprise-metrics chart calculate minio bucket name +*/}} +{{- define "mimir.minioBucketPrefix" -}} +{{- if .Values.enterprise.legacyLabels -}}enterprise-metrics{{- else -}}mimir{{- end -}} +{{- end -}} + +{{/* +Create the name of the general service account +*/}} +{{- define "mimir.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "mimir.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Create the name of the ruler service account +*/}} +{{- define "mimir.ruler.serviceAccountName" -}} +{{- if and .Values.ruler.serviceAccount.create (eq .Values.ruler.serviceAccount.name "") -}} +{{- $sa := default (include "mimir.fullname" .) .Values.serviceAccount.name }} +{{- printf "%s-%s" $sa "ruler" }} +{{- else if and .Values.ruler.serviceAccount.create (not (eq .Values.ruler.serviceAccount.name "")) -}} +{{- .Values.ruler.serviceAccount.name -}} +{{- else -}} +{{- include "mimir.serviceAccountName" . -}} +{{- end -}} +{{- end -}} + +{{/* +Create the app name for clients. Defaults to the same logic as "mimir.fullname", and default client expects "prometheus". +*/}} +{{- define "client.name" -}} +{{- if .Values.client.name -}} +{{- .Values.client.name -}} +{{- else if .Values.client.fullnameOverride -}} +{{- .Values.client.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default "prometheus" .Values.client.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Calculate the config from structured and unstructured text input +*/}} +{{- define "mimir.calculatedConfig" -}} +{{ tpl (mergeOverwrite (include "mimir.unstructuredConfig" . | fromYaml) .Values.mimir.structuredConfig | toYaml) . }} +{{- end -}} + +{{/* +Calculate the config from the unstructured text input +*/}} +{{- define "mimir.unstructuredConfig" -}} +{{ include (print $.Template.BasePath "/_config-render.tpl") . }} +{{- end -}} + +{{/* +The volume to mount for mimir configuration +*/}} +{{- define "mimir.configVolume" -}} +{{- if eq .Values.configStorageType "Secret" -}} +secret: + secretName: {{ tpl .Values.externalConfigSecretName . }} +{{- else if eq .Values.configStorageType "ConfigMap" -}} +configMap: + name: {{ tpl .Values.externalConfigSecretName . }} + items: + - key: "mimir.yaml" + path: "mimir.yaml" +{{- end -}} +{{- end -}} + +{{/* +Internal servers http listen port - derived from Mimir default +*/}} +{{- define "mimir.serverHttpListenPort" -}} +{{ (((.Values.mimir).structuredConfig).server).http_listen_port | default "8080" }} +{{- end -}} + +{{/* +Internal servers grpc listen port - derived from Mimir default +*/}} +{{- define "mimir.serverGrpcListenPort" -}} +{{ (((.Values.mimir).structuredConfig).server).grpc_listen_port | default "9095" }} +{{- end -}} + +{{/* +Alertmanager cluster bind address +*/}} +{{- define "mimir.alertmanagerClusterBindAddress" -}} +{{- if (include "mimir.calculatedConfig" . | fromYaml).alertmanager -}} +{{ (include "mimir.calculatedConfig" . | fromYaml).alertmanager.cluster_bind_address | default "" }} +{{- end -}} +{{- end -}} + +{{- define "mimir.chunksCacheAddress" -}} +dns+{{ template "mimir.fullname" . }}-chunks-cache.{{ .Release.Namespace }}.svc:{{ (index .Values "chunks-cache").port }} +{{- end -}} + +{{- define "mimir.indexCacheAddress" -}} +dns+{{ template "mimir.fullname" . }}-index-cache.{{ .Release.Namespace }}.svc:{{ (index .Values "index-cache").port }} +{{- end -}} + +{{- define "mimir.metadataCacheAddress" -}} +dns+{{ template "mimir.fullname" . }}-metadata-cache.{{ .Release.Namespace }}.svc:{{ (index .Values "metadata-cache").port }} +{{- end -}} + +{{- define "mimir.resultsCacheAddress" -}} +dns+{{ template "mimir.fullname" . }}-results-cache.{{ .Release.Namespace }}.svc:{{ (index .Values "results-cache").port }} +{{- end -}} + +{{- define "mimir.adminCacheAddress" -}} +dns+{{ template "mimir.fullname" . }}-admin-cache.{{ .Release.Namespace }}.svc:{{ (index .Values "admin-cache").port }} +{{- end -}} + +{{/* +Memberlist bind port +*/}} +{{- define "mimir.memberlistBindPort" -}} +{{ (((.Values.mimir).structuredConfig).memberlist).bind_port | default "7946" }} +{{- end -}} + +{{/* +Resource name template +Params: + ctx = . context + component = component name (optional) + rolloutZoneName = rollout zone name (optional) +*/}} +{{- define "mimir.resourceName" -}} +{{- $resourceName := include "mimir.fullname" .ctx -}} +{{- if .component -}}{{- $resourceName = printf "%s-%s" $resourceName .component -}}{{- end -}} +{{- if and (not .component) .rolloutZoneName -}}{{- printf "Component name cannot be empty if rolloutZoneName (%s) is set" .rolloutZoneName | fail -}}{{- end -}} +{{- if .rolloutZoneName -}}{{- $resourceName = printf "%s-%s" $resourceName .rolloutZoneName -}}{{- end -}} +{{- if gt (len $resourceName) 253 -}}{{- printf "Resource name (%s) exceeds kubernetes limit of 253 character. To fix: shorten release name if this will be a fresh install or shorten zone names (e.g. \"a\" instead of \"zone-a\") if using zone-awareness." $resourceName | fail -}}{{- end -}} +{{- $resourceName -}} +{{- end -}} + +{{/* +Resource labels +Params: + ctx = . context + component = component name (optional) + rolloutZoneName = rollout zone name (optional) +*/}} +{{- define "mimir.labels" -}} +{{- if .ctx.Values.enterprise.legacyLabels }} +{{- if .component -}} +app: {{ include "mimir.name" .ctx }}-{{ .component }} +{{- else -}} +app: {{ include "mimir.name" .ctx }} +{{- end }} +chart: {{ template "mimir.chart" .ctx }} +heritage: {{ .ctx.Release.Service }} +release: {{ .ctx.Release.Name }} + +{{- else -}} + +helm.sh/chart: {{ include "mimir.chart" .ctx }} +app.kubernetes.io/name: {{ include "mimir.name" .ctx }} +app.kubernetes.io/instance: {{ .ctx.Release.Name }} +{{- if .component }} +app.kubernetes.io/component: {{ .component }} +{{- end }} +{{- if .memberlist }} +app.kubernetes.io/part-of: memberlist +{{- end }} +{{- if .ctx.Chart.AppVersion }} +app.kubernetes.io/version: {{ .ctx.Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .ctx.Release.Service }} +{{- end }} +{{- if .rolloutZoneName }} +{{- if not .component }} +{{- printf "Component name cannot be empty if rolloutZoneName (%s) is set" .rolloutZoneName | fail }} +{{- end }} +name: "{{ .component }}-{{ .rolloutZoneName }}" {{- /* Currently required for rollout-operator. https://github.com/grafana/rollout-operator/issues/15 */}} +rollout-group: {{ .component }} +zone: {{ .rolloutZoneName }} +{{- end }} +{{- end -}} + +{{/* +POD labels +Params: + ctx = . context + component = name of the component + memberlist = true if part of memberlist gossip ring + rolloutZoneName = rollout zone name (optional) +*/}} +{{- define "mimir.podLabels" -}} +{{ with .ctx.Values.global.podLabels -}} +{{ toYaml . }} +{{ end }} +{{- if .ctx.Values.enterprise.legacyLabels }} +{{- if .component -}} +app: {{ include "mimir.name" .ctx }}-{{ .component }} +{{- if not .rolloutZoneName }} +name: {{ .component }} +{{- end }} +{{- end }} +{{- if .memberlist }} +gossip_ring_member: "true" +{{- end -}} +{{- if .component }} +target: {{ .component }} +release: {{ .ctx.Release.Name }} +{{- end }} +{{- else -}} +helm.sh/chart: {{ include "mimir.chart" .ctx }} +app.kubernetes.io/name: {{ include "mimir.name" .ctx }} +app.kubernetes.io/instance: {{ .ctx.Release.Name }} +app.kubernetes.io/version: {{ .ctx.Chart.AppVersion | quote }} +app.kubernetes.io/managed-by: {{ .ctx.Release.Service }} +{{- if .component }} +app.kubernetes.io/component: {{ .component }} +{{- end }} +{{- if .memberlist }} +app.kubernetes.io/part-of: memberlist +{{- end }} +{{- end }} +{{- $componentSection := include "mimir.componentSectionFromName" . | fromYaml }} +{{- with ($componentSection).podLabels }} +{{ toYaml . }} +{{- end }} +{{- if .rolloutZoneName }} +{{- if not .component }} +{{- printf "Component name cannot be empty if rolloutZoneName (%s) is set" .rolloutZoneName | fail }} +{{- end }} +name: "{{ .component }}-{{ .rolloutZoneName }}" {{- /* Currently required for rollout-operator. https://github.com/grafana/rollout-operator/issues/15 */}} +rollout-group: {{ .component }} +zone: {{ .rolloutZoneName }} +{{- end }} +{{- end -}} + +{{/* +POD annotations +Params: + ctx = . context + component = name of the component +*/}} +{{- define "mimir.podAnnotations" -}} +{{- if .ctx.Values.useExternalConfig }} +checksum/config: {{ .ctx.Values.externalConfigVersion | quote }} +{{- else -}} +checksum/config: {{ include (print .ctx.Template.BasePath "/mimir-config.yaml") .ctx | sha256sum }} +{{- end }} +{{- with .ctx.Values.global.podAnnotations }} +{{ toYaml . }} +{{- end }} +{{- if .component }} +{{- if .ctx.Values.vaultAgent.enabled }} +{{- include "mimir.vaultAgent.annotations" (dict "ctx" .ctx "component" .component) }} +{{- end }} +{{- $componentSection := include "mimir.componentSectionFromName" . | fromYaml }} +{{- with ($componentSection).podAnnotations }} +{{ toYaml . }} +{{- end }} +{{- end }} +{{- end -}} + +{{/* +Service selector labels +Params: + ctx = . context + component = name of the component + rolloutZoneName = rollout zone name (optional) +*/}} +{{- define "mimir.selectorLabels" -}} +{{- if .ctx.Values.enterprise.legacyLabels }} +{{- if .component -}} +app: {{ include "mimir.name" .ctx }}-{{ .component }} +{{- end }} +release: {{ .ctx.Release.Name }} +{{- else -}} +app.kubernetes.io/name: {{ include "mimir.name" .ctx }} +app.kubernetes.io/instance: {{ .ctx.Release.Name }} +{{- if .component }} +app.kubernetes.io/component: {{ .component }} +{{- end }} +{{- end -}} +{{- if .rolloutZoneName }} +{{- if not .component }} +{{- printf "Component name cannot be empty if rolloutZoneName (%s) is set" .rolloutZoneName | fail }} +{{- end }} +rollout-group: {{ .component }} +zone: {{ .rolloutZoneName }} +{{- end }} +{{- end -}} + + +{{/* +Alertmanager http prefix +*/}} +{{- define "mimir.alertmanagerHttpPrefix" -}} +{{- if (include "mimir.calculatedConfig" . | fromYaml).api }} +{{- (include "mimir.calculatedConfig" . | fromYaml).api.alertmanager_http_prefix | default "/alertmanager" -}} +{{- else -}} +{{- print "/alertmanager" -}} +{{- end -}} +{{- end -}} + + +{{/* +Prometheus http prefix +*/}} +{{- define "mimir.prometheusHttpPrefix" -}} +{{- if (include "mimir.calculatedConfig" . | fromYaml).api }} +{{- (include "mimir.calculatedConfig" . | fromYaml).api.prometheus_http_prefix | default "/prometheus" -}} +{{- else -}} +{{- print "/prometheus" -}} +{{- end -}} +{{- end -}} + +{{/* +KEDA Autoscaling Prometheus address +*/}} +{{- define "mimir.kedaPrometheusAddress" -}} +{{- if not .ctx.Values.kedaAutoscaling.prometheusAddress -}} +{{ include "mimir.metaMonitoring.metrics.remoteReadUrl" . }} +{{- else -}} +{{ .ctx.Values.kedaAutoscaling.prometheusAddress }} +{{- end -}} +{{- end -}} + + +{{/* +Cluster name that shows up in dashboard metrics +*/}} +{{- define "mimir.clusterName" -}} +{{ (include "mimir.calculatedConfig" . | fromYaml).cluster_name | default .Release.Name }} +{{- end -}} + +{{/* Allow KubeVersion to be overridden. */}} +{{- define "mimir.kubeVersion" -}} + {{- default .Capabilities.KubeVersion.Version .Values.kubeVersionOverride -}} +{{- end -}} + +{{/* Get API Versions */}} +{{- define "mimir.podDisruptionBudget.apiVersion" -}} + {{- if semverCompare ">= 1.21-0" (include "mimir.kubeVersion" .) -}} + {{- print "policy/v1" -}} + {{- else -}} + {{- print "policy/v1beta1" -}} + {{- end -}} +{{- end -}} + +{{/* +mimir.componentSectionFromName returns the sections from the user .Values in YAML +that corresponds to the requested component. mimir.componentSectionFromName takes two arguments + .ctx = the root context of the chart + .component = the name of the component. mimir.componentSectionFromName uses an internal mapping to know + which component lives where in the values.yaml +Examples: + $componentSection := include "mimir.componentSectionFromName" (dict "ctx" . "component" "store-gateway") | fromYaml + $componentSection.podLabels ... +*/}} +{{- define "mimir.componentSectionFromName" -}} +{{- $componentsMap := dict + "admin-api" "admin_api" + "admin-cache" "admin-cache" + "alertmanager" "alertmanager" + "chunks-cache" "chunks-cache" + "compactor" "compactor" + "continuous-test" "continuous_test" + "distributor" "distributor" + "gateway" "gateway" + "gr-aggr-cache" "gr-aggr-cache" + "gr-metricname-cache" "gr-metricname-cache" + "graphite-querier" "graphite.querier" + "graphite-write-proxy" "graphite.write_proxy" + "index-cache" "index-cache" + "ingester" "ingester" + "memcached" "memcached" + "metadata-cache" "metadata-cache" + "nginx" "nginx" + "overrides-exporter" "overrides_exporter" + "querier" "querier" + "query-frontend" "query_frontend" + "query-scheduler" "query_scheduler" + "results-cache" "results-cache" + "ruler" "ruler" + "smoke-test" "smoke_test" + "store-gateway" "store_gateway" + "tokengen" "tokengenJob" +-}} +{{- $componentSection := index $componentsMap .component -}} +{{- if not $componentSection -}}{{- printf "No component section mapping for %s not found in values; submit a bug report if you are a user, edit mimir.componentSectionFromName if you are a contributor" .component | fail -}}{{- end -}} +{{- $section := .ctx.Values -}} +{{- range regexSplit "\\." $componentSection -1 -}} + {{- $section = index $section . -}} + {{- if not $section -}}{{- printf "Component section %s not found in values; values: %s" . ($.ctx.Values | toJson | abbrev 100) | fail -}}{{- end -}} +{{- end -}} +{{- $section | toYaml -}} +{{- end -}} + +{{/* +Return the Vault Agent pod annotations if enabled and required by the component +mimir.vaultAgent.annotations takes 2 arguments + .ctx = the root context of the chart + .component = the name of the component +*/}} +{{- define "mimir.vaultAgent.annotations" -}} +{{- $vaultEnabledComponents := dict + "admin-api" true + "alertmanager" true + "compactor" true + "distributor" true + "gateway" true + "ingester" true + "overrides-exporter" true + "querier" true + "query-frontend" true + "query-scheduler" true + "ruler" true + "store-gateway" true +-}} +{{- if hasKey $vaultEnabledComponents .component }} +vault.hashicorp.com/agent-inject: 'true' +vault.hashicorp.com/role: '{{ .ctx.Values.vaultAgent.roleName }}' +vault.hashicorp.com/agent-inject-secret-client.crt: '{{ .ctx.Values.vaultAgent.clientCertPath }}' +vault.hashicorp.com/agent-inject-secret-client.key: '{{ .ctx.Values.vaultAgent.clientKeyPath }}' +vault.hashicorp.com/agent-inject-secret-server.crt: '{{ .ctx.Values.vaultAgent.serverCertPath }}' +vault.hashicorp.com/agent-inject-secret-server.key: '{{ .ctx.Values.vaultAgent.serverKeyPath }}' +vault.hashicorp.com/agent-inject-secret-root.crt: '{{ .ctx.Values.vaultAgent.caCertPath }}' +{{- end}} +{{- end -}} + +{{/* +Get the no_auth_tenant from the configuration +*/}} +{{- define "mimir.noAuthTenant" -}} +{{- (include "mimir.calculatedConfig" . | fromYaml).no_auth_tenant | default "anonymous" -}} +{{- end -}} + +{{/* +Return if we should create a PodSecurityPolicy. Takes into account user values and supported kubernetes versions. +*/}} +{{- define "mimir.rbac.usePodSecurityPolicy" -}} +{{- and + ( + or (semverCompare "< 1.24-0" (include "mimir.kubeVersion" .)) + (and (semverCompare "< 1.25-0" (include "mimir.kubeVersion" .)) .Values.rbac.forcePSPOnKubernetes124) + ) + (and .Values.rbac.create (eq .Values.rbac.type "psp")) +-}} +{{- end -}} + +{{/* +Return if we should create a SecurityContextConstraints. Takes into account user values and supported openshift versions. +*/}} +{{- define "mimir.rbac.useSecurityContextConstraints" -}} +{{- and .Values.rbac.create (eq .Values.rbac.type "scc") -}} +{{- end -}} + +{{- define "mimir.remoteWriteUrl.inCluster" -}} +{{ include "mimir.gatewayUrl" . }}/api/v1/push +{{- end -}} + +{{- define "mimir.remoteReadUrl.inCluster" -}} +{{ include "mimir.gatewayUrl" . }}{{ include "mimir.prometheusHttpPrefix" . }} +{{- end -}} + +{{/* +Creates dict for zone-aware replication configuration +Params: + ctx = . context + component = component name +Return value: + { + zoneName: { + affinity: , + nodeSelector: , + replicas: , + storageClass: + }, + ... + } +During migration there is a special case where an extra "zone" is generated with zonaName == "" empty string. +The empty string evaluates to false in boolean expressions so it is treated as the default (non zone-aware) zone, +which allows us to keep generating everything for the default zone. +*/}} +{{- define "mimir.zoneAwareReplicationMap" -}} +{{- $zonesMap := (dict) -}} +{{- $componentSection := include "mimir.componentSectionFromName" . | fromYaml -}} +{{- $defaultZone := (dict "affinity" $componentSection.affinity "nodeSelector" $componentSection.nodeSelector "replicas" $componentSection.replicas "storageClass" $componentSection.storageClass) -}} + +{{- if $componentSection.zoneAwareReplication.enabled -}} +{{- $numberOfZones := len $componentSection.zoneAwareReplication.zones -}} +{{- if lt $numberOfZones 3 -}} +{{- fail "When zone-awareness is enabled, you must have at least 3 zones defined." -}} +{{- end -}} + +{{- $requestedReplicas := $componentSection.replicas -}} +{{- if and (has .component (list "ingester" "alertmanager")) $componentSection.zoneAwareReplication.migration.enabled (not $componentSection.zoneAwareReplication.migration.writePath) -}} +{{- $requestedReplicas = $componentSection.zoneAwareReplication.migration.replicas }} +{{- end -}} +{{- $replicaPerZone := div (add $requestedReplicas $numberOfZones -1) $numberOfZones -}} + +{{- range $idx, $rolloutZone := $componentSection.zoneAwareReplication.zones -}} +{{- $_ := set $zonesMap $rolloutZone.name (dict + "affinity" (($rolloutZone.extraAffinity | default (dict)) | mergeOverwrite (include "mimir.zoneAntiAffinity" (dict "component" $.component "rolloutZoneName" $rolloutZone.name "topologyKey" $componentSection.zoneAwareReplication.topologyKey ) | fromYaml ) ) + "nodeSelector" ($rolloutZone.nodeSelector | default (dict) ) + "replicas" $replicaPerZone + "storageClass" $rolloutZone.storageClass + ) -}} +{{- end -}} +{{- if $componentSection.zoneAwareReplication.migration.enabled -}} +{{- if $componentSection.zoneAwareReplication.migration.scaleDownDefaultZone -}} +{{- $_ := set $defaultZone "replicas" 0 -}} +{{- end -}} +{{- $_ := set $zonesMap "" $defaultZone -}} +{{- end -}} + +{{- else -}} +{{- $_ := set $zonesMap "" $defaultZone -}} +{{- end -}} +{{- $zonesMap | toYaml }} + +{{- end -}} + +{{/* +Calculate anti-affinity for a zone +Params: + component = component name + rolloutZoneName = name of the rollout zone + topologyKey = topology key +*/}} +{{- define "mimir.zoneAntiAffinity" -}} +{{- if .topologyKey -}} +podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchExpressions: + - key: rollout-group + operator: In + values: + - {{ .component }} + - key: zone + operator: NotIn + values: + - {{ .rolloutZoneName }} + topologyKey: {{ .topologyKey | quote }} +{{- else -}} +{} +{{- end -}} +{{- end -}} + +{{/* +Calculate annotations with zone-awareness +Params: + ctx = . context + component = component name + rolloutZoneName = rollout zone name (optional) +*/}} +{{- define "mimir.componentAnnotations" -}} +{{- $componentSection := include "mimir.componentSectionFromName" . | fromYaml -}} +{{- if and (or $componentSection.zoneAwareReplication.enabled $componentSection.zoneAwareReplication.migration.enabled) .rolloutZoneName }} +{{- $map := dict "rollout-max-unavailable" ($componentSection.zoneAwareReplication.maxUnavailable | toString) -}} +{{- toYaml (deepCopy $map | mergeOverwrite $componentSection.annotations) }} +{{- else -}} +{{ toYaml $componentSection.annotations }} +{{- end -}} +{{- end -}} + + +{{- define "mimir.var_dump" -}} +{{- . | mustToPrettyJson | printf "\nThe JSON output of the dumped var is: \n%s" | fail }} +{{- end -}} + + +{{/* +siToBytes is used to convert Kubernetes byte units to bytes. +Works for a sub set of SI suffixes: m, k, M, G, T, and their power-of-two equivalents: Ki, Mi, Gi, Ti. + +mimir.siToBytes takes 1 argument + .value = the input value with SI unit +*/}} +{{- define "mimir.siToBytes" -}} + {{- if (hasSuffix "Ki" .value) -}} + {{- trimSuffix "Ki" .value | float64 | mul 1024 | ceil | int64 -}} + {{- else if (hasSuffix "Mi" .value) -}} + {{- trimSuffix "Mi" .value | float64 | mul 1048576 | ceil | int64 -}} + {{- else if (hasSuffix "Gi" .value) -}} + {{- trimSuffix "Gi" .value | float64 | mul 1073741824 | ceil | int64 -}} + {{- else if (hasSuffix "Ti" .value) -}} + {{- trimSuffix "Ti" .value | float64 | mul 1099511627776 | ceil | int64 -}} + {{- else if (hasSuffix "k" .value) -}} + {{- trimSuffix "k" .value | float64 | mul 1000 | ceil | int64 -}} + {{- else if (hasSuffix "M" .value) -}} + {{- trimSuffix "M" .value | float64 | mul 1000000 | ceil | int64 -}} + {{- else if (hasSuffix "G" .value) -}} + {{- trimSuffix "G" .value | float64 | mul 1000000000 | ceil | int64 -}} + {{- else if (hasSuffix "T" .value) -}} + {{- trimSuffix "T" .value | float64 | mul 1000000000000 | ceil | int64 -}} + {{- else if (hasSuffix "m" .value) -}} + {{- trimSuffix "m" .value | float64 | mulf 0.001 | ceil | int64 -}} + {{- else -}} + {{- .value }} + {{- end -}} +{{- end -}} + +{{/* +parseCPU is used to convert Kubernetes CPU units to the corresponding float value of CPU cores. +The returned value is a string representation. If you need to do any math on it, please parse the string first. + +mimir.parseCPU takes 1 argument + .value = the Kubernetes CPU request value +*/}} +{{- define "mimir.parseCPU" -}} + {{- $value_string := .value | toString -}} + {{- if (hasSuffix "m" $value_string) -}} + {{ trimSuffix "m" $value_string | float64 | mulf 0.001 -}} + {{- else -}} + {{- $value_string }} + {{- end -}} +{{- end -}} + +{{/* +cpuToMilliCPU is used to convert Kubernetes CPU units to MilliCPU. +The returned value is a string representation. If you need to do any math on it, please parse the string first. + +mimir.cpuToMilliCPU takes 1 argument + .value = the Kubernetes CPU request value +*/}} +{{- define "mimir.cpuToMilliCPU" -}} + {{- $value_string := .value | toString -}} + {{- if (hasSuffix "m" $value_string) -}} + {{ trimSuffix "m" $value_string -}} + {{- else -}} + {{- $value_string | float64 | mulf 1000 | toString }} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-api/admin-api-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-api/admin-api-dep.yaml new file mode 100644 index 0000000..3923ca1 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-api/admin-api-dep.yaml @@ -0,0 +1,138 @@ +{{- if .Values.enterprise.enabled -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + annotations: + {{- toYaml .Values.admin_api.annotations | nindent 4 }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "admin-api" "memberlist" true) | nindent 4 }} + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "admin-api") }} + namespace: {{ .Release.Namespace | quote }} +spec: + replicas: {{ .Values.admin_api.replicas }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "admin-api" "memberlist" true) | nindent 6 }} + strategy: + {{- toYaml .Values.admin_api.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "admin-api" "memberlist" true) | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "admin-api") | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.admin_api.priorityClassName }} + priorityClassName: {{ .Values.admin_api.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "admin-api") | nindent 8 }} + {{- with .Values.admin_api.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + containers: + - name: admin-api + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=admin-api" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + {{- range $key, $value := .Values.admin_api.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.admin_api.extraVolumeMounts }} + {{ toYaml .Values.admin_api.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + - name: license + mountPath: /license + - name: storage + mountPath: "/data" + subPath: {{ .Values.admin_api.persistence.subPath }} + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + - name: memberlist + containerPort: {{ include "mimir.memberlistBindPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.admin_api.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.admin_api.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.admin_api.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.admin_api.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.admin_api.env }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.admin_api }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.admin_api.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.admin_api.extraContainers }} + {{ toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.admin_api.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.admin_api.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "admin-api") | nindent 6 }} + {{- with .Values.admin_api.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.admin_api.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime + {{- if .Values.admin_api.extraVolumes }} + {{ toYaml .Values.admin_api.extraVolumes | nindent 8}} + {{- end }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + - name: storage + emptyDir: {} + - name: active-queries + emptyDir: {} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-api/admin-api-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-api/admin-api-pdb.yaml new file mode 100644 index 0000000..2b88fff --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-api/admin-api-pdb.yaml @@ -0,0 +1,3 @@ +{{- if .Values.enterprise.enabled -}} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "admin-api" "memberlist" true) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-api/admin-api-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-api/admin-api-servmon.yaml new file mode 100644 index 0000000..3b068fe --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-api/admin-api-servmon.yaml @@ -0,0 +1,3 @@ +{{- if .Values.enterprise.enabled -}} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" . "component" "admin-api" "memberlist" true) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-api/admin-api-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-api/admin-api-svc.yaml new file mode 100644 index 0000000..64dfb60 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-api/admin-api-svc.yaml @@ -0,0 +1,27 @@ +{{- if .Values.enterprise.enabled -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "admin-api") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "admin-api" "memberlist" true) | nindent 4 }} + {{- with .Values.admin_api.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.admin_api.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "admin-api" "memberlist" true) | nindent 4 }} +{{- end -}} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-cache/admin-cache-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-cache/admin-cache-pdb.yaml new file mode 100644 index 0000000..079ff0e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-cache/admin-cache-pdb.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled (index .Values "admin-cache" "enabled") -}} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "admin-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-cache/admin-cache-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-cache/admin-cache-servmon.yaml new file mode 100644 index 0000000..94a19bd --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-cache/admin-cache-servmon.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled (index .Values "admin-cache" "enabled") -}} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "admin-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-cache/admin-cache-statefulset.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-cache/admin-cache-statefulset.yaml new file mode 100644 index 0000000..619aeef --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-cache/admin-cache-statefulset.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled (index .Values "admin-cache" "enabled") -}} +{{- include "mimir.memcached.statefulSet" (dict "ctx" $ "component" "admin-cache" ) }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-cache/admin-cache-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-cache/admin-cache-svc-headless.yaml new file mode 100644 index 0000000..a4224d3 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/admin-cache/admin-cache-svc-headless.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled (index .Values "admin-cache" "enabled") -}} +{{- include "mimir.memcached.service" (dict "ctx" $ "component" "admin-cache" ) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-config.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-config.yaml new file mode 100644 index 0000000..bae1b7c --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-config.yaml @@ -0,0 +1,16 @@ +{{- if .Values.alertmanager.enabled -}} +{{- if .Values.alertmanager.fallbackConfig -}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "alertmanager") }}-fallback-config + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "alertmanager" "memberlist" true) | nindent 4 }} + annotations: + {{- toYaml .Values.alertmanager.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +data: + alertmanager_fallback_config.yaml: | + {{- .Values.alertmanager.fallbackConfig | nindent 4 }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-dep.yaml new file mode 100644 index 0000000..15f90a1 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-dep.yaml @@ -0,0 +1,155 @@ +{{- if .Values.alertmanager.enabled -}} +{{- if not .Values.alertmanager.statefulSet.enabled -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "alertmanager") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "alertmanager" "memberlist" true) | nindent 4 }} + annotations: + {{- toYaml .Values.alertmanager.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + replicas: {{ .Values.alertmanager.replicas }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "alertmanager" "memberlist" true) | nindent 6 }} + strategy: + {{- toYaml .Values.alertmanager.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "alertmanager" "memberlist" true) | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "alertmanager") | nindent 8 }} + {{- if .Values.alertmanager.fallbackConfig }} + checksum/alertmanager-fallback-config: {{ include (print .Template.BasePath "/alertmanager/alertmanager-config.yaml") . | sha256sum }} + {{- end }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.alertmanager.priorityClassName }} + priorityClassName: {{ .Values.query_frontend.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "alertmanager") | nindent 8 }} + {{- with .Values.alertmanager.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end}} + {{- end }} + containers: + - name: alertmanager + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=alertmanager" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + {{- range $key, $value := .Values.alertmanager.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.alertmanager.extraVolumeMounts }} + {{ toYaml .Values.alertmanager.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + - name: storage + mountPath: "/data" + subPath: {{ .Values.alertmanager.persistence.subPath }} + {{- if .Values.alertmanager.fallbackConfig }} + - name: alertmanager-fallback-config + mountPath: /configs/ + {{- end }} + - name: tmp + mountPath: /tmp + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + - name: memberlist + containerPort: {{ include "mimir.memberlistBindPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.alertmanager.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.alertmanager.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.alertmanager.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.alertmanager.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.alertmanager.env }} + {{- toYaml . | nindent 12 }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.alertmanager.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} +{{- if .Values.alertmanager.extraContainers }} +{{ toYaml .Values.alertmanager.extraContainers | indent 8}} +{{- end }} + {{- with .Values.alertmanager.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.alertmanager.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "alertmanager") | nindent 6 }} + {{- with .Values.alertmanager.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.alertmanager.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime +{{- if .Values.alertmanager.extraVolumes }} +{{ toYaml .Values.alertmanager.extraVolumes | indent 8}} +{{- end }} + - name: storage + emptyDir: {} + - name: tmp + emptyDir: {} + - name: active-queries + emptyDir: {} + {{- if .Values.alertmanager.fallbackConfig }} + - name: alertmanager-fallback-config + configMap: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "alertmanager") }}-fallback-config + {{- end }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-pdb.yaml new file mode 100644 index 0000000..c0acf97 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-pdb.yaml @@ -0,0 +1,3 @@ +{{- if .Values.alertmanager.enabled -}} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "alertmanager" "memberlist" true) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-servmon.yaml new file mode 100644 index 0000000..8e45219 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-servmon.yaml @@ -0,0 +1,3 @@ +{{- if .Values.alertmanager.enabled -}} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "alertmanager" "memberlist" true) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-statefulset.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-statefulset.yaml new file mode 100644 index 0000000..2daeab2 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-statefulset.yaml @@ -0,0 +1,217 @@ +{{- if .Values.alertmanager.enabled -}} +{{- if .Values.alertmanager.statefulSet.enabled -}} +{{- $args := dict "ctx" . "component" "alertmanager" "memberlist" true -}} +{{- $zonesMap := include "mimir.zoneAwareReplicationMap" $args | fromYaml -}} +{{- range $zoneName, $rolloutZone := $zonesMap }} +{{- with $ -}} +{{- $_ := set $args "rolloutZoneName" $zoneName -}} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "mimir.resourceName" $args }} + labels: + {{- include "mimir.labels" $args | nindent 4 }} + annotations: + {{- include "mimir.componentAnnotations" $args | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + replicas: {{ $rolloutZone.replicas }} + {{- if and (semverCompare ">= 1.23-0" (include "mimir.kubeVersion" .)) (.Values.alertmanager.persistentVolume.enableRetentionPolicy) }} + persistentVolumeClaimRetentionPolicy: + whenDeleted: {{ .Values.alertmanager.persistentVolume.whenDeleted }} + whenScaled: {{ .Values.alertmanager.persistentVolume.whenScaled }} + {{- end }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" $args | nindent 6 }} + updateStrategy: + {{- if $zoneName }} + type: OnDelete + {{- else }} + {{- toYaml .Values.alertmanager.statefulStrategy | nindent 4 }} + {{- end }} + serviceName: {{ template "mimir.fullname" . }}-alertmanager + {{- if .Values.alertmanager.persistentVolume.enabled }} + volumeClaimTemplates: + - metadata: + name: storage + {{- if .Values.alertmanager.persistentVolume.annotations }} + annotations: + {{ toYaml .Values.alertmanager.persistentVolume.annotations | nindent 10 }} + {{- end }} + spec: + {{- $storageClass := default .Values.alertmanager.persistentVolume.storageClass $rolloutZone.storageClass }} + {{- if $storageClass }} + {{- if (eq "-" $storageClass) }} + storageClassName: "" + {{- else }} + storageClassName: {{ $storageClass }} + {{- end }} + {{- end }} + accessModes: + {{- toYaml .Values.alertmanager.persistentVolume.accessModes | nindent 10 }} + resources: + requests: + storage: "{{ .Values.alertmanager.persistentVolume.size }}" + {{- end }} + template: + metadata: + labels: + {{- include "mimir.podLabels" $args | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" $args | nindent 8 }} + {{- if .Values.alertmanager.fallbackConfig }} + checksum/alertmanager-fallback-config: {{ include (print .Template.BasePath "/alertmanager/alertmanager-config.yaml") . | sha256sum }} + {{- end }} + namespace: {{ .Release.Namespace | quote }} + spec: + {{- with .Values.alertmanager.schedulerName }} + schedulerName: {{ . | quote }} + {{- end }} + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.alertmanager.priorityClassName }} + priorityClassName: {{ .Values.alertmanager.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "alertmanager") | nindent 8 }} + {{- with .Values.alertmanager.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + {{- with $rolloutZone.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with $rolloutZone.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "alertmanager") | nindent 6 }} + {{- with .Values.alertmanager.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.alertmanager.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime + {{- if not .Values.alertmanager.persistentVolume.enabled }} + - name: storage + emptyDir: {} + {{- end }} + - name: tmp + emptyDir: {} + - name: active-queries + emptyDir: {} + {{- if .Values.alertmanager.fallbackConfig }} + - name: alertmanager-fallback-config + configMap: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "alertmanager") }}-fallback-config + {{- end }} + {{- if .Values.alertmanager.extraVolumes }} + {{ toYaml .Values.alertmanager.extraVolumes | nindent 8 }} + {{- end }} + containers: + {{- if .Values.alertmanager.extraContainers }} + {{ toYaml .Values.alertmanager.extraContainers | nindent 8 }} + {{- end }} + - name: alertmanager + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=alertmanager" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + {{- if $zoneName }} + - "-alertmanager.sharding-ring.instance-availability-zone={{ $zoneName }}" + {{- else }} + {{- if .Values.alertmanager.zoneAwareReplication.enabled }} + - "-alertmanager.sharding-ring.instance-availability-zone=zone-default" + {{- end }} + {{- end }} + {{- range $key, $value := .Values.alertmanager.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.alertmanager.extraVolumeMounts }} + {{ toYaml .Values.alertmanager.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + - name: storage + mountPath: "/data" + {{- if .Values.alertmanager.persistentVolume.subPath }} + subPath: {{ .Values.alertmanager.persistentVolume.subPath }} + {{- else }} + {{- end }} + {{- if .Values.alertmanager.fallbackConfig }} + - name: alertmanager-fallback-config + mountPath: /configs/ + {{- end }} + - name: tmp + mountPath: /tmp + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + - name: memberlist + containerPort: {{ include "mimir.memberlistBindPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.alertmanager.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.alertmanager.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.alertmanager.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.alertmanager.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.alertmanager.env }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.alertmanager }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.alertmanager.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + +--- +{{ end }} +{{ end }} +{{ end }} +{{ end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-svc-headless.yaml new file mode 100644 index 0000000..f3ced60 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-svc-headless.yaml @@ -0,0 +1,34 @@ +{{- if .Values.alertmanager.enabled -}} +{{- $clusterPort := regexReplaceAll ".+[:]" (default "0.0.0.0:9094" (include "mimir.alertmanagerClusterBindAddress" .) ) "" -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "alertmanager") }}-headless + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "alertmanager" "memberlist" true) | nindent 4 }} + prometheus.io/service-monitor: "false" + {{- with .Values.alertmanager.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.alertmanager.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + clusterIP: None + publishNotReadyAddresses: true + ports: + - port: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + - port: {{ $clusterPort }} + protocol: TCP + name: cluster + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "alertmanager" "memberlist" true) | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-svc.yaml new file mode 100644 index 0000000..da6a718 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/alertmanager/alertmanager-svc.yaml @@ -0,0 +1,40 @@ +{{- if .Values.alertmanager.enabled -}} +{{- $args := dict "ctx" . "component" "alertmanager" "memberlist" true -}} +{{- $zonesMap := include "mimir.zoneAwareReplicationMap" $args | fromYaml -}} +{{- range $zoneName, $rolloutZone := $zonesMap }} +{{- with $ -}} +{{- $_ := set $args "rolloutZoneName" $zoneName -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" $args }} + labels: + {{- include "mimir.labels" $args | nindent 4 }} + {{- if and $zoneName .Values.alertmanager.zoneAwareReplication.migration.enabled }} + # Prevent scraping PODs via this service during migration as the original non zone-aware service already scrapes all PODs and you get duplicate metrics. + prometheus.io/service-monitor: "false" + {{- end }} + {{- with .Values.alertmanager.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.alertmanager.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" $args | nindent 4 }} + +--- +{{ end }} +{{ end }} +{{ end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/chunks-cache/chunks-cache-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/chunks-cache/chunks-cache-pdb.yaml new file mode 100644 index 0000000..ede7b03 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/chunks-cache/chunks-cache-pdb.yaml @@ -0,0 +1,3 @@ +{{- if index .Values "chunks-cache" "enabled" }} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "chunks-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/chunks-cache/chunks-cache-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/chunks-cache/chunks-cache-servmon.yaml new file mode 100644 index 0000000..1e28405 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/chunks-cache/chunks-cache-servmon.yaml @@ -0,0 +1,3 @@ +{{- if index .Values "chunks-cache" "enabled" }} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "chunks-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/chunks-cache/chunks-cache-statefulset.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/chunks-cache/chunks-cache-statefulset.yaml new file mode 100644 index 0000000..3a836f7 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/chunks-cache/chunks-cache-statefulset.yaml @@ -0,0 +1 @@ +{{- include "mimir.memcached.statefulSet" (dict "ctx" $ "component" "chunks-cache" ) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/chunks-cache/chunks-cache-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/chunks-cache/chunks-cache-svc-headless.yaml new file mode 100644 index 0000000..d2ece24 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/chunks-cache/chunks-cache-svc-headless.yaml @@ -0,0 +1 @@ +{{- include "mimir.memcached.service" (dict "ctx" $ "component" "chunks-cache" ) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/compactor/compactor-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/compactor/compactor-pdb.yaml new file mode 100644 index 0000000..095703b --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/compactor/compactor-pdb.yaml @@ -0,0 +1 @@ +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "compactor" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/compactor/compactor-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/compactor/compactor-servmon.yaml new file mode 100644 index 0000000..e60bf6b --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/compactor/compactor-servmon.yaml @@ -0,0 +1 @@ +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "compactor" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/compactor/compactor-statefulset.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/compactor/compactor-statefulset.yaml new file mode 100644 index 0000000..d906867 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/compactor/compactor-statefulset.yaml @@ -0,0 +1,176 @@ +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "compactor") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "compactor" "memberlist" true) | nindent 4 }} + annotations: + {{- toYaml .Values.compactor.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + podManagementPolicy: {{ .Values.compactor.podManagementPolicy }} + {{- if and (semverCompare ">= 1.23-0" (include "mimir.kubeVersion" .)) (.Values.compactor.persistentVolume.enableRetentionPolicy) }} + persistentVolumeClaimRetentionPolicy: + whenDeleted: {{ .Values.compactor.persistentVolume.whenDeleted }} + whenScaled: {{ .Values.compactor.persistentVolume.whenScaled }} + {{- end }} + replicas: {{ .Values.compactor.replicas }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "compactor" "memberlist" true) | nindent 6 }} + updateStrategy: + {{- toYaml .Values.compactor.strategy | nindent 4 }} + serviceName: {{ template "mimir.fullname" . }}-compactor + {{- if .Values.compactor.persistentVolume.enabled }} + volumeClaimTemplates: + - metadata: + name: storage + {{- if .Values.compactor.persistentVolume.annotations }} + annotations: + {{ toYaml .Values.compactor.persistentVolume.annotations | nindent 10 }} + {{- end }} + spec: + {{- if .Values.compactor.persistentVolume.storageClass }} + {{- if (eq "-" .Values.compactor.persistentVolume.storageClass) }} + storageClassName: "" + {{- else }} + storageClassName: "{{ .Values.compactor.persistentVolume.storageClass }}" + {{- end }} + {{- end }} + accessModes: + {{- toYaml .Values.compactor.persistentVolume.accessModes | nindent 10 }} + resources: + requests: + storage: "{{ .Values.compactor.persistentVolume.size }}" + {{- end }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "compactor" "memberlist" true) | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "compactor") | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + {{- with .Values.compactor.schedulerName }} + schedulerName: {{ . | quote }} + {{- end }} + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.compactor.priorityClassName }} + priorityClassName: {{ .Values.compactor.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "compactor") | nindent 8 }} + {{- with .Values.compactor.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.compactor.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.compactor.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "compactor") | nindent 6 }} + {{- with .Values.compactor.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.compactor.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime + {{- if not .Values.compactor.persistentVolume.enabled }} + - name: storage + emptyDir: {} + {{- end }} + {{- if .Values.compactor.extraVolumes }} + {{ toYaml .Values.compactor.extraVolumes | nindent 8 }} + {{- end }} + - name: active-queries + emptyDir: {} + containers: + {{- if .Values.compactor.extraContainers }} + {{ toYaml .Values.compactor.extraContainers | nindent 8 }} + {{- end }} + - name: compactor + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=compactor" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + {{- range $key, $value := .Values.compactor.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.compactor.extraVolumeMounts }} + {{ toYaml .Values.compactor.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + - name: storage + mountPath: "/data" + {{- if .Values.compactor.persistentVolume.subPath }} + subPath: {{ .Values.compactor.persistentVolume.subPath }} + {{- end }} + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + - name: memberlist + containerPort: {{ include "mimir.memberlistBindPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.compactor.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.compactor.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.compactor.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.compactor.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.compactor.env }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.compactor }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.compactor.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/compactor/compactor-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/compactor/compactor-svc.yaml new file mode 100644 index 0000000..a761a54 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/compactor/compactor-svc.yaml @@ -0,0 +1,25 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "compactor") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "compactor" "memberlist" true) | nindent 4 }} + {{- with .Values.compactor.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.compactor.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" .}} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "compactor" "memberlist" true) | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/continuous_test/continuous-test-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/continuous_test/continuous-test-dep.yaml new file mode 100644 index 0000000..31c9050 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/continuous_test/continuous-test-dep.yaml @@ -0,0 +1,118 @@ +{{- if .Values.continuous_test.enabled -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + annotations: + {{- toYaml .Values.continuous_test.annotations | nindent 4 }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "continuous-test") | nindent 4 }} + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "continuous-test") }} + namespace: {{ .Release.Namespace | quote }} +spec: + replicas: {{ .Values.continuous_test.replicas }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "continuous-test") | nindent 6 }} + strategy: + {{- toYaml .Values.continuous_test.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "continuous-test") | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "continuous-test") | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.continuous_test.priorityClassName }} + priorityClassName: {{ .Values.continuous_test.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "continuous-test") | nindent 8 }} + {{- with .Values.continuous_test.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + containers: + - name: continuous-test + image: {{ .Values.continuous_test.image.repository }}:{{ .Values.continuous_test.image.tag }} + imagePullPolicy: {{ .Values.continuous_test.image.pullPolicy }} + args: + - "-server.metrics-port={{ include "mimir.serverHttpListenPort" . }}" + - "-tests.write-read-series-test.num-series={{ .Values.continuous_test.numSeries }}" + - "-tests.write-read-series-test.max-query-age={{ .Values.continuous_test.maxQueryAge }}" + - "-tests.write-endpoint={{ template "mimir.gatewayUrl" . }}" + - "-tests.read-endpoint={{ template "mimir.gatewayUrl" . }}/prometheus" + - "-tests.run-interval={{ .Values.continuous_test.runInterval }}" + {{- if eq .Values.continuous_test.auth.type "tenantId" }} + - "-tests.tenant-id={{ .Values.continuous_test.auth.tenant }}" + {{- end }} + {{- if eq .Values.continuous_test.auth.type "basicAuth" }} + - "-tests.basic-auth-password={{ .Values.continuous_test.auth.password }}" + - "-tests.basic-auth-user={{ .Values.continuous_test.auth.tenant }}" + {{- end }} + {{- if eq .Values.continuous_test.auth.type "bearerToken" }} + - "-tests.bearer-token={{ .Values.continuous_test.auth.bearerToken }}" + {{- end }} + {{- range $key, $value := .Values.continuous_test.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.continuous_test.extraVolumeMounts }} + {{ toYaml .Values.continuous_test.extraVolumeMounts | nindent 12}} + {{- end }} + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + resources: + {{- toYaml .Values.continuous_test.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.continuous_test.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.continuous_test.env }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.continuous_test }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.continuous_test.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.continuous_test.extraContainers }} + {{ toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.continuous_test.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.continuous_test.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "continuous-test") | nindent 6 }} + {{- with .Values.continuous_test.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.continuous_test.terminationGracePeriodSeconds }} + volumes: + {{- if .Values.continuous_test.extraVolumes }} + {{ toYaml .Values.continuous_test.extraVolumes | nindent 8}} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/continuous_test/continuous-test-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/continuous_test/continuous-test-servmon.yaml new file mode 100644 index 0000000..a025708 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/continuous_test/continuous-test-servmon.yaml @@ -0,0 +1,3 @@ +{{- if .Values.continuous_test.enabled -}} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "continuous-test") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/continuous_test/continuous-test-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/continuous_test/continuous-test-svc-headless.yaml new file mode 100644 index 0000000..59aceb6 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/continuous_test/continuous-test-svc-headless.yaml @@ -0,0 +1,25 @@ +{{- if .Values.continuous_test.enabled -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "continuous-test") }}-headless + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "continuous-test") | nindent 4 }} + {{- with .Values.continuous_test.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.continuous_test.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + clusterIP: None + publishNotReadyAddresses: true + ports: + - port: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + name: http-metrics + targetPort: http-metrics + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "continuous-test") | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-dep.yaml new file mode 100644 index 0000000..3fccf57 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-dep.yaml @@ -0,0 +1,167 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "distributor") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "distributor" "memberlist" true) | nindent 4 }} + annotations: + {{- toYaml .Values.distributor.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + {{- if or (not .Values.distributor.kedaAutoscaling.enabled) (.Values.distributor.kedaAutoscaling.preserveReplicas) }} + # If replicas is not number (when using values file it's float64, when using --set arg it's int64) and is false (i.e. null) don't set it + {{- if or (or (kindIs "int64" .Values.distributor.replicas) (kindIs "float64" .Values.distributor.replicas)) (.Values.distributor.replicas) }} + replicas: {{ .Values.distributor.replicas }} + {{- end }} + {{- end }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "distributor" "memberlist" true) | nindent 6 }} + strategy: + {{- toYaml .Values.distributor.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "distributor" "memberlist" true) | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "distributor") | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.distributor.priorityClassName }} + priorityClassName: {{ .Values.distributor.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "distributor") | nindent 8 }} + {{- with .Values.distributor.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end}} + {{- end }} + containers: + - name: distributor + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=distributor" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + # When write requests go through distributors via gRPC, we want gRPC clients to re-resolve the distributors DNS + # endpoint before the distributor process is terminated, in order to avoid any failures during graceful shutdown. + # To achieve it, we set a shutdown delay greater than the gRPC max connection age. + - "-server.grpc.keepalive.max-connection-age=60s" + - "-server.grpc.keepalive.max-connection-age-grace=5m" + - "-server.grpc.keepalive.max-connection-idle=1m" + - "-shutdown-delay=90s" + {{- if .Values.ingester.zoneAwareReplication.migration.enabled }} + {{- if not .Values.ingester.zoneAwareReplication.migration.writePath }} + - "-ingester.ring.zone-awareness-enabled=false" + {{- end }} + {{- if .Values.ingester.zoneAwareReplication.migration.excludeDefaultZone }} + - "-ingester.ring.excluded-zones=zone-default" + {{- end }} + {{- end }} + {{- range $key, $value := .Values.distributor.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.distributor.extraVolumeMounts }} + {{ toYaml .Values.distributor.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + - name: storage + mountPath: "/data" + subPath: {{ .Values.distributor.persistence.subPath }} + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + - name: memberlist + containerPort: {{ include "mimir.memberlistBindPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.distributor.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.distributor.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.distributor.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.distributor.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.distributor.env }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- $cpu_request := dig "requests" "cpu" nil .Values.distributor.resources }} + {{- if $cpu_request }} + {{- $cpu_request_doubled := include "mimir.parseCPU" (dict "value" $cpu_request) | float64 | mulf 2 | ceil }} + - name: "GOMAXPROCS" + value: {{ max $cpu_request_doubled 8 | toString | toYaml }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.distributor }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.distributor.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} +{{- if .Values.distributor.extraContainers }} +{{ toYaml .Values.distributor.extraContainers | indent 8}} +{{- end }} + {{- with .Values.distributor.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.distributor.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "distributor") | nindent 6 }} + {{- with .Values.distributor.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.distributor.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime +{{- if .Values.distributor.extraVolumes }} +{{ toYaml .Values.distributor.extraVolumes | indent 8}} +{{- end }} + - name: storage + emptyDir: {} + - name: active-queries + emptyDir: {} + diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-pdb.yaml new file mode 100644 index 0000000..f99c602 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-pdb.yaml @@ -0,0 +1 @@ +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "distributor" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-servmon.yaml new file mode 100644 index 0000000..d113fd9 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-servmon.yaml @@ -0,0 +1 @@ +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "distributor" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-so.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-so.yaml new file mode 100644 index 0000000..a0680f8 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-so.yaml @@ -0,0 +1,44 @@ +{{- if .Values.distributor.kedaAutoscaling.enabled }} +apiVersion: keda.sh/v1alpha1 +kind: ScaledObject +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "distributor") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "distributor") | nindent 4 }} + annotations: + {{- toYaml .Values.distributor.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + advanced: + horizontalPodAutoscalerConfig: + {{- with .Values.distributor.kedaAutoscaling.behavior }} + behavior: + {{- toYaml . | nindent 8 }} + {{- end }} + maxReplicaCount: {{ .Values.distributor.kedaAutoscaling.maxReplicaCount }} + minReplicaCount: {{ .Values.distributor.kedaAutoscaling.minReplicaCount }} + pollingInterval: {{ .Values.kedaAutoscaling.pollingInterval }} + scaleTargetRef: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "distributor") }} + apiVersion: apps/v1 + kind: Deployment + triggers: + - metadata: + query: max_over_time(sum(sum by (pod) (rate(container_cpu_usage_seconds_total{container="distributor",namespace="{{ .Release.Namespace }}"}[5m])) and max by (pod) (up{container="distributor",namespace="{{ .Release.Namespace }}"}) > 0)[15m:]) * 1000 + serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }} + {{- $cpu_request := dig "requests" "cpu" nil .Values.distributor.resources }} + threshold: {{ mulf (include "mimir.cpuToMilliCPU" (dict "value" $cpu_request)) (divf .Values.distributor.kedaAutoscaling.targetCPUUtilizationPercentage 100) | floor | int64 | quote }} + {{- if .Values.kedaAutoscaling.customHeaders }} + customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }} + {{- end }} + type: prometheus + - metadata: + query: max_over_time(sum((sum by (pod) (container_memory_working_set_bytes{container="distributor",namespace="{{ .Release.Namespace }}"}) and max by (pod) (up{container="distributor",namespace="{{ .Release.Namespace }}"}) > 0) or vector(0))[15m:]) + sum(sum by (pod) (max_over_time(kube_pod_container_resource_requests{container="distributor",namespace="{{ .Release.Namespace }}", resource="memory"}[15m])) and max by (pod) (changes(kube_pod_container_status_restarts_total{container="distributor",namespace="{{ .Release.Namespace }}"}[15m]) > 0) and max by (pod) (kube_pod_container_status_last_terminated_reason{container="distributor",namespace="{{ .Release.Namespace }}", reason="OOMKilled"}) or vector(0)) + serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }} + {{- $mem_request := dig "requests" "memory" nil .Values.distributor.resources }} + threshold: {{ mulf (include "mimir.siToBytes" (dict "value" $mem_request)) (divf .Values.distributor.kedaAutoscaling.targetMemoryUtilizationPercentage 100) | floor | int64 | quote }} + {{- if .Values.kedaAutoscaling.customHeaders }} + customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }} + {{- end }} + type: prometheus +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-svc-headless.yaml new file mode 100644 index 0000000..d59b78c --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-svc-headless.yaml @@ -0,0 +1,27 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "distributor") }}-headless + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "distributor" "memberlist" true) | nindent 4 }} + prometheus.io/service-monitor: "false" + {{- with .Values.distributor.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.distributor.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + clusterIP: None + ports: + - port: {{ include "mimir.serverHttpListenPort" .}} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "distributor" "memberlist" true) | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-svc.yaml new file mode 100644 index 0000000..868949d --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/distributor/distributor-svc.yaml @@ -0,0 +1,25 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "distributor") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "distributor" "memberlist" true) | nindent 4 }} + {{- with .Values.distributor.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.distributor.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" .}} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "distributor" "memberlist" true) | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/extra-manifests.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/extra-manifests.yaml new file mode 100644 index 0000000..a9bb3b6 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/extra-manifests.yaml @@ -0,0 +1,4 @@ +{{ range .Values.extraObjects }} +--- +{{ tpl (toYaml .) $ }} +{{ end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/_helpers.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/_helpers.tpl new file mode 100644 index 0000000..7c25d79 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/_helpers.tpl @@ -0,0 +1,21 @@ +{{/* +nginx auth Secret name +*/}} +{{- define "mimir.gateway.nginx.authSecret" -}} +{{ .Values.gateway.nginx.basicAuth.existingSecret | default (include "mimir.resourceName" (dict "ctx" . "component" "gateway-nginx") ) }} +{{- end }} + +{{/* +Name of the gateway Service resource +*/}} +{{- define "mimir.gateway.service.name" -}} +{{ .Values.gateway.service.nameOverride | default (include "mimir.resourceName" (dict "ctx" . "component" "gateway") ) }} +{{- end }} + + +{{/* +Returns "true" or "false" strings if the gateway component (nginx or GEM gateway) should be deployed +*/}} +{{- define "mimir.gateway.isEnabled" -}} +{{- or .Values.gateway.enabledNonEnterprise .Values.enterprise.enabled -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-dep.yaml new file mode 100644 index 0000000..0bcbf63 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-dep.yaml @@ -0,0 +1,183 @@ +{{- if (eq (include "mimir.gateway.isEnabled" .) "true") }} +{{- with .Values.gateway }} +{{- $isGEMGateway := $.Values.enterprise.enabled -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + annotations: + {{- toYaml .annotations | nindent 4 }} + labels: + {{- include "mimir.labels" (dict "ctx" $ "component" "gateway") | nindent 4 }} + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "gateway") }} + namespace: {{ $.Release.Namespace | quote }} +spec: +{{- if not .autoscaling.enabled }} + replicas: {{ .replicas }} +{{- end }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" $ "component" "gateway") | nindent 6 }} +{{- with .strategy }} + strategy: +{{ toYaml . | trim | indent 4 }} +{{- end }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" $ "component" "gateway") | nindent 8 }} + annotations: + {{- $annotations := include "mimir.podAnnotations" (dict "ctx" $ "component" "gateway") | fromYaml -}} + {{- if not $isGEMGateway -}} + {{- $annotations = (dict "checksum/config" (include (print $.Template.BasePath "/gateway/nginx-configmap.yaml") $ | sha256sum )) | mergeOverwrite $annotations -}} + {{- end -}} + {{- $annotations | toYaml | nindent 8 }} + namespace: {{ $.Release.Namespace | quote }} + spec: + serviceAccountName: {{ include "mimir.serviceAccountName" $ }} + {{- if .priorityClassName }} + priorityClassName: {{ .priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" $ "component" "gateway") | nindent 8 }} + {{- with .initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if $.Values.image.pullSecrets }} + imagePullSecrets: + {{- range $.Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + containers: + {{- if $isGEMGateway }} + - name: gateway + image: {{ include "mimir.imageReference" $ | quote }} + imagePullPolicy: {{ $.Values.image.pullPolicy }} + args: + - "-target=gateway" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + {{- range $key, $value := .extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- with .extraVolumeMounts }} + {{ toYaml . | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + - name: runtime-config + mountPath: /var/{{ include "mimir.name" $ }} + - name: license + mountPath: /license + - name: tmp + mountPath: /data + - name: active-queries + mountPath: /active-query-tracker + {{- else }} + - name: nginx + image: {{ .nginx.image.registry }}/{{ .nginx.image.repository }}:{{ .nginx.image.tag }} + imagePullPolicy: {{ $.Values.image.pullPolicy }} + args: + {{- with .extraArgs }} + {{- range $key, $value := . }} + - "-{{ $key }} {{ $value }}" + {{- end }} + {{- end }} + volumeMounts: + {{- if .extraVolumeMounts }} + {{ toYaml .extraVolumeMounts | nindent 12 }} + {{- end }} + - name: nginx-config + mountPath: /etc/nginx/nginx.conf + subPath: nginx.conf + {{- if .nginx.basicAuth.enabled }} + - name: auth + mountPath: /etc/nginx/secrets + {{- end }} + - name: tmp + mountPath: /tmp + - name: docker-entrypoint-d-override + mountPath: /docker-entrypoint.d + {{- end }} + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" $ }} + protocol: TCP + readinessProbe: + {{- toYaml .readinessProbe | nindent 12 }} + resources: + {{- toYaml .resources | nindent 12 }} + securityContext: + {{- toYaml .containerSecurityContext | nindent 12 }} + env: + {{- with $.Values.global.extraEnv }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- with .env }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil . }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with $.Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .extraContainers }} + {{ toYaml . | nindent 8 }} + {{- end }} + {{- with .nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" $ "component" "gateway") | nindent 6 }} + {{- with .tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" $ | nindent 10 }} + - name: runtime-config + configMap: + name: {{ include "mimir.fullname" $ }}-runtime + {{- if not $isGEMGateway }} + - name: nginx-config + configMap: + name: {{ include "mimir.fullname" $ }}-gateway-nginx + - name: docker-entrypoint-d-override + emptyDir: {} + {{- end }} + {{- if .nginx.basicAuth.enabled }} + - name: auth + secret: + secretName: {{ include "mimir.gateway.nginx.authSecret" $ }} + {{- end }} + - name: tmp + emptyDir: {} + {{- if $isGEMGateway }} + - name: license + secret: + secretName: {{ tpl $.Values.license.secretName $ }} + - name: storage + emptyDir: {} + - name: active-queries + emptyDir: {} + {{- end -}} + {{- if .extraVolumes }} + {{- toYaml .extraVolumes | nindent 8 }} + {{- end }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-ingress.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-ingress.yaml new file mode 100644 index 0000000..b6880de --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-ingress.yaml @@ -0,0 +1,44 @@ +{{- if and (eq (include "mimir.gateway.isEnabled" .) "true") .Values.gateway.ingress.enabled -}} +apiVersion: networking.k8s.io/v1 +kind: Ingress +metadata: + name: {{ .Values.gateway.ingress.nameOverride | default (include "mimir.resourceName" (dict "ctx" . "component" "gateway") ) }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "gateway") | nindent 4 }} + {{- with .Values.gateway.ingress.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ .Release.Namespace | quote }} +spec: + {{- with .Values.gateway.ingress.ingressClassName }} + ingressClassName: {{ . }} + {{- end -}} + {{- with .Values.gateway.ingress.tls }} + tls: + {{- range . }} + - hosts: + {{- range .hosts }} + - {{ tpl . $ | quote }} + {{- end }} + {{- with .secretName }} + secretName: {{ . }} + {{- end }} + {{- end }} + {{- end }} + rules: + {{- range .Values.gateway.ingress.hosts }} + - host: {{ tpl .host $ | quote }} + http: + paths: + {{- range .paths }} + - path: {{ .path }} + pathType: {{ .pathType }} + backend: + service: + name: {{ include "mimir.gateway.service.name" $ }} + port: + number: {{ $.Values.gateway.service.port }} + {{- end }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-pdb.yaml new file mode 100644 index 0000000..98ed873 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-pdb.yaml @@ -0,0 +1,3 @@ +{{- if eq (include "mimir.gateway.isEnabled" .) "true" -}} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "gateway") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-route.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-route.yaml new file mode 100644 index 0000000..a8a0887 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-route.yaml @@ -0,0 +1,25 @@ +{{- if .Values.gateway.route.enabled }} +kind: Route +apiVersion: route.openshift.io/v1 +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "gateway") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "gateway") | nindent 4 }} + {{- with .Values.gateway.route.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ .Release.Namespace | quote }} +spec: + host: {{ tpl .Values.gateway.route.host $ | quote }} + to: + kind: Service + name: {{ include "mimir.gateway.service.name" . }} + weight: 100 + port: + targetPort: http-metrics +{{- with .Values.gateway.route.tls }} + tls: + {{- toYaml . | nindent 4 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-servmon.yaml new file mode 100644 index 0000000..1902f73 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-servmon.yaml @@ -0,0 +1,3 @@ +{{- if and (eq (include "mimir.gateway.isEnabled" .) "true") (not .Values.gateway.enabledNonEnterprise) -}} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "gateway") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-svc.yaml new file mode 100644 index 0000000..67853fb --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-svc.yaml @@ -0,0 +1,37 @@ +{{- if eq (include "mimir.gateway.isEnabled" .) "true" -}} +{{- with .Values.gateway -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.gateway.service.name" $ }} + labels: + {{- include "mimir.labels" (dict "ctx" $ "component" "gateway") | nindent 4 }} + {{- with .service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .service.annotations | nindent 4 }} + namespace: {{ $.Release.Namespace | quote }} +spec: + type: {{ .service.type }} + {{- with .service.clusterIP }} + clusterIP: {{ . }} + {{- end }} + {{- if and (eq "LoadBalancer" .service.type) .service.loadBalancerIP }} + loadBalancerIP: {{ .service.loadBalancerIP }} + {{- end }} + ports: + - port: {{ .service.port }} + protocol: TCP + name: http-metrics + targetPort: http-metrics + {{- with .service.legacyPort }} + - port: {{ . }} + protocol: TCP + name: legacy-http-metrics + targetPort: http-metrics + {{- end }} + selector: + {{- include "mimir.selectorLabels" (dict "ctx" $ "component" "gateway") | nindent 4 }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-v2-hpa.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-v2-hpa.yaml new file mode 100644 index 0000000..b6ae526 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-v2-hpa.yaml @@ -0,0 +1,35 @@ +{{- if .Values.gateway.autoscaling.enabled }} +{{- if eq (include "mimir.hpa.version" .) "autoscaling/v2" }} +apiVersion: autoscaling/v2 +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "gateway") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "gateway") | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "gateway") }} + minReplicas: {{ .Values.gateway.autoscaling.minReplicas }} + maxReplicas: {{ .Values.gateway.autoscaling.maxReplicas }} + metrics: + {{- with .Values.gateway.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + target: + type: Utilization + averageUtilization: {{ . }} + {{- end }} + {{- with .Values.gateway.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + target: + type: Utilization + averageUtilization: {{ . }} + {{- end }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-v2beta1-hpa.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-v2beta1-hpa.yaml new file mode 100644 index 0000000..90e08cc --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/gateway-v2beta1-hpa.yaml @@ -0,0 +1,31 @@ +{{- if .Values.gateway.autoscaling.enabled }} +{{- if eq (include "mimir.hpa.version" .) "autoscaling/v2beta1" }} +apiVersion: autoscaling/v2beta1 +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "gateway") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "gateway") | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "gateway") }} + minReplicas: {{ .Values.gateway.autoscaling.minReplicas }} + maxReplicas: {{ .Values.gateway.autoscaling.maxReplicas }} + metrics: + {{- with .Values.gateway.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + targetAverageUtilization: {{ . }} + {{- end }} + {{- with .Values.gateway.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + targetAverageUtilization: {{ . }} + {{- end }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/nginx-configmap.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/nginx-configmap.yaml new file mode 100644 index 0000000..8a24a4e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/nginx-configmap.yaml @@ -0,0 +1,12 @@ +{{- if and (not .Values.enterprise.enabled) .Values.gateway.enabledNonEnterprise -}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "gateway-nginx") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "gateway-nginx") | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +data: + nginx.conf: | + {{- tpl .Values.gateway.nginx.config.file . | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/nginx-secret.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/nginx-secret.yaml new file mode 100644 index 0000000..1540273 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gateway/nginx-secret.yaml @@ -0,0 +1,14 @@ +{{- if not .Values.enterprise.enabled -}} +{{- if and .Values.gateway.enabledNonEnterprise .Values.gateway.nginx.basicAuth.enabled (not .Values.gateway.nginx.basicAuth.existingSecret) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "gateway-nginx") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "gateway-nginx") | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +stringData: + .htpasswd: | + {{- tpl .Values.gateway.nginx.basicAuth.htpasswd $ | nindent 4 }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gossip-ring/_helpers.gossip-ring.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/gossip-ring/_helpers.gossip-ring.tpl new file mode 100644 index 0000000..b4a932e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gossip-ring/_helpers.gossip-ring.tpl @@ -0,0 +1,11 @@ +{{/* +gossip-ring selector labels +*/}} +{{- define "mimir.gossipRingSelectorLabels" -}} +{{ include "mimir.selectorLabels" . }} +{{- if .ctx.Values.enterprise.legacyLabels }} +gossip_ring_member: "true" +{{- else }} +app.kubernetes.io/part-of: memberlist +{{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/gossip-ring/gossip-ring-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/gossip-ring/gossip-ring-svc.yaml new file mode 100644 index 0000000..32da7fa --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/gossip-ring/gossip-ring-svc.yaml @@ -0,0 +1,19 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "gossip-ring") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "gossip-ring") | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: gossip-ring + port: {{ include "mimir.memberlistBindPort" . }} + appProtocol: tcp + protocol: TCP + targetPort: {{ include "mimir.memberlistBindPort" . }} + publishNotReadyAddresses: true + selector: + {{- include "mimir.gossipRingSelectorLabels" (dict "ctx" .) | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-aggregation-cache/graphite-aggregation-cache-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-aggregation-cache/graphite-aggregation-cache-pdb.yaml new file mode 100644 index 0000000..b545f57 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-aggregation-cache/graphite-aggregation-cache-pdb.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "gr-aggr-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-aggregation-cache/graphite-aggregation-cache-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-aggregation-cache/graphite-aggregation-cache-servmon.yaml new file mode 100644 index 0000000..37077a8 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-aggregation-cache/graphite-aggregation-cache-servmon.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "gr-aggr-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-aggregation-cache/graphite-aggregation-cache-statefulset.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-aggregation-cache/graphite-aggregation-cache-statefulset.yaml new file mode 100644 index 0000000..1cba14a --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-aggregation-cache/graphite-aggregation-cache-statefulset.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +{{- include "mimir.memcached.statefulSet" (dict "ctx" $ "component" "gr-aggr-cache" ) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-aggregation-cache/graphite-aggregation-cache-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-aggregation-cache/graphite-aggregation-cache-svc-headless.yaml new file mode 100644 index 0000000..a9adf93 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-aggregation-cache/graphite-aggregation-cache-svc-headless.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +{{- include "mimir.memcached.service" (dict "ctx" $ "component" "gr-aggr-cache" ) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-metric-name-cache/graphite-metric-name-cache-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-metric-name-cache/graphite-metric-name-cache-pdb.yaml new file mode 100644 index 0000000..bd778c8 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-metric-name-cache/graphite-metric-name-cache-pdb.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "gr-metricname-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-metric-name-cache/graphite-metric-name-cache-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-metric-name-cache/graphite-metric-name-cache-servmon.yaml new file mode 100644 index 0000000..b4249b9 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-metric-name-cache/graphite-metric-name-cache-servmon.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "gr-metricname-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-metric-name-cache/graphite-metric-name-cache-statefulset.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-metric-name-cache/graphite-metric-name-cache-statefulset.yaml new file mode 100644 index 0000000..c9aecb2 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-metric-name-cache/graphite-metric-name-cache-statefulset.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +{{- include "mimir.memcached.statefulSet" (dict "ctx" $ "component" "gr-metricname-cache" ) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-metric-name-cache/graphite-metric-name-cache-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-metric-name-cache/graphite-metric-name-cache-svc-headless.yaml new file mode 100644 index 0000000..0844f2a --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-metric-name-cache/graphite-metric-name-cache-svc-headless.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +{{- include "mimir.memcached.service" (dict "ctx" $ "component" "gr-metricname-cache" ) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-dep.yaml new file mode 100644 index 0000000..c4b6ca1 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-dep.yaml @@ -0,0 +1,138 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "graphite-querier") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "graphite-querier") | nindent 4 }} + annotations: + {{- toYaml .Values.graphite.querier.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + replicas: {{ .Values.graphite.querier.replicas }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "graphite-querier") | nindent 6 }} + strategy: + {{- toYaml .Values.graphite.querier.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "graphite-querier") | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "graphite-querier") | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.graphite.querier.priorityClassName }} + priorityClassName: {{ .Values.graphite.querier.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "graphite-querier") | nindent 8 }} + {{- with .Values.graphite.querier.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + containers: + {{- if .Values.graphite.querier.extraContainers }} + {{ toYaml .Values.graphite.querier.extraContainers | nindent 8 }} + {{- end }} + - name: graphite-querier + image: {{ include "mimir.imageReference" . | quote }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - -target=graphite-querier + - -config.file=/etc/mimir/mimir.yaml + {{- range $key, $value := .Values.graphite.querier.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.graphite.querier.extraVolumeMounts }} + {{ toYaml .Values.graphite.querier.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + - name: graphite-schemas + mountPath: /etc/graphite-proxy + - name: license + mountPath: /license + - name: storage + mountPath: "/data" + subPath: {{ .Values.graphite.querier.persistence.subPath }} + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.graphite.querier.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.graphite.querier.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.graphite.querier.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.graphite.querier.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.graphite.querier.env }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.graphite.querier }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.admin_api.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.graphite.querier.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.graphite.querier.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.graphite.querier.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.graphite.querier.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime + - name: graphite-schemas + configMap: + name: {{ template "mimir.fullname" . }}-graphite-schemas + {{- if .Values.graphite.querier.extraVolumes }} + {{ toYaml .Values.graphite.querier.extraVolumes | indent 8}} + {{- end }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + - name: storage + emptyDir: {} + - name: active-queries + emptyDir: {} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-pdb.yaml new file mode 100644 index 0000000..4a717a4 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-pdb.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "graphite-querier") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-schemas-configmap.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-schemas-configmap.yaml new file mode 100644 index 0000000..1445a58 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-schemas-configmap.yaml @@ -0,0 +1,14 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "graphite-schemas") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "graphite-schemas") | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +data: + storage-schemas.conf: | +{{ .Values.graphite.querier.schemasConfiguration.storageSchemas | indent 4 }} + storage-aggregations.conf: | +{{ .Values.graphite.querier.schemasConfiguration.storageAggregations | indent 4 }} +{{- end -}} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-servmon.yaml new file mode 100644 index 0000000..6092015 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-servmon.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "graphite-querier") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-svc.yaml new file mode 100644 index 0000000..b954ebe --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-querier/graphite-querier-svc.yaml @@ -0,0 +1,27 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "graphite-querier") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "graphite-querier") | nindent 4 }} + {{- with .Values.graphite.querier.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.graphite.querier.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "graphite-querier") | nindent 4 }} +{{- end -}} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-write-proxy/graphite-write-proxy-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-write-proxy/graphite-write-proxy-dep.yaml new file mode 100644 index 0000000..af33079 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-write-proxy/graphite-write-proxy-dep.yaml @@ -0,0 +1,136 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "graphite-write-proxy") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "graphite-write-proxy") | nindent 4 }} + annotations: + {{- toYaml .Values.graphite.write_proxy.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + replicas: {{ .Values.graphite.write_proxy.replicas }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "graphite-write-proxy") | nindent 6 }} + strategy: + {{- toYaml .Values.graphite.write_proxy.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "graphite-write-proxy") | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "graphite-write-proxy") | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.graphite.write_proxy.priorityClassName }} + priorityClassName: {{ .Values.graphite.write_proxy.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "graphite-write-proxy") | nindent 8 }} + {{- with .Values.graphite.write_proxy.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end}} + {{- end }} + containers: + {{- if .Values.graphite.write_proxy.extraContainers }} + {{ toYaml .Values.graphite.write_proxy.extraContainers | nindent 8 }} + {{- end }} + - name: graphite-write-proxy + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - -target=graphite-write-proxy + - -config.file=/etc/mimir/mimir.yaml + {{- range $key, $value := .Values.graphite.write_proxy.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.graphite.write_proxy.extraVolumeMounts }} + {{ toYaml .Values.graphite.write_proxy.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + - name: license + mountPath: /license + - name: storage + mountPath: "/data" + subPath: {{ .Values.graphite.write_proxy.persistence.subPath }} + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.graphite.write_proxy.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.graphite.write_proxy.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.graphite.write_proxy.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.graphite.write_proxy.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.graphite.write_proxy.env }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.graphite.write_proxy }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.graphite.write_proxy.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.graphite.write_proxy.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.graphite.write_proxy.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.graphite.write_proxy.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.graphite.write_proxy.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime + - name: graphite-schemas + configMap: + name: {{ template "mimir.fullname" . }}-graphite-schemas + {{- if .Values.graphite.write_proxy.extraVolumes }} + {{ toYaml .Values.graphite.write_proxy.extraVolumes | indent 8}} + {{- end }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + - name: storage + emptyDir: {} + - name: active-queries + emptyDir: {} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-write-proxy/graphite-write-proxy-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-write-proxy/graphite-write-proxy-pdb.yaml new file mode 100644 index 0000000..163431e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-write-proxy/graphite-write-proxy-pdb.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "graphite-write-proxy") }} +{{- end -}} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-write-proxy/graphite-write-proxy-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-write-proxy/graphite-write-proxy-servmon.yaml new file mode 100644 index 0000000..8f7dbdb --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-write-proxy/graphite-write-proxy-servmon.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "graphite-write-proxy") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-write-proxy/graphite-write-proxy-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-write-proxy/graphite-write-proxy-svc.yaml new file mode 100644 index 0000000..07c02f1 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/graphite-proxy/graphite-write-proxy/graphite-write-proxy-svc.yaml @@ -0,0 +1,27 @@ +{{- if and .Values.enterprise.enabled .Values.graphite.enabled -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "graphite-write-proxy") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "graphite-write-proxy") | nindent 4 }} + {{- with .Values.graphite.write_proxy.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.graphite.write_proxy.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "graphite-write-proxy") | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/index-cache/index-cache-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/index-cache/index-cache-pdb.yaml new file mode 100644 index 0000000..0d0232d --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/index-cache/index-cache-pdb.yaml @@ -0,0 +1,3 @@ +{{- if index .Values "index-cache" "enabled" }} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "index-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/index-cache/index-cache-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/index-cache/index-cache-servmon.yaml new file mode 100644 index 0000000..3fc39b0 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/index-cache/index-cache-servmon.yaml @@ -0,0 +1,3 @@ +{{- if index .Values "index-cache" "enabled" }} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "index-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/index-cache/index-cache-statefulset.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/index-cache/index-cache-statefulset.yaml new file mode 100644 index 0000000..98362ee --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/index-cache/index-cache-statefulset.yaml @@ -0,0 +1 @@ +{{- include "mimir.memcached.statefulSet" (dict "ctx" $ "component" "index-cache" ) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/index-cache/index-cache-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/index-cache/index-cache-svc-headless.yaml new file mode 100644 index 0000000..b86b205 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/index-cache/index-cache-svc-headless.yaml @@ -0,0 +1 @@ +{{- include "mimir.memcached.service" (dict "ctx" $ "component" "index-cache" ) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-pdb.yaml new file mode 100644 index 0000000..80b49b2 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-pdb.yaml @@ -0,0 +1 @@ +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "ingester" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-servmon.yaml new file mode 100644 index 0000000..cb49e62 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-servmon.yaml @@ -0,0 +1 @@ +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "ingester" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-statefulset.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-statefulset.yaml new file mode 100644 index 0000000..2a8c4af --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-statefulset.yaml @@ -0,0 +1,200 @@ +{{- $args := dict "ctx" . "component" "ingester" "memberlist" true -}} +{{- $zonesMap := include "mimir.zoneAwareReplicationMap" $args | fromYaml -}} +{{- range $zoneName, $rolloutZone := $zonesMap }} +{{- with $ -}} +{{- $_ := set $args "rolloutZoneName" $zoneName -}} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "mimir.resourceName" $args }} + labels: + {{- include "mimir.labels" $args | nindent 4 }} + annotations: + {{- include "mimir.componentAnnotations" $args | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + podManagementPolicy: {{ .Values.ingester.podManagementPolicy }} + replicas: {{ $rolloutZone.replicas }} + {{- if and (semverCompare ">= 1.23-0" (include "mimir.kubeVersion" .)) (.Values.ingester.persistentVolume.enableRetentionPolicy) }} + persistentVolumeClaimRetentionPolicy: + whenDeleted: {{ .Values.ingester.persistentVolume.whenDeleted }} + whenScaled: {{ .Values.ingester.persistentVolume.whenScaled }} + {{- end }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" $args | nindent 6 }} + updateStrategy: + {{- if $zoneName }} + type: OnDelete + {{- else }} + {{- toYaml .Values.ingester.statefulStrategy | nindent 4 }} + {{- end }} + serviceName: {{ template "mimir.fullname" . }}-ingester{{- if not .Values.enterprise.legacyLabels -}}-headless{{- end -}} + {{- if .Values.ingester.persistentVolume.enabled }} + volumeClaimTemplates: + - metadata: + name: storage + {{- if .Values.ingester.persistentVolume.annotations }} + annotations: + {{- toYaml .Values.ingester.persistentVolume.annotations | nindent 10 }} + {{- end }} + spec: + {{- $storageClass := default .Values.ingester.persistentVolume.storageClass $rolloutZone.storageClass }} + {{- if $storageClass }} + {{- if (eq "-" $storageClass) }} + storageClassName: "" + {{- else }} + storageClassName: {{ $storageClass }} + {{- end }} + {{- end }} + accessModes: + {{- toYaml .Values.ingester.persistentVolume.accessModes | nindent 10 }} + resources: + requests: + storage: "{{ .Values.ingester.persistentVolume.size }}" + {{- end }} + template: + metadata: + labels: + {{- include "mimir.podLabels" $args | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" $args | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + {{- with .Values.ingester.schedulerName }} + schedulerName: {{ . | quote }} + {{- end }} + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.ingester.priorityClassName }} + priorityClassName: {{ .Values.ingester.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" $args | nindent 8 }} + {{- with .Values.ingester.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + {{- with $rolloutZone.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with $rolloutZone.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "ingester") | nindent 6 }} + {{- with .Values.ingester.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.ingester.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime + {{- if not .Values.ingester.persistentVolume.enabled }} + - name: storage + emptyDir: {} + {{- end }} + {{- if .Values.ingester.extraVolumes }} + {{ toYaml .Values.ingester.extraVolumes | nindent 8 }} + {{- end }} + - name: active-queries + emptyDir: {} + containers: + {{- if .Values.ingester.extraContainers }} + {{ toYaml .Values.ingester.extraContainers | nindent 8 }} + {{- end }} + - name: ingester + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=ingester" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + {{- if $zoneName }} + - "-ingester.ring.instance-availability-zone={{ $zoneName }}" + {{- else }} + - "-ingester.ring.instance-availability-zone=zone-default" + {{- if .Values.ingester.zoneAwareReplication.migration.enabled }} + - "-blocks-storage.tsdb.flush-blocks-on-shutdown=true" + - "-ingester.ring.unregister-on-shutdown=true" + {{- end }} + - "-server.grpc-max-concurrent-streams=500" + {{- end }} + {{- range $key, $value := .Values.ingester.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.ingester.extraVolumeMounts }} + {{ toYaml .Values.ingester.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + - name: storage + mountPath: "/data" + {{- if .Values.ingester.persistentVolume.subPath }} + subPath: {{ .Values.ingester.persistentVolume.subPath }} + {{- else }} + {{- end }} + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + - name: memberlist + containerPort: {{ include "mimir.memberlistBindPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.ingester.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.ingester.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.ingester.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.ingester.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ingester.env }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.ingester }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ingester.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} +--- +{{ end }} +{{ end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-svc-headless.yaml new file mode 100644 index 0000000..0c5c430 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-svc-headless.yaml @@ -0,0 +1,27 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "ingester") }}-headless + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "ingester" "memberlist" true) | nindent 4 }} + prometheus.io/service-monitor: "false" + {{- with .Values.ingester.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.ingester.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + clusterIP: None + ports: + - port: {{ include "mimir.serverHttpListenPort" .}} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "ingester" "memberlist" true) | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-svc.yaml new file mode 100644 index 0000000..21afa4d --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/ingester/ingester-svc.yaml @@ -0,0 +1,38 @@ +{{- $args := dict "ctx" . "component" "ingester" "memberlist" true -}} +{{- $zonesMap := include "mimir.zoneAwareReplicationMap" $args | fromYaml -}} +{{- range $zoneName, $rolloutZone := $zonesMap }} +{{- with $ -}} +{{- $_ := set $args "rolloutZoneName" $zoneName -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" $args }} + labels: + {{- include "mimir.labels" $args | nindent 4 }} + {{- if and $zoneName .Values.ingester.zoneAwareReplication.migration.enabled }} + # Prevent scraping PODs via this service during migration as the original non zone-aware service already scrapes all PODs and you get duplicate metrics. + prometheus.io/service-monitor: "false" + {{- end }} + {{- with .Values.ingester.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.ingester.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" .}} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" $args | nindent 4 }} + +--- +{{ end }} +{{ end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/ingress.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/ingress.yaml new file mode 100644 index 0000000..97eb406 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/ingress.yaml @@ -0,0 +1,46 @@ +{{- if .Values.ingress.enabled }} +apiVersion: networking.k8s.io/v1 +kind: Ingress +metadata: + name: {{ include "mimir.fullname" . }} + labels: + {{- include "mimir.labels" (dict "ctx" .) | nindent 4 }} + {{- with .Values.ingress.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ .Release.Namespace | quote }} +spec: + {{- with .Values.ingress.ingressClassName }} + ingressClassName: {{ . }} + {{- end -}} + {{- with .Values.ingress.tls }} + tls: + {{- range . }} + - hosts: + {{- range .hosts }} + - {{ tpl . $ | quote }} + {{- end }} + {{- with .secretName }} + secretName: {{ . }} + {{- end }} + {{- end }} + {{- end }} + rules: + {{- range $.Values.ingress.hosts }} + - host: {{ tpl . $ | quote }} + http: + paths: + {{- range $svcName, $paths := $.Values.ingress.paths }} + {{- range $paths }} + - path: {{ .path }} + pathType: {{ .pathType | default "Prefix" }} + backend: + service: + name: {{ include "mimir.fullname" $ }}-{{ $svcName }} + port: + number: {{ include "mimir.serverHttpListenPort" $ }} + {{- end }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/map-to-csv.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/map-to-csv.tpl new file mode 100644 index 0000000..e31974d --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/map-to-csv.tpl @@ -0,0 +1,17 @@ +{{/* +Convert labels to string like: key1=value1, key2=value2, ... +Example: + customHeaders: + X-Scope-OrgID: tenant-1 +becomes: + customHeaders: "X-Scope-OrgID=tenant-1" +Params: + map = map to convert to csv string +*/}} +{{- define "mimir.lib.mapToCSVString" -}} +{{- $list := list -}} +{{- range $k, $v := $.map -}} +{{- $list = append $list (printf "%s=%s" $k $v) -}} +{{- end -}} +{{ join "," $list }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/pdb.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/pdb.tpl new file mode 100644 index 0000000..81239bb --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/pdb.tpl @@ -0,0 +1,23 @@ +{{/* +Mimir common PodDisruptionBudget definition +Params: + ctx = . context + component = name of the component +*/}} +{{- define "mimir.lib.podDisruptionBudget" -}} +{{- $componentSection := include "mimir.componentSectionFromName" . | fromYaml }} +{{ with ($componentSection).podDisruptionBudget }} +apiVersion: {{ include "mimir.podDisruptionBudget.apiVersion" $.ctx }} +kind: PodDisruptionBudget +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $.ctx "component" $.component) }} + labels: + {{- include "mimir.labels" (dict "ctx" $.ctx "component" $.component) | nindent 4 }} + namespace: {{ $.ctx.Release.Namespace | quote }} +spec: + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" $.ctx "component" $.component) | nindent 6 }} +{{ toYaml . | indent 2 }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/podSecurityContext.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/podSecurityContext.tpl new file mode 100644 index 0000000..334c9db --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/podSecurityContext.tpl @@ -0,0 +1,13 @@ +{{/* +Mimir common podSecurityContext +Params: + ctx = . context + component = name of the component +*/}} +{{- define "mimir.lib.podSecurityContext" -}} +{{- $componentSection := include "mimir.componentSectionFromName" . | fromYaml }} +{{- /* Some components have security context in the values.yalm as podSecurityContext and others as securityContext */}} +{{- $podSecurityContextSection := $componentSection.securityContext | default $componentSection.podSecurityContext -}} +{{- $defaultContext := deepCopy .ctx.Values.rbac.podSecurityContext }} +{{- $podSecurityContextSection | mustMergeOverwrite $defaultContext | toYaml -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/service-monitor.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/service-monitor.tpl new file mode 100644 index 0000000..ab0dbb2 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/service-monitor.tpl @@ -0,0 +1,73 @@ +{{/* +Mimir common ServiceMonitor definition +Params: + ctx = . context + component = name of the component + memberlist = true/false, whether component is part of memberlist +*/}} +{{- define "mimir.lib.serviceMonitor" -}} +{{- with .ctx.Values.metaMonitoring.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "mimir.resourceName" $ }} + namespace: {{ .namespace | default $.ctx.Release.Namespace | quote }} + labels: + {{- include "mimir.labels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + namespaceSelector: + {{- if .namespaceSelector }} + {{- toYaml .namespaceSelector | nindent 4 }} + {{- else }} + matchNames: + - {{ $.ctx.Release.Namespace }} + {{- end }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" $ | nindent 6 }} + matchExpressions: + - key: prometheus.io/service-monitor + operator: NotIn + values: + - "false" + endpoints: + - port: http-metrics + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + relabelings: + - sourceLabels: [job] + replacement: "{{ $.ctx.Release.Namespace }}/{{ $.component }}" + targetLabel: job + {{- if kindIs "string" .clusterLabel }} + - replacement: "{{ .clusterLabel | default (include "mimir.clusterName" $.ctx) }}" + targetLabel: cluster + {{- end }} + {{- with .relabelings }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end -}} +{{- end -}} +{{- end -}} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/topologySpreadConstraints.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/topologySpreadConstraints.tpl new file mode 100644 index 0000000..06cea50 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/lib/topologySpreadConstraints.tpl @@ -0,0 +1,21 @@ +{{- define "mimir.lib.topologySpreadConstraints" -}} +{{- $componentSection := include "mimir.componentSectionFromName" . | fromYaml -}} +{{- $topologySpreadConstraintsSection := $componentSection.topologySpreadConstraints -}} +{{- $selectorLabels := include "mimir.selectorLabels" . -}} +{{- if $topologySpreadConstraintsSection -}} +{{- $constraints := kindIs "slice" $topologySpreadConstraintsSection | ternary $topologySpreadConstraintsSection (list $topologySpreadConstraintsSection) -}} +topologySpreadConstraints: +{{- range $constraint := $constraints }} +- maxSkew: {{ $constraint.maxSkew }} + topologyKey: {{ $constraint.topologyKey }} + whenUnsatisfiable: {{ $constraint.whenUnsatisfiable }} + labelSelector: + {{- if $constraint.labelSelector -}} + {{- $constraint.labelSelector | toYaml | nindent 4 -}} + {{- else }} + matchLabels: + {{- $selectorLabels | nindent 6 }} + {{- end -}} +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/license-secret.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/license-secret.yaml new file mode 100644 index 0000000..c992e88 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/license-secret.yaml @@ -0,0 +1,13 @@ +{{- if .Values.enterprise.enabled -}} +{{- if not .Values.license.external }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ tpl .Values.license.secretName . }} + labels: + {{- include "mimir.labels" (dict "ctx" .) | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +data: + license.jwt: {{ .Values.license.contents | b64enc }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/memcached/_memcached-statefulset.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/memcached/_memcached-statefulset.tpl new file mode 100644 index 0000000..0c4bd00 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/memcached/_memcached-statefulset.tpl @@ -0,0 +1,149 @@ +{{/* +memcached StatefulSet +*/}} +{{- define "mimir.memcached.statefulSet" -}} +{{ with (index $.ctx.Values $.component) }} +{{- if .enabled -}} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $.ctx "component" $.component) }} + labels: + {{- include "mimir.labels" (dict "ctx" $.ctx "component" "memcached") | nindent 4 }} + annotations: + {{- toYaml .annotations | nindent 4 }} + namespace: {{ $.ctx.Release.Namespace | quote }} +spec: + podManagementPolicy: {{ .podManagementPolicy }} + replicas: {{ .replicas }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" $.ctx "component" $.component) | nindent 6 }} + updateStrategy: + {{- toYaml .statefulStrategy | nindent 4 }} + serviceName: {{ template "mimir.fullname" $.ctx }}-{{ $.component }} + + template: + metadata: + labels: + {{- include "mimir.podLabels" $ | nindent 8 }} + annotations: + {{- with $.ctx.Values.global.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" $.ctx }} + {{- if .priorityClassName }} + priorityClassName: {{ .priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" $.ctx "component" "memcached") | nindent 8 }} + {{- with .initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" $ | nindent 6 }} + {{- with .tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .terminationGracePeriodSeconds }} + {{- if $.ctx.Values.image.pullSecrets }} + imagePullSecrets: + {{- range $.ctx.Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + {{- if .extraVolumes }} + volumes: + {{- toYaml .extraVolumes | nindent 8 }} + {{- end }} + containers: + {{- if .extraContainers }} + {{ toYaml .extraContainers | nindent 8 }} + {{- end }} + - name: memcached + {{- with $.ctx.Values.memcached.image }} + image: {{ .repository }}:{{ .tag }} + imagePullPolicy: {{ .pullPolicy }} + {{- end }} + resources: + {{- if .resources }} + {{- toYaml .resources | nindent 12 }} + {{- else }} + {{- /* Calculate requested memory as round(allocatedMemory * 1.2). But with integer built-in operators. */}} + {{- $requestMemory := div (add (mul .allocatedMemory 12) 5) 10 }} + limits: + memory: {{ $requestMemory }}Mi + requests: + cpu: 500m + memory: {{ $requestMemory }}Mi + {{- end }} + ports: + - containerPort: {{ .port }} + name: client + args: + - -m {{ .allocatedMemory }} + - --extended=modern,track_sizes{{ with .extraExtendedOptions }},{{ . }}{{ end }} + - -I {{ .maxItemMemory }}m + - -c {{ .connectionLimit }} + - -v + - -u {{ .port }} + {{- range $key, $value := .extraArgs }} + - "-{{ $key }}{{ if $value }} {{ $value }}{{ end }}" + {{- end }} + env: + {{- with $.ctx.Values.global.extraEnv }} + {{ toYaml . | nindent 12 }} + {{- end }} + envFrom: + {{- with $.ctx.Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml $.ctx.Values.memcached.containerSecurityContext | nindent 12 }} + {{- if .extraVolumeMounts }} + volumeMounts: + {{- toYaml .extraVolumeMounts | nindent 12 }} + {{- end }} + + {{- if $.ctx.Values.memcachedExporter.enabled }} + - name: exporter + {{- with $.ctx.Values.memcachedExporter.image }} + image: {{ .repository}}:{{ .tag }} + imagePullPolicy: {{ .pullPolicy }} + {{- end }} + ports: + - containerPort: 9150 + name: http-metrics + args: + - "--memcached.address=localhost:{{ .port }}" + - "--web.listen-address=0.0.0.0:9150" + {{- range $key, $value := $.ctx.Values.memcachedExporter.extraArgs }} + - "--{{ $key }}{{ if $value }}={{ $value }}{{ end }}" + {{- end }} + resources: + {{- toYaml $.ctx.Values.memcachedExporter.resources | nindent 12 }} + securityContext: + {{- toYaml $.ctx.Values.memcachedExporter.containerSecurityContext | nindent 12 }} + {{- if .extraVolumeMounts }} + volumeMounts: + {{- toYaml .extraVolumeMounts | nindent 12 }} + {{- end }} + {{- end }} +{{- end -}} +{{- end -}} +{{- end -}} + diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/memcached/_memcached-svc.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/memcached/_memcached-svc.tpl new file mode 100644 index 0000000..b70862a --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/memcached/_memcached-svc.tpl @@ -0,0 +1,35 @@ +{{/* +memcached Service +*/}} +{{- define "mimir.memcached.service" -}} +{{ with (index $.ctx.Values $.component) }} +{{- if .enabled -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $.ctx "component" $.component) }} + labels: + {{- include "mimir.labels" (dict "ctx" $.ctx "component" $.component) | nindent 4 }} + {{- with .service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .service.annotations | nindent 4 }} + namespace: {{ $.ctx.Release.Namespace | quote }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: memcached-client + port: {{ .port }} + targetPort: {{ .port }} + {{ if $.ctx.Values.memcachedExporter.enabled }} + - name: http-metrics + port: 9150 + targetPort: 9150 + {{ end }} + selector: + {{- include "mimir.selectorLabels" (dict "ctx" $.ctx "component" $.component) | nindent 4 }} +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metadata-cache/metadata-cache-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metadata-cache/metadata-cache-pdb.yaml new file mode 100644 index 0000000..dc03f8e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metadata-cache/metadata-cache-pdb.yaml @@ -0,0 +1,3 @@ +{{- if index .Values "metadata-cache" "enabled" }} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "metadata-cache" ) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metadata-cache/metadata-cache-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metadata-cache/metadata-cache-servmon.yaml new file mode 100644 index 0000000..c6d9139 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metadata-cache/metadata-cache-servmon.yaml @@ -0,0 +1,3 @@ +{{- if index .Values "metadata-cache" "enabled" }} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "metadata-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metadata-cache/metadata-cache-statefulset.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metadata-cache/metadata-cache-statefulset.yaml new file mode 100644 index 0000000..5a73fe4 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metadata-cache/metadata-cache-statefulset.yaml @@ -0,0 +1 @@ +{{- include "mimir.memcached.statefulSet" (dict "ctx" $ "component" "metadata-cache" ) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metadata-cache/metadata-cache-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metadata-cache/metadata-cache-svc-headless.yaml new file mode 100644 index 0000000..5cc5ad6 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metadata-cache/metadata-cache-svc-headless.yaml @@ -0,0 +1 @@ +{{- include "mimir.memcached.service" (dict "ctx" $ "component" "metadata-cache" ) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/_helpers.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/_helpers.tpl new file mode 100644 index 0000000..88008fe --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/_helpers.tpl @@ -0,0 +1,70 @@ +{{- define "mimir.metaMonitoring.metrics.remoteWrite" -}} +{{- $writeBackToMimir := not .url -}} +{{- $url := .url -}} +{{- if $writeBackToMimir -}} +{{- $url = include "mimir.remoteWriteUrl.inCluster" .ctx }} +{{- end -}} +- url: {{ $url }} + {{- if .auth }} + basicAuth: + {{- if .auth.username }} + username: + name: {{ include "mimir.resourceName" (dict "ctx" $.ctx "component" "metrics-instance-usernames") }} + key: {{ .usernameKey | quote }} + {{- end }} + {{- with .auth }} + {{- if and .passwordSecretKey .passwordSecretName }} + password: + name: {{ .passwordSecretName | quote }} + key: {{ .passwordSecretKey | quote }} + {{- else if or .passwordSecretKey .passwordSecretName }}{{ required "Set either both passwordSecretKey and passwordSecretName or neither" nil }} + {{- end }} + {{- end }} + {{- end }} + {{- $headers := .headers -}} + {{- if $writeBackToMimir -}}{{- $_ := set $headers "X-Scope-OrgID" "metamonitoring" -}}{{- end -}} + {{- with $headers }} + headers: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end -}} + +{{- define "mimir.metaMonitoring.logs.client" -}} +{{- if .url }} +- url: {{ .url }} + {{- if .auth }} + {{- if .auth.tenantId }} + tenantId: {{ .auth.tenantId | quote }} + {{- end }} + basicAuth: + {{- if .auth.username }} + username: + name: {{ include "mimir.resourceName" (dict "ctx" $.ctx "component" "logs-instance-usernames") }} + key: {{ .usernameKey | quote }} + {{- end }} + {{- with .auth }} + {{- if and .passwordSecretKey .passwordSecretName }} + password: + name: {{ .passwordSecretName | quote }} + key: {{ .passwordSecretKey | quote }} + {{- else if or .passwordSecretKey .passwordSecretName }} + {{ required "Set either both passwordSecretKey and passwordSecretName or neither" nil }} + {{- end }} + {{- end }} + {{- end }} + externalLabels: + cluster: {{ include "mimir.clusterName" $.ctx | quote}} +{{- end -}} +{{- end -}} + +{{- define "mimir.metaMonitoring.metrics.remoteReadUrl" -}} +{{- with $.ctx.Values.metaMonitoring.grafanaAgent.metrics }} +{{- $writeBackToMimir := not (.remote).url -}} +{{- if $writeBackToMimir -}} +{{- include "mimir.remoteReadUrl.inCluster" $.ctx }} +{{- else -}} +{{- $parsed := urlParse (.remote).url -}} +{{ $parsed.scheme }}://{{ $parsed.host }}/prometheus +{{- end }} +{{- end -}} +{{- end -}} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/grafana-agent-cluster-role-binding.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/grafana-agent-cluster-role-binding.yaml new file mode 100644 index 0000000..47d8cf5 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/grafana-agent-cluster-role-binding.yaml @@ -0,0 +1,19 @@ +{{- with (.Values.metaMonitoring).grafanaAgent }} +{{- if .enabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "grafana-agent") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" $ "component" "meta-monitoring" ) | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "grafana-agent") }} +subjects: + - kind: ServiceAccount + name: {{ include "mimir.serviceAccountName" $ }} + namespace: {{ .namespace | default $.Release.Namespace }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/grafana-agent-cluster-role.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/grafana-agent-cluster-role.yaml new file mode 100644 index 0000000..678d916 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/grafana-agent-cluster-role.yaml @@ -0,0 +1,39 @@ +{{- with (.Values.metaMonitoring).grafanaAgent }} +{{- if .enabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "grafana-agent") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" $ "component" "meta-monitoring" ) | nindent 4 }} +rules: + - apiGroups: + - "" + resources: + - nodes + - nodes/proxy + - nodes/metrics + - services + - endpoints + - pods + - events + verbs: + - get + - list + - watch + - apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch + - nonResourceURLs: + - /metrics + - /metrics/cadvisor + verbs: + - get +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/grafana-agent.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/grafana-agent.yaml new file mode 100644 index 0000000..9d0afaa --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/grafana-agent.yaml @@ -0,0 +1,59 @@ +{{- with (.Values.metaMonitoring).grafanaAgent }} +{{- if .enabled }} +apiVersion: monitoring.grafana.com/v1alpha1 +kind: GrafanaAgent +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "meta-monitoring") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" $ "component" "meta-monitoring" ) | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + serviceAccountName: {{ include "mimir.serviceAccountName" $ }} + {{- with .podSecurityContext }} + securityContext: + {{- . | toYaml | nindent 4 }} + {{- end }} + containers: + # The container specs here are merged with the ones in the operator using a strategic merge patch. + - name: config-reloader + {{- if .imageRepo }}{{ if .imageRepo.configReloader }} + {{- with .imageRepo.configReloader }} + image: {{ .repo }}/{{ .image }}:{{ .tag }} + {{- end }} + {{- end }}{{ end }} + {{- with .containerSecurityContext }} + securityContext: + {{- . | toYaml | nindent 8 }} + {{- end }} + - name: grafana-agent + {{- if .imageRepo }}{{ if .imageRepo.grafanaAgent }} + {{- with .imageRepo.grafanaAgent }} + image: {{ .repo }}/{{ .image }}:{{ .tag }} + {{- end }} + {{- end }}{{ end }} + {{- with .containerSecurityContext }} + securityContext: + {{- . | toYaml | nindent 8 }} + {{- end }} + + logs: + instanceSelector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" $ "component" "meta-monitoring") | nindent 8 }} + # cluster label for logs is added in the LogsInstance + metrics: + scrapeInterval: {{ .metrics.scrapeInterval }} + instanceSelector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" $ "component" "meta-monitoring") | nindent 8 }} + externalLabels: + cluster: {{ include "mimir.clusterName" $ }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/grafana-dashboards.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/grafana-dashboards.yaml new file mode 100644 index 0000000..1b05dbc --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/grafana-dashboards.yaml @@ -0,0 +1,27 @@ +{{- $currentScope := .Values.metaMonitoring.dashboards }} +{{- if $currentScope.enabled }} +{{ range $path, $_ := $.Files.Glob "mixins/dashboards/*.json" }} +{{ $file := $path | base }} +{{ $name := print ($file | trimSuffix ".json") "-dashboard" }} +{{- with $currentScope}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ $name }} + namespace: {{ $.Release.Namespace }} + labels: + {{- include "mimir.labels" (dict "ctx" $) | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +data: + {{ $file }}: |- +{{ $.Files.Get $path | indent 4 }} +--- +{{- end }} +{{ end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/kube-state-metrics-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/kube-state-metrics-servmon.yaml new file mode 100644 index 0000000..d8b82aa --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/kube-state-metrics-servmon.yaml @@ -0,0 +1,49 @@ +{{- if and .Values.metaMonitoring.grafanaAgent.enabled .Values.metaMonitoring.grafanaAgent.metrics.enabled .Values.metaMonitoring.grafanaAgent.metrics.scrapeK8s.enabled }} +{{- with .Values.metaMonitoring.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "k8s-ksm") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" $ "component" "meta-monitoring") | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + endpoints: + - port: {{ $.Values.metaMonitoring.grafanaAgent.metrics.scrapeK8s.kubeStateMetrics.service.port }} + metricRelabelings: + - action: keep + regex: "(^|.*;){{ include "mimir.resourceName" (dict "ctx" $) }}.*" + sourceLabels: + - deployment + - statefulset + - pod + separator: ';' + {{- if kindIs "string" .clusterLabel }} + relabelings: + - targetLabel: cluster + replacement: "{{ .clusterLabel | default (include "mimir.clusterName" $) }}" + {{- end }} + path: /metrics + honorLabels: true # retain namespace label from kube-state-metrics + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with ((((($.Values).metaMonitoring).grafanaAgent).metrics).scrapeK8s).kubeStateMetrics }} + namespaceSelector: + matchNames: + - {{ .namespace }} + selector: + matchLabels: + {{- toYaml .labelSelectors | nindent 6 }} + {{- end -}} +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/kubelet-cadvisor-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/kubelet-cadvisor-servmon.yaml new file mode 100644 index 0000000..0446ce0 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/kubelet-cadvisor-servmon.yaml @@ -0,0 +1,91 @@ +{{- if and .Values.metaMonitoring.grafanaAgent.enabled .Values.metaMonitoring.grafanaAgent.metrics.enabled .Values.metaMonitoring.grafanaAgent.metrics.scrapeK8s.enabled }} +{{- with .Values.metaMonitoring.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "k8s-kubelet-cadvisor") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" $ "component" "meta-monitoring") | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + port: https-metrics + honorLabels: true # retain namespace label from kubelet + relabelings: + - replacement: kubelet # add so that e.g. up{} metric doesn't get clashes with the other endpoint + targetLabel: source + {{- if kindIs "string" .clusterLabel }} + - targetLabel: cluster + replacement: "{{ .clusterLabel | default (include "mimir.clusterName" $) }}" + {{- end }} + {{- with .relabelings }} + {{- toYaml . | nindent 8 }} + {{- end }} + metricRelabelings: + - action: keep + regex: storage-{{ include "mimir.resourceName" (dict "ctx" $) }}.* + sourceLabels: + - persistentvolumeclaim # present on kubelet_volume_stats* metrics + - targetLabel: instance # replace so that the metrics work with the default metrics mixin + sourceLabels: + - node + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + path: /metrics/cadvisor + port: https-metrics + honorLabels: true # retain namespace label from cadvisor + relabelings: + - replacement: cadvisor # add so that e.g. up{} metric doesn't get clashes with the other endpoint + targetLabel: source + - targetLabel: instance # replace so that the metrics work with the default metrics mixin + sourceLabels: + - node + {{- if kindIs "string" .clusterLabel }} + - targetLabel: cluster + replacement: "{{ .clusterLabel | default (include "mimir.clusterName" $) }}" + {{- end }} + {{- with .relabelings }} + {{- toYaml . | nindent 8 }} + {{- end }} + metricRelabelings: + - action: keep + regex: {{ include "mimir.resourceName" (dict "ctx" $) }}.* + sourceLabels: + - pod + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + namespaceSelector: + matchNames: + # "default" is the default namespace in which the operator creates the kubelet service. + - default + selector: + matchLabels: + # This is a service added by the agent operator, so this labels is hardcoded to what the operator creates. + app.kubernetes.io/name: kubelet +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/logs-instance-usernames-secret.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/logs-instance-usernames-secret.yaml new file mode 100644 index 0000000..22e558b --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/logs-instance-usernames-secret.yaml @@ -0,0 +1,17 @@ +{{- if and .Values.metaMonitoring.grafanaAgent.enabled .Values.metaMonitoring.grafanaAgent.logs.enabled }} +{{- with ((.Values.metaMonitoring).grafanaAgent).logs }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "logs-instance-usernames") }} + namespace: {{ (($.Values.metaMonitoring).grafanaAgent).namespace | default $.Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" $ "component" "meta-monitoring") | nindent 4 }} +data: + {{- range $i, $cfg := prepend (.additionalClientConfigs | default list) .remote }} + {{- if (($cfg).auth).username }} + username-{{ $i }}: {{ (($cfg).auth).username | b64enc | quote }} + {{- end }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/logs-instance.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/logs-instance.yaml new file mode 100644 index 0000000..11c47e5 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/logs-instance.yaml @@ -0,0 +1,36 @@ +{{- with (.Values.metaMonitoring).grafanaAgent }} +{{- if and .enabled .logs.enabled }} +apiVersion: monitoring.grafana.com/v1alpha1 +kind: LogsInstance +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "meta-monitoring") }} + namespace: {{ (($.Values.metaMonitoring).grafanaAgent).namespace | default $.Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" $ "component" "meta-monitoring" ) | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + clients: + {{- if or (.logs).additionalClientConfigs (.logs).remote }} + {{- range $i, $cfg := prepend ((.logs).additionalClientConfigs | default list) (.logs).remote }} + {{- with $cfg }} + {{- include "mimir.metaMonitoring.logs.client" (dict "ctx" $ "url" .url "auth" .auth "usernameKey" (printf "username-%d" $i)) | nindent 6 -}} + {{- end }} + {{- end }} + {{- end }} + + # Supply an empty namespace selector to look in all namespaces. Remove + # this to only look in the same namespace as the LogsInstance CR + podLogsNamespaceSelector: {} + + podLogsSelector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" $) | nindent 6 }} + +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/metrics-instance-usernames-secret.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/metrics-instance-usernames-secret.yaml new file mode 100644 index 0000000..bd540fb --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/metrics-instance-usernames-secret.yaml @@ -0,0 +1,19 @@ +{{- with .Values.metaMonitoring.grafanaAgent }} +{{- if and .enabled .metrics.enabled }} +{{- with .metrics }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "metrics-instance-usernames") }} + namespace: {{ $.Values.metaMonitoring.grafanaAgent.namespace | default $.Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" $ "component" "meta-monitoring") | nindent 4 }} +data: + {{- range $i, $cfg := prepend (.additionalRemoteWriteConfigs | default list) .remote }} + {{- if (($cfg).auth).username }} + username-{{ $i }}: {{ $cfg.auth.username | b64enc | quote }} + {{- end }} + {{- end }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/metrics-instance.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/metrics-instance.yaml new file mode 100644 index 0000000..4549ad1 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/metrics-instance.yaml @@ -0,0 +1,36 @@ +{{- with .Values.metaMonitoring.grafanaAgent }} +{{- if and .enabled .metrics.enabled }} +apiVersion: monitoring.grafana.com/v1alpha1 +kind: MetricsInstance +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "meta-monitoring") }} + namespace: {{ $.Values.metaMonitoring.grafanaAgent.namespace | default $.Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" $ "component" "meta-monitoring" ) | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + remoteWrite: + {{- if or (.metrics).additionalRemoteWriteConfigs (.metrics).remote }} + {{- range $i, $cfg := prepend ((.metrics).additionalRemoteWriteConfigs | default list) (.metrics).remote }} + {{- with $cfg }} + {{- include "mimir.metaMonitoring.metrics.remoteWrite" (dict "ctx" $ "url" .url "auth" .auth "usernameKey" (printf "username-%d" $i) "headers" .headers ) | nindent 6 -}} + {{- end }} + {{- end }} + {{- end }} + + # Supply an empty namespace selector to look in all namespaces. Remove + # this to only look in the same namespace as the MetricsInstance CR + serviceMonitorNamespaceSelector: {} + + serviceMonitorSelector: + # Scrape ServiceMonitors from all components + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" $) | nindent 6 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/mixin-alerts.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/mixin-alerts.yaml new file mode 100644 index 0000000..29023f3 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/mixin-alerts.yaml @@ -0,0 +1,20 @@ +{{- with .Values.metaMonitoring.prometheusRule }} +{{- if .mimirAlerts }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "alerts") }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "mimir.labels" (dict "ctx" $) | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} +spec: + {{- $.Files.Get "mixins/alerts.yaml" | nindent 2 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/pod-logs.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/pod-logs.yaml new file mode 100644 index 0000000..78b799d --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/pod-logs.yaml @@ -0,0 +1,45 @@ +{{- with (.Values.metaMonitoring).grafanaAgent }} +{{- if and .enabled .logs.enabled }} +apiVersion: monitoring.grafana.com/v1alpha1 +kind: PodLogs +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "meta-monitoring") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" $ "component" "meta-monitoring") | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + pipelineStages: + - cri: { } + relabelings: + - action: replace # For consistency with metrics + replacement: $1 + separator: / + sourceLabels: + - __meta_kubernetes_namespace + - __meta_kubernetes_pod_container_name + targetLabel: job + - action: replace # Necessary for slow queries dashboard + sourceLabels: + - __meta_kubernetes_pod_container_name + targetLabel: name + - targetLabel: cluster + replacement: {{ include "mimir.clusterName" $ }} + + namespaceSelector: + matchNames: + - {{ $.Release.Namespace | quote }} + + selector: + matchLabels: + # Scrape logs from all components + {{- include "mimir.selectorLabels" (dict "ctx" $) | nindent 6 }} + +{{- end -}} +{{- end -}} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/prometheusrule.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/prometheusrule.yaml new file mode 100644 index 0000000..9af08e8 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/prometheusrule.yaml @@ -0,0 +1,21 @@ +{{- with .Values.metaMonitoring.prometheusRule }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "prometheus-rule") }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "mimir.labels" (dict "ctx" $) | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} +spec: + groups: + {{- toYaml .groups | nindent 4 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/recording-rules.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/recording-rules.yaml new file mode 100644 index 0000000..682236f --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/metamonitoring/recording-rules.yaml @@ -0,0 +1,20 @@ +{{- with .Values.metaMonitoring.prometheusRule }} +{{- if .mimirRules }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "rules") }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "mimir.labels" (dict "ctx" $) | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} +spec: + {{- $.Files.Get "mixins/rules.yaml" | nindent 2 }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/mimir-config.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/mimir-config.yaml new file mode 100644 index 0000000..af72cc8 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/mimir-config.yaml @@ -0,0 +1,21 @@ +{{- if not .Values.useExternalConfig }} +apiVersion: v1 +{{- if eq .Values.configStorageType "Secret" }} +kind: Secret +{{- else }} +kind: ConfigMap +{{- end }} +metadata: + name: {{ tpl .Values.externalConfigSecretName . }} + labels: + {{- include "mimir.labels" (dict "ctx" .) | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +{{- if eq .Values.configStorageType "Secret" }} +data: + mimir.yaml: {{ include "mimir.calculatedConfig" . | b64enc }} +{{- else }} +data: + mimir.yaml: | + {{ include "mimir.calculatedConfig" . | nindent 4 }} +{{- end -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/minio-secrets.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/minio-secrets.yaml new file mode 100644 index 0000000..e646f65 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/minio-secrets.yaml @@ -0,0 +1,13 @@ +{{- if ((.Values.testing).minio).use_secret }} +apiVersion: v1 +kind: Secret +metadata: + name: mimir-minio-secret + labels: + {{- include "mimir.labels" (dict "ctx" .) | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +type: Opaque +data: + MINIO_ROOT_USER: {{ .Values.minio.rootUser | b64enc }} + MINIO_ROOT_PASSWORD: {{ .Values.minio.rootPassword | b64enc }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/minio/create-bucket-job.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/minio/create-bucket-job.yaml new file mode 100644 index 0000000..7750dba --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/minio/create-bucket-job.yaml @@ -0,0 +1,92 @@ +# Minio provides post-install hook to create bucket +# however the hook won't be executed if helm install is run +# with --wait flag. Hence this job is a workaround for that. +# See https://github.com/grafana/mimir/issues/2464 +{{- if .Values.minio.enabled }} +{{- if .Values.minio.buckets }} +apiVersion: batch/v1 +kind: Job +metadata: + {{- $minioSub := index .Subcharts "minio" }} + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "make-minio-buckets") }}-{{ $minioSub.Chart.Version }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }}-make-bucket-job + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +{{- with .Values.minio.makeBucketJob.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} +spec: + template: + metadata: + labels: + app: {{ template "minio.name" . }}-job + release: {{ .Release.Name }} +{{- if .Values.minio.podLabels }} +{{ toYaml .Values.minio.podLabels | indent 8 }} +{{- end }} +{{- if .Values.minio.makeBucketJob.podAnnotations }} + annotations: +{{ toYaml .Values.minio.makeBucketJob.podAnnotations | indent 8 }} +{{- end }} + spec: + restartPolicy: OnFailure +{{- include "minio.imagePullSecrets" . | indent 6 }} +{{- if .Values.minio.nodeSelector }} + nodeSelector: +{{ toYaml .Values.minio.makeBucketJob.nodeSelector | indent 8 }} +{{- end }} +{{- with .Values.minio.makeBucketJob.affinity }} + affinity: +{{ toYaml . | indent 8 }} +{{- end }} +{{- with .Values.minio.makeBucketJob.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} +{{- end }} +{{- if .Values.minio.makeBucketJob.securityContext.enabled }} + securityContext: + runAsUser: {{ .Values.minio.makeBucketJob.securityContext.runAsUser }} + runAsGroup: {{ .Values.minio.makeBucketJob.securityContext.runAsGroup }} + fsGroup: {{ .Values.minio.makeBucketJob.securityContext.fsGroup }} +{{- end }} + volumes: + - name: minio-configuration + projected: + sources: + - configMap: + name: {{ .Release.Name }}-minio + - secret: + name: {{ .Release.Name }}-minio + {{- if .Values.minio.tls.enabled }} + - name: cert-secret-volume-mc + secret: + secretName: {{ .Values.minio.tls.certSecret }} + items: + - key: {{ .Values.minio.tls.publicCrt }} + path: CAs/public.crt + {{ end }} + containers: + - name: minio-mc + image: "{{ .Values.minio.mcImage.repository }}:{{ .Values.minio.mcImage.tag }}" + imagePullPolicy: {{ .Values.minio.mcImage.pullPolicy }} + command: ["/bin/sh", "/config/initialize"] + env: + - name: MINIO_ENDPOINT + value: {{ .Release.Name }}-minio + - name: MINIO_PORT + value: {{ .Values.minio.service.port | quote }} + volumeMounts: + - name: minio-configuration + mountPath: /config + {{- if .Values.minio.tls.enabled }} + - name: cert-secret-volume-mc + mountPath: {{ .Values.minio.configPathmc }}certs + {{ end }} + resources: +{{ toYaml .Values.minio.makeBucketJob.resources | indent 10 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/_helpers.tpl b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/_helpers.tpl new file mode 100644 index 0000000..be55df3 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/_helpers.tpl @@ -0,0 +1,17 @@ +{{/* +nginx auth secret name +*/}} +{{- define "mimir.nginxAuthSecret" -}} +{{ .Values.nginx.basicAuth.existingSecret | default (include "mimir.resourceName" (dict "ctx" . "component" "nginx") ) }} +{{- end }} + +{{/* +Returns the HorizontalPodAutoscaler API version for this version of kubernetes. +*/}} +{{- define "mimir.hpa.version" -}} +{{- if semverCompare ">= 1.23-0" (include "mimir.kubeVersion" .) -}} +autoscaling/v2 +{{- else -}} +autoscaling/v2beta1 +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/ingress.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/ingress.yaml new file mode 100644 index 0000000..1ca7da7 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/ingress.yaml @@ -0,0 +1,48 @@ +{{- if not .Values.enterprise.enabled -}} +{{- if .Values.nginx.enabled -}} +{{- if .Values.nginx.ingress.enabled -}} +apiVersion: networking.k8s.io/v1 +kind: Ingress +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "nginx") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "nginx") | nindent 4 }} + {{- with .Values.nginx.ingress.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ .Release.Namespace | quote }} +spec: + {{- if .Values.nginx.ingress.ingressClassName }} + ingressClassName: {{ .Values.nginx.ingress.ingressClassName }} + {{- end -}} + {{- if .Values.nginx.ingress.tls }} + tls: + {{- range .Values.nginx.ingress.tls }} + - hosts: + {{- range .hosts }} + - {{ . | quote }} + {{- end }} + {{- with .secretName }} + secretName: {{ . }} + {{- end }} + {{- end }} + {{- end }} + rules: + {{- range .Values.nginx.ingress.hosts }} + - host: {{ .host | quote }} + http: + paths: + {{- range .paths }} + - path: {{ .path }} + pathType: {{ .pathType }} + backend: + service: + name: {{ include "mimir.resourceName" (dict "ctx" $ "component" "nginx") }} + port: + number: {{ $.Values.nginx.service.port }} + {{- end }} + {{- end }} +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-configmap.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-configmap.yaml new file mode 100644 index 0000000..2f4ebef --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-configmap.yaml @@ -0,0 +1,14 @@ +{{- if not .Values.enterprise.enabled -}} +{{- if .Values.nginx.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "nginx") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "nginx") | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +data: + nginx.conf: | + {{- tpl .Values.nginx.nginxConfig.file . | nindent 4 }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-dep.yaml new file mode 100644 index 0000000..cc62d8c --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-dep.yaml @@ -0,0 +1,132 @@ +{{- if not .Values.enterprise.enabled -}} +{{- if .Values.nginx.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "nginx") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "nginx") | nindent 4 }} + annotations: + {{- toYaml .Values.nginx.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: +{{- if not .Values.nginx.autoscaling.enabled }} + replicas: {{ .Values.nginx.replicas }} +{{- end }} +{{- with .Values.nginx.deploymentStrategy }} + strategy: +{{ toYaml . | trim | indent 4 }} +{{- end }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "nginx") | nindent 6 }} + template: + metadata: + annotations: + checksum/config: {{ include (print .Template.BasePath "/nginx/nginx-configmap.yaml") . | sha256sum }} + {{- with .Values.global.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.nginx.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "nginx") | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ include "mimir.serviceAccountName" . }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + {{- if .Values.nginx.priorityClassName }} + priorityClassName: {{ .Values.nginx.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "nginx") | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.nginx.terminationGracePeriodSeconds }} + containers: + - name: nginx + image: {{ .Values.nginx.image.registry }}/{{ .Values.nginx.image.repository }}:{{ .Values.nginx.image.tag }} + imagePullPolicy: {{ .Values.nginx.image.pullPolicy }} + {{- with .Values.nginx.extraArgs }} + args: + {{- range $key, $value := . }} + - "-{{ $key }} {{ $value }}" + {{- end }} + {{- end }} + ports: + - name: http-metric + containerPort: 8080 + protocol: TCP + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.nginx.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.nginx.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + readinessProbe: + {{- toYaml .Values.nginx.readinessProbe | nindent 12 }} + securityContext: + {{- toYaml .Values.nginx.containerSecurityContext | nindent 12 }} + volumeMounts: + - name: config + mountPath: /etc/nginx/nginx.conf + subPath: nginx.conf + {{- if .Values.nginx.basicAuth.enabled }} + - name: auth + mountPath: /etc/nginx/secrets + {{- end }} + - name: tmp + mountPath: /tmp + - name: docker-entrypoint-d-override + mountPath: /docker-entrypoint.d + {{- if .Values.nginx.extraVolumeMounts }} + {{- toYaml .Values.nginx.extraVolumeMounts | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.nginx.resources | nindent 12 }} + {{- if .Values.nginx.extraContainers }} + {{- toYaml .Values.nginx.extraContainers | nindent 8}} + {{- end }} + {{- with .Values.nginx.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "nginx") | nindent 6 }} + {{- with .Values.nginx.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.nginx.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + configMap: + name: {{ include "mimir.fullname" . }}-nginx + {{- if .Values.nginx.basicAuth.enabled }} + - name: auth + secret: + secretName: {{ include "mimir.nginxAuthSecret" . }} + {{- end }} + - name: tmp + emptyDir: {} + - name: docker-entrypoint-d-override + emptyDir: {} + {{- if .Values.nginx.extraVolumes }} + {{- toYaml .Values.nginx.extraVolumes | nindent 8 }} + {{- end }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-pdb.yaml new file mode 100644 index 0000000..712a665 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-pdb.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.nginx.enabled (not .Values.enterprise.enabled) -}} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "nginx") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-secret.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-secret.yaml new file mode 100644 index 0000000..3bb1d01 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-secret.yaml @@ -0,0 +1,14 @@ +{{- if not .Values.enterprise.enabled -}} +{{- if and .Values.nginx.enabled .Values.nginx.basicAuth.enabled (not .Values.nginx.basicAuth.existingSecret) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "nginx") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "nginx") | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +stringData: + .htpasswd: | + {{- tpl .Values.nginx.basicAuth.htpasswd $ | nindent 4 }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-svc.yaml new file mode 100644 index 0000000..1cad15b --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-svc.yaml @@ -0,0 +1,34 @@ +{{- if not .Values.enterprise.enabled -}} +{{- if .Values.nginx.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "nginx") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "nginx") | nindent 4 }} + {{- with .Values.nginx.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.nginx.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: {{ .Values.nginx.service.type }} + {{- with .Values.nginx.service.clusterIP }} + clusterIP: {{ . }} + {{- end }} + {{- if and (eq "LoadBalancer" .Values.nginx.service.type) .Values.nginx.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.nginx.service.loadBalancerIP }} + {{- end }} + ports: + - name: http-metric + port: {{ .Values.nginx.service.port }} + targetPort: http-metric + {{- if and (eq "NodePort" .Values.nginx.service.type) .Values.nginx.service.nodePort }} + nodePort: {{ .Values.nginx.service.nodePort }} + {{- end }} + protocol: TCP + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "nginx") | nindent 4 }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-v2-hpa.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-v2-hpa.yaml new file mode 100644 index 0000000..3b7e022 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-v2-hpa.yaml @@ -0,0 +1,37 @@ +{{- if not .Values.enterprise.enabled -}} +{{- if .Values.nginx.autoscaling.enabled }} +{{- if eq (include "mimir.hpa.version" .) "autoscaling/v2" }} +apiVersion: autoscaling/v2 +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "nginx") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "nginx") | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "nginx") }} + minReplicas: {{ .Values.nginx.autoscaling.minReplicas }} + maxReplicas: {{ .Values.nginx.autoscaling.maxReplicas }} + metrics: + {{- with .Values.nginx.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + target: + type: Utilization + averageUtilization: {{ . }} + {{- end }} + {{- with .Values.nginx.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + target: + type: Utilization + averageUtilization: {{ . }} + {{- end }} +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-v2beta1-hpa.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-v2beta1-hpa.yaml new file mode 100644 index 0000000..9ce76db --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/nginx-v2beta1-hpa.yaml @@ -0,0 +1,33 @@ +{{- if not .Values.enterprise.enabled -}} +{{- if .Values.nginx.autoscaling.enabled }} +{{- if eq (include "mimir.hpa.version" .) "autoscaling/v2beta1" }} +apiVersion: autoscaling/v2beta1 +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "nginx") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "nginx") | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "nginx") }} + minReplicas: {{ .Values.nginx.autoscaling.minReplicas }} + maxReplicas: {{ .Values.nginx.autoscaling.maxReplicas }} + metrics: + {{- with .Values.nginx.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + targetAverageUtilization: {{ . }} + {{- end }} + {{- with .Values.nginx.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + targetAverageUtilization: {{ . }} + {{- end }} +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/route.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/route.yaml new file mode 100644 index 0000000..4eb3645 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/nginx/route.yaml @@ -0,0 +1,25 @@ +{{- if .Values.nginx.route.enabled }} +kind: Route +apiVersion: route.openshift.io/v1 +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "nginx") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "nginx") | nindent 4 }} + {{- with .Values.nginx.route.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ .Release.Namespace | quote }} +spec: + host: {{ .Values.nginx.route.host }} + to: + kind: Service + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "nginx") }} + weight: 100 + port: + targetPort: http-metric +{{- if .Values.nginx.route.tls }} + tls: + {{- toYaml .Values.nginx.route.tls | nindent 4 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/overrides-exporter/overrides-exporter-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/overrides-exporter/overrides-exporter-dep.yaml new file mode 100644 index 0000000..19b4142 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/overrides-exporter/overrides-exporter-dep.yaml @@ -0,0 +1,139 @@ +{{- if .Values.overrides_exporter.enabled -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + annotations: + {{- toYaml .Values.overrides_exporter.annotations | nindent 4 }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "overrides-exporter") | nindent 4 }} + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "overrides-exporter") }} + namespace: {{ .Release.Namespace | quote }} +spec: + replicas: {{ .Values.overrides_exporter.replicas }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "overrides-exporter") | nindent 6 }} + strategy: + {{- toYaml .Values.overrides_exporter.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "overrides-exporter") | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "overrides-exporter") | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.overrides_exporter.priorityClassName }} + priorityClassName: {{ .Values.overrides_exporter.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "overrides-exporter") | nindent 8 }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.overrides_exporter.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: overrides-exporter + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=overrides-exporter" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + {{- range $key, $value := .Values.overrides_exporter.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.overrides_exporter.extraVolumeMounts }} + {{ toYaml .Values.overrides_exporter.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + - name: storage + mountPath: "/data" + subPath: {{ .Values.overrides_exporter.persistence.subPath }} + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.overrides_exporter.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.overrides_exporter.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.overrides_exporter.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.overrides_exporter.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.overrides_exporter.env }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.overrides_exporter }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.overrides_exporter.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.overrides_exporter.extraContainers }} + {{ toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.overrides_exporter.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.overrides_exporter.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "overrides-exporter") | nindent 6 }} + {{- with .Values.overrides_exporter.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.overrides_exporter.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime + {{- if .Values.overrides_exporter.extraVolumes }} + {{ toYaml .Values.overrides_exporter.extraVolumes | nindent 8}} + {{- end }} + - name: storage + emptyDir: {} + - name: active-queries + emptyDir: {} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/overrides-exporter/overrides-exporter-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/overrides-exporter/overrides-exporter-pdb.yaml new file mode 100644 index 0000000..ab30728 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/overrides-exporter/overrides-exporter-pdb.yaml @@ -0,0 +1,3 @@ +{{- if .Values.overrides_exporter.enabled -}} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "overrides-exporter") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/overrides-exporter/overrides-exporter-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/overrides-exporter/overrides-exporter-servmon.yaml new file mode 100644 index 0000000..809d0e7 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/overrides-exporter/overrides-exporter-servmon.yaml @@ -0,0 +1,3 @@ +{{- if .Values.overrides_exporter.enabled -}} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "overrides-exporter") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/overrides-exporter/overrides-exporter-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/overrides-exporter/overrides-exporter-svc.yaml new file mode 100644 index 0000000..5e42a7f --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/overrides-exporter/overrides-exporter-svc.yaml @@ -0,0 +1,27 @@ +{{- if .Values.overrides_exporter.enabled -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "overrides-exporter") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "overrides-exporter") | nindent 4 }} + {{- with .Values.overrides_exporter.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.overrides_exporter.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" .}} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "overrides-exporter") | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/podsecuritypolicy.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/podsecuritypolicy.yaml new file mode 100644 index 0000000..f9113d3 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/podsecuritypolicy.yaml @@ -0,0 +1,45 @@ +{{- if eq (include "mimir.rbac.usePodSecurityPolicy" .) "true" }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" .) }} + labels: + {{- include "mimir.labels" (dict "ctx" .) | nindent 4 }} + annotations: + "seccomp.security.alpha.kubernetes.io/allowedProfileNames": {{ .Values.rbac.podSecurityPolicy.seccompProfile }} +spec: + privileged: {{ .Values.rbac.podSecurityPolicy.privileged }} + allowPrivilegeEscalation: {{ .Values.rbac.podSecurityPolicy.allowPrivilegeEscalation }} + volumes: + - 'configMap' + - 'emptyDir' + - 'persistentVolumeClaim' + - 'secret' + {{- range $volumes := .Values.rbac.podSecurityPolicy.additionalVolumes }} + - '{{ $volumes }}' + {{- end }} + hostNetwork: {{ .Values.rbac.podSecurityPolicy.hostNetwork }} + hostIPC: {{ .Values.rbac.podSecurityPolicy.hostIPC }} + hostPID: {{ .Values.rbac.podSecurityPolicy.hostPID }} + runAsUser: + rule: {{ .Values.rbac.podSecurityPolicy.runAsUser.rule }} + seLinux: + rule: {{ .Values.rbac.podSecurityPolicy.seLinux.rule }} + supplementalGroups: + rule: {{ .Values.rbac.podSecurityPolicy.supplementalGroups.rule }} + ranges: + {{- range $range := .Values.rbac.podSecurityPolicy.supplementalGroups.ranges }} + - min: {{ $range.min }} + max: {{ $range.max }} + {{- end }} + fsGroup: + rule: {{ .Values.rbac.podSecurityPolicy.fsGroup.rule }} + ranges: + {{- range $range := .Values.rbac.podSecurityPolicy.fsGroup.ranges }} + - min: {{ $range.min }} + max: {{ $range.max }} + {{- end }} + readOnlyRootFilesystem: {{ .Values.rbac.podSecurityPolicy.readOnlyRootFilesystem }} + requiredDropCapabilities: + - ALL +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-dep.yaml new file mode 100644 index 0000000..b9c6dbd --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-dep.yaml @@ -0,0 +1,162 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "querier") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "querier" "memberlist" true) | nindent 4 }} + annotations: + {{- toYaml .Values.querier.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + {{- if or (not .Values.querier.kedaAutoscaling.enabled) (.Values.querier.kedaAutoscaling.preserveReplicas) }} + # If replicas is not number (when using values file it's float64, when using --set arg it's int64) and is false (i.e. null) don't set it + {{- if or (or (kindIs "int64" .Values.querier.replicas) (kindIs "float64" .Values.querier.replicas)) (.Values.querier.replicas) }} + replicas: {{ .Values.querier.replicas }} + {{- end }} + {{- end }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "querier" "memberlist" true) | nindent 6 }} + strategy: + {{- toYaml .Values.querier.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "querier" "memberlist" true) | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "querier") | nindent 8 }} + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.querier.priorityClassName }} + priorityClassName: {{ .Values.querier.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "querier") | nindent 8 }} + {{- with .Values.querier.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end}} + {{- end }} + containers: + - name: querier + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=querier" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + {{- if .Values.ingester.zoneAwareReplication.migration.enabled }} + {{- if not .Values.ingester.zoneAwareReplication.migration.readPath }} + - "-ingester.ring.zone-awareness-enabled=false" + {{- end }} + {{- end }} + {{- if .Values.store_gateway.zoneAwareReplication.migration.enabled }} + {{- if not .Values.store_gateway.zoneAwareReplication.migration.readPath }} + - "-store-gateway.sharding-ring.prefix=collectors/" + - "-store-gateway.sharding-ring.zone-awareness-enabled=false" + {{- end }} + {{- end }} + {{- range $key, $value := .Values.querier.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.querier.extraVolumeMounts }} + {{ toYaml .Values.querier.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + - name: storage + mountPath: "/data" + subPath: {{ .Values.querier.persistence.subPath }} + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + - name: memberlist + containerPort: {{ include "mimir.memberlistBindPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.querier.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.querier.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.querier.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.querier.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.querier.env }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- $cpu_request := dig "requests" "cpu" nil .Values.querier.resources }} + {{- if $cpu_request }} + {{- $cpu_request_doubled := include "mimir.parseCPU" (dict "value" $cpu_request) | float64 | mulf 2 | ceil }} + {{- $cpu_request_plus_four := include "mimir.parseCPU" (dict "value" $cpu_request) | float64 | addf 4 | ceil }} + - name: "GOMAXPROCS" + value: {{ max $cpu_request_doubled $cpu_request_plus_four | toString | toYaml }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.querier }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.querier.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} +{{- if .Values.querier.extraContainers }} +{{ toYaml .Values.querier.extraContainers | indent 8}} +{{- end }} + {{- with .Values.querier.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.affinity}} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "querier") | nindent 6 }} + {{- with .Values.querier.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.querier.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime +{{- if .Values.querier.extraVolumes }} +{{ toYaml .Values.querier.extraVolumes | indent 8}} +{{- end }} + - name: storage + emptyDir: {} + - name: active-queries + emptyDir: {} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-pdb.yaml new file mode 100644 index 0000000..07ed28d --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-pdb.yaml @@ -0,0 +1 @@ +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "querier" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-servmon.yaml new file mode 100644 index 0000000..516603c --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-servmon.yaml @@ -0,0 +1 @@ +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "querier" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-so.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-so.yaml new file mode 100644 index 0000000..6649ced --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-so.yaml @@ -0,0 +1,47 @@ +{{- if .Values.querier.kedaAutoscaling.enabled }} +{{- if not .Values.query_scheduler.enabled }} +{{- fail "KEDA autoscaling for querier requires query scheduler to be enabled" }} +{{- end }} +apiVersion: keda.sh/v1alpha1 +kind: ScaledObject +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "querier") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "querier") | nindent 4 }} + annotations: + {{- toYaml .Values.querier.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + advanced: + horizontalPodAutoscalerConfig: + {{- with .Values.querier.kedaAutoscaling.behavior }} + behavior: + {{- toYaml . | nindent 8 }} + {{- end }} + maxReplicaCount: {{ .Values.querier.kedaAutoscaling.maxReplicaCount }} + minReplicaCount: {{ .Values.querier.kedaAutoscaling.minReplicaCount }} + pollingInterval: {{ .Values.kedaAutoscaling.pollingInterval }} + scaleTargetRef: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "querier") }} + apiVersion: apps/v1 + kind: Deployment + triggers: + - metadata: + query: sum(max_over_time(cortex_query_scheduler_inflight_requests{container="query-scheduler",namespace="{{ .Release.Namespace }}",quantile="0.5"}[1m])) + serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }} + threshold: {{ .Values.querier.kedaAutoscaling.querySchedulerInflightRequestsThreshold | quote }} + {{- if .Values.kedaAutoscaling.customHeaders }} + customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }} + {{- end }} + name: cortex_querier_hpa_default + type: prometheus + - metadata: + query: sum(rate(cortex_querier_request_duration_seconds_sum{container="querier",namespace="{{ .Release.Namespace }}"}[1m])) + serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }} + threshold: {{ .Values.querier.kedaAutoscaling.querySchedulerInflightRequestsThreshold | quote }} + {{- if .Values.kedaAutoscaling.customHeaders }} + customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }} + {{- end }} + name: cortex_querier_hpa_default_requests_duration + type: prometheus +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-svc.yaml new file mode 100644 index 0000000..1eb323e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/querier/querier-svc.yaml @@ -0,0 +1,25 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "querier") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "querier" "memberlist" true) | nindent 4 }} + {{- with .Values.querier.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.querier.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" .}} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "querier" "memberlist" true) | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-dep.yaml new file mode 100644 index 0000000..132ab1d --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-dep.yaml @@ -0,0 +1,147 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "query-frontend") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "query-frontend") | nindent 4 }} + annotations: + {{- toYaml .Values.query_frontend.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + {{- if or (not .Values.query_frontend.kedaAutoscaling.enabled) (.Values.query_frontend.kedaAutoscaling.preserveReplicas) }} + # If replicas is not number (when using values file it's float64, when using --set arg it's int64) and is false (i.e. null) don't set it + {{- if or (or (kindIs "int64" .Values.query_frontend.replicas) (kindIs "float64" .Values.query_frontend.replicas)) (.Values.query_frontend.replicas) }} + replicas: {{ .Values.query_frontend.replicas }} + {{- end }} + {{- end }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "query-frontend") | nindent 6 }} + strategy: + {{- toYaml .Values.query_frontend.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "query-frontend") | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "query-frontend") | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.query_frontend.priorityClassName }} + priorityClassName: {{ .Values.query_frontend.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "query-frontend") | nindent 8 }} + {{- with .Values.query_frontend.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end}} + {{- end }} + containers: + - name: query-frontend + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=query-frontend" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + # Reduce the likelihood of queries hitting terminated query-frontends. + - "-server.grpc.keepalive.max-connection-age=30s" + - "-shutdown-delay=90s" + {{- range $key, $value := .Values.query_frontend.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.query_frontend.extraVolumeMounts }} + {{ toYaml .Values.query_frontend.extraVolumeMounts | nindent 12}} + {{- end }} + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + - name: config + mountPath: /etc/mimir + - name: storage + mountPath: /data + {{- if .Values.query_frontend.persistence.subPath }} + subPath: {{ .Values.query_frontend.persistence.subPath }} + {{- end }} + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.query_frontend.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.query_frontend.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.query_frontend.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.query_frontend.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.query_frontend.env }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.query_frontend }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.query_frontend.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} +{{- if .Values.query_frontend.extraContainers }} +{{ toYaml .Values.query_frontend.extraContainers | indent 8}} +{{- end }} + {{- with .Values.query_frontend.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.query_frontend.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "query-frontend") | nindent 6 }} + {{- with .Values.query_frontend.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.query_frontend.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime +{{- if .Values.query_frontend.extraVolumes }} +{{ toYaml .Values.query_frontend.extraVolumes | indent 8}} +{{- end }} + - name: storage + emptyDir: {} + - name: active-queries + emptyDir: {} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-pdb.yaml new file mode 100644 index 0000000..e6cb8e1 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-pdb.yaml @@ -0,0 +1 @@ +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "query-frontend") }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-servmon.yaml new file mode 100644 index 0000000..0b2585f --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-servmon.yaml @@ -0,0 +1 @@ +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "query-frontend") }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-so.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-so.yaml new file mode 100644 index 0000000..2ed9502 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-so.yaml @@ -0,0 +1,44 @@ +{{- if .Values.query_frontend.kedaAutoscaling.enabled }} +apiVersion: keda.sh/v1alpha1 +kind: ScaledObject +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "query-frontend") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "query-frontend") | nindent 4 }} + annotations: + {{- toYaml .Values.query_frontend.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + advanced: + horizontalPodAutoscalerConfig: + {{- with .Values.query_frontend.kedaAutoscaling.behavior }} + behavior: + {{- toYaml . | nindent 8 }} + {{- end }} + maxReplicaCount: {{ .Values.query_frontend.kedaAutoscaling.maxReplicaCount }} + minReplicaCount: {{ .Values.query_frontend.kedaAutoscaling.minReplicaCount }} + pollingInterval: {{ .Values.kedaAutoscaling.pollingInterval }} + scaleTargetRef: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "query-frontend") }} + apiVersion: apps/v1 + kind: Deployment + triggers: + - metadata: + query: max_over_time(sum(sum by (pod) (rate(container_cpu_usage_seconds_total{container="query-frontend",namespace="{{ .Release.Namespace }}"}[5m])) and max by (pod) (up{container="query-frontend",namespace="{{ .Release.Namespace }}"}) > 0)[15m:]) * 1000 + serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }} + {{- $cpu_request := dig "requests" "cpu" nil .Values.query_frontend.resources }} + threshold: {{ mulf (include "mimir.cpuToMilliCPU" (dict "value" $cpu_request)) (divf .Values.query_frontend.kedaAutoscaling.targetCPUUtilizationPercentage 100) | floor | int64 | quote }} + {{- if .Values.kedaAutoscaling.customHeaders }} + customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }} + {{- end }} + type: prometheus + - metadata: + query: max_over_time(sum((sum by (pod) (container_memory_working_set_bytes{container="query-frontend",namespace="{{ .Release.Namespace }}"}) and max by (pod) (up{container="query-frontend",namespace="{{ .Release.Namespace }}"}) > 0) or vector(0))[15m:]) + sum(sum by (pod) (max_over_time(kube_pod_container_resource_requests{container="query-frontend",namespace="{{ .Release.Namespace }}", resource="memory"}[15m])) and max by (pod) (changes(kube_pod_container_status_restarts_total{container="query-frontend",namespace="{{ .Release.Namespace }}"}[15m]) > 0) and max by (pod) (kube_pod_container_status_last_terminated_reason{container="query-frontend",namespace="{{ .Release.Namespace }}", reason="OOMKilled"}) or vector(0)) + serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }} + {{- $mem_request := dig "requests" "memory" nil .Values.query_frontend.resources }} + threshold: {{ mulf (include "mimir.siToBytes" (dict "value" $mem_request)) (divf .Values.query_frontend.kedaAutoscaling.targetMemoryUtilizationPercentage 100) | floor | int64 | quote }} + {{- if .Values.kedaAutoscaling.customHeaders }} + customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }} + {{- end }} + type: prometheus +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-svc-headless.yaml new file mode 100644 index 0000000..b30e7f8 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-svc-headless.yaml @@ -0,0 +1,30 @@ +{{- if not .Values.query_scheduler.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "query-frontend") }}-headless + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "query-frontend") | nindent 4 }} + prometheus.io/service-monitor: "false" + {{- with .Values.query_frontend.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.query_frontend.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + clusterIP: None + publishNotReadyAddresses: true + ports: + - port: {{ include "mimir.serverHttpListenPort" .}} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "query-frontend") | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-svc.yaml new file mode 100644 index 0000000..3eec5d6 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-frontend/query-frontend-svc.yaml @@ -0,0 +1,25 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "query-frontend") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "query-frontend") | nindent 4 }} + {{- with .Values.query_frontend.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.query_frontend.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" .}} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "query-frontend") | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-dep.yaml new file mode 100644 index 0000000..e763019 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-dep.yaml @@ -0,0 +1,140 @@ +{{- if .Values.query_scheduler.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "query-scheduler") }} + namespace: {{ .Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "query-scheduler") | nindent 4 }} + annotations: + {{- toYaml .Values.query_scheduler.annotations | nindent 4 }} +spec: + replicas: {{ .Values.query_scheduler.replicas }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "query-scheduler") | nindent 6 }} + strategy: + {{- toYaml .Values.query_scheduler.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "query-scheduler") | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "query-scheduler") | nindent 8 }} + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.query_scheduler.priorityClassName }} + priorityClassName: {{ .Values.query_scheduler.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "query-scheduler") | nindent 8 }} + {{- with .Values.query_scheduler.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end}} + {{- end }} + containers: + - name: query-scheduler + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=query-scheduler" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + {{- range $key, $value := .Values.query_scheduler.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.query_scheduler.extraVolumeMounts }} + {{ toYaml .Values.query_scheduler.extraVolumeMounts | nindent 12}} + {{- end }} + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + - name: config + mountPath: /etc/mimir + - name: storage + mountPath: /data + {{- if .Values.query_scheduler.persistence.subPath }} + subPath: {{ .Values.query_scheduler.persistence.subPath }} + {{- end }} + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.query_scheduler.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.query_scheduler.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.query_scheduler.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.query_scheduler.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.query_scheduler.env }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.query_scheduler }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.query_scheduler.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} +{{- if .Values.query_scheduler.extraContainers }} +{{ toYaml .Values.query_scheduler.extraContainers | indent 8}} +{{- end }} + {{- with .Values.query_scheduler.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.query_scheduler.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "query-scheduler") | nindent 6 }} + {{- with .Values.query_scheduler.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.query_scheduler.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime +{{- if .Values.query_scheduler.extraVolumes }} +{{ toYaml .Values.query_scheduler.extraVolumes | indent 8}} +{{- end }} + - name: storage + emptyDir: {} + - name: active-queries + emptyDir: {} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-pdb.yaml new file mode 100644 index 0000000..f38e16f --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-pdb.yaml @@ -0,0 +1,3 @@ +{{- if .Values.query_scheduler.podDisruptionBudget -}} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "query-scheduler") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-servmon.yaml new file mode 100644 index 0000000..f20a68a --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-servmon.yaml @@ -0,0 +1,3 @@ +{{- if .Values.query_scheduler.enabled }} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "query-scheduler") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-svc-headless.yaml new file mode 100644 index 0000000..c02dba7 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-svc-headless.yaml @@ -0,0 +1,30 @@ +{{- if .Values.query_scheduler.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "query-scheduler") }}-headless + namespace: {{ .Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "query-scheduler") | nindent 4 }} + prometheus.io/service-monitor: "false" + {{- with .Values.query_scheduler.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.query_scheduler.service.annotations | nindent 4 }} +spec: + type: ClusterIP + clusterIP: None + publishNotReadyAddresses: true + ports: + - port: {{ include "mimir.serverHttpListenPort" .}} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "query-scheduler") | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-svc.yaml new file mode 100644 index 0000000..abef45e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/query-scheduler/query-scheduler-svc.yaml @@ -0,0 +1,27 @@ +{{- if .Values.query_scheduler.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "query-scheduler") }} + namespace: {{ .Release.Namespace | quote }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "query-scheduler") | nindent 4 }} + {{- with .Values.query_scheduler.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.query_scheduler.service.annotations | nindent 4 }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" .}} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "query-scheduler") | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/results-cache/results-cache-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/results-cache/results-cache-pdb.yaml new file mode 100644 index 0000000..097cff9 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/results-cache/results-cache-pdb.yaml @@ -0,0 +1,3 @@ +{{- if index .Values "results-cache" "enabled" }} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "results-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/results-cache/results-cache-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/results-cache/results-cache-servmon.yaml new file mode 100644 index 0000000..6b14392 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/results-cache/results-cache-servmon.yaml @@ -0,0 +1,3 @@ +{{- if index .Values "results-cache" "enabled" }} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "results-cache") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/results-cache/results-cache-statefulset.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/results-cache/results-cache-statefulset.yaml new file mode 100644 index 0000000..8689c85 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/results-cache/results-cache-statefulset.yaml @@ -0,0 +1 @@ +{{- include "mimir.memcached.statefulSet" (dict "ctx" $ "component" "results-cache" ) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/results-cache/results-cache-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/results-cache/results-cache-svc-headless.yaml new file mode 100644 index 0000000..1cdec33 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/results-cache/results-cache-svc-headless.yaml @@ -0,0 +1 @@ +{{- include "mimir.memcached.service" (dict "ctx" $ "component" "results-cache" ) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/role.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/role.yaml new file mode 100644 index 0000000..8e1eff7 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/role.yaml @@ -0,0 +1,28 @@ +{{- $usePSP := (eq (include "mimir.rbac.usePodSecurityPolicy" .) "true") }} +{{- $useSCC := (eq (include "mimir.rbac.useSecurityContextConstraints" .) "true") }} +{{- if or $usePSP $useSCC }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" .) }} + labels: + {{- include "mimir.labels" (dict "ctx" .) | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +rules: +{{- if $usePSP }} +- apiGroups: ['extensions'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: [{{ include "mimir.resourceName" (dict "ctx" .) }}] +{{- end }} +{{- if $useSCC }} +- apiGroups: + - security.openshift.io + resources: + - securitycontextconstraints + verbs: + - use + resourceNames: + - {{ include "mimir.resourceName" (dict "ctx" .) }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/rolebinding.yaml new file mode 100644 index 0000000..7450540 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/rolebinding.yaml @@ -0,0 +1,26 @@ +{{- $usePSP := (eq (include "mimir.rbac.usePodSecurityPolicy" .) "true") }} +{{- $useSCC := (eq (include "mimir.rbac.useSecurityContextConstraints" .) "true") }} +{{- if or $usePSP $useSCC }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" .) }} + labels: + {{- include "mimir.labels" (dict "ctx" .) | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "mimir.resourceName" (dict "ctx" .) }} +subjects: +- kind: ServiceAccount + name: {{ template "mimir.serviceAccountName" . }} +{{- if .Values.rollout_operator.enabled }} +- kind: ServiceAccount + name: {{ include "rollout-operator.serviceAccountName" . }} +{{- end }} +{{- if .Values.ruler.serviceAccount.create }} +- kind: ServiceAccount + name: {{ template "mimir.ruler.serviceAccountName" . }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-dep.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-dep.yaml new file mode 100644 index 0000000..7169196 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-dep.yaml @@ -0,0 +1,159 @@ +{{- if .Values.ruler.enabled -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "ruler") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "ruler" "memberlist" true) | nindent 4 }} + annotations: + {{- toYaml .Values.ruler.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + {{- if or (not .Values.ruler.kedaAutoscaling.enabled) (.Values.ruler.kedaAutoscaling.preserveReplicas) }} + replicas: {{ .Values.ruler.replicas }} + {{- end }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "ruler" "memberlist" true) | nindent 6 }} + strategy: + {{- toYaml .Values.ruler.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "ruler" "memberlist" true) | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "ruler") | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "mimir.ruler.serviceAccountName" . }} + {{- if .Values.ruler.priorityClassName }} + priorityClassName: {{ .Values.ruler.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "ruler") | nindent 8 }} + {{- with .Values.ruler.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end}} + {{- end }} + containers: + - name: ruler + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=ruler" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + - "-distributor.remote-timeout=10s" + {{- if .Values.ingester.zoneAwareReplication.migration.enabled }} + {{- if not .Values.ingester.zoneAwareReplication.migration.writePath }} + - "-ingester.ring.zone-awareness-enabled=false" + {{- end }} + {{- if .Values.ingester.zoneAwareReplication.migration.excludeDefaultZone }} + - "-ingester.ring.excluded-zones=zone-default" + {{- end }} + {{- end }} + {{- if .Values.store_gateway.zoneAwareReplication.migration.enabled }} + {{- if not .Values.store_gateway.zoneAwareReplication.migration.readPath }} + - "-store-gateway.sharding-ring.prefix=collectors/" + - "-store-gateway.sharding-ring.zone-awareness-enabled=false" + {{- end }} + {{- end }} + {{- range $key, $value := .Values.ruler.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.ruler.extraVolumeMounts }} + {{ toYaml .Values.ruler.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + - name: storage + mountPath: "/data" + subPath: {{ .Values.ruler.persistence.subPath }} + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + - name: memberlist + containerPort: {{ include "mimir.memberlistBindPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.ruler.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.ruler.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.ruler.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.ruler.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ruler.env }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.ruler }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ruler.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} +{{- if .Values.ruler.extraContainers }} +{{ toYaml .Values.ruler.extraContainers | indent 8}} +{{- end }} + {{- with .Values.ruler.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ruler.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "ruler") | nindent 6 }} + {{- with .Values.ruler.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.ruler.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime +{{- if .Values.ruler.extraVolumes }} +{{ toYaml .Values.ruler.extraVolumes | indent 8}} +{{- end }} + - name: storage + emptyDir: {} + - name: active-queries + emptyDir: {} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-pdb.yaml new file mode 100644 index 0000000..4693d45 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-pdb.yaml @@ -0,0 +1,3 @@ +{{- if .Values.ruler.enabled -}} +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "ruler" "memberlist" true) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-sa.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-sa.yaml new file mode 100644 index 0000000..8993cf1 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-sa.yaml @@ -0,0 +1,14 @@ +{{- if .Values.ruler.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ template "mimir.ruler.serviceAccountName" . }} + labels: + {{- include "mimir.labels" (dict "ctx" .) | nindent 4 }} + {{- with .Values.ruler.serviceAccount.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.ruler.serviceAccount.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-servmon.yaml new file mode 100644 index 0000000..67d2142 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-servmon.yaml @@ -0,0 +1,3 @@ +{{- if .Values.ruler.enabled -}} +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "ruler" "memberlist" true) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-so.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-so.yaml new file mode 100644 index 0000000..670037e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-so.yaml @@ -0,0 +1,44 @@ +{{- if .Values.ruler.kedaAutoscaling.enabled }} +apiVersion: keda.sh/v1alpha1 +kind: ScaledObject +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "ruler") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "ruler") | nindent 4 }} + annotations: + {{- toYaml .Values.ruler.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + advanced: + horizontalPodAutoscalerConfig: + {{- with .Values.ruler.kedaAutoscaling.behavior }} + behavior: + {{- toYaml . | nindent 8 }} + {{- end }} + maxReplicaCount: {{ .Values.ruler.kedaAutoscaling.maxReplicaCount }} + minReplicaCount: {{ .Values.ruler.kedaAutoscaling.minReplicaCount }} + pollingInterval: {{ .Values.kedaAutoscaling.pollingInterval }} + scaleTargetRef: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "ruler") }} + apiVersion: apps/v1 + kind: Deployment + triggers: + - metadata: + query: max_over_time(sum(sum by (pod) (rate(container_cpu_usage_seconds_total{container="ruler",namespace="{{ .Release.Namespace }}"}[5m])) and max by (pod) (up{container="ruler",namespace="{{ .Release.Namespace }}"}) > 0)[15m:]) * 1000 + serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }} + {{- $cpu_request := dig "requests" "cpu" nil .Values.ruler.resources }} + threshold: {{ mulf (include "mimir.cpuToMilliCPU" (dict "value" $cpu_request)) (divf .Values.ruler.kedaAutoscaling.targetCPUUtilizationPercentage 100) | floor | int64 | quote }} + {{- if .Values.kedaAutoscaling.customHeaders }} + customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }} + {{- end }} + type: prometheus + - metadata: + query: max_over_time(sum((sum by (pod) (container_memory_working_set_bytes{container="ruler",namespace="{{ .Release.Namespace }}"}) and max by (pod) (up{container="ruler",namespace="{{ .Release.Namespace }}"}) > 0) or vector(0))[15m:]) + sum(sum by (pod) (max_over_time(kube_pod_container_resource_requests{container="ruler",namespace="{{ .Release.Namespace }}", resource="memory"}[15m])) and max by (pod) (changes(kube_pod_container_status_restarts_total{container="ruler",namespace="{{ .Release.Namespace }}"}[15m]) > 0) and max by (pod) (kube_pod_container_status_last_terminated_reason{container="ruler",namespace="{{ .Release.Namespace }}", reason="OOMKilled"}) or vector(0)) + serverAddress: {{ include "mimir.kedaPrometheusAddress" (dict "ctx" $) }} + {{- $mem_request := dig "requests" "memory" nil .Values.ruler.resources }} + threshold: {{ mulf (include "mimir.siToBytes" (dict "value" $mem_request)) (divf .Values.ruler.kedaAutoscaling.targetMemoryUtilizationPercentage 100) | floor | int64 | quote }} + {{- if .Values.kedaAutoscaling.customHeaders }} + customHeaders: {{ (include "mimir.lib.mapToCSVString" (dict "map" .Values.kedaAutoscaling.customHeaders)) | quote }} + {{- end }} + type: prometheus +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-svc.yaml new file mode 100644 index 0000000..477f626 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/ruler/ruler-svc.yaml @@ -0,0 +1,23 @@ +{{- if .Values.ruler.enabled -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "ruler") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "ruler" "memberlist" true) | nindent 4 }} + {{- with .Values.ruler.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.ruler.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + name: http-metrics + targetPort: http-metrics + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "ruler" "memberlist" true) | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/runtime-configmap.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/runtime-configmap.yaml new file mode 100644 index 0000000..bdca1c8 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/runtime-configmap.yaml @@ -0,0 +1,10 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "runtime") }} + labels: + {{- include "mimir.labels" (dict "ctx" .) | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +data: + runtime.yaml: | + {{ tpl (toYaml .Values.runtimeConfig) . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/securitycontextconstraints.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/securitycontextconstraints.yaml new file mode 100644 index 0000000..dcb3758 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/securitycontextconstraints.yaml @@ -0,0 +1,42 @@ +{{- if eq (include "mimir.rbac.useSecurityContextConstraints" .) "true" }} +apiVersion: security.openshift.io/v1 +kind: SecurityContextConstraints +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" .) }} + labels: + {{- include "mimir.labels" (dict "ctx" .) | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +allowHostDirVolumePlugin: true +allowHostIPC: false +allowHostNetwork: false +allowHostPID: false +allowHostPorts: false +allowPrivilegeEscalation: true +allowPrivilegedContainer: false +allowedCapabilities: null +defaultAddCapabilities: null +fsGroup: + type: RunAsAny +groups: [] +priority: 10 +readOnlyRootFilesystem: false +requiredDropCapabilities: + - MKNOD +runAsUser: + type: RunAsAny +seLinuxContext: + type: MustRunAs +supplementalGroups: + type: RunAsAny +users: + - system:serviceaccount:openshift-infra:pv-recycler-controller +volumes: + - configMap + - downwardAPI + - emptyDir + - hostPath + - nfs + - persistentVolumeClaim + - projected + - secret +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/serviceaccount.yaml new file mode 100644 index 0000000..732a68b --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/serviceaccount.yaml @@ -0,0 +1,14 @@ +{{- if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ template "mimir.serviceAccountName" . }} + labels: + {{- include "mimir.labels" (dict "ctx" .) | nindent 4 }} + {{- with .Values.serviceAccount.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.serviceAccount.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/smoke-test/smoke-test-job.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/smoke-test/smoke-test-job.yaml new file mode 100644 index 0000000..323c0d2 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/smoke-test/smoke-test-job.yaml @@ -0,0 +1,76 @@ +{{ if not .Values.enterprise.enabled -}} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "smoke-test") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "smoke-test") | nindent 4 }} + annotations: + {{- if .Values.smoke_test.annotations }} + {{- toYaml .Values.smoke_test.annotations | nindent 4 }} + {{- end }} + "helm.sh/hook": test + namespace: {{ .Release.Namespace | quote }} +spec: + backoffLimit: 5 + completions: 1 + parallelism: 1 + selector: + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "smoke-test") | nindent 8 }} + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.smoke_test.priorityClassName }} + priorityClassName: {{ .Values.smoke_test.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "smoke-test") | nindent 8 }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + initContainers: + {{- toYaml .Values.smoke_test.initContainers | nindent 8 }} + containers: + - name: smoke-test + image: "{{ .Values.smoke_test.image.repository }}:{{ .Values.smoke_test.image.tag }}" + imagePullPolicy: {{ .Values.smoke_test.image.pullPolicy }} + args: + - "-tests.smoke-test" + - "-tests.write-endpoint={{ template "mimir.gatewayUrl" . }}" + - "-tests.read-endpoint={{ template "mimir.gatewayUrl" . }}/prometheus" + - "-tests.tenant-id={{ .Values.smoke_test.tenantId }}" + - "-tests.write-read-series-test.num-series=1000" + - "-tests.write-read-series-test.max-query-age=48h" + - "-server.metrics-port={{ include "mimir.serverHttpListenPort" . }}" + {{- range $key, $value := .Values.smoke_test.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.smoke_test.extraVolumeMounts }} + {{ toYaml .Values.smoke_test.extraVolumeMounts | nindent 12 }} + {{- end }} + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.smoke_test.env }} + {{- toYaml . | nindent 12 }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.smoke_test.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + restartPolicy: OnFailure + volumes: + {{- if .Values.smoke_test.extraVolumes }} + {{ toYaml .Values.smoke_test.extraVolumes | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-pdb.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-pdb.yaml new file mode 100644 index 0000000..29ab26f --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-pdb.yaml @@ -0,0 +1 @@ +{{- include "mimir.lib.podDisruptionBudget" (dict "ctx" $ "component" "store-gateway" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-servmon.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-servmon.yaml new file mode 100644 index 0000000..39da841 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-servmon.yaml @@ -0,0 +1 @@ +{{- include "mimir.lib.serviceMonitor" (dict "ctx" $ "component" "store-gateway" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-statefulset.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-statefulset.yaml new file mode 100644 index 0000000..4da75e1 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-statefulset.yaml @@ -0,0 +1,210 @@ +{{- $args := dict "ctx" $ "component" "store-gateway" "memberlist" true -}} +{{- $zonesMap := include "mimir.zoneAwareReplicationMap" $args | fromYaml -}} +{{- range $zoneName, $rolloutZone := $zonesMap }} +{{- with $ -}} +{{- $_ := set $args "rolloutZoneName" $zoneName -}} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "mimir.resourceName" $args }} + labels: + {{- include "mimir.labels" $args | nindent 4 }} + annotations: + {{- include "mimir.componentAnnotations" $args | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + podManagementPolicy: {{ .Values.store_gateway.podManagementPolicy }} + replicas: {{ $rolloutZone.replicas }} + {{- if and (semverCompare ">= 1.23-0" (include "mimir.kubeVersion" .)) (.Values.store_gateway.persistentVolume.enableRetentionPolicy) }} + persistentVolumeClaimRetentionPolicy: + whenDeleted: {{ .Values.store_gateway.persistentVolume.whenDeleted }} + whenScaled: {{ .Values.store_gateway.persistentVolume.whenScaled }} + {{- end }} + selector: + matchLabels: + {{- include "mimir.selectorLabels" $args | nindent 6 }} + updateStrategy: + {{- if $zoneName }} + type: OnDelete + {{- else }} + {{- toYaml .Values.store_gateway.strategy | nindent 4 }} + {{- end }} + serviceName: {{ template "mimir.fullname" . }}-store-gateway{{- if not .Values.enterprise.legacyLabels -}}-headless{{- end -}} + {{- if .Values.store_gateway.persistentVolume.enabled }} + volumeClaimTemplates: + - metadata: + name: storage + {{- if .Values.store_gateway.persistentVolume.annotations }} + annotations: + {{- toYaml .Values.store_gateway.persistentVolume.annotations | nindent 10 }} + {{- end }} + spec: + {{- $storageClass := default .Values.store_gateway.persistentVolume.storageClass $rolloutZone.storageClass }} + {{- if $storageClass }} + {{- if (eq "-" $storageClass) }} + storageClassName: "" + {{- else }} + storageClassName: {{ $storageClass }} + {{- end }} + {{- end }} + accessModes: + {{- toYaml .Values.store_gateway.persistentVolume.accessModes | nindent 10 }} + resources: + requests: + storage: "{{ .Values.store_gateway.persistentVolume.size }}" + {{- end }} + template: + metadata: + labels: + {{- include "mimir.podLabels" $args | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" $args | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + {{- with .Values.store_gateway.schedulerName }} + schedulerName: {{ . | quote }} + {{- end }} + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.store_gateway.priorityClassName }} + priorityClassName: {{ .Values.store_gateway.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" $args | nindent 8 }} + {{- with .Values.store_gateway.initContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + {{- with $rolloutZone.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with $rolloutZone.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "mimir.lib.topologySpreadConstraints" (dict "ctx" . "component" "store-gateway") | nindent 6 }} + {{- with .Values.store_gateway.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.store_gateway.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + - name: runtime-config + configMap: + name: {{ template "mimir.fullname" . }}-runtime + {{- if not .Values.store_gateway.persistentVolume.enabled }} + - name: storage + emptyDir: {} + {{- end }} + {{- if .Values.store_gateway.extraVolumes }} + {{ toYaml .Values.store_gateway.extraVolumes | nindent 8 }} + {{- end }} + - name: active-queries + emptyDir: {} + containers: + {{- if .Values.store_gateway.extraContainers }} + {{ toYaml .Values.store_gateway.extraContainers | nindent 8 }} + {{- end }} + - name: store-gateway + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=store-gateway" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + {{- if $zoneName }} + - "-store-gateway.sharding-ring.instance-availability-zone={{ $zoneName }}" + {{- else }} + {{- if .Values.store_gateway.zoneAwareReplication.migration.enabled }} + - "-store-gateway.sharding-ring.prefix=collectors/" + - "-store-gateway.sharding-ring.zone-awareness-enabled=false" + {{- end }} + {{- end }} + {{- range $key, $value := .Values.store_gateway.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.store_gateway.extraVolumeMounts }} + {{ toYaml .Values.store_gateway.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /etc/mimir + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + - name: runtime-config + mountPath: /var/{{ include "mimir.name" . }} + - name: storage + mountPath: "/data" + {{- if .Values.store_gateway.persistentVolume.subPath }} + subPath: {{ .Values.store_gateway.persistentVolume.subPath }} + {{- end }} + - name: active-queries + mountPath: /active-query-tracker + ports: + - name: http-metrics + containerPort: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + - name: memberlist + containerPort: {{ include "mimir.memberlistBindPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.store_gateway.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.store_gateway.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.store_gateway.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.store_gateway.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.store_gateway.env }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- $cpu_request := dig "requests" "cpu" nil .Values.store_gateway.resources }} + {{- if $cpu_request }} + {{- $cpu_request_doubled := include "mimir.parseCPU" (dict "value" $cpu_request) | float64 | mulf 2 | ceil }} + {{- $cpu_request_plus_four := include "mimir.parseCPU" (dict "value" $cpu_request) | float64 | addf 4 | ceil }} + - name: "GOMAXPROCS" + value: {{ max $cpu_request_doubled $cpu_request_plus_four | toString | toYaml }} + {{- end }} + {{- $mem_request := dig "requests" "memory" nil .Values.store_gateway.resources }} + {{- if $mem_request }} + - name: "GOMEMLIMIT" + value: {{include "mimir.siToBytes" (dict "value" $mem_request) | toString | toYaml }} + {{- end }} + {{- $jaeger_queue_size := dig "jaegerReporterMaxQueueSize" nil .Values.store_gateway }} + {{- if $jaeger_queue_size }} + - name: "JAEGER_REPORTER_MAX_QUEUE_SIZE" + value: {{$jaeger_queue_size | toString | toYaml }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.store_gateway.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + +--- +{{ end }} +{{ end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-svc-headless.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-svc-headless.yaml new file mode 100644 index 0000000..2fb878e --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-svc-headless.yaml @@ -0,0 +1,27 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "store-gateway") }}-headless + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "store-gateway" "memberlist" true) | nindent 4 }} + prometheus.io/service-monitor: "false" + {{- with .Values.store_gateway.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.store_gateway.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + clusterIP: None + ports: + - port: {{ include "mimir.serverHttpListenPort" .}} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" (dict "ctx" . "component" "store-gateway" "memberlist" true) | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-svc.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-svc.yaml new file mode 100644 index 0000000..d637a07 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/store-gateway/store-gateway-svc.yaml @@ -0,0 +1,38 @@ +{{- $args := dict "ctx" $ "component" "store-gateway" "memberlist" true -}} +{{- $zonesMap := include "mimir.zoneAwareReplicationMap" $args | fromYaml -}} +{{- range $zoneName, $rolloutZone := $zonesMap }} +{{- with $ -}} +{{- $_ := set $args "rolloutZoneName" $zoneName -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mimir.resourceName" $args }} + labels: + {{- include "mimir.labels" $args | nindent 4 }} + {{- if and $zoneName .Values.store_gateway.zoneAwareReplication.migration.enabled }} + # Prevent scraping PODs via this service during migration as the original non zone-aware service already scrapes all PODs and you get duplicate metrics. + prometheus.io/service-monitor: "false" + {{- end }} + {{- with .Values.store_gateway.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.store_gateway.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "mimir.serverHttpListenPort" . }} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "mimir.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "mimir.selectorLabels" $args | nindent 4 }} + +--- +{{ end }} +{{ end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/tokengen/tokengen-job.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/tokengen/tokengen-job.yaml new file mode 100644 index 0000000..7af1ba5 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/tokengen/tokengen-job.yaml @@ -0,0 +1,94 @@ +{{- if .Values.enterprise.enabled -}} +{{ if .Values.tokengenJob.enable }} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ include "mimir.resourceName" (dict "ctx" . "component" "tokengen") }} + labels: + {{- include "mimir.labels" (dict "ctx" . "component" "tokengen") | nindent 4 }} + annotations: + {{- if .Values.tokengenJob.annotations }} + {{- toYaml .Values.tokengenJob.annotations | nindent 4 }} + {{- end }} + "helm.sh/hook": post-install + namespace: {{ .Release.Namespace | quote }} +spec: + backoffLimit: 6 + completions: 1 + parallelism: 1 + selector: + template: + metadata: + labels: + {{- include "mimir.podLabels" (dict "ctx" . "component" "tokengen") | nindent 8 }} + annotations: + {{- include "mimir.podAnnotations" (dict "ctx" . "component" "tokengen") | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "mimir.serviceAccountName" . }} + {{- if .Values.tokengenJob.priorityClassName }} + priorityClassName: {{ .Values.tokengenJob.priorityClassName }} + {{- end }} + securityContext: + {{- include "mimir.lib.podSecurityContext" (dict "ctx" . "component" "tokengen") | nindent 8 }} + {{- if .Values.image.pullSecrets }} + imagePullSecrets: + {{- range .Values.image.pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} + initContainers: + {{- toYaml .Values.tokengenJob.initContainers | nindent 8 }} + containers: + - name: tokengen + image: "{{ include "mimir.imageReference" . }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-target=tokengen" + - "-config.expand-env=true" + - "-config.file=/etc/mimir/mimir.yaml" + {{- range $key, $value := .Values.tokengenJob.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.tokengenJob.extraVolumeMounts }} + {{ toYaml .Values.tokengenJob.extraVolumeMounts | nindent 12 }} + {{- end }} + - name: config + mountPath: /etc/mimir + - name: license + mountPath: /license + - name: active-queries + mountPath: /active-query-tracker + env: + {{- with .Values.global.extraEnv }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.tokengenJob.env }} + {{ toYaml . | nindent 12 }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.tokengenJob.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.tokengenJob.containerSecurityContext | nindent 12 }} + restartPolicy: OnFailure + volumes: + - name: config + {{- include "mimir.configVolume" . | nindent 10 }} + {{- if .Values.tokengenJob.extraVolumes }} + {{ toYaml .Values.tokengenJob.extraVolumes | nindent 8 }} + {{- end }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + - name: storage + emptyDir: {} + - name: active-queries + emptyDir: {} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/validate.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/validate.yaml new file mode 100644 index 0000000..f2dd5e9 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/validate.yaml @@ -0,0 +1,266 @@ +{{- $calculatedConfig := include "mimir.calculatedConfig" . | fromYaml }} +{{- $unstructuredConfig := include "mimir.unstructuredConfig" . | fromYaml }} + +{{- if .Values.config }} +{{- fail "Top level 'config' is not allowed. In 'mimir.config', provide the configuration as a string that can contain template expressions. Alternatively, you can provide the configuration as an external secret." }} +{{- end }} + +{{- if .Values.podDisruptionBudget }} +{{- fail "Top level 'podDisruptionBudget' is removed in favour of per component podDisruptionBudget" }} +{{- end }} + +{{- if not ($calculatedConfig.activity_tracker).filepath }} +{{- fail "The 'activity_tracker.filepath' in 'mimir.config' should be set to a path that is on a writeable volume. For example: '/active-query-tracker/activity.log'." }} +{{- end }} + +{{- if ($unstructuredConfig.server).http_listen_port }} +{{- fail "The setting 'server.http_listen_port' is not allowed in 'mimir.config' as it leads to a circular dependency. Set it in 'mimir.structuredConfig' instead." }} +{{- end }} + +{{- if ($unstructuredConfig.server).grpc_listen_port }} +{{- fail "The setting 'server.grpc_listen_port' is not allowed in 'mimir.config' as it leads to a circular dependency. Set it in 'mimir.structuredConfig' instead." }} +{{- end }} + +{{- if ($unstructuredConfig.memberlist).bind_port }} +{{- fail "The setting 'memberlist.bind_port' is not allowed in 'mimir.config' as it leads to a circular dependency. Set it in 'mimir.structuredConfig' instead." }} +{{- end }} + +{{- if not (has .Values.configStorageType (list "Secret" "ConfigMap")) }} +{{- fail "The setting 'configStorageType' should be one of 'Secret' or 'ConfigMap'." }} +{{- end }} + +{{- with .Values.metaMonitoring.grafanaAgent }} +{{/* + !servmon.Enabled + && agent.Enabled + && (remote.url != "" || (len(additionalConfigs) > 0 && additionalConfigs.url != "")) +*/}} +{{- if and + (not ((($.Values).metaMonitoring).serviceMonitor).enabled) + .enabled + (or + (not (empty ((.metrics).remote).url)) + (and + (not (empty (.metrics).additionalRemoteWriteConfigs)) + (not (empty (first (.metrics).additionalRemoteWriteConfigs).url)) + ) + ) + }} +{{- fail "metaMonitoring.grafanaAgent.remote.url is set, but metaMonitoring.serviceMonitor is disabled; you will not see any metrics, so enable the metaMonitoring.serviceMonitor or remove the remote configuration" }} +{{- end }} +{{- end }} + +{{- with ($calculatedConfig.blocks_storage).bucket_store }} + {{- with .chunks_cache }} + {{- if and + (index $.Values "chunks-cache" "enabled") + (eq .backend "memcached") + (ne .memcached.addresses (include "mimir.chunksCacheAddress" $)) + }} + {{- fail (cat + "you set chunks-cache.enabled, but the address of the chunks cache in the Mimir configuration in 'blocks_storage.bucket_store.chunks_cache.memcached.addresses'" + " is different from the address of the memcached instance created by the chart. (actual: " + .memcached.addresses + ", expected: " + (include "mimir.chunksCacheAddress" $) + "). If you want to use your own memcached cluster, disable chunks-cache.enabled and keep the Mimir configuration in mimir.config or mimir.structuredConfig") + }} + {{- end }} + {{- end }} + {{- with .metadata_cache }} + {{- if and + (index $.Values "metadata-cache" "enabled") + (eq .backend "memcached") + (ne .memcached.addresses (include "mimir.metadataCacheAddress" $)) + }} + {{- fail (cat + "you set metadata-cache.enabled, but the address of the metadata cache in the Mimir configuration in 'blocks_storage.bucket_store.metadata_cache.memcached.addresses'" + " is different from the address of the memcached instance created by the chart. (actual: " + .memcached.addresses + ", expected: " + (include "mimir.metadataCacheAddress" $) + "). If you want to use your own memcached cluster, disable metadata-cache.enabled and keep the Mimir configuration in mimir.config or mimir.structuredConfig") + }} + {{- end }} + {{- end }} + {{- with .index_cache }} + {{- if and + (index $.Values "index-cache" "enabled") + (eq .backend "memcached") + (ne .memcached.addresses (include "mimir.indexCacheAddress" $)) + }} + {{- fail (cat + "you set index-cache.enabled, but the address of the index cache in the Mimir configuration in 'blocks_storage.bucket_store.index_cache.memcached.addresses'" + " is different from the address of the memcached instance created by the chart. (actual: " + .memcached.addresses + ", expected: " + (include "mimir.indexCacheAddress" $) + "). If you want to use your own memcached cluster, disable index-cache.enabled and keep the Mimir configuration in mimir.config or mimir.structuredConfig") + }} + {{- end }} + {{- end }} +{{- end }} + +{{- with ($calculatedConfig.frontend) }} + {{- with .results_cache }} + {{- if and + (index $.Values "results-cache" "enabled") + (eq .backend "memcached") + (ne .memcached.addresses (include "mimir.resultsCacheAddress" $)) + }} + {{- fail (cat + "you set results-cache.enabled, but the address of the results cache in the Mimir configuration in 'frontend.results_cache.memcached.addresses'" + " is different from the address of the memcached instance created by the chart. (actual: " + .memcached.addresses + ", expected: " + (include "mimir.resultsCacheAddress" $) + "). If you want to use your own memcached cluster, disable results-cache.enabled and keep the Mimir configuration in mimir.config or mimir.structuredConfig") + }} + {{- end }} + {{- end }} +{{- end }} + +{{- with .Values.memcached }} + {{- if .enabled }} + {{- fail "memcached.enabled has been renamed to chunks-cache.enabled" }} + {{- end }} +{{- end }} + +{{- with (index .Values "memcached-metadata") }} + {{- if .enabled }} + {{- fail "memcached-metadata.enabled has been renamed to metadata-cache.enabled" }} + {{- end }} +{{- end }} + +{{- with (index .Values "memcached-queries") }} + {{- if .enabled }} + {{- fail "memcached-queries.enabled has been renamed to index-cache.enabled" }} + {{- end }} +{{- end }} + +{{- with (index .Values "memcached-results") }} + {{- if .enabled }} + {{- fail "memcached-results.enabled has been renamed to results-cache.enabled" }} + {{- end }} +{{- end }} + +{{- if not .Values.ingester.statefulSet.enabled -}} +{{- fail "You have set ingester.statefulSet.enabled=false. Ingesters are stateful, kubernetes Deployment workloads are no longer supported. Please refer to the documentation for more details." }} +{{- end -}} + + +{{- if and .Values.ingester.zoneAwareReplication.enabled (not ((($calculatedConfig).ingester).ring).zone_awareness_enabled) -}} +{{- fail "You have set ingester.zoneAwareReplication.enabled=true. The mimir.config must include ingester.ring.zone_awareness_enabled=true. Please merge the latest mimir.config from the chart with your mimir.config."}} +{{- end -}} + +{{- if and .Values.ingester.zoneAwareReplication.migration.enabled (not .Values.ingester.zoneAwareReplication.enabled) -}} +{{- fail "You have set ingester.zoneAwareReplication.migration.enabled=true, but ingester.zoneAwareReplication.enabled=false. Please consult the Migrating from single zone with Helm document."}} +{{- end -}} + +{{- with $.Values.ingester.zoneAwareReplication.migration }} +{{- if and .replicas (not .enabled) }} +{{- fail "You have set ingester.zoneAwareReplication.migration.replicas, but ingester.zoneAwareReplication.migration.enabled=false. Please consult the Migrating from single zone with Helm document."}} +{{- end -}} +{{/* Check that if a migration step is enabled, every previous step is also enabled. */}} +{{- $steps := list "enabled" "writePath" "readPath" "excludeDefaultZone" "scaleDownDefaultZone" }} +{{- range $i, $item := rest $steps -}} +{{- range $j, $mustHave := slice $steps 0 $i }} +{{- with $.Values.ingester.zoneAwareReplication.migration }} +{{- if and (index . $item) (not (index . $mustHave)) -}} +{{- printf "You have set ingester.zoneAwareReplication.migration.%s=true, but ingester.zoneAwareReplication.migration.%s=false. Please consult the Migrating from single zone with Helm document." $item $mustHave | fail }} +{{- end -}} +{{- end -}} +{{- end -}} +{{- end -}} +{{- end -}} + + +{{- if and .Values.store_gateway.zoneAwareReplication.enabled (not ((($calculatedConfig).store_gateway).sharding_ring).zone_awareness_enabled) -}} +{{- fail "You have set store_gateway.zoneAwareReplication.enabled=true. The mimir.config must include store_gateway.sharding_ring.zone_awareness_enabled=true. Please merge the latest mimir.config from the chart with your mimir.config."}} +{{- end -}} + +{{- if and .Values.store_gateway.zoneAwareReplication.migration.enabled (ne (((($calculatedConfig).store_gateway).sharding_ring).kvstore).prefix "multi-zone/") -}} +{{- fail "You have set store_gateway.zoneAwareReplication.migration.enabled=true. The mimir.config must include store_gateway.sharding_ring.kvstore.prefix=multi-zone/. Please merge the latest mimir.config from the chart with your mimir.config."}} +{{- end -}} + +{{- if and .Values.store_gateway.zoneAwareReplication.migration.enabled (not .Values.store_gateway.zoneAwareReplication.enabled) -}} +{{- fail "You have set store_gateway.zoneAwareReplication.migration.enabled=true, but store_gateway.zoneAwareReplication.enabled=false. Please consult the Migrating from single zone with Helm document."}} +{{- end -}} + +{{- with $.Values.store_gateway.zoneAwareReplication.migration }} +{{/* Check that if a migration step is enabled, every previous step is also enabled. */}} +{{- $steps := list "enabled" "readPath" }} +{{- range $i, $item := rest $steps -}} +{{- range $j, $mustHave := slice $steps 0 $i }} +{{- with $.Values.store_gateway.zoneAwareReplication.migration }} +{{- if and (index . $item) (not (index . $mustHave)) -}} +{{- printf "You have set store_gateway.zoneAwareReplication.migration.%s=true, but store_gateway.zoneAwareReplication.migration.%s=false. Please consult the Migrating from single zone with Helm document." $item $mustHave | fail }} +{{- end -}} +{{- end -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{- if and .Values.alertmanager.zoneAwareReplication.enabled (not .Values.alertmanager.statefulSet.enabled) -}} +{{- fail "You have set alertmanager.zoneAwareReplication.enabled=true, but alertmanager.statefulSet.enabled=false. This is not a supported configuration." -}} +{{- end -}} + +{{- if and .Values.alertmanager.zoneAwareReplication.enabled (not ((($calculatedConfig).alertmanager).sharding_ring).zone_awareness_enabled) -}} +{{- fail "You have set alertmanager.zoneAwareReplication.enabled=true. The mimir.config must include alertmanager.sharding_ring.zone_awareness_enabled=true. Please merge the latest mimir.config from the chart with your mimir.config."}} +{{- end -}} + +{{- if and .Values.alertmanager.zoneAwareReplication.migration.enabled (not .Values.alertmanager.zoneAwareReplication.enabled) -}} +{{- fail "You have set alertmanager.zoneAwareReplication.migration.enabled=true, but alertmanager.zoneAwareReplication.enabled=false. Please consult the Migrating from single zone with Helm document."}} +{{- end -}} + +{{- with $.Values.alertmanager.zoneAwareReplication.migration }} +{{/* Check that if a migration step is enabled, every previous step is also enabled. */}} +{{- $steps := list "enabled" "writePath" }} +{{- range $i, $item := rest $steps -}} +{{- range $j, $mustHave := slice $steps 0 $i }} +{{- with $.Values.alertmanager.zoneAwareReplication.migration }} +{{- if and (index . $item) (not (index . $mustHave)) -}} +{{- printf "You have set alertmanager.zoneAwareReplication.migration.%s=true, but alertmanager.zoneAwareReplication.migration.%s=false. Please consult the Migrating from single zone with Helm document." $item $mustHave | fail }} +{{- end -}} +{{- end -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{- with .Values.nginx -}} +{{- if and .autoscaling.enabled .autoscaling.targetCPUUtilizationPercentage (not ((.resources).requests).cpu) -}} +{{- fail "You have enabled nginx.autoscaling.targetCPUUtilizationPercentage, you must also set nginx.resources.requests.cpu." -}} +{{- end -}} +{{- if and .autoscaling.enabled .autoscaling.targetMemoryUtilizationPercentage (not ((.resources).requests).memory) -}} +{{- fail "You have enabled nginx.autoscaling.targetMemoryUtilizationPercentage, you must also set nginx.resources.requests.memory." -}} +{{- end -}} +{{- end -}} + +{{- with .Values.gateway -}} +{{- if and .autoscaling.enabled .autoscaling.targetCPUUtilizationPercentage (not ((.resources).requests).cpu) -}} +{{- fail "You have enabled gateway.autoscaling.targetCPUUtilizationPercentage, you must also set gateway.resources.requests.cpu." -}} +{{- end -}} +{{- if and .autoscaling.enabled .autoscaling.targetMemoryUtilizationPercentage (not ((.resources).requests).memory) -}} +{{- fail "You have enabled gateway.autoscaling.targetMemoryUtilizationPercentage, you must also set gateway.resources.requests.memory." -}} +{{- end -}} +{{- end -}} + +{{- if eq .Values.rbac.type "scc" -}} +{{- with .Values.rbac.podSecurityContext -}} +{{- if or (hasKey . "fsGroup") (hasKey . "runAsGroup") (hasKey . "runAsUser") -}} +{{- fail "You have selected rbac.type=scc, you must set the values fsGroup, runAsGroup, runAsUser to null in rbac.podSecurityContext" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{- if eq .Values.rbac.type "scc" -}} +{{- with .Values.rollout_operator.podSecurityContext -}} +{{- if or (hasKey . "fsGroup") (hasKey . "runAsGroup") (hasKey . "runAsUser") -}} +{{- fail "You have selected rbac.type=scc, you must set the values fsGroup, runAsGroup, runAsUser to null in rollout_operator.podSecurityContext" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{- if and .Values.ingress.enabled .Values.gateway.ingress.enabled -}} +{{- fail "You have selected both ingress.enabled and gateway.ingress.enabled, you must select either ingress or gateway but not both" -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/templates/values-for-rego-tests.yaml b/observability/lgtm-distributed/charts/mimir-distributed/templates/values-for-rego-tests.yaml new file mode 100644 index 0000000..abf8678 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/templates/values-for-rego-tests.yaml @@ -0,0 +1,6 @@ +{{- if .Values.regoTestGenerateValues }} +apiVersion: v1 +kind: Values +spec: + {{- .Values | toYaml | nindent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/mimir-distributed/values.yaml b/observability/lgtm-distributed/charts/mimir-distributed/values.yaml new file mode 100644 index 0000000..e037731 --- /dev/null +++ b/observability/lgtm-distributed/charts/mimir-distributed/values.yaml @@ -0,0 +1,3978 @@ +# Grafana Enterprise Metrics specific values and features are found after the `enterprise:` key +# +# The default values specified in this file are enough to deploy all of the +# Grafana Mimir or Grafana Enterprise Metrics microservices but are not suitable for +# production load. +# To configure the resources for production load, refer to the small.yaml or +# large.yaml values files. + +# Note: The values in this file are not backward compatible. Copying and pasting the values is discouraged, but if you do so, +# make sure to use the values.yaml from the branch or tag that matches the mimir-distributed Helm chart version that you +# want to install. You also can see values.yaml for a specific version by running +# `helm show values grafana/mimir-distributed --version ` + +# If you want to get the values file from Github, build the URL as follows because we git tag every release: +# `https://github.com/grafana/mimir/blob/mimir-distributed-/operations/helm/charts/mimir-distributed/values.yaml`. +# For example, https://github.com/grafana/mimir/blob/mimir-distributed-3.1.0/operations/helm/charts/mimir-distributed/values.yaml. + +# -- Overrides the version used to determine compatibility of resources with the target Kubernetes cluster. +# This is useful when using `helm template`, because then helm will use the client version of kubectl as the Kubernetes version, +# which may or may not match your cluster's server version. Example: 'v1.24.4'. Set to null to use the version that helm +# devises. +kubeVersionOverride: null + +# -- Overrides the chart's name. Used to change mimir/enterprise-metrics infix in the resource names. E.g. myRelease-mimir-ingester-1 to myRelease-nameOverride-ingester-1. +# This option is used to align resource names with Cortex, when doing a migration from Cortex to Grafana Mimir. +# Note: Grafana provided dashboards rely on the default naming and will need changes. +nameOverride: null + +# -- Overrides the chart's computed fullname. Used to change the full prefix of resource names. E.g. myRelease-mimir-ingester-1 to fullnameOverride-ingester-1. +# Note: Grafana provided dashboards rely on the default naming and will need changes. +fullnameOverride: null + +image: + # -- Grafana Mimir container image repository. Note: for Grafana Enterprise Metrics use the value 'enterprise.image.repository' + repository: grafana/mimir + # -- Grafana Mimir container image tag. Note: for Grafana Enterprise Metrics use the value 'enterprise.image.tag' + tag: 2.12.0 + # -- Container pull policy - shared between Grafana Mimir and Grafana Enterprise Metrics + pullPolicy: IfNotPresent + # -- Optionally specify an array of imagePullSecrets - shared between Grafana Mimir and Grafana Enterprise Metrics + # Secrets must be manually created in the namespace. + # ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + # pullSecrets: + # - myRegistryKeySecretName + +global: + # -- Definitions to set up nginx resolver + dnsService: kube-dns + dnsNamespace: kube-system + clusterDomain: cluster.local. + + # -- Common environment variables to add to all pods directly managed by this chart. + # scope: admin-api, alertmanager, compactor, distributor, gateway, ingester, memcached, nginx, overrides-exporter, querier, query-frontend, query-scheduler, ruler, store-gateway, smoke-test, tokengen + extraEnv: [] + + # -- Common source of environment injections to add to all pods directly managed by this chart. + # scope: admin-api, alertmanager, compactor, distributor, gateway, ingester, memcached, nginx, overrides-exporter, querier, query-frontend, query-scheduler, ruler, store-gateway, smoke-test, tokengen + # For example to inject values from a Secret, use: + # extraEnvFrom: + # - secretRef: + # name: mysecret + extraEnvFrom: [] + + # -- Pod annotations for all pods directly managed by this chart. Usable for example to associate a version to 'global.extraEnv' and 'global.extraEnvFrom' and trigger a restart of the affected services. + # scope: admin-api, alertmanager, compactor, distributor, gateway, ingester, memcached, nginx, overrides-exporter, querier, query-frontend, query-scheduler, ruler, store-gateway, tokengen + podAnnotations: {} + + # -- Pod labels for all pods directly managed by this chart. + # scope: admin-api, alertmanager, compactor, distributor, gateway, ingester, memcached, nginx, overrides-exporter, querier, query-frontend, query-scheduler, ruler, store-gateway, tokengen + podLabels: {} + +serviceAccount: + # -- Whether to create a service account or not. In case 'create' is false, do set 'name' to an existing service account name. + create: true + # -- Override for the generated service account name. + name: + annotations: {} + labels: {} + +# -- Configuration is loaded from the secret called 'externalConfigSecretName'. If 'useExternalConfig' is true, then the configuration is not generated, just consumed. +useExternalConfig: false + +# -- Defines what kind of object stores the configuration, a ConfigMap or a Secret. +# In order to move sensitive information (such as credentials) from the ConfigMap/Secret to a more secure location (e.g. vault), it is possible to use [environment variables in the configuration](https://grafana.com/docs/mimir/latest/reference-configuration-parameters/#use-environment-variables-in-the-configuration). +# Such environment variables can be then stored in a separate Secret and injected via the global.extraEnvFrom value. For details about environment injection from a Secret please see [Secrets](https://kubernetes.io/docs/concepts/configuration/secret/#use-case-as-container-environment-variables). +configStorageType: ConfigMap + +# -- Name of the Secret or ConfigMap that contains the configuration (used for naming even if config is internal). +externalConfigSecretName: '{{ include "mimir.resourceName" (dict "ctx" . "component" "config") }}' + +# -- When 'useExternalConfig' is true, then changing 'externalConfigVersion' triggers restart of services - otherwise changes to the configuration cause a restart. +externalConfigVersion: "0" + +# --Vault Agent config to mount secrets to TLS configurable components. This requires Vault and Vault Agent to already be running. +vaultAgent: + enabled: false + # -- Vault Kubernetes Authentication role + roleName: "" + # -- Path to client certificate in Vault + clientCertPath: "" + # -- Path to client key in Vault + clientKeyPath: "" + # -- Path to server certificate in Vault + serverCertPath: "" + # -- Path to server key in Vault + serverKeyPath: "" + # -- Path to client CA certificate in Vault + caCertPath: "" + +mimir: + # -- Base config file for Grafana Mimir and Grafana Enterprise Metrics. Contains Helm templates that are evaulated at install/upgrade. + # To modify the resulting configuration, either copy and alter 'mimir.config' as a whole or use the 'mimir.structuredConfig' to add and modify certain YAML elements. + config: | + usage_stats: + installation_mode: helm + + activity_tracker: + filepath: /active-query-tracker/activity.log + + {{- if .Values.enterprise.enabled }} + admin_api: + leader_election: + enabled: true + ring: + kvstore: + store: "memberlist" + + admin_client: + storage: + {{- if .Values.minio.enabled }} + type: s3 + s3: + access_key_id: {{ .Values.minio.rootUser }} + bucket_name: enterprise-metrics-admin + endpoint: {{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000 + insecure: true + secret_access_key: {{ .Values.minio.rootPassword }} + {{- end }} + {{- if (index .Values "admin-cache" "enabled") }} + cache: + backend: memcached + memcached: + addresses: {{ include "mimir.adminCacheAddress" . }} + max_item_size: {{ mul (index .Values "admin-cache").maxItemMemory 1024 1024 }} + {{- end }} + {{- end }} + + alertmanager: + data_dir: /data + enable_api: true + external_url: /alertmanager + {{- if .Values.alertmanager.zoneAwareReplication.enabled }} + sharding_ring: + zone_awareness_enabled: true + {{- end }} + {{- if .Values.alertmanager.fallbackConfig }} + fallback_config_file: /configs/alertmanager_fallback_config.yaml + {{- end }} + + {{- if .Values.minio.enabled }} + alertmanager_storage: + backend: s3 + s3: + access_key_id: {{ .Values.minio.rootUser }} + bucket_name: {{ include "mimir.minioBucketPrefix" . }}-ruler + endpoint: {{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000 + insecure: true + secret_access_key: {{ .Values.minio.rootPassword }} + {{- end }} + + {{- if .Values.enterprise.enabled }} + auth: + type: enterprise + {{- end }} + + # This configures how the store-gateway synchronizes blocks stored in the bucket. It uses Minio by default for getting started (configured via flags) but this should be changed for production deployments. + blocks_storage: + backend: s3 + bucket_store: + {{- if index .Values "chunks-cache" "enabled" }} + chunks_cache: + backend: memcached + memcached: + addresses: {{ include "mimir.chunksCacheAddress" . }} + max_item_size: {{ mul (index .Values "chunks-cache").maxItemMemory 1024 1024 }} + timeout: 750ms + max_idle_connections: 150 + {{- end }} + {{- if index .Values "index-cache" "enabled" }} + index_cache: + backend: memcached + memcached: + addresses: {{ include "mimir.indexCacheAddress" . }} + max_item_size: {{ mul (index .Values "index-cache").maxItemMemory 1024 1024 }} + timeout: 750ms + max_idle_connections: 150 + {{- end }} + {{- if index .Values "metadata-cache" "enabled" }} + metadata_cache: + backend: memcached + memcached: + addresses: {{ include "mimir.metadataCacheAddress" . }} + max_item_size: {{ mul (index .Values "metadata-cache").maxItemMemory 1024 1024 }} + max_idle_connections: 150 + {{- end }} + sync_dir: /data/tsdb-sync + {{- if .Values.minio.enabled }} + s3: + access_key_id: {{ .Values.minio.rootUser }} + bucket_name: {{ include "mimir.minioBucketPrefix" . }}-tsdb + endpoint: {{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000 + insecure: true + secret_access_key: {{ .Values.minio.rootPassword }} + {{- end }} + tsdb: + dir: /data/tsdb + head_compaction_interval: 15m + wal_replay_concurrency: 3 + + {{- if .Values.enterprise.enabled }} + cluster_name: "{{ .Release.Name }}" + {{- end }} + + compactor: + compaction_interval: 30m + deletion_delay: 2h + max_closing_blocks_concurrency: 2 + max_opening_blocks_concurrency: 4 + symbols_flushers_concurrency: 4 + first_level_compaction_wait_period: 25m + data_dir: "/data" + sharding_ring: + wait_stability_min_duration: 1m + heartbeat_period: 1m + heartbeat_timeout: 4m + + distributor: + ring: + heartbeat_period: 1m + heartbeat_timeout: 4m + + frontend: + parallelize_shardable_queries: true + {{- if index .Values "results-cache" "enabled" }} + results_cache: + backend: memcached + memcached: + timeout: 500ms + addresses: {{ include "mimir.resultsCacheAddress" . }} + max_item_size: {{ mul (index .Values "results-cache").maxItemMemory 1024 1024 }} + cache_results: true + query_sharding_target_series_per_shard: 2500 + {{- end }} + {{- if .Values.query_scheduler.enabled }} + scheduler_address: {{ template "mimir.fullname" . }}-query-scheduler-headless.{{ .Release.Namespace }}.svc:{{ include "mimir.serverGrpcListenPort" . }} + {{- end }} + + frontend_worker: + grpc_client_config: + max_send_msg_size: 419430400 # 400MiB + {{- if .Values.query_scheduler.enabled }} + scheduler_address: {{ template "mimir.fullname" . }}-query-scheduler-headless.{{ .Release.Namespace }}.svc:{{ include "mimir.serverGrpcListenPort" . }} + {{- else }} + frontend_address: {{ template "mimir.fullname" . }}-query-frontend-headless.{{ .Release.Namespace }}.svc:{{ include "mimir.serverGrpcListenPort" . }} + {{- end }} + + {{- if and .Values.enterprise.enabled }} + gateway: + proxy: + admin_api: + url: http://{{ template "mimir.fullname" . }}-admin-api.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }} + alertmanager: + url: http://{{ template "mimir.fullname" . }}-alertmanager-headless.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }} + compactor: + url: http://{{ template "mimir.fullname" . }}-compactor.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }} + default: + url: http://{{ template "mimir.fullname" . }}-admin-api.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }} + distributor: + url: dns:///{{ template "mimir.fullname" . }}-distributor-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:{{ include "mimir.serverGrpcListenPort" . }} + ingester: + url: http://{{ template "mimir.fullname" . }}-ingester-headless.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }} + query_frontend: + url: http://{{ template "mimir.fullname" . }}-query-frontend.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }} + ruler: + url: http://{{ template "mimir.fullname" . }}-ruler.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }} + store_gateway: + url: http://{{ template "mimir.fullname" . }}-store-gateway-headless.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }} + {{- if and .Values.enterprise.enabled .Values.graphite.enabled }} + graphite_write_proxy: + url: http://{{ template "mimir.fullname" . }}-graphite-write-proxy.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }} + graphite_querier: + url: http://{{ template "mimir.fullname" . }}-graphite-querier.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }} + {{- end}} + {{- end }} + + ingester: + ring: + final_sleep: 0s + num_tokens: 512 + tokens_file_path: /data/tokens + unregister_on_shutdown: false + heartbeat_period: 2m + heartbeat_timeout: 10m + {{- if .Values.ingester.zoneAwareReplication.enabled }} + zone_awareness_enabled: true + {{- end }} + + ingester_client: + grpc_client_config: + max_recv_msg_size: 104857600 + max_send_msg_size: 104857600 + + {{- if .Values.enterprise.enabled }} + instrumentation: + enabled: true + distributor_client: + address: dns:///{{ template "mimir.fullname" . }}-distributor-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:{{ include "mimir.serverGrpcListenPort" . }} + + license: + path: "/license/license.jwt" + {{- end }} + + limits: + # Limit queries to 500 days. You can override this on a per-tenant basis. + max_total_query_length: 12000h + # Adjust max query parallelism to 16x sharding, without sharding we can run 15d queries fully in parallel. + # With sharding we can further shard each day another 16 times. 15 days * 16 shards = 240 subqueries. + max_query_parallelism: 240 + # Avoid caching results newer than 10m because some samples can be delayed + # This presents caching incomplete results + max_cache_freshness: 10m + + memberlist: + abort_if_cluster_join_fails: false + compression_enabled: false + join_members: + - dns+{{ include "mimir.fullname" . }}-gossip-ring.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:{{ include "mimir.memberlistBindPort" . }} + + querier: + # With query sharding we run more but smaller queries. We must strike a balance + # which allows us to process more sharded queries in parallel when requested, but not overload + # queriers during non-sharded queries. + max_concurrent: 16 + + query_scheduler: + # Increase from default of 100 to account for queries created by query sharding + max_outstanding_requests_per_tenant: 800 + + ruler: + alertmanager_url: dnssrvnoa+http://_http-metrics._tcp.{{ template "mimir.fullname" . }}-alertmanager-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}/alertmanager + enable_api: true + rule_path: /data + + {{- if or (.Values.minio.enabled) (index .Values "metadata-cache" "enabled") }} + ruler_storage: + {{- if .Values.minio.enabled }} + backend: s3 + s3: + endpoint: {{ .Release.Name }}-minio.{{ .Release.Namespace }}.svc:9000 + bucket_name: {{ include "mimir.minioBucketPrefix" . }}-ruler + access_key_id: {{ .Values.minio.rootUser }} + secret_access_key: {{ .Values.minio.rootPassword }} + insecure: true + {{- end }} + {{- if index .Values "metadata-cache" "enabled" }} + cache: + backend: memcached + memcached: + addresses: {{ include "mimir.metadataCacheAddress" . }} + max_item_size: {{ mul (index .Values "metadata-cache").maxItemMemory 1024 1024 }} + {{- end }} + {{- end }} + + runtime_config: + file: /var/{{ include "mimir.name" . }}/runtime.yaml + + store_gateway: + sharding_ring: + heartbeat_period: 1m + heartbeat_timeout: 4m + wait_stability_min_duration: 1m + {{- if .Values.store_gateway.zoneAwareReplication.enabled }} + kvstore: + prefix: multi-zone/ + {{- end }} + tokens_file_path: /data/tokens + unregister_on_shutdown: false + {{- if .Values.store_gateway.zoneAwareReplication.enabled }} + zone_awareness_enabled: true + {{- end }} + + {{- if and .Values.enterprise.enabled .Values.graphite.enabled }} + graphite: + enabled: true + + write_proxy: + distributor_client: + address: dns:///{{ template "mimir.fullname" . }}-distributor.{{ .Release.Namespace }}.svc:{{ include "mimir.serverGrpcListenPort" . }} + + querier: + remote_read: + query_address: http://{{ template "mimir.fullname" . }}-query-frontend.{{ .Release.Namespace }}.svc:{{ include "mimir.serverHttpListenPort" . }}/prometheus + proxy_bad_requests: false + + schemas: + default_storage_schemas_file: /etc/graphite-proxy/storage-schemas.conf + default_storage_aggregations_file: /etc/graphite-proxy/storage-aggregations.conf + aggregation_cache: + memcached: + addresses: dnssrvnoa+{{ template "mimir.fullname" . }}-gr-aggr-cache.{{ .Release.Namespace}}.svc:11211 + timeout: 1s + metric_name_cache: + memcached: + addresses: dnssrvnoa+{{ template "mimir.fullname" . }}-gr-metricname-cache.{{ .Release.Namespace}}.svc:11211 + timeout: 1s + {{- end}} + + # -- Additional structured values on top of the text based 'mimir.config'. Applied after the text based config is evaluated for templates. Enables adding and modifying YAML elements in the evaulated 'mimir.config'. + # + # Additionally, consider the optional "insecure_skip_verify" key below, it allows you to skip_verify_false in case the s3_endpoint certificate is not trusted. + # For more information see https://grafana.com/docs/mimir/latest/references/configuration-parameters/ + # + # Example: + # + # structuredConfig: + # common: + # storage: + # backend: s3 + # s3: + # bucket_name: "${BUCKET_NAME}" + # endpoint: "${BUCKET_HOST}:${BUCKET_PORT}" + # access_key_id: "${AWS_ACCESS_KEY_ID}" # This is a secret injected via an environment variable + # secret_access_key: "${AWS_SECRET_ACCESS_KEY}" # This is a secret injected via an environment variable + # http: + # insecure_skip_verify: true + structuredConfig: {} + +# -- runtimeConfig provides a reloadable runtime configuration. Changing the runtimeConfig doesn't require a restart of all components. +# For more infromation see https://grafana.com/docs/mimir/latest/configure/about-runtime-configuration/ +# +# Example: +# +# runtimeConfig: +# ingester_limits: # limits that each ingester replica enforces +# max_ingestion_rate: 20000 +# max_series: 1500000 +# max_tenants: 1000 +# max_inflight_push_requests: 30000 +# distributor_limits: # limits that each distributor replica enforces +# max_ingestion_rate: 20000 +# max_inflight_push_requests: 30000 +# max_inflight_push_requests_bytes: 50000000 +# overrides: +# tenant-1: # limits for tenant-1 that the whole cluster enforces +# ingestion_tenant_shard_size: 9 +# max_global_series_per_user: 1500000 +# max_fetched_series_per_query: 100000 +runtimeConfig: {} + +# RBAC configuration +rbac: + # -- If true, PodSecurityPolicy will be rendered by the chart on Kuberentes 1.24. + # By default the PodSecurityPolicy is not rendered on version 1.24. + create: true + # -- PSP configuration + podSecurityPolicy: + seccompProfile: runtime/default + privileged: false + allowPrivilegeEscalation: false + hostNetwork: false + hostIPC: false + hostPID: false + readOnlyRootFilesystem: true + runAsUser: + rule: "MustRunAsNonRoot" + seLinux: + rule: "RunAsAny" + supplementalGroups: + rule: "MustRunAs" + ranges: + - min: 1 + max: 65535 + fsGroup: + rule: "MustRunAs" + ranges: + - min: 1 + max: 65535 + additionalVolumes: [] + forcePSPOnKubernetes124: false + # -- For GKE/EKS/AKS use 'type: psp'. For OpenShift use 'type: scc' + type: psp + # -- podSecurityContext is the default pod security context for Mimir, GEM, gateway, and cache components. + # When installing on OpenShift, override podSecurityContext settings with + # + # rbac: + # podSecurityContext: + # fsGroup: null + # runAsGroup: null + # runAsUser: null + podSecurityContext: + fsGroup: 10001 + runAsGroup: 10001 + runAsNonRoot: true + runAsUser: 10001 + seccompProfile: + type: RuntimeDefault + +# -- KEDA Autoscaling configuration +kedaAutoscaling: + # -- A Prometheus-compatible URL. Cadvisor and Mimir metrics for the Mimir pods are expected in this server. + # For more information on the required metrics see [Monitor system health](https://grafana.com/docs/helm-charts/mimir-distributed/latest/run-production-environment-with-helm/monitor-system-health/). + # If empty, the helm chart uses the metamonitoring URL from metaMonitoring.grafanaAgent.metrics.remote.url. + # If that is empty, then the Mimir cluster is used. + prometheusAddress: "" + customHeaders: {} + pollingInterval: 10 + +alertmanager: + enabled: true + # -- Total number of replicas for the alertmanager across all availability zones + # If alertmanager.zoneAwareReplication.enabled=false, this number is taken as is. + # Otherwise each zone starts `ceil(replicas / number_of_zones)` number of pods. + # E.g. if 'replicas' is set to 4 and there are 3 zones, then 4/3=1.33 and after rounding up it means 2 pods per zone are started. + replicas: 1 + + statefulSet: + enabled: true + + service: + annotations: {} + labels: {} + + # -- Optionally set the scheduler for pods of the alertmanager + schedulerName: "" + + resources: + requests: + cpu: 10m + memory: 32Mi + + # -- Fallback config for alertmanager. + # When a tenant doesn't have an Alertmanager configuration, the Grafana Mimir Alertmanager uses the fallback configuration. + fallbackConfig: | + receivers: + - name: default-receiver + route: + receiver: default-receiver + + extraArgs: {} + + # Pod Labels + podLabels: {} + + # Pod Annotations + podAnnotations: {} + + # -- Pod Disruption Budget for alertmanager, this will be applied across availability zones to prevent losing redundancy + podDisruptionBudget: + maxUnavailable: 1 + + # -- The name of the PriorityClass for alertmanager pods + priorityClassName: null + + # -- NodeSelector to pin alertmanager pods to certain set of nodes. This is ignored when alertmanager.zoneAwareReplication.enabled=true. + nodeSelector: {} + # -- Pod affinity settings for the alertmanager. This is ignored when alertmanager.zoneAwareReplication.enabled=true. + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: + maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + + annotations: {} + persistence: + # SubPath in emptyDir for persistence, only enabled if alertmanager.statefulSet.enabled is false + subPath: + + persistentVolume: + # If true and alertmanager.statefulSet.enabled is true, + # Alertmanager will create/use a Persistent Volume Claim + # If false, use emptyDir + enabled: true + + # Alertmanager data Persistent Volume Claim annotations + # + annotations: {} + + # Alertmanager data Persistent Volume access modes + # Must match those of existing PV or dynamic provisioner + # Ref: http://kubernetes.io/docs/user-guide/persistent-volumes/ + # + accessModes: + - ReadWriteOnce + + # Alertmanager data Persistent Volume size + # + size: 1Gi + + # Subdirectory of Alertmanager data Persistent Volume to mount + # Useful if the volume's root directory is not empty + # + subPath: "" + + # Alertmanager data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", storageClassName: "", which disables dynamic provisioning + # If undefined (the default) or set to null, no storageClassName spec is + # set, choosing the default provisioner. + # + # A per-zone storageClass configuration in `alertmanager.zoneAwareReplication.zones[*].storageClass` takes precedence over this field. + # storageClass: "-" + + # -- Enable StatefulSetAutoDeletePVC feature + # https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#persistentvolumeclaim-retention + enableRetentionPolicy: false + whenDeleted: Retain + whenScaled: Retain + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + + # -- SecurityContext override for alermeneger pods + securityContext: {} + + # -- The SecurityContext for alertmanager containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + # Tolerations for pod assignment + # ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + tolerations: [] + + strategy: + type: RollingUpdate + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + # -- updateStrategy of the alertmanager statefulset. This is ignored when alertmanager.zoneAwareReplication.enabled=true. + statefulStrategy: + type: RollingUpdate + + terminationGracePeriodSeconds: 60 + + initContainers: [] + # Init containers to be added to the alertmanager pod. + # - name: my-init-container + # image: busybox:latest + # command: ['sh', '-c', 'echo hello'] + + extraContainers: [] + # Additional containers to be added to the alertmanager pod. + # - name: reverse-proxy + # image: angelbarrera92/basic-auth-reverse-proxy:dev + # args: + # - "serve" + # - "--upstream=http://localhost:3100" + # - "--auth-config=/etc/reverse-proxy-conf/authn.yaml" + # ports: + # - name: http + # containerPort: 11811 + # protocol: TCP + # volumeMounts: + # - name: reverse-proxy-auth-config + # mountPath: /etc/reverse-proxy-conf + + extraVolumes: [] + # Additional volumes to the alertmanager pod. + # - name: reverse-proxy-auth-config + # secret: + # secretName: reverse-proxy-auth-config + + # Extra volume mounts that will be added to the alertmanager container + extraVolumeMounts: [] + + # Extra env variables to pass to the alertmanager container + env: [] + extraEnvFrom: [] + + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: null + + # -- Options to configure zone-aware replication for alertmanager + # Example configuration with full geographical redundancy: + # rollout_operator: + # enabled: true + # alertmanager: + # zoneAwareReplication: + # enabled: true + # topologyKey: 'kubernetes.io/hostname' # This generates default anti-affinity rules + # zones: # Zone list has to be fully redefined for modification. Update with you actual zones or skip to use logical zones only. + # - name: zone-a + # nodeSelector: + # topology.kubernetes.io/zone: us-central1-a + # - name: zone-a + # nodeSelector: + # topology.kubernetes.io/zone: us-central1-b + # - name: zone-c + # nodeSelector: + # topology.kubernetes.io/zone: us-central1-c + # + zoneAwareReplication: + # -- Enable zone-aware replication for alertmanager + enabled: false + # -- Maximum number of alertmanagers that can be unavailable per zone during rollout + maxUnavailable: 2 + # -- topologyKey to use in pod anti-affinity. If unset, no anti-affinity rules are generated. If set, the generated anti-affinity rule makes sure that pods from different zones do not mix. + # E.g.: topologyKey: 'kubernetes.io/hostname' + topologyKey: null + # -- Auxiliary values for migration, see https://grafana.com/docs/helm-charts/mimir-distributed/latest/migration-guides/migrate-from-single-zone-with-helm/ + migration: + # -- Indicate if migration is ongoing for multi zone alertmanager + enabled: false + # -- Start zone-aware alertmanagers + writePath: false + # -- Zone definitions for alertmanager zones. Note: you have to redefine the whole list to change parts as YAML does not allow to modify parts of a list. + zones: + # -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + - name: zone-a + # -- nodeselector to restrict where pods of this zone can be placed. E.g.: + # nodeSelector: + # topology.kubernetes.io/zone: zone-a + nodeSelector: null + # -- extraAffinity adds user defined custom affinity rules (merged with generated rules) + extraAffinity: {} + # -- Alertmanager data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning + # If undefined or set to null (the default), then fall back to the value of `alertmanager.persistentVolume.storageClass`. + storageClass: null + # -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + - name: zone-b + # -- nodeselector to restrict where pods of this zone can be placed. E.g.: + # nodeSelector: + # topology.kubernetes.io/zone: zone-b + nodeSelector: null + # -- extraAffinity adds user defined custom affinity rules (merged with generated rules) + extraAffinity: {} + # -- Alertmanager data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning + # If undefined or set to null (the default), then fall back to the value of `alertmanager.persistentVolume.storageClass`. + storageClass: null + # -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + - name: zone-c + # -- nodeselector to restrict where pods of this zone can be placed. E.g.: + # nodeSelector: + # topology.kubernetes.io/zone: zone-c + nodeSelector: null + # -- extraAffinity adds user defined custom affinity rules (merged with generated rules) + extraAffinity: {} + # -- Alertmanager data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning + # If undefined or set to null (the default), then fall back to the value of `alertmanager.persistentVolume.storageClass`. + storageClass: null + +distributor: + # Setting it to null will produce a deployment without replicas set, allowing you to use autoscaling with the deployment + replicas: 1 + + # -- [Experimental] Configure autoscaling via KEDA (https://keda.sh). This requires having + # KEDA already installed in the Kubernetes cluster. The metrics for scaling are read + # according to top-level kedaAutoscaling.prometheusAddress (defaulting to metamonitoring remote-write destination). + # Basic auth and extra HTTP headers from metaMonitoring are ignored, please use customHeaders. + # The remote URL is used even if metamonitoring is disabled. + # See https://github.com/grafana/mimir/issues/7367 for more details on how to migrate to autoscaled resources without disruptions. + kedaAutoscaling: + enabled: false + # -- preserveReplicas gives you the option to migrate from non-autoscaled to autoscaled deployments without losing replicas. When set to true, the replica fields in the component will be left intact. + # For futher details see [helm: autoscaling migration procedure](https://github.com/grafana/mimir/issues/7367) + preserveReplicas: false + minReplicaCount: 1 + maxReplicaCount: 10 + targetCPUUtilizationPercentage: 100 + targetMemoryUtilizationPercentage: 100 + behavior: + scaleDown: + policies: + - periodSeconds: 600 + type: Percent + value: 10 + + service: + annotations: {} + labels: {} + + resources: + requests: + cpu: 100m + memory: 512Mi + + # Additional distributor container arguments, e.g. log level (debug, info, warn, error) + extraArgs: {} + + # Pod Labels + podLabels: {} + + # Pod Annotations + podAnnotations: {} + + # Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + + # -- The name of the PriorityClass for distributor pods + priorityClassName: null + + nodeSelector: {} + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: + maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + + annotations: {} + persistence: + subPath: + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + + # -- SecurityContext override for distributor pods + securityContext: {} + + # -- The SecurityContext for distributor containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + strategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 15% + + # Keep the termination grace period higher than the -shutdown-delay configured on the distributor. + terminationGracePeriodSeconds: 100 + + tolerations: [] + initContainers: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + env: [] + extraEnvFrom: [] + + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: 1000 + +ingester: + # -- Total number of replicas for the ingester across all availability zones + # If ingester.zoneAwareReplication.enabled=false, this number is taken as is. + # Otherwise each zone starts `ceil(replicas / number_of_zones)` number of pods. + # E.g. if 'replicas' is set to 4 and there are 3 zones, then 4/3=1.33 and after rounding up it means 2 pods per zone are started. + replicas: 3 + + statefulSet: + enabled: true + + service: + annotations: {} + labels: {} + + # -- Optionally set the scheduler for pods of the ingester + schedulerName: "" + + resources: + requests: + cpu: 100m + memory: 512Mi + + # Additional ingester container arguments, e.g. log level (debug, info, warn, error) + extraArgs: {} + # Pod Labels + podLabels: {} + + # Pod Annotations + podAnnotations: {} + + # -- The name of the PriorityClass for ingester pods + priorityClassName: null + + # -- Pod Disruption Budget for ingester, this will be applied across availability zones to prevent losing redundancy + podDisruptionBudget: + maxUnavailable: 1 + + podManagementPolicy: Parallel + + # -- NodeSelector to pin ingester pods to certain set of nodes. This is ignored when ingester.zoneAwareReplication.enabled=true. + nodeSelector: {} + # -- Pod affinity settings for the ingester. This is ignored when ingester.zoneAwareReplication.enabled=true. + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + # It is recommended to replace this with requiredDuringSchedulingIgnoredDuringExecution podAntiAffinity rules when + # deploying to production. + topologySpreadConstraints: + maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + + annotations: {} + + persistentVolume: + # If true and ingester.statefulSet.enabled is true, + # Ingester will create/use a Persistent Volume Claim + # If false, use emptyDir + # + enabled: true + + # Ingester data Persistent Volume Claim annotations + # + annotations: {} + + # Ingester data Persistent Volume access modes + # Must match those of existing PV or dynamic provisioner + # Ref: http://kubernetes.io/docs/user-guide/persistent-volumes/ + accessModes: + - ReadWriteOnce + + # Ingester data Persistent Volume size + size: 2Gi + + # Subdirectory of Ingester data Persistent Volume to mount + # Useful if the volume's root directory is not empty + subPath: "" + + # -- Enable StatefulSetAutoDeletePVC feature + # https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#persistentvolumeclaim-retention + enableRetentionPolicy: false + whenDeleted: Retain + whenScaled: Retain + + # Ingester data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", storageClassName: "", which disables dynamic provisioning + # If undefined (the default) or set to null, no storageClassName spec is + # set, choosing the default provisioner. + # + # A per-zone storageClass configuration in `ingester.zoneAwareReplication.zones[*].storageClass` takes precedence over this field. + # + # storageClass: "-" + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 60 + + # -- SecurityContext override for ingester pods + securityContext: {} + + # -- The SecurityContext for ingester containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + # -- updateStrategy of the ingester statefulset. This is ignored when ingester.zoneAwareReplication.enabled=true. + statefulStrategy: + type: RollingUpdate + + terminationGracePeriodSeconds: 240 + + tolerations: [] + initContainers: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + env: [] + extraEnvFrom: [] + + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: 1000 + + # -- Options to configure zone-aware replication for ingester + # Example configuration with full geographical redundancy: + # rollout_operator: + # enabled: true + # ingester: + # zoneAwareReplication: + # enabled: true + # topologyKey: 'kubernetes.io/hostname' # This generates default anti-affinity rules + # zones: # Zone list has to be fully redefined for modification. Update with you actual zones or skip to use logical zones only. + # - name: zone-a + # nodeSelector: + # topology.kubernetes.io/zone: us-central1-a + # storageClass: storage-class-us-central1-a + # - name: zone-a + # nodeSelector: + # topology.kubernetes.io/zone: us-central1-b + # storageClass: storage-class-us-central1-b + # - name: zone-c + # nodeSelector: + # topology.kubernetes.io/zone: us-central1-c + # storageClass: storage-class-us-central1-c + # + zoneAwareReplication: + # -- Enable zone-aware replication for ingester + enabled: true + # -- Maximum number of ingesters that can be unavailable per zone during rollout + maxUnavailable: 50 + # -- topologyKey to use in pod anti-affinity. If unset, no anti-affinity rules are generated. If set, the generated anti-affinity rule makes sure that pods from different zones do not mix. + # E.g.: topologyKey: 'kubernetes.io/hostname' + topologyKey: null + # -- Auxiliary values for migration, see https://grafana.com/docs/helm-charts/mimir-distributed/latest/migration-guides/migrate-from-single-zone-with-helm/ + migration: + # -- Indicate if migration is ongoing for multi zone ingester + enabled: false + # -- Exclude default zone on write path + excludeDefaultZone: false + # -- Enable zone-awareness, read path only + readPath: false + # -- Total number of replicas to start in availability zones when migration is enabled + replicas: 0 + # -- Scale default zone ingesters to 0 + scaleDownDefaultZone: false + # -- Enable zone-awareness, write path only + writePath: false + # -- Zone definitions for ingester zones. Note: you have to redefine the whole list to change parts as YAML does not allow to modify parts of a list. + zones: + # -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + - name: zone-a + # -- nodeselector to restrict where pods of this zone can be placed. E.g.: + # nodeSelector: + # topology.kubernetes.io/zone: zone-a + nodeSelector: null + # -- extraAffinity adds user defined custom affinity rules (merged with generated rules) + extraAffinity: {} + # -- Ingester data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning + # If undefined or set to null (the default), then fall back to the value of `ingester.persistentVolume.storageClass`. + storageClass: null + # -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + - name: zone-b + # -- nodeselector to restrict where pods of this zone can be placed. E.g.: + # nodeSelector: + # topology.kubernetes.io/zone: zone-b + nodeSelector: null + # -- extraAffinity adds user defined custom affinity rules (merged with generated rules) + extraAffinity: {} + # -- Ingester data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning + # If undefined or set to null (the default), then fall back to the value of `ingester.persistentVolume.storageClass`. + storageClass: null + # -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + - name: zone-c + # -- nodeselector to restrict where pods of this zone can be placed. E.g.: + # nodeSelector: + # topology.kubernetes.io/zone: zone-c + nodeSelector: null + # -- extraAffinity adds user defined custom affinity rules (merged with generated rules) + extraAffinity: {} + # -- Ingester data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning + # If undefined or set to null (the default), then fall back to the value of `ingester.persistentVolume.storageClass`. + storageClass: null + +overrides_exporter: + enabled: true + replicas: 1 + + annotations: {} + + initContainers: [] + + service: + annotations: {} + labels: {} + + strategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 15% + + podLabels: {} + podAnnotations: {} + # Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + + # -- The name of the PriorityClass for overrides-exporter pods + priorityClassName: null + + nodeSelector: {} + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: {} + # maxSkew: 1 + # topologyKey: kubernetes.io/hostname + # whenUnsatisfiable: ScheduleAnyway + + # -- SecurityContext override for overrides-exporter pods + securityContext: {} + + # -- The SecurityContext for overrides-exporter containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + extraArgs: {} + + persistence: + subPath: + + livenessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + + resources: + requests: + cpu: 100m + memory: 128Mi + + terminationGracePeriodSeconds: 60 + + tolerations: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + env: [] + extraEnvFrom: [] + + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: null + +ruler: + enabled: true + replicas: 1 + + # -- [Experimental] Configure autoscaling via KEDA (https://keda.sh). This requires having + # KEDA already installed in the Kubernetes cluster. The metrics for scaling are read + # according to top-level kedaAutoscaling.prometheusAddress (defaulting to metamonitoring remote-write destination). + # Basic auth and extra HTTP headers from metaMonitoring are ignored, please use customHeaders. + # The remote URL is used even if metamonitoring is disabled. + # See https://github.com/grafana/mimir/issues/7367 for more details on how to migrate to autoscaled resources without disruptions. + kedaAutoscaling: + enabled: false + # -- preserveReplicas gives you the option to migrate from non-autoscaled to autoscaled deployments without losing replicas. When set to true, the replica fields in the component will be left intact. + # For futher details see [helm: autoscaling migration procedure](https://github.com/grafana/mimir/issues/7367) + preserveReplicas: false + minReplicaCount: 1 + maxReplicaCount: 10 + targetCPUUtilizationPercentage: 100 + targetMemoryUtilizationPercentage: 100 + behavior: + scaleDown: + policies: + - periodSeconds: 600 + type: Percent + value: 10 + + service: + annotations: {} + labels: {} + + # -- Dedicated service account for ruler pods. + # If not set, the default service account defined at the begining of this file will be used. + # This service account can be used even if the default one is not set. + serviceAccount: + create: false + # -- Ruler specific service account name. If not set and create is set to true, the default + # name will be the default mimir service account's name with the "-ruler" suffix. + name: "" + annotations: {} + labels: {} + + resources: + requests: + cpu: 100m + memory: 128Mi + + # Additional ruler container arguments, e.g. log level (debug, info, warn, error) + extraArgs: {} + # log.level: debug + + # Pod Labels + podLabels: {} + + # Pod Annotations + podAnnotations: {} + + # Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + + nodeSelector: {} + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: + maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + + annotations: {} + persistence: + subPath: + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + + # -- SecurityContext override for ruler pods + securityContext: {} + + # -- The SecurityContext for ruler containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + strategy: + type: RollingUpdate + rollingUpdate: + maxSurge: 50% + maxUnavailable: 0 + + terminationGracePeriodSeconds: 180 + + tolerations: [] + initContainers: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + env: [] + extraEnvFrom: [] + + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: 1000 + +querier: + replicas: 2 + + # -- [Experimental] Configure autoscaling via KEDA (https://keda.sh). This requires having + # KEDA already installed in the Kubernetes cluster. The metrics for scaling are read + # according to top-level kedaAutoscaling.prometheusAddress (defaulting to metamonitoring remote-write destination). + # Basic auth and extra HTTP headers from metaMonitoring are ignored, please use customHeaders. + # The remote URL is used even if metamonitoring is disabled. + # See https://github.com/grafana/mimir/issues/7367 for more details on how to migrate to autoscaled resources without disruptions. + kedaAutoscaling: + enabled: false + # -- preserveReplicas gives you the option to migrate from non-autoscaled to autoscaled deployments without losing replicas. When set to true, the replica fields in the component will be left intact. + # For futher details see [helm: autoscaling migration procedure](https://github.com/grafana/mimir/issues/7367) + preserveReplicas: false + minReplicaCount: 1 + maxReplicaCount: 10 + querySchedulerInflightRequestsThreshold: 12 + behavior: + scaleDown: + policies: + - periodSeconds: 120 + type: Percent + value: 10 + stabilizationWindowSeconds: 600 + scaleUp: + policies: + - periodSeconds: 120 + type: Percent + value: 50 + - periodSeconds: 120 + type: Pods + value: 15 + stabilizationWindowSeconds: 60 + + service: + annotations: {} + labels: {} + + resources: + requests: + cpu: 100m + memory: 128Mi + + # Additional querier container arguments, e.g. log level (debug, info, warn, error) + extraArgs: {} + + # Pod Labels + podLabels: {} + + # Pod Annotations + podAnnotations: {} + + # Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + + # -- The name of the PriorityClass for querier pods + priorityClassName: null + + nodeSelector: {} + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: + maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + + annotations: {} + persistence: + subPath: + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + + # -- SecurityContext override for querier pods + securityContext: {} + + # -- The SecurityContext for querier containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + strategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 15% + + terminationGracePeriodSeconds: 180 + + tolerations: [] + initContainers: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + env: [] + extraEnvFrom: [] + + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: 5000 + +query_frontend: + # Setting it to null will produce a deployment without replicas set, allowing you to use autoscaling with the deployment + replicas: 1 + + # -- [Experimental] Configure autoscaling via KEDA (https://keda.sh). This requires having + # KEDA already installed in the Kubernetes cluster. The metrics for scaling are read + # according to top-level kedaAutoscaling.prometheusAddress (defaulting to metamonitoring remote-write destination). + # Basic auth and extra HTTP headers from metaMonitoring are ignored, please use customHeaders. + # The remote URL is used even if metamonitoring is disabled. + # See https://github.com/grafana/mimir/issues/7367 for more details on how to migrate to autoscaled resources without disruptions. + kedaAutoscaling: + enabled: false + # -- preserveReplicas gives you the option to migrate from non-autoscaled to autoscaled deployments without losing replicas. When set to true, the replica fields in the component will be left intact. + # For futher details see [helm: autoscaling migration procedure](https://github.com/grafana/mimir/issues/7367) + preserveReplicas: false + minReplicaCount: 1 + maxReplicaCount: 10 + targetCPUUtilizationPercentage: 75 + targetMemoryUtilizationPercentage: 100 + behavior: + scaleDown: + policies: + - periodSeconds: 60 + type: Percent + value: 10 + + service: + annotations: {} + labels: {} + + resources: + requests: + cpu: 100m + memory: 128Mi + + # Additional query-frontend container arguments, e.g. log level (debug, info, warn, error) + extraArgs: {} + + # Pod Labels + podLabels: {} + + # Pod Annotations + podAnnotations: {} + + # Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + + # -- The name of the PriorityClass for query-frontend pods + priorityClassName: null + + nodeSelector: {} + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: + maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + + annotations: {} + persistence: + subPath: + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + + # -- SecurityContext override for query-fronted pods + securityContext: {} + + # -- The SecurityContext for query-frontend containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + strategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 15% + + terminationGracePeriodSeconds: 390 + + tolerations: [] + initContainers: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + env: [] + extraEnvFrom: [] + + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: 5000 + +query_scheduler: + enabled: true + replicas: 2 + + service: + annotations: {} + labels: {} + + resources: + requests: + cpu: 100m + memory: 128Mi + + # Additional query-scheduler container arguments, e.g. log level (debug, info, warn, error) + extraArgs: {} + + # Pod Labels + podLabels: {} + + # Pod Annotations + podAnnotations: {} + + # Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + + # -- The name of the PriorityClass for query-scheduler pods + priorityClassName: null + + nodeSelector: {} + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: + maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + + annotations: {} + persistence: + subPath: + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + + # -- SecurityContext override for query-scheduler pods + securityContext: {} + + # -- The SecurityContext for query-scheduler containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + strategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 1 + + terminationGracePeriodSeconds: 180 + + tolerations: [] + initContainers: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + env: [] + extraEnvFrom: [] + + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: null + +store_gateway: + # -- Total number of replicas for the store-gateway across all availability zones + # If store_gateway.zoneAwareReplication.enabled=false, this number is taken as is. + # Otherwise each zone starts `ceil(replicas / number_of_zones)` number of pods. + # E.g. if 'replicas' is set to 4 and there are 3 zones, then 4/3=1.33 and after rounding up it means 2 pods per zone are started. + replicas: 1 + + service: + annotations: {} + labels: {} + + # -- Optionally set the scheduler for pods of the store-gateway + schedulerName: "" + + resources: + requests: + cpu: 100m + memory: 512Mi + + # Additional store-gateway container arguments, e.g. log level (debug, info, warn, error) + extraArgs: {} + + # Pod Labels + podLabels: {} + + # Pod Annotations + podAnnotations: {} + + # -- Management policy for store-gateway pods + # New variable introduced with Helm chart version 5.1.0. For backwards compatibility it is set to `OrderedReady` + # On new deployments it is highly recommended to switch it to `Parallel` as this will be the new default from 6.0.0 + podManagementPolicy: OrderedReady + + # -- Pod Disruption Budget for store-gateway, this will be applied across availability zones to prevent losing redundancy + podDisruptionBudget: + maxUnavailable: 1 + + # -- The name of the PriorityClass for store-gateway pods + priorityClassName: null + + # -- NodeSelector to pin store-gateway pods to certain set of nodes. This is ignored when store_gateway.zoneAwareReplication.enabled=true. + nodeSelector: {} + # -- Pod affinity settings for the store_gateway. This is ignored when store_gateway.zoneAwareReplication.enabled=true. + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + # It is recommended to replace this with requiredDuringSchedulingIgnoredDuringExecution podAntiAffinity rules when + # deploying to production. + topologySpreadConstraints: + maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + + annotations: {} + + persistentVolume: + # If true Store-gateway will create/use a Persistent Volume Claim + # If false, use emptyDir + # + enabled: true + + # Store-gateway data Persistent Volume Claim annotations + # + annotations: {} + + # Store-gateway data Persistent Volume access modes + # Must match those of existing PV or dynamic provisioner + # Ref: http://kubernetes.io/docs/user-guide/persistent-volumes/ + # + accessModes: + - ReadWriteOnce + + # Store-gateway data Persistent Volume size + # + size: 2Gi + + # Subdirectory of Store-gateway data Persistent Volume to mount + # Useful if the volume's root directory is not empty + # + subPath: "" + + # Store-gateway data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", storageClassName: "", which disables dynamic provisioning + # If undefined (the default) or set to null, no storageClassName spec is + # set, choosing the default provisioner. + # + # A per-zone storageClass configuration in `store_gateway.zoneAwareReplication.zones[*].storageClass` takes precedence over this field. + # storageClass: "-" + + # -- Enable StatefulSetAutoDeletePVC feature + # https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#persistentvolumeclaim-retention + enableRetentionPolicy: false + whenDeleted: Retain + whenScaled: Retain + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 60 + + # -- SecurityContext override for store-gateway pods + securityContext: {} + + # -- The SecurityContext for store-gateway containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + # -- updateStrategy of the store-gateway statefulset. This is ignored when store_gateway.zoneAwareReplication.enabled=true. + strategy: + type: RollingUpdate + + terminationGracePeriodSeconds: 240 + + tolerations: [] + initContainers: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + env: [] + extraEnvFrom: [] + + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: 1000 + + # -- Options to configure zone-aware replication for store-gateway + # Example configuration with full geographical redundancy: + # rollout_operator: + # enabled: true + # store_gateway: + # zoneAwareReplication: + # enabled: true + # topologyKey: 'kubernetes.io/hostname' # This generates default anti-affinity rules + # zones: # Zone list has to be fully redefined for modification. Update with you actual zones or skip to use logical zones only. + # - name: zone-a + # nodeSelector: + # topology.kubernetes.io/zone: us-central1-a + # - name: zone-a + # nodeSelector: + # topology.kubernetes.io/zone: us-central1-b + # - name: zone-c + # nodeSelector: + # topology.kubernetes.io/zone: us-central1-c + # + zoneAwareReplication: + # -- Enable zone-aware replication for store-gateway + enabled: true + # -- Maximum number of store-gateways that can be unavailable per zone during rollout + maxUnavailable: 50 + # -- topologyKey to use in pod anti-affinity. If unset, no anti-affinity rules are generated. If set, the generated anti-affinity rule makes sure that pods from different zones do not mix. + # E.g.: topologyKey: 'kubernetes.io/hostname' + topologyKey: null + # -- Auxiliary values for migration, see https://grafana.com/docs/helm-charts/mimir-distributed/latest/migration-guides/migrate-from-single-zone-with-helm/ + migration: + # -- Indicate if migration is ongoing for multi zone store-gateway + enabled: false + # -- Enable zone-awareness on the readPath + readPath: false + # -- Zone definitions for store-gateway zones. Note: you have to redefine the whole list to change parts as YAML does not allow to modify parts of a list. + zones: + # -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + - name: zone-a + # -- nodeselector to restrict where pods of this zone can be placed. E.g.: + # nodeSelector: + # topology.kubernetes.io/zone: zone-a + nodeSelector: null + # -- extraAffinity adds user defined custom affinity rules (merged with generated rules) + extraAffinity: {} + # -- StoreGateway data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning + # If undefined or set to null (the default), then fall back to the value of `store_gateway.persistentVolume.storageClass`. + storageClass: null + # -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + - name: zone-b + # -- nodeselector to restrict where pods of this zone can be placed. E.g.: + # nodeSelector: + # topology.kubernetes.io/zone: zone-b + nodeSelector: null + # -- extraAffinity adds user defined custom affinity rules (merged with generated rules) + extraAffinity: {} + # -- StoreGateway data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning + # If undefined or set to null (the default), then fall back to the value of `store_gateway.persistentVolume.storageClass`. + storageClass: null + # -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + - name: zone-c + # -- nodeselector to restrict where pods of this zone can be placed. E.g.: + # nodeSelector: + # topology.kubernetes.io/zone: zone-c + nodeSelector: null + # -- extraAffinity adds user defined custom affinity rules (merged with generated rules) + extraAffinity: {} + # -- StoreGateway data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning + # If undefined or set to null (the default), then fall back to the value of `store_gateway.persistentVolume.storageClass`. + storageClass: null + +compactor: + replicas: 1 + + service: + annotations: {} + labels: {} + + # -- Optionally set the scheduler for pods of the compactor + schedulerName: "" + + resources: + requests: + cpu: 100m + memory: 512Mi + + # Additional compactor container arguments, e.g. log level (debug, info, warn, error) + extraArgs: {} + + # Pod Labels + podLabels: {} + + # Pod Annotations + podAnnotations: {} + + # Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + + podManagementPolicy: OrderedReady + + # -- The name of the PriorityClass for compactor pods + priorityClassName: null + + nodeSelector: {} + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: + maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + + annotations: {} + + persistentVolume: + # If true compactor will create/use a Persistent Volume Claim + # If false, use emptyDir + # + enabled: true + + # compactor data Persistent Volume Claim annotations + # + annotations: {} + + # compactor data Persistent Volume access modes + # Must match those of existing PV or dynamic provisioner + # Ref: http://kubernetes.io/docs/user-guide/persistent-volumes/ + # + accessModes: + - ReadWriteOnce + + # compactor data Persistent Volume size + # + size: 2Gi + + # Subdirectory of compactor data Persistent Volume to mount + # Useful if the volume's root directory is not empty + # + subPath: "" + + # compactor data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", storageClassName: "", which disables dynamic provisioning + # If undefined (the default) or set to null, no storageClassName spec is + # set, choosing the default provisioner. + # + # storageClass: "-" + + # -- Enable StatefulSetAutoDeletePVC feature + # https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#persistentvolumeclaim-retention + enableRetentionPolicy: false + whenDeleted: Retain + whenScaled: Retain + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 60 + + # -- SecurityContext override for compactor pods + securityContext: {} + + # -- The SecurityContext for compactor containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + strategy: + type: RollingUpdate + + terminationGracePeriodSeconds: 240 + + tolerations: [] + initContainers: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + env: [] + extraEnvFrom: [] + + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: null + +memcached: + image: + # -- Memcached Docker image repository + repository: memcached + # -- Memcached Docker image tag + tag: 1.6.25-alpine + # -- Memcached Docker image pull policy + pullPolicy: IfNotPresent + + # -- The SecurityContext override for memcached pods + podSecurityContext: {} + + # -- The name of the PriorityClass for memcached pods + priorityClassName: null + + # -- The SecurityContext for memcached containers + containerSecurityContext: + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + allowPrivilegeEscalation: false + +memcachedExporter: + # -- Whether memcached metrics should be exported + enabled: true + + image: + repository: prom/memcached-exporter + tag: v0.14.3 + pullPolicy: IfNotPresent + + resources: + requests: {} + limits: {} + + # -- The SecurityContext for memcached exporter containers + containerSecurityContext: + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + allowPrivilegeEscalation: false + + # -- Extra args to add to the exporter container. + # Example: + # extraArgs: + # memcached.tls.enable: true + # memcached.tls.cert-file: /certs/cert.crt + # memcached.tls.key-file: /certs/cert.key + # memcached.tls.ca-file: /certs/ca.crt + # memcached.tls.insecure-skip-verify: false + # memcached.tls.server-name: memcached + extraArgs: {} + +chunks-cache: + # -- Specifies whether memcached based chunks-cache should be enabled + enabled: false + + # -- Total number of chunks-cache replicas + replicas: 1 + + # -- Port of the chunks-cache service + port: 11211 + + # -- Amount of memory allocated to chunks-cache for object storage (in MB). + allocatedMemory: 8192 + + # -- Maximum item memory for chunks-cache (in MB). + maxItemMemory: 1 + + # -- Maximum number of connections allowed + connectionLimit: 16384 + + # -- Extra init containers for chunks-cache pods + initContainers: [] + + # -- Annotations for the chunks-cache pods + annotations: {} + # -- Node selector for chunks-cache pods + nodeSelector: {} + # -- Affinity for chunks-cache pods + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: {} + # maxSkew: 1 + # topologyKey: kubernetes.io/hostname + # whenUnsatisfiable: ScheduleAnyway + + # -- Tolerations for chunks-cache pods + tolerations: [] + # -- Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + # -- The name of the PriorityClass for chunks-cache pods + priorityClassName: null + # -- Labels for chunks-cache pods + podLabels: {} + # -- Annotations for chunks-cache pods + podAnnotations: {} + # -- Management policy for chunks-cache pods + podManagementPolicy: Parallel + # -- Grace period to allow the chunks-cache to shutdown before it is killed + terminationGracePeriodSeconds: 60 + + # -- Stateful chunks-cache strategy + statefulStrategy: + type: RollingUpdate + + # -- Add extended options for chunks-cache memcached container. The format is the same as for the memcached -o/--extend flag. + # Example: + # extraExtendedOptions: 'tls,no_hashexpand' + extraExtendedOptions: "" + + # -- Additional CLI args for chunks-cache + extraArgs: {} + + # -- Additional containers to be added to the chunks-cache pod. + extraContainers: [] + + # -- Additional volumes to be added to the chunks-cache pod (applies to both memcached and exporter containers). + # Example: + # extraVolumes: + # - name: extra-volume + # secret: + # secretName: extra-volume-secret + extraVolumes: [] + + # -- Additional volume mounts to be added to the chunks-cache pod (applies to both memcached and exporter containers). + # Example: + # extraVolumeMounts: + # - name: extra-volume + # mountPath: /etc/extra-volume + # readOnly: true + extraVolumeMounts: [] + + # -- Resource requests and limits for the chunks-cache + # By default a safe memory limit will be requested based on allocatedMemory value (floor (* 1.2 allocatedMemory)). + resources: null + + # -- Service annotations and labels + service: + annotations: {} + labels: {} + +index-cache: + # -- Specifies whether memcached based index-cache should be enabled + enabled: false + + # -- Total number of index-cache replicas + replicas: 1 + + # -- Port of the index-cache service + port: 11211 + + # -- Amount of memory allocated to index-cache for object storage (in MB). + allocatedMemory: 2048 + + # -- Maximum item index-cache for memcached (in MB). + maxItemMemory: 5 + + # -- Maximum number of connections allowed + connectionLimit: 16384 + + # -- Extra init containers for index-cache pods + initContainers: [] + + # -- Annotations for the index-cache pods + annotations: {} + # -- Node selector for index-cache pods + nodeSelector: {} + # -- Affinity for index-cache pods + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: {} + # maxSkew: 1 + # topologyKey: kubernetes.io/hostname + # whenUnsatisfiable: ScheduleAnyway + + # -- Tolerations for index-cache pods + tolerations: [] + # -- Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + # -- The name of the PriorityClass for index-cache pods + priorityClassName: null + # -- Labels for index-cache pods + podLabels: {} + # -- Annotations for index-cache pods + podAnnotations: {} + # -- Management policy for index-cache pods + podManagementPolicy: Parallel + # -- Grace period to allow the index-cache to shutdown before it is killed + terminationGracePeriodSeconds: 60 + + # -- Stateful index-cache strategy + statefulStrategy: + type: RollingUpdate + + # -- Add extended options for index-cache memcached container. The format is the same as for the memcached -o/--extend flag. + # Example: + # extraExtendedOptions: 'tls,modern,track_sizes' + extraExtendedOptions: "" + + # -- Additional CLI args for index-cache + extraArgs: {} + + # -- Additional containers to be added to the index-cache pod. + extraContainers: [] + + # -- Additional volumes to be added to the index-cache pod (applies to both memcached and exporter containers). + # Example: + # extraVolumes: + # - name: extra-volume + # secret: + # secretName: extra-volume-secret + extraVolumes: [] + + # -- Additional volume mounts to be added to the index-cache pod (applies to both memcached and exporter containers). + # Example: + # extraVolumeMounts: + # - name: extra-volume + # mountPath: /etc/extra-volume + # readOnly: true + extraVolumeMounts: [] + + # -- Resource requests and limits for the index-cache + # By default a safe memory limit will be requested based on allocatedMemory value (floor (* 1.2 allocatedMemory)). + resources: null + + # -- Service annotations and labels + service: + annotations: {} + labels: {} + +metadata-cache: + # -- Specifies whether memcached based metadata-cache should be enabled + enabled: false + + # -- Total number of metadata-cache replicas + replicas: 1 + + # -- Port of the metadata-cache service + port: 11211 + + # -- Amount of memory allocated to metadata-cache for object storage (in MB). + allocatedMemory: 512 + + # -- Maximum item metadata-cache for memcached (in MB). + maxItemMemory: 1 + + # -- Maximum number of connections allowed + connectionLimit: 16384 + + # -- Extra init containers for metadata-cache pods + initContainers: [] + + # -- Annotations for the metadata-cache pods + annotations: {} + # -- Node selector for metadata-cache pods + nodeSelector: {} + # -- Affinity for metadata-cache pods + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: {} + # maxSkew: 1 + # topologyKey: kubernetes.io/hostname + # whenUnsatisfiable: ScheduleAnyway + + # -- Tolerations for metadata-cache pods + tolerations: [] + # -- Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + # -- The name of the PriorityClass for metadata-cache pods + priorityClassName: null + # -- Labels for metadata-cache pods + podLabels: {} + # -- Annotations for metadata-cache pods + podAnnotations: {} + # -- Management policy for metadata-cache pods + podManagementPolicy: Parallel + # -- Grace period to allow the metadata-cache to shutdown before it is killed + terminationGracePeriodSeconds: 60 + + # -- Stateful metadata-cache strategy + statefulStrategy: + type: RollingUpdate + + # -- Add extended options for metadata-cache memcached container. The format is the same as for the memcached -o/--extend flag. + # Example: + # extraExtendedOptions: 'tls,modern,track_sizes' + extraExtendedOptions: "" + + # -- Additional CLI args for metadata-cache + extraArgs: {} + + # -- Additional containers to be added to the metadata-cache pod. + extraContainers: [] + + # -- Additional volumes to be added to the metadata-cache pod (applies to both memcached and exporter containers). + # Example: + # extraVolumes: + # - name: extra-volume + # secret: + # secretName: extra-volume-secret + extraVolumes: [] + + # -- Additional volume mounts to be added to the metadata-cache pod (applies to both memcached and exporter containers). + # Example: + # extraVolumeMounts: + # - name: extra-volume + # mountPath: /etc/extra-volume + # readOnly: true + extraVolumeMounts: [] + + # -- Resource requests and limits for the metadata-cache + # By default a safe memory limit will be requested based on allocatedMemory value (floor (* 1.2 allocatedMemory)). + resources: null + + # -- Service annotations and labels + service: + annotations: {} + labels: {} + +results-cache: + # -- Specifies whether memcached based results-cache should be enabled + enabled: false + + # -- Total number of results-cache replicas + replicas: 1 + + # -- Port of the results-cache service + port: 11211 + + # -- Amount of memory allocated to results-cache for object storage (in MB). + allocatedMemory: 512 + + # -- Maximum item results-cache for memcached (in MB). + maxItemMemory: 5 + + # -- Maximum number of connections allowed + connectionLimit: 16384 + + # -- Extra init containers for results-cache pods + initContainers: [] + + # -- Annotations for the results-cache pods + annotations: {} + # -- Node selector for results-cache pods + nodeSelector: {} + # -- Affinity for results-cache pods + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: {} + # maxSkew: 1 + # topologyKey: kubernetes.io/hostname + # whenUnsatisfiable: ScheduleAnyway + + # -- Tolerations for results-cache pods + tolerations: [] + # -- Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + # -- The name of the PriorityClass for results-cache pods + priorityClassName: null + # -- Labels for results-cache pods + podLabels: {} + # -- Annotations for results-cache pods + podAnnotations: {} + # -- Management policy for results-cache pods + podManagementPolicy: Parallel + # -- Grace period to allow the results-cache to shutdown before it is killed + terminationGracePeriodSeconds: 60 + + # -- Stateful results-cache strategy + statefulStrategy: + type: RollingUpdate + + # -- Add extended options for results-cache memcached container. The format is the same as for the memcached -o/--extend flag. + # Example: + # extraExtendedOptions: 'tls,modern,track_sizes' + extraExtendedOptions: "" + + # -- Additional CLI args for results-cache + extraArgs: {} + + # -- Additional containers to be added to the results-cache pod. + extraContainers: [] + + # -- Additional volumes to be added to the results-cache pod (applies to both memcached and exporter containers). + # Example: + # extraVolumes: + # - name: extra-volume + # secret: + # secretName: extra-volume-secret + extraVolumes: [] + + # -- Additional volume mounts to be added to the results-cache pod (applies to both memcached and exporter containers). + # Example: + # extraVolumeMounts: + # - name: extra-volume + # mountPath: /etc/extra-volume + # readOnly: true + extraVolumeMounts: [] + + # -- Resource requests and limits for the results-cache + # By default a safe memory limit will be requested based on allocatedMemory value (floor (* 1.2 allocatedMemory)). + resources: null + + # -- Service annotations and labels + service: + annotations: {} + labels: {} + +# -- Setting for the Grafana Rollout Operator https://github.com/grafana/helm-charts/tree/main/charts/rollout-operator +rollout_operator: + enabled: true + + # -- podSecurityContext is the pod security context for the rollout operator. + # When installing on OpenShift, override podSecurityContext settings with + # + # rollout_operator: + # podSecurityContext: + # fsGroup: null + # runAsGroup: null + # runAsUser: null + podSecurityContext: + fsGroup: 10001 + runAsGroup: 10001 + runAsNonRoot: true + runAsUser: 10001 + seccompProfile: + type: RuntimeDefault + + # Set the container security context + securityContext: + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + allowPrivilegeEscalation: false + +minio: + enabled: true + mode: standalone + rootUser: grafana-mimir + buckets: + - name: mimir-tsdb + policy: none + purge: false + - name: mimir-ruler + policy: none + purge: false + - name: enterprise-metrics-tsdb + policy: none + purge: false + - name: enterprise-metrics-admin + policy: none + purge: false + - name: enterprise-metrics-ruler + policy: none + purge: false + persistence: + enabled: true + size: 5Gi + resources: + requests: + cpu: 100m + memory: 128Mi + rootPassword: supersecret + # Changed the mc config path to '/tmp' from '/etc' as '/etc' is only writable by root and OpenShift will not permit this. + configPathmc: "/tmp/minio/mc/" + +# -- DEPRECATED: use the 'gateway' section instead. For a migration guide refer to +# https://grafana.com/docs/helm-charts/mimir-distributed/latest/migration-guides/migrate-to-unified-proxy-deployment/ +# +# Configuration for nginx gateway. +# Can only be enabled when 'enterprise.enabled' is false. +nginx: + # -- Specifies whether nginx should be enabled + enabled: true + # -- Number of replicas for nginx + replicas: 1 + # -- Enable logging of 2xx and 3xx HTTP requests + verboseLogging: true + autoscaling: + # -- Enable autoscaling for nginx + enabled: false + # -- Minimum autoscaling replicas for nginx + minReplicas: 1 + # -- Maximum autoscaling replicas for nginx + maxReplicas: 3 + # -- Target CPU utilisation percentage for nginx + targetCPUUtilizationPercentage: 60 + # -- Target memory utilisation percentage for nginx + targetMemoryUtilizationPercentage: + # -- See `kubectl explain deployment.spec.strategy` for more, + # ref: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy + deploymentStrategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 15% + image: + # -- The Docker registry for nginx image + registry: docker.io + # -- The nginx image repository + repository: nginxinc/nginx-unprivileged + # -- The nginx image tag + tag: 1.25-alpine + # -- The nginx image pull policy + pullPolicy: IfNotPresent + # -- The name of the PriorityClass for nginx pods + priorityClassName: null + # -- Labels for nginx pods + podLabels: {} + # -- Annotations for nginx pods + podAnnotations: {} + # -- Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + # -- Additional CLI args for nginx + extraArgs: {} + # -- Environment variables to add to the nginx pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the nginx pods + extraEnvFrom: [] + # -- Volumes to add to the nginx pods + extraVolumes: [] + # -- Volume mounts to add to the nginx pods + extraVolumeMounts: [] + # -- The SecurityContext override for nginx containers + podSecurityContext: {} + + # -- The SecurityContext for nginx containers + containerSecurityContext: + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + allowPrivilegeEscalation: false + # -- Resource requests and limits for the nginx + resources: {} + # -- Grace period to allow the nginx to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- Affinity for nginx pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: "" + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: + maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + + annotations: {} + + # -- Node selector for nginx pods + nodeSelector: {} + # -- Tolerations for nginx pods + tolerations: [] + # Nginx service configuration + service: + # -- Port of the nginx service + port: 80 + # -- Type of the nginx service + type: ClusterIP + # -- ClusterIP of the nginx service + clusterIP: null + # -- Node port if service type is NodePort + nodePort: null + # -- Load balancer IP address if service type is LoadBalancer + loadBalancerIP: null + # -- Annotations for the nginx service + annotations: {} + # -- Labels for nginx service + labels: {} + # Ingress configuration + ingress: + # -- Specifies whether an ingress for the nginx should be created + enabled: false + # -- Ingress Class Name. MAY be required for Kubernetes versions >= 1.18 + # ingressClassName: nginx + # -- Annotations for the nginx ingress + annotations: {} + # -- Hosts configuration for the nginx ingress + hosts: + - host: nginx.mimir.example.com + paths: + - path: / + # -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers + # pathType: Prefix + # -- TLS configuration for the nginx ingress + tls: + - secretName: mimir-nginx-tls + hosts: + - nginx.mimir.example.com + # -- Route configuration (for OpenShift only) + route: + # -- Specifies whether an OpenShift route for the nginx should be created + enabled: false + # -- Annotations for the nginx route + annotations: {} + # -- Hostname configuration + host: nginx.mimir.example.com + # -- TLS configuration for OpenShift Route + tls: + # -- More details about TLS configuration and termination types: https://docs.openshift.com/container-platform/3.11/architecture/networking/routes.html#secured-routes + # For OpenShift 4: https://docs.openshift.com/container-platform/4.11/networking/routes/secured-routes.html + termination: edge + # Basic auth configuration + basicAuth: + # -- Enables basic authentication for nginx + enabled: false + # -- The basic auth username for nginx + username: null + # -- The basic auth password for nginx + password: null + # -- Uses the specified username and password to compute a htpasswd using Sprig's `htpasswd` function. + # The value is templated using `tpl`. Override this to use a custom htpasswd, e.g. in case the default causes + # high CPU load. + htpasswd: >- + {{ htpasswd (required "'nginx.basicAuth.username' is required" .Values.nginx.basicAuth.username) (required "'nginx.basicAuth.password' is required" .Values.nginx.basicAuth.password) }} + # -- Existing basic auth secret to use. Must contain '.htpasswd' + existingSecret: null + # Configures the readiness probe for nginx + readinessProbe: + httpGet: + path: / + port: http-metric + initialDelaySeconds: 15 + timeoutSeconds: 1 + + # -- Additional containers to be added to the nginx pod. + extraContainers: [] + # - name: dnsmasq + # image: "janeczku/go-dnsmasq:release-1.0.7" + # imagePullPolicy: IfNotPresent + # args: + # - --listen + # - "127.0.0.1:8053" + # - --hostsfile=/etc/hosts + # - --enable-search + # - --verbose + + nginxConfig: + # -- NGINX log format + logFormat: |- + main '$remote_addr - $remote_user [$time_local] $status ' + '"$request" $body_bytes_sent "$http_referer" ' + '"$http_user_agent" "$http_x_forwarded_for"'; + # -- Sets the log level of the NGINX error log. One of `debug`, `info`, `notice`, `warn`, `error`, `crit`, `alert`, or `emerg` + errorLogLevel: error + # -- Enables NGINX access logs + accessLogEnabled: true + # -- Allows appending custom configuration to the server block + serverSnippet: "" + # -- Allows appending custom configuration to the http block + httpSnippet: "" + # -- Allows to set a custom resolver + resolver: null + # -- Config file contents for Nginx. Passed through the `tpl` function to allow templating + # @default -- See values.yaml + file: | + worker_processes 5; ## Default: 1 + error_log /dev/stderr {{ .Values.nginx.nginxConfig.errorLogLevel }}; + pid /tmp/nginx.pid; + worker_rlimit_nofile 8192; + + events { + worker_connections 4096; ## Default: 1024 + } + + http { + client_body_temp_path /tmp/client_temp; + proxy_temp_path /tmp/proxy_temp_path; + fastcgi_temp_path /tmp/fastcgi_temp; + uwsgi_temp_path /tmp/uwsgi_temp; + scgi_temp_path /tmp/scgi_temp; + + default_type application/octet-stream; + log_format {{ .Values.nginx.nginxConfig.logFormat }} + + {{- if .Values.nginx.verboseLogging }} + access_log /dev/stderr main; + {{- else }} + + map $status $loggable { + ~^[23] 0; + default 1; + } + access_log {{ .Values.nginx.nginxConfig.accessLogEnabled | ternary "/dev/stderr main if=$loggable;" "off;" }} + {{- end }} + + sendfile on; + tcp_nopush on; + proxy_http_version 1.1; + + {{- if .Values.nginx.nginxConfig.resolver }} + resolver {{ .Values.nginx.nginxConfig.resolver }}; + {{- else }} + resolver {{ .Values.global.dnsService }}.{{ .Values.global.dnsNamespace }}.svc.{{ .Values.global.clusterDomain }}; + {{- end }} + + {{- with .Values.nginx.nginxConfig.httpSnippet }} + {{ . | nindent 2 }} + {{- end }} + + # Ensure that X-Scope-OrgID is always present, default to the no_auth_tenant for backwards compatibility when multi-tenancy was turned off. + map $http_x_scope_orgid $ensured_x_scope_orgid { + default $http_x_scope_orgid; + "" "{{ include "mimir.noAuthTenant" . }}"; + } + + map $http_x_scope_orgid $has_multiple_orgid_headers { + default 0; + "~^.+,.+$" 1; + } + + proxy_read_timeout 300; + server { + listen 8080; + listen [::]:8080; + + {{- if .Values.nginx.basicAuth.enabled }} + auth_basic "Mimir"; + auth_basic_user_file /etc/nginx/secrets/.htpasswd; + {{- end }} + + if ($has_multiple_orgid_headers = 1) { + return 400 'Sending multiple X-Scope-OrgID headers is not allowed. Use a single header with | as separator instead.'; + } + + location = / { + return 200 'OK'; + auth_basic off; + } + + proxy_set_header X-Scope-OrgID $ensured_x_scope_orgid; + + # Distributor endpoints + location /distributor { + set $distributor {{ template "mimir.fullname" . }}-distributor-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$distributor:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + location = /api/v1/push { + set $distributor {{ template "mimir.fullname" . }}-distributor-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$distributor:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + location /otlp/v1/metrics { + set $distributor {{ template "mimir.fullname" . }}-distributor-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$distributor:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + # Alertmanager endpoints + location {{ template "mimir.alertmanagerHttpPrefix" . }} { + set $alertmanager {{ template "mimir.fullname" . }}-alertmanager-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$alertmanager:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + location = /multitenant_alertmanager/status { + set $alertmanager {{ template "mimir.fullname" . }}-alertmanager-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$alertmanager:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + location = /api/v1/alerts { + set $alertmanager {{ template "mimir.fullname" . }}-alertmanager-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$alertmanager:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + # Ruler endpoints + location {{ template "mimir.prometheusHttpPrefix" . }}/config/v1/rules { + set $ruler {{ template "mimir.fullname" . }}-ruler.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$ruler:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + location {{ template "mimir.prometheusHttpPrefix" . }}/api/v1/rules { + set $ruler {{ template "mimir.fullname" . }}-ruler.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$ruler:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + location {{ template "mimir.prometheusHttpPrefix" . }}/api/v1/alerts { + set $ruler {{ template "mimir.fullname" . }}-ruler.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$ruler:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + location = /ruler/ring { + set $ruler {{ template "mimir.fullname" . }}-ruler.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$ruler:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + # Rest of {{ template "mimir.prometheusHttpPrefix" . }} goes to the query frontend + location {{ template "mimir.prometheusHttpPrefix" . }} { + set $query_frontend {{ template "mimir.fullname" . }}-query-frontend.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$query_frontend:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + # Buildinfo endpoint can go to any component + location = /api/v1/status/buildinfo { + set $query_frontend {{ template "mimir.fullname" . }}-query-frontend.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$query_frontend:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + # Compactor endpoint for uploading blocks + location /api/v1/upload/block/ { + set $compactor {{ template "mimir.fullname" . }}-compactor.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$compactor:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + {{- with .Values.nginx.nginxConfig.serverSnippet }} + {{ . | nindent 4 }} + {{- end }} + } + } + +# -- Use either this ingress or the gateway, but not both at once. +# If you enable this, make sure to disable the gateway's ingress. +ingress: + enabled: false + # ingressClassName: nginx + annotations: {} + paths: + distributor-headless: + - path: /distributor + # -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers + # pathType: Prefix + - path: /api/v1/push + - path: /otlp/v1/metrics + alertmanager-headless: + - path: /alertmanager + - path: /multitenant_alertmanager/status + - path: /api/v1/alerts + ruler: + - path: /prometheus/config/v1/rules + - path: /prometheus/api/v1/rules + - path: /prometheus/api/v1/alerts + query-frontend: + - path: /prometheus + - path: /api/v1/status/buildinfo + compactor: + - path: /api/v1/upload/block/ + hosts: + - mimir.example.com + # tls: + # - secretName: mimir-distributed-tls + # hosts: + # - mimir.example.com + +# -- A reverse proxy deployment that is meant to receive traffic for Mimir or GEM. +# When enterprise.enabled is true the GEM gateway is deployed. Otherwise, it is an nginx. +# Options except those under gateway.nginx apply to both versions - nginx and GEM gateway. +gateway: + # -- The gateway is deployed by default for enterprise installations (enterprise.enabled=true). + # Toggle this to have it deployed for non-enterprise installations too. + enabledNonEnterprise: false + + # -- Number of replicas for the Deployment + replicas: 1 + + # -- HorizontalPodAutoscaler + autoscaling: + enabled: false + minReplicas: 1 + maxReplicas: 3 + targetCPUUtilizationPercentage: 70 + targetMemoryUtilizationPercentage: 70 + + # -- Deployment strategy. See `kubectl explain deployment.spec.strategy` for more, + # ref: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy + strategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 15% + + # -- The name of the PriorityClass + priorityClassName: null + # -- Labels for Deployment Pods + podLabels: {} + # -- Annotations Deployment Pods + podAnnotations: {} + # -- PodDisruptionBudget https://kubernetes.io/docs/tasks/run-application/configure-pdb/ + podDisruptionBudget: + maxUnavailable: 1 + # -- Additional CLI args for the container + extraArgs: {} + # -- Environment variables to add to the Pods. https://kubernetes.io/docs/tasks/inject-data-application/define-environment-variable-container/ + env: [] + # -- Environment variables from secrets or configmaps to add to the Pods. + extraEnvFrom: [] + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: null + # -- Volumes to add to the Pods + extraVolumes: [] + # -- Volume mounts to add to the Pods + extraVolumeMounts: [] + # -- Additional containers to be added to the Pods. + extraContainers: [] + # - name: dnsmasq + # image: "janeczku/go-dnsmasq:release-1.0.7" + # imagePullPolicy: IfNotPresent + # args: + # - --listen + # - "127.0.0.1:8053" + # - --hostsfile=/etc/hosts + # - --enable-search + # - --verbose + + # -- Init containers https://kubernetes.io/docs/concepts/workloads/pods/init-containers/ + initContainers: [] + + # -- SecurityContext override for gateway pods + securityContext: {} + # -- The SecurityContext for gateway containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + # -- Resource requests and limits for the container + resources: {} + # -- Grace period to allow the gateway container to shut down before it is killed + terminationGracePeriodSeconds: 30 + + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: + maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + + # Annotations for the Deployment + annotations: {} + + # -- Node selector for Deployment Pods + nodeSelector: {} + # -- Tolerations for Deployment Pods + tolerations: [] + # -- Gateway Service configuration + service: + # -- Port on which the Service listens + port: 80 + # -- Type of the Service + type: ClusterIP + # -- ClusterIP of the Service + clusterIP: null + # -- Node port if service type is NodePort + nodePort: null + # -- Load balancer IP address if service type is LoadBalancer + loadBalancerIP: null + # -- Annotations for the Service + annotations: {} + # -- Labels for the Service + labels: {} + # -- DEPRECATED Legacy compatibility port the GEM gateway service listens on, set to 'null' to disable + legacyPort: 8080 + # -- Overrides the name of the Service. Useful if you are switching from the deprecated nginx or + # GEM gateway configuration and want to use the same in-cluster address for Mimir/GEM. + # By using the same name as the nginx/GEM gateway Service, Helm will not delete the Service Resource. + # Instead, it will update the existing one in place. + # If left as an empty string, a name is generated. + nameOverride: "" + + ingress: + enabled: false + # -- Overrides the name of the Ingress. Useful if you are switching from the deprecated nginx or + # GEM gateway configuration and you Ingress Controller needs time to reconcile a new Ingress resource. + # By using the same name as the nginx/GEM gateway Ingress, Helm will not delete the Ingress Resource. + # Instead, it will update the existing one in place. + # If left as an empty string, a name is generated. + nameOverride: "" + # -- Ingress Class Name. MAY be required for Kubernetes versions >= 1.18 + ingressClassName: "" + # -- Annotations for the Ingress + annotations: {} + # -- Hosts configuration for the Ingress + hosts: + # -- Passed through the `tpl` function to allow templating. + - host: "{{ .Release.Name }}.mimir.example.com" + paths: + - path: / + # -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers + # pathType: Prefix + # -- TLS configuration for the nginx ingress + tls: + - secretName: mimir-tls + # -- Hosts included in the tls certificate. Passed through the `tpl` function to allow templating. + hosts: + - "{{ .Release.Name }}.mimir.example.com" + + # -- OpenShift Route configuration + route: + enabled: false + # -- Annotations for the Route + annotations: {} + # -- Passed through the `tpl` function to allow templating. + host: "{{ .Release.Name }}.mimir.example.com" + + tls: + # -- More details about TLS configuration and termination types: https://docs.openshift.com/container-platform/3.11/architecture/networking/routes.html#secured-routes + # For OpenShift 4: https://docs.openshift.com/container-platform/4.11/networking/routes/secured-routes.html + termination: edge + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 15 + timeoutSeconds: 1 + + nginx: + # -- Enable logging of 2xx and 3xx HTTP requests + verboseLogging: true + + # -- Image for the nginx. pullPolicy and optional pullSecrets are set in toplevel 'image' section, not here. + image: + # -- The Docker registry for nginx image + registry: docker.io + # -- The nginx image repository + repository: nginxinc/nginx-unprivileged + # -- The nginx image tag + tag: 1.25-alpine + + # -- Basic auth configuration + basicAuth: + # -- Enables basic authentication for nginx + enabled: false + # -- The basic auth username for nginx + username: null + # -- The basic auth password for nginx + password: null + # -- Uses the specified username and password to compute a htpasswd using Sprig's `htpasswd` function. + # The value is templated using `tpl`. Override this to use a custom htpasswd, e.g. in case the default causes + # high CPU load. + htpasswd: >- + {{ htpasswd (required "'gateway.nginx.basicAuth.username' is required" .Values.gateway.nginx.basicAuth.username) (required "'gateway.nginx.basicAuth.password' is required" .Values.gateway.nginx.basicAuth.password) }} + # -- Name of an existing basic auth secret to use instead of gateway.nginx.basicAuth.htpasswd. Must contain '.htpasswd' key + existingSecret: null + + config: + # -- NGINX log format + logFormat: |- + main '$remote_addr - $remote_user [$time_local] $status ' + '"$request" $body_bytes_sent "$http_referer" ' + '"$http_user_agent" "$http_x_forwarded_for"'; + # -- Sets the log level of the NGINX error log. One of `debug`, `info`, `notice`, `warn`, `error`, `crit`, `alert`, or `emerg` + errorLogLevel: error + # -- Enables NGINX access logs + accessLogEnabled: true + # -- Allows appending custom configuration to the server block + serverSnippet: "" + # -- Allows appending custom configuration to the http block + httpSnippet: "" + # -- Allows to set a custom resolver + resolver: null + # -- Configures whether or not NGINX bind IPv6 + enableIPv6: true + # -- Config file contents for Nginx. Passed through the `tpl` function to allow templating. + file: | + worker_processes 5; ## Default: 1 + error_log /dev/stderr {{ .Values.gateway.nginx.config.errorLogLevel }}; + pid /tmp/nginx.pid; + worker_rlimit_nofile 8192; + + events { + worker_connections 4096; ## Default: 1024 + } + + http { + client_body_temp_path /tmp/client_temp; + proxy_temp_path /tmp/proxy_temp_path; + fastcgi_temp_path /tmp/fastcgi_temp; + uwsgi_temp_path /tmp/uwsgi_temp; + scgi_temp_path /tmp/scgi_temp; + + default_type application/octet-stream; + log_format {{ .Values.gateway.nginx.config.logFormat }} + + {{- if .Values.gateway.nginx.verboseLogging }} + access_log /dev/stderr main; + {{- else }} + + map $status $loggable { + ~^[23] 0; + default 1; + } + access_log {{ .Values.gateway.nginx.config.accessLogEnabled | ternary "/dev/stderr main if=$loggable;" "off;" }} + {{- end }} + + sendfile on; + tcp_nopush on; + proxy_http_version 1.1; + + {{- if .Values.gateway.nginx.config.resolver }} + resolver {{ .Values.gateway.nginx.config.resolver }}; + {{- else }} + resolver {{ .Values.global.dnsService }}.{{ .Values.global.dnsNamespace }}.svc.{{ .Values.global.clusterDomain }}; + {{- end }} + + {{- with .Values.gateway.nginx.config.httpSnippet }} + {{ . | nindent 2 }} + {{- end }} + + # Ensure that X-Scope-OrgID is always present, default to the no_auth_tenant for backwards compatibility when multi-tenancy was turned off. + map $http_x_scope_orgid $ensured_x_scope_orgid { + default $http_x_scope_orgid; + "" "{{ include "mimir.noAuthTenant" . }}"; + } + + map $http_x_scope_orgid $has_multiple_orgid_headers { + default 0; + "~^.+,.+$" 1; + } + + proxy_read_timeout 300; + server { + listen {{ include "mimir.serverHttpListenPort" . }}; + {{- if .Values.gateway.nginx.config.enableIPv6 }} + listen [::]:{{ include "mimir.serverHttpListenPort" . }}; + {{- end }} + + {{- if .Values.gateway.nginx.basicAuth.enabled }} + auth_basic "Mimir"; + auth_basic_user_file /etc/nginx/secrets/.htpasswd; + {{- end }} + + if ($has_multiple_orgid_headers = 1) { + return 400 'Sending multiple X-Scope-OrgID headers is not allowed. Use a single header with | as separator instead.'; + } + + location = / { + return 200 'OK'; + auth_basic off; + } + + location = /ready { + return 200 'OK'; + auth_basic off; + } + + proxy_set_header X-Scope-OrgID $ensured_x_scope_orgid; + + # Distributor endpoints + location /distributor { + set $distributor {{ template "mimir.fullname" . }}-distributor-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$distributor:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + location = /api/v1/push { + set $distributor {{ template "mimir.fullname" . }}-distributor-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$distributor:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + location /otlp/v1/metrics { + set $distributor {{ template "mimir.fullname" . }}-distributor-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$distributor:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + # Alertmanager endpoints + location {{ template "mimir.alertmanagerHttpPrefix" . }} { + set $alertmanager {{ template "mimir.fullname" . }}-alertmanager-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$alertmanager:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + location = /multitenant_alertmanager/status { + set $alertmanager {{ template "mimir.fullname" . }}-alertmanager-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$alertmanager:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + location = /api/v1/alerts { + set $alertmanager {{ template "mimir.fullname" . }}-alertmanager-headless.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$alertmanager:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + # Ruler endpoints + location {{ template "mimir.prometheusHttpPrefix" . }}/config/v1/rules { + set $ruler {{ template "mimir.fullname" . }}-ruler.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$ruler:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + location {{ template "mimir.prometheusHttpPrefix" . }}/api/v1/rules { + set $ruler {{ template "mimir.fullname" . }}-ruler.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$ruler:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + location {{ template "mimir.prometheusHttpPrefix" . }}/api/v1/alerts { + set $ruler {{ template "mimir.fullname" . }}-ruler.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$ruler:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + location = /ruler/ring { + set $ruler {{ template "mimir.fullname" . }}-ruler.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$ruler:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + # Rest of {{ template "mimir.prometheusHttpPrefix" . }} goes to the query frontend + location {{ template "mimir.prometheusHttpPrefix" . }} { + set $query_frontend {{ template "mimir.fullname" . }}-query-frontend.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$query_frontend:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + # Buildinfo endpoint can go to any component + location = /api/v1/status/buildinfo { + set $query_frontend {{ template "mimir.fullname" . }}-query-frontend.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$query_frontend:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + # Compactor endpoint for uploading blocks + location /api/v1/upload/block/ { + set $compactor {{ template "mimir.fullname" . }}-compactor.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}; + proxy_pass http://$compactor:{{ include "mimir.serverHttpListenPort" . }}$request_uri; + } + + {{- with .Values.gateway.nginx.config.serverSnippet }} + {{ . | nindent 4 }} + {{- end }} + } + } + +metaMonitoring: + # Dashboard configuration for deploying Grafana dashboards for Mimir + dashboards: + # -- If enabled, Grafana dashboards are deployed + enabled: false + # -- Annotations to add to the Grafana dashboard ConfigMap + annotations: + k8s-sidecar-target-directory: /tmp/dashboards/Mimir Dashboards + # -- Labels to add to the Grafana dashboard ConfigMap + labels: + grafana_dashboard: "1" + + # ServiceMonitor configuration for monitoring Kubernetes Services with Prometheus Operator and/or Grafana Agent + serviceMonitor: + # -- If enabled, ServiceMonitor resources for Prometheus Operator are created + enabled: false + # -- To disable setting a 'cluster' label in metrics, set to 'null'. + # To overwrite the 'cluster' label with your own value, set to a non-empty string. + # Keep empty string "" to have the default value in the 'cluster' label, which is the helm release name for Mimir and the actual cluster name for Enterprise Metrics. + clusterLabel: "" + # -- Alternative namespace for ServiceMonitor resources + # If left unset, the default is to install the ServiceMonitor resources in the namespace where the chart is installed, i.e. the namespace specified for the helm command. + namespace: null + # -- Namespace selector for ServiceMonitor resources + # If left unset, the default is to select the namespace where the chart is installed, i.e. the namespace specified for the helm command. + namespaceSelector: null + # -- ServiceMonitor annotations + annotations: {} + # -- Additional ServiceMonitor labels + labels: {} + # -- ServiceMonitor scrape interval + interval: null + # -- ServiceMonitor scrape timeout in Go duration format (e.g. 15s) + scrapeTimeout: null + # -- ServiceMonitor relabel configs to apply to targets before scraping + # https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#monitoring.coreos.com/v1.RelabelConfig + relabelings: [] + # -- ServiceMonitor metric relabel configs to apply to samples before ingestion + # https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#monitoring.coreos.com/v1.RelabelConfig + metricRelabelings: [] + # -- ServiceMonitor will use http by default, but you can pick https as well + scheme: http + # -- ServiceMonitor will use these tlsConfig settings to make the health check requests + tlsConfig: null + + # Rules for the Prometheus Operator + prometheusRule: + # -- If enabled, a PrometheusRule resource for Prometheus Operator is created + enabled: false + # -- Create standard Mimir alerts in Prometheus Operator via a PrometheusRule CRD + mimirAlerts: false + # -- Create standard Mimir recording rules in Prometheus Operator via a PrometheusRule CRD + mimirRules: false + # -- PrometheusRule annotations + annotations: {} + # -- Additional PrometheusRule labels. To find out what your Prometheus operator expects, + # see the Prometheus object and field spec.ruleSelector + labels: {} + # -- prometheusRule namespace. This should be the namespace where the Prometheus Operator is installed, + # unless the Prometheus Operator is set up to look for rules outside its namespace + namespace: null + # -- Contents of Prometheus rules file + groups: [] + # - name: mimir_api_1 + # rules: + # - expr: histogram_quantile(0.99, sum(rate(cortex_request_duration_seconds_bucket[1m])) + # by (le, cluster, job)) + # record: cluster_job:cortex_request_duration_seconds:99quantile + # - expr: histogram_quantile(0.50, sum(rate(cortex_request_duration_seconds_bucket[1m])) + # by (le, cluster, job)) + # record: cluster_job:cortex_request_duration_seconds:50quantile + # - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job) / sum(rate(cortex_request_duration_seconds_count[1m])) + # by (cluster, job) + # record: cluster_job:cortex_request_duration_seconds:avg + # - expr: sum(rate(cortex_request_duration_seconds_bucket[1m])) by (le, cluster, job) + # record: cluster_job:cortex_request_duration_seconds_bucket:sum_rate + # - expr: sum(rate(cortex_request_duration_seconds_sum[1m])) by (cluster, job) + # record: cluster_job:cortex_request_duration_seconds_sum:sum_rate + # - expr: sum(rate(cortex_request_duration_seconds_count[1m])) by (cluster, job) + # record: cluster_job:cortex_request_duration_seconds_count:sum_rate + + # metaMonitoringAgent configures the built in Grafana Agent that can scrape metrics and logs and send them to a local or remote destination + grafanaAgent: + # -- Controls whether to create PodLogs, MetricsInstance, LogsInstance, and GrafanaAgent CRs to scrape the + # ServiceMonitors of the chart and ship metrics and logs to the remote endpoints below. + # Note that you need to configure serviceMonitor in order to have some metrics available. + enabled: false + + # -- Controls the image repository and tag for config-reloader and grafana-agent containers in the meta-monitoring + # StatefulSet and DaemonSet created by the grafana-agent-operator. You can define one or both sections under imageRepo. + # If a section is defined, you must pass repo, image and tag keys. + imageRepo: + # configReloader: + # repo: quay.io + # image: prometheus-operator/prometheus-config-reloader + # tag: v0.47.0 + # grafanaAgent: + # repo: docker.io + # image: grafana/agent + # tag: v0.29.0 + + # -- Controls whether to install the Grafana Agent Operator and its CRDs. + # Note that helm will not install CRDs if this flag is enabled during an upgrade. + # In that case install the CRDs manually from https://github.com/grafana/agent/tree/main/operations/agent-static-operator/crds + installOperator: false + + logs: + # -- Controls whether to create resources PodLogs and LogsInstance resources + enabled: true + + # -- Default destination for logs. The config here is translated to Promtail client + # configuration to write logs to this Loki-compatible remote. Optional. + remote: + # -- Full URL for Loki push endpoint. Usually ends in /loki/api/v1/push + url: "" + + auth: + # -- Used to set X-Scope-OrgID header on requests. Usually not used in combination with username and password. + tenantId: "" + + # -- Basic authentication username. Optional. + username: "" + + # -- The value under key passwordSecretKey in this secret will be used as the basic authentication password. Required only if passwordSecretKey is set. + passwordSecretName: "" + # -- The value under this key in passwordSecretName will be used as the basic authentication password. Required only if passwordSecretName is set. + passwordSecretKey: "" + + # -- Client configurations for the LogsInstance that will scrape Mimir pods. Follows the format of .remote. + additionalClientConfigs: [] + + metrics: + # -- Controls whether to create MetricsInstance resources and ServiceMonitor resources for scraping Kubernetes (when .scrapeK8s.enabled=true). + enabled: true + + # -- Default destination for metrics. The config here is translated to remote_write + # configuration to push metrics to this Prometheus-compatible remote. Optional. + # Note that you need to configure serviceMonitor in order to have some metrics available. + # + # If you leave the metaMonitoring.grafanaAgent.metrics.remote.url field empty, + # then the chart automatically fills in the address of the GEM gateway Service + # or the Mimir NGINX Service. + # + # If you have deployed Mimir, and metaMonitoring.grafanaAgent.metrics.remote.url is not set, + # then the metamonitoring metrics are be sent to the Mimir cluster. + # You can query these metrics using the HTTP header X-Scope-OrgID: metamonitoring + # + # If you have deployed GEM, then there are two cases: + # * If are using the 'trust' authentication type (mimir.structuredConfig.auth.type: trust), + # then the same instructions apply as for Mimir. + # + # * If you are using the enterprise authentication type (mimir.structuredConfig.auth.type=enterprise, which is also the default when enterprise.enabled=true), + # then you also need to provide a Secret with the authentication token for the tenant. + # The token should be to an access policy with metrics:read scope. + # To set up the Secret, refer to https://grafana.com/docs/helm-charts/mimir-distributed/latest/run-production-environment-with-helm/monitor-system-health/ + # Assuming you are using the GEM authentication model, the Helm chart values should look like the following example. + # + # remote: + # auth: + # username: metamonitoring + # passwordSecretName: gem-tokens + # passwordSecretKey: metamonitoring + remote: + # -- Full URL for Prometheus remote-write. Usually ends in /push. + # If you leave the url field empty, then the chart automatically fills in the + # address of the GEM gateway Service or the Mimir NGINX Service. + url: "" + + # -- Used to add HTTP headers to remote-write requests. + headers: {} + auth: + # -- Basic authentication username. Optional. + username: "" + + # -- The value under key passwordSecretKey in this secret will be used as the basic authentication password. Required only if passwordSecretKey is set. + passwordSecretName: "" + # -- The value under this key in passwordSecretName will be used as the basic authentication password. Required only if passwordSecretName is set. + passwordSecretKey: "" + + # -- Additional remote-write for the MetricsInstance that will scrape Mimir pods. Follows the format of .remote. + additionalRemoteWriteConfigs: [] + + scrapeK8s: + # -- When grafanaAgent.enabled and serviceMonitor.enabled, controls whether to create ServiceMonitors CRs + # for cadvisor, kubelet, and kube-state-metrics. The scraped metrics are reduced to those pertaining to + # Mimir pods only. + enabled: true + + # -- Controls service discovery of kube-state-metrics. + kubeStateMetrics: + namespace: kube-system + labelSelectors: + app.kubernetes.io/name: kube-state-metrics + service: + port: http-metrics + + # -- The scrape interval for all ServiceMonitors. + scrapeInterval: 60s + + # -- Sets the namespace of the resources. Leave empty or unset to use the same namespace as the Helm release. + namespace: "" + + # -- Labels to add to all monitoring.grafana.com custom resources. + # Does not affect the ServiceMonitors for kubernetes metrics; use serviceMonitor.labels for that. + labels: {} + + # -- Annotations to add to all monitoring.grafana.com custom resources. + # Does not affect the ServiceMonitors for kubernetes metrics; use serviceMonitor.annotations for that. + annotations: {} + + # -- SecurityContext of Grafana Agent pods. This is different from the SecurityContext that the operator pod runs with. + # The operator pod SecurityContext is configured in the grafana-agent-operator.podSecurityContext value. + # As of mimir-distributed 4.0.0 the Agent DaemonSet that collects logs needs to run as root and be able to access the + # pod logs on each host. Because of that the agent subchart is incompatible with the PodSecurityPolicy of the + # mimir-distributed chart and with the Restricted policy of Pod Security Standards https://kubernetes.io/docs/concepts/security/pod-security-standards/ + podSecurityContext: + # fsGroup: 10001 + # runAsGroup: 10001 + # runAsNonRoot: true + # runAsUser: 10001 + # seccompProfile: + # type: RuntimeDefault + + # -- SecurityContext of Grafana Agent containers. This is different from the SecurityContext that the operator container runs with. + # As of mimir-distributed 4.0.0 the agent subchart needs to have root file system write access so that the Agent pods can write temporary files where. + # This makes the subchart incompatible with the PodSecurityPolicy of the mimir-distributed chart. + containerSecurityContext: + # allowPrivilegeEscalation: false + # runAsUser: 10001 + # capabilities: + # drop: [ALL] + +# -- Values exposed by the [Grafana agent-operator chart](https://github.com/grafana/helm-charts/blob/main/charts/agent-operator/values.yaml) +grafana-agent-operator: + podSecurityContext: + fsGroup: 10001 + runAsGroup: 10001 + runAsNonRoot: true + runAsUser: 10001 + seccompProfile: + type: RuntimeDefault + + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + +############################################################################## +# The values in and after the `enterprise:` key configure the enterprise features +enterprise: + # Enable enterprise features. License must be provided, nginx gateway is not installed, instead + # the enterprise gateway is used. + enabled: false + + # Whether to generate pre-2.0 Grafana Enterprise Metrics resource labels and selectors, or generate new Kubernetes standard selectors. + # Rolling upgrade from version 1.7.x without downtime requires this setting to be true. Fresh installation or upgrade with downtime can set + # it to false. + legacyLabels: false + + image: + # -- Grafana Enterprise Metrics container image repository. Note: for Grafana Mimir use the value 'image.repository' + repository: grafana/enterprise-metrics + # -- Grafana Enterprise Metrics container image tag. Note: for Grafana Mimir use the value 'image.tag' + tag: v2.12.0 + # Note: pullPolicy and optional pullSecrets are set in toplevel 'image' section, not here + +# In order to use Grafana Enterprise Metrics features, you will need to provide the contents of your Grafana Enterprise Metrics +# license, either by providing the contents of the license.jwt, or the name Kubernetes Secret that contains your license.jwt. +# To set the license contents, use the flag `--set-file 'license.contents=./license.jwt'` +# To use your own Kubernetes Secret, `--set license.external=true`. +license: + contents: "NOTAVALIDLICENSE" + external: false + secretName: '{{ include "mimir.resourceName" (dict "ctx" . "component" "license") }}' + +# Settings for the initial admin(istrator) token generator job. Can only be enabled if +# enterprise.enabled is true - requires license. +tokengenJob: + enable: true + extraArgs: {} + env: [] + extraEnvFrom: [] + annotations: {} + initContainers: [] + + # -- SecurityContext override for tokengenjob pods + securityContext: {} + + # -- The SecurityContext for tokengenjob containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + # -- The name of the PriorityClass for tokenjobgen pods + priorityClassName: null + +# Settings for the admin_api service providing authentication and authorization service. +# Can only be enabled if enterprise.enabled is true - requires license. +admin_api: + replicas: 1 + + annotations: {} + service: + annotations: {} + labels: {} + + initContainers: [] + + strategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 15% + + podLabels: {} + podAnnotations: {} + + nodeSelector: {} + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: + maxSkew: 1 + topologyKey: kubernetes.io/hostname + whenUnsatisfiable: ScheduleAnyway + + # Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + + # -- The name of the PriorityClass for admin-api pods + priorityClassName: null + + # -- SecurityContext override for admin-api pods + securityContext: {} + + # -- The SecurityContext for admin_api containers + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + extraArgs: {} + + persistence: + subPath: + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + + resources: + requests: + cpu: 10m + memory: 32Mi + + terminationGracePeriodSeconds: 60 + + tolerations: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + env: [] + extraEnvFrom: [] + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: null + +# -- Cache for admin bucket. +# If this is disabled, in-memory cache will be set by default. +# You can use Redis too for cache and set the configuration via structuredConfig. +# See GEM documentation for Redis configuration option. +admin-cache: + # -- Specifies whether admin-cache using memcached should be enabled + enabled: false + + # -- Total number of admin-cache replicas + replicas: 1 + + # -- Port of the admin-cache service + port: 11211 + + # -- Amount of memory allocated to admin-cache for object storage (in MB). + allocatedMemory: 64 + + # -- Maximum item memory for admin-cache (in MB). + maxItemMemory: 1 + + # -- Maximum number of connections allowed + connectionLimit: 16384 + + # -- Extra init containers for admin-cache pods + initContainers: [] + + # -- Annotations for the admin-cache pods + annotations: {} + # -- Node selector for admin-cache pods + nodeSelector: {} + # -- Affinity for admin-cache pods + affinity: {} + + # -- topologySpreadConstraints allows to customize the default topologySpreadConstraints. This can be either a single dict as shown below or a slice of topologySpreadConstraints. + # labelSelector is taken from the constraint itself (if it exists) or is generated by the chart using the same selectors as for services. + topologySpreadConstraints: {} + # maxSkew: 1 + # topologyKey: kubernetes.io/hostname + # whenUnsatisfiable: ScheduleAnyway + + # -- Tolerations for admin-cache pods + tolerations: [] + # -- Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + # -- The name of the PriorityClass for admin-cache pods + priorityClassName: null + # -- Labels for admin-cache pods + podLabels: {} + # -- Annotations for admin-cache pods + podAnnotations: {} + # -- Management policy for admin-cache pods + podManagementPolicy: Parallel + # -- Grace period to allow the admin-cache to shutdown before it is killed + terminationGracePeriodSeconds: 60 + + # -- Stateful admin-cache strategy + statefulStrategy: + type: RollingUpdate + + # -- Additional CLI args for admin-cache + extraArgs: {} + + # -- Additional containers to be added to the admin-cache pod. + extraContainers: [] + + # -- Resource requests and limits for the admin-cache + # By default a safe memory limit will be requested based on allocatedMemory value (floor (* 1.2 allocatedMemory)). + resources: null + + # -- Service annotations and labels + service: + annotations: {} + labels: {} + +graphite: + # -- If true, enables graphite querier and graphite write proxy functionality. + # Read more in https://grafana.com/docs/enterprise-metrics/latest/graphite/ + enabled: false + + querier: + # Setting it to null will produce a deployment without replicas set, allowing you to use autoscaling with the deployment + replicas: 2 + + schemasConfiguration: + storageSchemas: |- + [default] + pattern = .* + intervals = 0:1s + retentions = 10s:8d,10min:1y + storageAggregations: |- + [default] + aggregationMethod = avg + pattern = .* + xFilesFactor = 0.1 + + service: + annotations: {} + labels: {} + + # -- Resources for graphite-querier pods + resources: + requests: + cpu: 100m + memory: 128Mi + + # -- Additional graphite-querier container arguments, e.g. log level (debug, info, warn, error) + extraArgs: {} + # -- The name of the PriorityClass for graphite-querier pods + priorityClassName: null + # -- Labels for graphite-querier pods + podLabels: {} + # -- Annotations for graphite-querier pods + podAnnotations: {} + + nodeSelector: {} + affinity: + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchExpressions: + - key: app.kubernetes.io/component + operator: In + values: + - graphite-querier + topologyKey: "kubernetes.io/hostname" + + livenessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + + annotations: {} + persistence: + subPath: + + # -- SecurityContext override for graphite querier pods + securityContext: {} + + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + strategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 15% + + terminationGracePeriodSeconds: 180 + + env: [] + extraEnvFrom: [] + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: null + tolerations: [] + podDisruptionBudget: + maxUnavailable: 1 + initContainers: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + + write_proxy: + replicas: 2 + + service: + annotations: {} + labels: {} + + # -- Resources for graphite-write-proxy pods + resources: + requests: + cpu: 100m + memory: 128Mi + + # -- Additional graphite-write-proxy container arguments, e.g. log level (debug, info, warn, error) + extraArgs: {} + # -- The name of the PriorityClass for graphite-write-proxy pods + priorityClassName: null + # -- Labels for graphite-write-proxy pods + podLabels: {} + # -- Annotations for graphite-write-proxy pods + podAnnotations: {} + # -- Node selector for graphite-write-proxy pods + nodeSelector: {} + # -- Affinity for graphite-write-proxy pods + affinity: + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchExpressions: + - key: app.kubernetes.io/component + operator: In + values: + - graphite-write-proxy + topologyKey: "kubernetes.io/hostname" + + livenessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + + annotations: {} + persistence: + subPath: + + # -- SecurityContext override for graphite write-proxy pods + securityContext: {} + + containerSecurityContext: + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + + strategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 15% + + # -- Grace period to allow the graphite-write-proxy to shutdown before it is killed + terminationGracePeriodSeconds: 180 + env: [] + extraEnvFrom: [] + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: null + tolerations: [] + podDisruptionBudget: + maxUnavailable: 1 + initContainers: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + +# Graphite's aggregation cache. If you want to know more about it please check +# https://grafana.com/docs/enterprise-metrics/latest/graphite/graphite_querier/#aggregation-cache +gr-aggr-cache: + # -- Specifies whether memcached based graphite-aggregation-cache should be enabled. Note that the cache will only appear if graphite is also enabled. + enabled: true + + # -- Total number of graphite-aggregation-cache replicas + replicas: 1 + + # -- Port of the graphite-aggregation-cache service + port: 11211 + + # -- Amount of memory allocated to graphite-aggregation-cache for object storage (in MB). + allocatedMemory: 8192 + + # -- Maximum item memory for graphite-aggregation-cache (in MB). + maxItemMemory: 1 + + # -- Maximum number of connections allowed + connectionLimit: 16384 + + # -- Extra init containers for graphite-aggregation-cache pods + initContainers: [] + + # -- Annotations for the graphite-aggregation-cache pods + annotations: {} + # -- Node selector for graphite-aggregation-cache pods + nodeSelector: {} + # -- Affinity for graphite-aggregation-cache pods + affinity: {} + # -- Tolerations for graphite-aggregation-cache pods + tolerations: [] + # -- Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + # -- The name of the PriorityClass for graphite-aggregation-cache pods + priorityClassName: null + # -- Labels for graphite-aggregation-cache pods + podLabels: {} + # -- Annotations for graphite-aggregation-cache pods + podAnnotations: {} + # -- Management policy for graphite-aggregation-cache pods + podManagementPolicy: Parallel + # -- Grace period to allow the graphite-aggregation-cache to shutdown before it is killed + terminationGracePeriodSeconds: 60 + + # -- Stateful graphite-aggregation-cache strategy + statefulStrategy: + type: RollingUpdate + + # -- Additional CLI args for graphite-aggregation-cache + extraArgs: {} + + # -- Additional containers to be added to the graphite-aggregation-cache pod. + extraContainers: [] + + # -- Resource requests and limits for the graphite-aggregation-cache + # By default a safe memory limit will be requested based on allocatedMemory value (floor (* 1.2 allocatedMemory)). + resources: null + + # -- Service annotations and labels + service: + annotations: {} + labels: {} + +# Graphite's metric name cache. If you want to know more about it please check +# https://grafana.com/docs/enterprise-metrics/latest/graphite/graphite_querier/#metric-name-cache +gr-metricname-cache: + # -- Specifies whether memcached based graphite-metric-name-cache should be enabled. Note that the cache will only appear if graphite is also enabled. + enabled: true + + # -- Total number of graphite-metric-name-cache replicas + replicas: 1 + + # -- Port of the graphite-metric-name-cache service + port: 11211 + + # -- Amount of memory allocated to graphite-metric-name-cache for object storage (in MB). + allocatedMemory: 8192 + + # -- Maximum item memory for graphite-metric-name-cache (in MB). + maxItemMemory: 1 + + # -- Maximum number of connections allowed + connectionLimit: 16384 + + # -- Extra init containers for graphite-metric-name-cache pods + initContainers: [] + + # -- Annotations for the graphite-metric-name-cache pods + annotations: {} + # -- Node selector for graphite-metric-name-cache pods + nodeSelector: {} + # -- Affinity for graphite-metric-name-cache pods + affinity: {} + # -- Tolerations for graphite-metric-name-cache pods + tolerations: [] + # -- Pod Disruption Budget + podDisruptionBudget: + maxUnavailable: 1 + # -- The name of the PriorityClass for graphite-metric-name-cache pods + priorityClassName: null + # -- Labels for graphite-metric-name-cache pods + podLabels: {} + # -- Annotations for graphite-metric-name-cache pods + podAnnotations: {} + # -- Management policy for graphite-metric-name-cache pods + podManagementPolicy: Parallel + # -- Grace period to allow the graphite-metric-name-cache to shutdown before it is killed + terminationGracePeriodSeconds: 60 + + # -- Stateful graphite-metric-name-cache strategy + statefulStrategy: + type: RollingUpdate + + # -- Additional CLI args for graphite-metric-name-cache + extraArgs: {} + + # -- Additional containers to be added to the graphite-metric-name-cache pod. + extraContainers: [] + + # -- Resource requests and limits for the graphite-metric-name-cache + # By default a safe memory limit will be requested based on allocatedMemory value (floor (* 1.2 allocatedMemory)). + resources: null + + # -- Service annotations and labels + service: + annotations: {} + labels: {} + +# -- Settings for the smoke-test job. This is meant to run as a Helm test hook +# (`helm test RELEASE`) after installing the chart. It quickly verifies +# that writing and reading metrics works. Currently not supported for +# installations using GEM token-based authentication. +smoke_test: + image: + repository: grafana/mimir-continuous-test + tag: 2.12.0 + pullPolicy: IfNotPresent + tenantId: "" + extraArgs: {} + env: [] + extraEnvFrom: [] + annotations: {} + initContainers: [] + # -- The name of the PriorityClass for smoke-test pods + priorityClassName: null + +# -- Settings for mimir-continuous-test. +# This continuously writes and reads metrics from Mimir. +# https://grafana.com/docs/mimir/latest/manage/tools/mimir-continuous-test/ +continuous_test: + enabled: false + # -- Number of replicas to start of continuous test + replicas: 1 + image: + repository: grafana/mimir-continuous-test + tag: 2.12.0 + pullPolicy: IfNotPresent + # Note: optional pullSecrets are set in toplevel 'image' section, not here + + # -- Authentication settings of continuous test + auth: + # -- Type of authentication to use (tenantId, basicAuth, bearerToken) + type: tenantId + # -- The tenant to use for tenantId or basicAuth authentication type + # In case of tenantId authentication, it is injected as the X-Scope-OrgID header on requests. + # In case of basicAuth, it is set as the username. + tenant: "mimir-continuous-test" + # -- Password for basicAuth auth (note: can be environment variable from secret attached in extraEnvFrom, e.g. $(PASSWORD)) + # For GEM, it should contain an access token created for an access policy that allows `metrics:read` and `metrics:write` for the tenant. + password: null + # -- Bearer token for bearerToken auth (note: can be environment variable from secret attached in extraEnvFrom, e.g. $(TOKEN)) + bearerToken: null + # -- The maximum number of series to write in a single request. + numSeries: 1000 + # -- How far back in the past metrics can be queried at most. + maxQueryAge: "48h" + # -- Interval between test runs + runInterval: "5m" + + # -- Pod affinity settings for the continuous test replicas + affinity: {} + # -- Annotations for the continuous test Deployment + annotations: {} + # -- The SecurityContext for continuous test containers + containerSecurityContext: + readOnlyRootFilesystem: true + # -- Extra environment variables for continuous test containers + env: [] + # -- Extra command line arguments for the continuous test container + extraArgs: {} + # -- Extra environment from secret/configmap for continuous test containers + extraEnvFrom: [] + # -- Jaeger reporter queue size + # Set to 'null' to use the Jaeger client's default value + jaegerReporterMaxQueueSize: null + # -- Extra volumes for the continuous test container + extraVolumes: [] + # -- Extra volume mounts for the continuous test container + extraVolumeMounts: [] + # -- Extra containers for the continuous test Deployment + extraContainers: [] + # -- Extra initContainers for the continuous test Deployment + initContainers: [] + # -- Nodeselector of continuous test replicas + nodeSelector: {} + # -- The name of the PriorityClass for continuous test pods + priorityClassName: null + # -- Kubernetes resource requests and limits for continuous test + resources: + limits: + memory: 1Gi + requests: + cpu: "1" + memory: 512Mi + # -- Security context for the continuous test Deployment + securityContext: {} + # -- Service for monitoring continuous test + service: + annotations: {} + labels: {} + # -- Upgrade strategy for the continuous test Deployment + strategy: + type: RollingUpdate + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + + tolerations: [] + terminationGracePeriodSeconds: 30 + +# -- Add dynamic manifests via values. Example: +# extraObjects: +# - kind: ConfigMap +# apiVersion: v1 +# metadata: +# name: extra-cm-{{ .Release.Name }} +# data: | +# extra.yml: "does-my-install-need-extra-info: true" +extraObjects: [] diff --git a/observability/lgtm-distributed/charts/oncall/.helmignore b/observability/lgtm-distributed/charts/oncall/.helmignore new file mode 100644 index 0000000..fd6e5fd --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/.helmignore @@ -0,0 +1,26 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*.orig +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ + +# exclude helm unit tests +tests/ diff --git a/observability/lgtm-distributed/charts/oncall/Chart.lock b/observability/lgtm-distributed/charts/oncall/Chart.lock new file mode 100644 index 0000000..e550990 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/Chart.lock @@ -0,0 +1,27 @@ +dependencies: +- name: cert-manager + repository: https://charts.jetstack.io + version: v1.8.0 +- name: mariadb + repository: https://charts.bitnami.com/bitnami + version: 12.2.5 +- name: postgresql + repository: https://charts.bitnami.com/bitnami + version: 11.9.10 +- name: rabbitmq + repository: https://charts.bitnami.com/bitnami + version: 12.0.0 +- name: redis + repository: https://charts.bitnami.com/bitnami + version: 16.13.2 +- name: grafana + repository: https://grafana.github.io/helm-charts + version: 6.57.1 +- name: ingress-nginx + repository: https://kubernetes.github.io/ingress-nginx + version: 4.1.4 +- name: prometheus + repository: https://prometheus-community.github.io/helm-charts + version: 25.8.2 +digest: sha256:edc9fef449a694cd319135e37ac84f8247ac9ad0c48ac86099dae4e428beb7b7 +generated: "2024-06-20T17:56:01.397630734Z" diff --git a/observability/lgtm-distributed/charts/oncall/Chart.yaml b/observability/lgtm-distributed/charts/oncall/Chart.yaml new file mode 100644 index 0000000..2646403 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/Chart.yaml @@ -0,0 +1,39 @@ +apiVersion: v2 +appVersion: v1.7.2 +dependencies: +- condition: cert-manager.enabled + name: cert-manager + repository: https://charts.jetstack.io + version: v1.8.0 +- condition: mariadb.enabled + name: mariadb + repository: https://charts.bitnami.com/bitnami + version: 12.2.5 +- condition: postgresql.enabled + name: postgresql + repository: https://charts.bitnami.com/bitnami + version: 11.9.10 +- condition: rabbitmq.enabled + name: rabbitmq + repository: https://charts.bitnami.com/bitnami + version: 12.0.0 +- condition: redis.enabled + name: redis + repository: https://charts.bitnami.com/bitnami + version: 16.13.2 +- condition: grafana.enabled + name: grafana + repository: https://grafana.github.io/helm-charts + version: 6.57.1 +- condition: ingress-nginx.enabled + name: ingress-nginx + repository: https://kubernetes.github.io/ingress-nginx + version: 4.1.4 +- condition: prometheus.enabled + name: prometheus + repository: https://prometheus-community.github.io/helm-charts + version: 25.8.2 +description: Developer-friendly incident response with brilliant Slack integration +name: oncall +type: application +version: 1.7.2 diff --git a/observability/lgtm-distributed/charts/oncall/README.md b/observability/lgtm-distributed/charts/oncall/README.md new file mode 100644 index 0000000..993f064 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/README.md @@ -0,0 +1,431 @@ +# Grafana OnCall Helm Chart + +This Grafana OnCall Chart is the best way to operate Grafana OnCall on Kubernetes. +It will deploy Grafana OnCall engine and celery workers, along with RabbitMQ cluster, Redis Cluster, and MySQL 5.7 database. +It will also deploy cert manager and nginx ingress controller, as Grafana OnCall backend might need to be externally available +to receive alerts from other monitoring systems. Grafana OnCall engine acts as a backend and can be connected to the +Grafana frontend plugin named Grafana OnCall. +Architecture diagram can be found [here](https://raw.githubusercontent.com/grafana/oncall/dev/docs/img/architecture_diagram.png) + +## Production usage + +**Default helm chart configuration is not intended for production.** +The helm chart includes all the services into a single release, which is not recommended for production usage. +It is recommended to run stateful services such as MySQL and RabbitMQ separately from this release or use managed +PaaS solutions. It will significantly reduce the overhead of managing them. +Here are the instructions on how to set up your own [ingress](#set-up-external-access), [MySQL](#connect-external-mysql), +[RabbitMQ](#connect-external-rabbitmq), [Redis](#connect-external-redis) + +### Cluster requirements + +- ensure you can run x86-64/amd64 workloads. arm64 architecture is currently not supported +- kubernetes version 1.25+ is not supported, if cert-manager is enabled + +## Install + +### Prepare the repo + +```bash +# Add the repository +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update +``` + +### Installing the helm chart + +```bash +# Install the chart +helm install \ + --wait \ + --set base_url=example.com \ + --set grafana."grafana\.ini".server.domain=example.com \ + release-oncall \ + grafana/oncall +``` + +Follow the `helm install` output to finish setting up Grafana OnCall backend and Grafana OnCall frontend plugin e.g. + +```bash +👋 Your Grafana OnCall instance has been successfully deployed + + ❗ Set up a DNS record for your domain (use A Record and "@" to point a root domain to the IP address) + Get the external IP address by running the following commands and point example.com to it: + + kubectl get ingress release-oncall -o jsonpath="{.status.loadBalancer.ingress[0].ip}" + + Wait until the dns record got propagated. + NOTE: Check with the following command: nslookup example.com + Try reaching https://example.com/ready/ from the browser, make sure it is not cached locally + + 🦎 Grafana was installed as a part of this helm release. Open https://example.com/grafana/plugins/grafana-oncall-app + The User is admin + Get password by running this command: + + kubectl get secret --namespace default release-oncall-grafana -o jsonpath="{.data.admin-password}" | base64 --decode ; echo + + 🔗 Connect Grafana OnCall Plugin to Grafana OnCall backend: + + Fill the Grafana OnCall Backend URL: + + http://release-oncall-engine:8080 + +🎉🎉🎉 Done! 🎉🎉🎉 +``` + +## Configuration + +You can edit values.yml to make changes to the helm chart configuration and re-deploy the release with the following command: + +```bash +helm upgrade \ + --install \ + --wait \ + --set base_url=example.com \ + --set grafana."grafana\.ini".server.domain=example.com \ + release-oncall \ + grafana/oncall +``` + +### Passwords and external secrets + +As OnCall subcharts are Bitname charts, there is a common approach to secrets. Bundled charts allow specifying passwords +in values.yaml explicitly or as K8s secret value. OnCall chart refers either to secret created in sub-chart or +to specified external secret. +Similarly, if component chart is disabled, the password(s) can be supplied in `external` value +(e.g. externalMysql) explicitly or as K8s secret value. In the first case, the secret is created with the specified +value. In the second case the external secret is used. + +- If `.auth.existingSecret` is non-empty, then this secret is used. Secret keys are pre-defined by chart. +- If subchart supports password files and `.customPasswordFiles` dictionary is non-empty, then password files + are used. Dictionary keys are pre-defined per sub-chart. Password files are not supported by OnCall chart and should + not be used with bundled sub-charts. +- Passwords are specified via `auth` section values, e.g. `auth.password`. K8s secret is created. + - If `.auth.forcePassword` is `true`, then passwords MUST be specified. Otherwise, missing passwords + are generated. + +If external component is used instead of the bundled one: + +- If existingSecret within appropriate external component values is non-empty (e.g. `externalMysql.existingSecret`) then + it is used together with corresponding key names, e.g. `externalMysql.passwordKey`. +- Otherwise, corresponding password values are used, e.g. `externalMysql.password`. K8s secret is created by OnCall chart. + +Below is the summary for the dependent charts. + +MySQL/MariaDB: + +```yaml +database: + type: "mysql" # This is default +mariaDB: + enabled: true # Default + auth: + existingSecret: "" + forcePassword: false + # Secret name: `-mariadb` + rootPassword: "" # Secret key: mariadb-root-password + password: "" # Secret key: mariadb-password + replicationPassword: "" # Secret key: mariadb-replication-password +externalMysql: + password: "" + existingSecret: "" + passwordKey: "" +``` + +Postgres: + +```yaml +database: + type: postgresql +mariadb: + enabled: false # Must be set to false for Postgres +postgresql: + enabled: true # Must be set to true for bundled Postgres + auth: + existingSecret: "" + secretKeys: + adminPasswordKey: "" + userPasswordKey: "" # Not needed + replicationPasswordKey: "" # Not needed with disabled replication + # Secret name: `-postgresql` + postgresPassword: "" # password for admin user postgres. As non-admin user is not created, only this one is relevant. + password: "" # Not needed + replicationPassword: "" # Not needed with disabled replication +externalPostgresql: + user: "" + password: "" + existingSecret: "" + passwordKey: "" +``` + +Rabbitmq: + +```yaml +rabbitmq: + enabled: true + auth: + existingPasswordSecret: "" # Must contain `rabbitmq-password` key + existingErlangSecret: "" # Must contain `rabbitmq-erlang-cookie` key + # Secret name: `-rabbitmq` + password: "" + erlangCookie: "" +externalRabbitmq: + user: "" + password: "" + existingSecret: "" + passwordKey: "" + usernameKey: "" +``` + +Redis: + +```yaml +redis: + enabled: true + auth: + existingSecret: "" + existingSecretPasswordKey: "" + # Secret name: `-redis` + password: "" +externalRedis: + password: "" + existingSecret: "" + passwordKey: "" +``` + +### Running split ingestion and API services + +You can run a detached service for handling integrations by setting up the following variables: + +```yaml +detached_integrations: + enabled: true +detached_integrations_service: + enabled: true +``` + +This will run an integrations-only service listening by default in port 30003. + +### Set up Slack and Telegram + +You can set up Slack connection via following variables: + +```yaml +oncall: + slack: + enabled: true + commandName: oncall + clientId: ~ + clientSecret: ~ + signingSecret: ~ + existingSecret: "" + clientIdKey: "" + clientSecretKey: "" + signingSecretKey: "" + redirectHost: ~ +``` + +`oncall.slack.commandName` is used for changing default bot slash command, +`oncall`. In slack, it could be called via `/`. + +To set up Telegram token and webhook url use: + +```yaml +oncall: + telegram: + enabled: true + token: ~ + webhookUrl: ~ +``` + +To use Telegram long polling instead of webhook use: + +```yaml +telegramPolling: + enabled: true +``` + +### Set up external access + +Grafana OnCall can be connected to the external monitoring systems or grafana deployed to the other cluster. +Nginx Ingress Controller and Cert Manager charts are included in the helm chart with the default configuration. +If you set the DNS A Record pointing to the external IP address of the installation with the Hostname matching +base_url parameter, https will be automatically set up. If grafana is enabled in the chart values, it will also be +available on `https:///grafana/`. See the details in `helm install` output. + +To use a different ingress controller or tls certificate management system, set the following values to +false and edit ingress settings + +```yaml +ingress-nginx: + enabled: false + +cert-manager: + enabled: false + +ingress: + enabled: true + annotations: + kubernetes.io/ingress.class: "nginx" + cert-manager.io/issuer: "letsencrypt-prod" +``` + +### Use PostgreSQL instead of MySQL + +It is possible to use PostgreSQL instead of MySQL. To do so, set mariadb.enabled to `false`, +postgresql.enabled to `true` and database.type to `postgresql`. + +```yaml +mariadb: + enabled: false + +postgresql: + enabled: true + +database: + type: postgresql +``` + +### Connect external MySQL + +It is recommended to use the managed MySQL 5.7 database provided by your cloud provider +Make sure to create the database with the following parameters before installing this chart + +```sql +CREATE DATABASE oncall CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci; +``` + +To use an external MySQL instance set mariadb.enabled to `false` and configure the `externalMysql` parameters. + +```yaml +mariadb: + enabled: false + +# Make sure to create the database with the following parameters: +# CREATE DATABASE oncall CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci; +externalMysql: + host: + port: + db_name: + user: + password: + existingSecret: "" + usernameKey: username + passwordKey: password +``` + +### Connect external PostgreSQL + +To use an external PostgreSQL instance set mariadb.enabled to `false`, +postgresql.enabled to `false`, database.type to `postgresql` and configure +the `externalPostgresql` parameters. + +```yaml +mariadb: + enabled: false + +postgresql: + enabled: false + +database: + type: postgresql + +# Make sure to create the database with the following parameters: +# CREATE DATABASE oncall WITH ENCODING UTF8; +externalPostgresql: + host: + port: + db_name: + user: + password: + existingSecret: "" + passwordKey: password +``` + +### Connect external RabbitMQ + +Option 1. Install RabbitMQ separately into the cluster using the [official documentation](https://www.rabbitmq.com/kubernetes/operator/operator-overview.html) +Option 2. Use managed solution such as [CloudAMPQ](https://www.cloudamqp.com/) + +To use an external RabbitMQ instance set rabbitmq.enabled to `false` and configure the `externalRabbitmq` parameters. + +```yaml +rabbitmq: + enabled: false # Disable the RabbitMQ dependency from the release + +externalRabbitmq: + host: + port: + user: + password: + protocol: + vhost: + existingSecret: "" + passwordKey: password + usernameKey: username +``` + +### Connect external Redis + +To use an external Redis instance set redis.enabled to `false` and configure the `externalRedis` parameters. + +```yaml +redis: + enabled: false # Disable the Redis dependency from the release + +externalRedis: + host: + password: + existingSecret: "" + passwordKey: password +``` + +## Update + +```bash +# Add & upgrade the repository +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update + +# Re-deploy +helm upgrade \ + --install \ + --wait \ + --set base_url=example.com \ + --set grafana."grafana\.ini".server.domain=example.com \ + release-oncall \ + grafana/oncall +``` + +After re-deploying, please also update the Grafana OnCall plugin on the plugin version page. +See [Grafana docs](https://grafana.com/docs/grafana/latest/administration/plugin-management/#update-a-plugin) for +more info on updating Grafana plugins. + +## Uninstall + +### Uninstalling the helm chart + +```bash +helm delete release-oncall +``` + +### Clean up PVC's + +```bash +kubectl delete pvc data-release-oncall-mariadb-0 data-release-oncall-rabbitmq-0 \ +redis-data-release-oncall-redis-master-0 redis-data-release-oncall-redis-replicas-0 \ +redis-data-release-oncall-redis-replicas-1 redis-data-release-oncall-redis-replicas-2 +``` + +### Clean up secrets + +```bash +kubectl delete secrets certificate-tls release-oncall-cert-manager-webhook-ca release-oncall-ingress-nginx-admission +``` + +## Troubleshooting + +### Issues during initial configuration + +In the event that you run into issues during initial configuration, it is possible that mismatching versions between +your OnCall backend and UI is the culprit. Ensure that the versions match, and if not, +consider updating your `helm` deployment. diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/Chart.yaml new file mode 100644 index 0000000..44da745 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/Chart.yaml @@ -0,0 +1,22 @@ +annotations: + artifacthub.io/prerelease: "false" + artifacthub.io/signKey: | + fingerprint: 1020CF3C033D4F35BAE1C19E1226061C665DF13E + url: https://cert-manager.io/public-keys/cert-manager-keyring-2021-09-20-1020CF3C033D4F35BAE1C19E1226061C665DF13E.gpg +apiVersion: v1 +appVersion: v1.8.0 +description: A Helm chart for cert-manager +home: https://github.com/cert-manager/cert-manager +icon: https://raw.githubusercontent.com/jetstack/cert-manager/master/logo/logo.png +keywords: +- cert-manager +- kube-lego +- letsencrypt +- tls +maintainers: +- email: cert-manager-maintainers@googlegroups.com + name: cert-manager-maintainers +name: cert-manager +sources: +- https://github.com/cert-manager/cert-manager +version: v1.8.0 diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/README.md b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/README.md new file mode 100644 index 0000000..5adc560 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/README.md @@ -0,0 +1,220 @@ +# cert-manager + +cert-manager is a Kubernetes addon to automate the management and issuance of +TLS certificates from various issuing sources. + +It will ensure certificates are valid and up to date periodically, and attempt +to renew certificates at an appropriate time before expiry. + +## Prerequisites + +- Kubernetes 1.18+ + +## Installing the Chart + +Full installation instructions, including details on how to configure extra +functionality in cert-manager can be found in the [installation docs](https://cert-manager.io/docs/installation/kubernetes/). + +Before installing the chart, you must first install the cert-manager CustomResourceDefinition resources. +This is performed in a separate step to allow you to easily uninstall and reinstall cert-manager without deleting your installed custom resources. + +```bash +$ kubectl apply -f https://github.com/cert-manager/cert-manager/releases/download/v1.8.0/cert-manager.crds.yaml +``` + +To install the chart with the release name `my-release`: + +```console +## Add the Jetstack Helm repository +$ helm repo add jetstack https://charts.jetstack.io + +## Install the cert-manager helm chart +$ helm install my-release --namespace cert-manager --version v1.8.0 jetstack/cert-manager +``` + +In order to begin issuing certificates, you will need to set up a ClusterIssuer +or Issuer resource (for example, by creating a 'letsencrypt-staging' issuer). + +More information on the different types of issuers and how to configure them +can be found in [our documentation](https://cert-manager.io/docs/configuration/). + +For information on how to configure cert-manager to automatically provision +Certificates for Ingress resources, take a look at the +[Securing Ingresses documentation](https://cert-manager.io/docs/usage/ingress/). + +> **Tip**: List all releases using `helm list` + +## Upgrading the Chart + +Special considerations may be required when upgrading the Helm chart, and these +are documented in our full [upgrading guide](https://cert-manager.io/docs/installation/upgrading/). + +**Please check here before performing upgrades!** + +## Uninstalling the Chart + +To uninstall/delete the `my-release` deployment: + +```console +$ helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + +If you want to completely uninstall cert-manager from your cluster, you will also need to +delete the previously installed CustomResourceDefinition resources: + +```console +$ kubectl delete -f https://github.com/cert-manager/cert-manager/releases/download/v1.8.0/cert-manager.crds.yaml +``` + +## Configuration + +The following table lists the configurable parameters of the cert-manager chart and their default values. + +| Parameter | Description | Default | +| --------- | ----------- | ------- | +| `global.imagePullSecrets` | Reference to one or more secrets to be used when pulling images | `[]` | +| `global.rbac.create` | If `true`, create and use RBAC resources (includes sub-charts) | `true` | +| `global.priorityClassName`| Priority class name for cert-manager and webhook pods | `""` | +| `global.podSecurityPolicy.enabled` | If `true`, create and use PodSecurityPolicy (includes sub-charts) | `false` | +| `global.podSecurityPolicy.useAppArmor` | If `true`, use Apparmor seccomp profile in PSP | `true` | +| `global.leaderElection.namespace` | Override the namespace used to store the ConfigMap for leader election | `kube-system` | +| `global.leaderElection.leaseDuration` | The duration that non-leader candidates will wait after observing a leadership renewal until attempting to acquire leadership of a led but unrenewed leader slot. This is effectively the maximum duration that a leader can be stopped before it is replaced by another candidate | | +| `global.leaderElection.renewDeadline` | The interval between attempts by the acting master to renew a leadership slot before it stops leading. This must be less than or equal to the lease duration | | +| `global.leaderElection.retryPeriod` | The duration the clients should wait between attempting acquisition and renewal of a leadership | | +| `installCRDs` | If true, CRD resources will be installed as part of the Helm chart. If enabled, when uninstalling CRD resources will be deleted causing all installed custom resources to be DELETED | `false` | +| `image.repository` | Image repository | `quay.io/jetstack/cert-manager-controller` | +| `image.tag` | Image tag | `v1.8.0` | +| `image.pullPolicy` | Image pull policy | `IfNotPresent` | +| `replicaCount` | Number of cert-manager replicas | `1` | +| `clusterResourceNamespace` | Override the namespace used to store DNS provider credentials etc. for ClusterIssuer resources | Same namespace as cert-manager pod | +| `featureGates` | Set of comma-separated key=value pairs that describe feature gates on the controller. Some feature gates may also have to be enabled on other components, and can be set supplying the `feature-gate` flag to `.extraArgs` | `` | +| `extraArgs` | Optional flags for cert-manager | `[]` | +| `extraEnv` | Optional environment variables for cert-manager | `[]` | +| `serviceAccount.create` | If `true`, create a new service account | `true` | +| `serviceAccount.name` | Service account to be used. If not set and `serviceAccount.create` is `true`, a name is generated using the fullname template | | +| `serviceAccount.annotations` | Annotations to add to the service account | | +| `serviceAccount.automountServiceAccountToken` | Automount API credentials for the Service Account | `true` | +| `volumes` | Optional volumes for cert-manager | `[]` | +| `volumeMounts` | Optional volume mounts for cert-manager | `[]` | +| `resources` | CPU/memory resource requests/limits | `{}` | +| `securityContext` | Optional security context. The yaml block should adhere to the [SecurityContext spec](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.22/#securitycontext-v1-core) | `{}` | +| `securityContext.enabled` | Deprecated (use `securityContext`) - Enable security context | `false` | +| `containerSecurityContext` | Security context to be set on the controller component container | `{}` | +| `nodeSelector` | Node labels for pod assignment | `{}` | +| `affinity` | Node affinity for pod assignment | `{}` | +| `tolerations` | Node tolerations for pod assignment | `[]` | +| `ingressShim.defaultIssuerName` | Optional default issuer to use for ingress resources | | +| `ingressShim.defaultIssuerKind` | Optional default issuer kind to use for ingress resources | | +| `ingressShim.defaultIssuerGroup` | Optional default issuer group to use for ingress resources | | +| `prometheus.enabled` | Enable Prometheus monitoring | `true` | +| `prometheus.servicemonitor.enabled` | Enable Prometheus Operator ServiceMonitor monitoring | `false` | +| `prometheus.servicemonitor.namespace` | Define namespace where to deploy the ServiceMonitor resource | (namespace where you are deploying) | +| `prometheus.servicemonitor.prometheusInstance` | Prometheus Instance definition | `default` | +| `prometheus.servicemonitor.targetPort` | Prometheus scrape port | `9402` | +| `prometheus.servicemonitor.path` | Prometheus scrape path | `/metrics` | +| `prometheus.servicemonitor.interval` | Prometheus scrape interval | `60s` | +| `prometheus.servicemonitor.labels` | Add custom labels to ServiceMonitor | | +| `prometheus.servicemonitor.scrapeTimeout` | Prometheus scrape timeout | `30s` | +| `prometheus.servicemonitor.honorLabels` | Enable label honoring for metrics scraped by Prometheus (see [Prometheus scrape config docs](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#scrape_config) for details). By setting `honorLabels` to `true`, Prometheus will prefer label contents given by cert-manager on conflicts. Can be used to remove the "exported_namespace" label for example. | `false` | +| `podAnnotations` | Annotations to add to the cert-manager pod | `{}` | +| `deploymentAnnotations` | Annotations to add to the cert-manager deployment | `{}` | +| `podDnsPolicy` | Optional cert-manager pod [DNS policy](https://kubernetes.io/docs/concepts/services-networking/dns-pod-service/#pods-dns-policy) | | +| `podDnsConfig` | Optional cert-manager pod [DNS configurations](https://kubernetes.io/docs/concepts/services-networking/dns-pod-service/#pods-dns-config) | | +| `podLabels` | Labels to add to the cert-manager pod | `{}` | +| `serviceLabels` | Labels to add to the cert-manager controller service | `{}` | +| `serviceAnnotations` | Annotations to add to the cert-manager service | `{}` | +| `http_proxy` | Value of the `HTTP_PROXY` environment variable in the cert-manager pod | | +| `https_proxy` | Value of the `HTTPS_PROXY` environment variable in the cert-manager pod | | +| `no_proxy` | Value of the `NO_PROXY` environment variable in the cert-manager pod | | +| `webhook.replicaCount` | Number of cert-manager webhook replicas | `1` | +| `webhook.timeoutSeconds` | Seconds the API server should wait the webhook to respond before treating the call as a failure. | `10` | +| `webhook.podAnnotations` | Annotations to add to the webhook pods | `{}` | +| `webhook.podLabels` | Labels to add to the cert-manager webhook pod | `{}` | +| `webhook.serviceLabels` | Labels to add to the cert-manager webhook service | `{}` | +| `webhook.deploymentAnnotations` | Annotations to add to the webhook deployment | `{}` | +| `webhook.mutatingWebhookConfigurationAnnotations` | Annotations to add to the mutating webhook configuration | `{}` | +| `webhook.validatingWebhookConfigurationAnnotations` | Annotations to add to the validating webhook configuration | `{}` | +| `webhook.serviceAnnotations` | Annotations to add to the webhook service | `{}` | +| `webhook.config` | WebhookConfiguration YAML used to configure flags for the webhook. Generates a ConfigMap containing contents of the field. See `values.yaml` for example. | `{}` | +| `webhook.extraArgs` | Optional flags for cert-manager webhook component | `[]` | +| `webhook.serviceAccount.create` | If `true`, create a new service account for the webhook component | `true` | +| `webhook.serviceAccount.name` | Service account for the webhook component to be used. If not set and `webhook.serviceAccount.create` is `true`, a name is generated using the fullname template | | +| `webhook.serviceAccount.annotations` | Annotations to add to the service account for the webhook component | | +| `webhook.serviceAccount.automountServiceAccountToken` | Automount API credentials for the webhook Service Account | | +| `webhook.resources` | CPU/memory resource requests/limits for the webhook pods | `{}` | +| `webhook.nodeSelector` | Node labels for webhook pod assignment | `{}` | +| `webhook.affinity` | Node affinity for webhook pod assignment | `{}` | +| `webhook.tolerations` | Node tolerations for webhook pod assignment | `[]` | +| `webhook.image.repository` | Webhook image repository | `quay.io/jetstack/cert-manager-webhook` | +| `webhook.image.tag` | Webhook image tag | `v1.8.0` | +| `webhook.image.pullPolicy` | Webhook image pull policy | `IfNotPresent` | +| `webhook.securePort` | The port that the webhook should listen on for requests. | `10250` | +| `webhook.securityContext` | Security context for webhook pod assignment | `{}` | +| `webhook.containerSecurityContext` | Security context to be set on the webhook component container | `{}` | +| `webhook.hostNetwork` | If `true`, run the Webhook on the host network. | `false` | +| `webhook.serviceType` | The type of the `Service`. | `ClusterIP` | +| `webhook.loadBalancerIP` | The specific load balancer IP to use (when `serviceType` is `LoadBalancer`). | | +| `webhook.url.host` | The host to use to reach the webhook, instead of using internal cluster DNS for the service. | | +| `webhook.livenessProbe.failureThreshold` | The liveness probe failure threshold | `3` | +| `webhook.livenessProbe.initialDelaySeconds` | The liveness probe initial delay (in seconds) | `60` | +| `webhook.livenessProbe.periodSeconds` | The liveness probe period (in seconds) | `10` | +| `webhook.livenessProbe.successThreshold` | The liveness probe success threshold | `1` | +| `webhook.livenessProbe.timeoutSeconds` | The liveness probe timeout (in seconds) | `1` | +| `webhook.readinessProbe.failureThreshold` | The readiness probe failure threshold | `3` | +| `webhook.readinessProbe.initialDelaySeconds` | The readiness probe initial delay (in seconds) | `5` | +| `webhook.readinessProbe.periodSeconds` | The readiness probe period (in seconds) | `5` | +| `webhook.readinessProbe.successThreshold` | The readiness probe success threshold | `1` | +| `webhook.readinessProbe.timeoutSeconds` | The readiness probe timeout (in seconds) | `1` | +| `cainjector.enabled` | Toggles whether the cainjector component should be installed (required for the webhook component to work) | `true` | +| `cainjector.replicaCount` | Number of cert-manager cainjector replicas | `1` | +| `cainjector.podAnnotations` | Annotations to add to the cainjector pods | `{}` | +| `cainjector.podLabels` | Labels to add to the cert-manager cainjector pod | `{}` | +| `cainjector.deploymentAnnotations` | Annotations to add to the cainjector deployment | `{}` | +| `cainjector.extraArgs` | Optional flags for cert-manager cainjector component | `[]` | +| `cainjector.serviceAccount.create` | If `true`, create a new service account for the cainjector component | `true` | +| `cainjector.serviceAccount.name` | Service account for the cainjector component to be used. If not set and `cainjector.serviceAccount.create` is `true`, a name is generated using the fullname template | | +| `cainjector.serviceAccount.annotations` | Annotations to add to the service account for the cainjector component | | +| `cainjector.serviceAccount.automountServiceAccountToken` | Automount API credentials for the cainjector Service Account | `true` | +| `cainjector.resources` | CPU/memory resource requests/limits for the cainjector pods | `{}` | +| `cainjector.nodeSelector` | Node labels for cainjector pod assignment | `{}` | +| `cainjector.affinity` | Node affinity for cainjector pod assignment | `{}` | +| `cainjector.tolerations` | Node tolerations for cainjector pod assignment | `[]` | +| `cainjector.image.repository` | cainjector image repository | `quay.io/jetstack/cert-manager-cainjector` | +| `cainjector.image.tag` | cainjector image tag | `v1.8.0` | +| `cainjector.image.pullPolicy` | cainjector image pull policy | `IfNotPresent` | +| `cainjector.securityContext` | Security context for cainjector pod assignment | `{}` | +| `cainjector.containerSecurityContext` | Security context to be set on cainjector component container | `{}` | +| `startupapicheck.enabled` | Toggles whether the startupapicheck Job should be installed | `true` | +| `startupapicheck.securityContext` | Pod Security Context to be set on the startupapicheck component Pod | `{}` | +| `startupapicheck.timeout` | Timeout for 'kubectl check api' command | `1m` | +| `startupapicheck.backoffLimit` | Job backoffLimit | `4` | +| `startupapicheck.jobAnnotations` | Optional additional annotations to add to the startupapicheck Job | `{}` | +| `startupapicheck.podAnnotations` | Optional additional annotations to add to the startupapicheck Pods | `{}` | +| `startupapicheck.extraArgs` | Optional additional arguments for startupapicheck | `[]` | +| `startupapicheck.resources` | CPU/memory resource requests/limits for the startupapicheck pod | `{}` | +| `startupapicheck.nodeSelector` | Node labels for startupapicheck pod assignment | `{}` | +| `startupapicheck.affinity` | Node affinity for startupapicheck pod assignment | `{}` | +| `startupapicheck.tolerations` | Node tolerations for startupapicheck pod assignment | `[]` | +| `startupapicheck.podLabels` | Optional additional labels to add to the startupapicheck Pods | `{}` | +| `startupapicheck.image.repository` | startupapicheck image repository | `quay.io/jetstack/cert-manager-ctl` | +| `startupapicheck.image.tag` | startupapicheck image tag | `v1.8.0` | +| `startupapicheck.image.pullPolicy` | startupapicheck image pull policy | `IfNotPresent` | +| `startupapicheck.serviceAccount.create` | If `true`, create a new service account for the startupapicheck component | `true` | +| `startupapicheck.serviceAccount.name` | Service account for the startupapicheck component to be used. If not set and `startupapicheck.serviceAccount.create` is `true`, a name is generated using the fullname template | | +| `startupapicheck.serviceAccount.annotations` | Annotations to add to the service account for the startupapicheck component | | +| `startupapicheck.serviceAccount.automountServiceAccountToken` | Automount API credentials for the startupapicheck Service Account | `true` | + +Specify each parameter using the `--set key=value[,key=value]` argument to `helm install`. + +Alternatively, a YAML file that specifies the values for the above parameters can be provided while installing the chart. For example, + +```console +$ helm install my-release -f values.yaml . +``` +> **Tip**: You can use the default [values.yaml](https://github.com/cert-manager/cert-manager/blob/master/deploy/charts/cert-manager/values.yaml) + +## Contributing + +This chart is maintained at [github.com/cert-manager/cert-manager](https://github.com/cert-manager/cert-manager/tree/master/deploy/charts/cert-manager). diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/NOTES.txt new file mode 100644 index 0000000..1025354 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/NOTES.txt @@ -0,0 +1,15 @@ +cert-manager {{ .Chart.AppVersion }} has been deployed successfully! + +In order to begin issuing certificates, you will need to set up a ClusterIssuer +or Issuer resource (for example, by creating a 'letsencrypt-staging' issuer). + +More information on the different types of issuers and how to configure them +can be found in our documentation: + +https://cert-manager.io/docs/configuration/ + +For information on how to configure cert-manager to automatically provision +Certificates for Ingress resources, take a look at the `ingress-shim` +documentation: + +https://cert-manager.io/docs/usage/ingress/ diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/_helpers.tpl new file mode 100644 index 0000000..2b6ee7f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/_helpers.tpl @@ -0,0 +1,159 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "cert-manager.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "cert-manager.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Create the name of the service account to use +*/}} +{{- define "cert-manager.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "cert-manager.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Webhook templates +*/}} + +{{/* +Expand the name of the chart. +Manually fix the 'app' and 'name' labels to 'webhook' to maintain +compatibility with the v0.9 deployment selector. +*/}} +{{- define "webhook.name" -}} +{{- printf "webhook" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "webhook.fullname" -}} +{{- $trimmedName := printf "%s" (include "cert-manager.fullname" .) | trunc 55 | trimSuffix "-" -}} +{{- printf "%s-webhook" $trimmedName | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{- define "webhook.caRef" -}} +{{ .Release.Namespace }}/{{ template "webhook.fullname" . }}-ca +{{- end -}} + +{{/* +Create the name of the service account to use +*/}} +{{- define "webhook.serviceAccountName" -}} +{{- if .Values.webhook.serviceAccount.create -}} + {{ default (include "webhook.fullname" .) .Values.webhook.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.webhook.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +cainjector templates +*/}} + +{{/* +Expand the name of the chart. +Manually fix the 'app' and 'name' labels to 'cainjector' to maintain +compatibility with the v0.9 deployment selector. +*/}} +{{- define "cainjector.name" -}} +{{- printf "cainjector" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "cainjector.fullname" -}} +{{- $trimmedName := printf "%s" (include "cert-manager.fullname" .) | trunc 52 | trimSuffix "-" -}} +{{- printf "%s-cainjector" $trimmedName | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create the name of the service account to use +*/}} +{{- define "cainjector.serviceAccountName" -}} +{{- if .Values.cainjector.serviceAccount.create -}} + {{ default (include "cainjector.fullname" .) .Values.cainjector.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.cainjector.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +startupapicheck templates +*/}} + +{{/* +Expand the name of the chart. +Manually fix the 'app' and 'name' labels to 'startupapicheck' to maintain +compatibility with the v0.9 deployment selector. +*/}} +{{- define "startupapicheck.name" -}} +{{- printf "startupapicheck" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "startupapicheck.fullname" -}} +{{- $trimmedName := printf "%s" (include "cert-manager.fullname" .) | trunc 52 | trimSuffix "-" -}} +{{- printf "%s-startupapicheck" $trimmedName | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create the name of the service account to use +*/}} +{{- define "startupapicheck.serviceAccountName" -}} +{{- if .Values.startupapicheck.serviceAccount.create -}} + {{ default (include "startupapicheck.fullname" .) .Values.startupapicheck.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.startupapicheck.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "chartName" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Labels that should be added on each resource +*/}} +{{- define "labels" -}} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- if eq (default "helm" .Values.creator) "helm" }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +helm.sh/chart: {{ include "chartName" . }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-deployment.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-deployment.yaml new file mode 100644 index 0000000..b617527 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-deployment.yaml @@ -0,0 +1,102 @@ +{{- if .Values.cainjector.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "cainjector.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ include "cainjector.name" . }} + app.kubernetes.io/name: {{ include "cainjector.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cainjector" + {{- include "labels" . | nindent 4 }} + {{- with .Values.cainjector.deploymentAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.cainjector.replicaCount }} + selector: + matchLabels: + app.kubernetes.io/name: {{ include "cainjector.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cainjector" + {{- with .Values.cainjector.strategy }} + strategy: + {{- toYaml . | nindent 4 }} + {{- end }} + template: + metadata: + labels: + app: {{ include "cainjector.name" . }} + app.kubernetes.io/name: {{ include "cainjector.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cainjector" + {{- include "labels" . | nindent 8 }} + {{- with .Values.cainjector.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.cainjector.podAnnotations }} + annotations: + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ template "cainjector.serviceAccountName" . }} + {{- with .Values.global.priorityClassName }} + priorityClassName: {{ . | quote }} + {{- end }} + {{- with .Values.cainjector.securityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: {{ .Chart.Name }} + {{- with .Values.cainjector.image }} + image: "{{- if .registry -}}{{ .registry }}/{{- end -}}{{ .repository }}{{- if (.digest) -}} @{{ .digest }}{{- else -}}:{{ default $.Chart.AppVersion .tag }} {{- end -}}" + {{- end }} + imagePullPolicy: {{ .Values.cainjector.image.pullPolicy }} + args: + {{- if .Values.global.logLevel }} + - --v={{ .Values.global.logLevel }} + {{- end }} + {{- with .Values.global.leaderElection }} + - --leader-election-namespace={{ .namespace }} + {{- if .leaseDuration }} + - --leader-election-lease-duration={{ .leaseDuration }} + {{- end }} + {{- if .renewDeadline }} + - --leader-election-renew-deadline={{ .renewDeadline }} + {{- end }} + {{- if .retryPeriod }} + - --leader-election-retry-period={{ .retryPeriod }} + {{- end }} + {{- end }} + {{- with .Values.cainjector.extraArgs }} + {{- toYaml . | nindent 10 }} + {{- end }} + env: + - name: POD_NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + {{- with .Values.cainjector.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.cainjector.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.cainjector.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.cainjector.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.cainjector.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-psp-clusterrole.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-psp-clusterrole.yaml new file mode 100644 index 0000000..b75b9eb --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-psp-clusterrole.yaml @@ -0,0 +1,20 @@ +{{- if .Values.cainjector.enabled }} +{{- if .Values.global.podSecurityPolicy.enabled }} +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ template "cainjector.fullname" . }}-psp + labels: + app: {{ include "cainjector.name" . }} + app.kubernetes.io/name: {{ include "cainjector.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cainjector" + {{- include "labels" . | nindent 4 }} +rules: +- apiGroups: ['policy'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ template "cainjector.fullname" . }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-psp-clusterrolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-psp-clusterrolebinding.yaml new file mode 100644 index 0000000..b287802 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-psp-clusterrolebinding.yaml @@ -0,0 +1,22 @@ +{{- if .Values.cainjector.enabled }} +{{- if .Values.global.podSecurityPolicy.enabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "cainjector.fullname" . }}-psp + labels: + app: {{ include "cainjector.name" . }} + app.kubernetes.io/name: {{ include "cainjector.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cainjector" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "cainjector.fullname" . }}-psp +subjects: + - kind: ServiceAccount + name: {{ template "cainjector.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-psp.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-psp.yaml new file mode 100644 index 0000000..24f01da --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-psp.yaml @@ -0,0 +1,51 @@ +{{- if .Values.cainjector.enabled }} +{{- if .Values.global.podSecurityPolicy.enabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "cainjector.fullname" . }} + labels: + app: {{ include "cainjector.name" . }} + app.kubernetes.io/name: {{ include "cainjector.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cainjector" + {{- include "labels" . | nindent 4 }} + annotations: + seccomp.security.alpha.kubernetes.io/allowedProfileNames: 'docker/default' + seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default' + {{- if .Values.global.podSecurityPolicy.useAppArmor }} + apparmor.security.beta.kubernetes.io/allowedProfileNames: 'runtime/default' + apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default' + {{- end }} +spec: + privileged: false + allowPrivilegeEscalation: false + allowedCapabilities: [] # default set of capabilities are implicitly allowed + volumes: + - 'configMap' + - 'emptyDir' + - 'projected' + - 'secret' + - 'downwardAPI' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + rule: 'MustRunAs' + ranges: + - min: 1000 + max: 1000 + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + - min: 1000 + max: 1000 + fsGroup: + rule: 'MustRunAs' + ranges: + - min: 1000 + max: 1000 +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-rbac.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-rbac.yaml new file mode 100644 index 0000000..6cb396e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-rbac.yaml @@ -0,0 +1,103 @@ +{{- if .Values.cainjector.enabled }} +{{- if .Values.global.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "cainjector.fullname" . }} + labels: + app: {{ include "cainjector.name" . }} + app.kubernetes.io/name: {{ include "cainjector.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cainjector" + {{- include "labels" . | nindent 4 }} +rules: + - apiGroups: ["cert-manager.io"] + resources: ["certificates"] + verbs: ["get", "list", "watch"] + - apiGroups: [""] + resources: ["secrets"] + verbs: ["get", "list", "watch"] + - apiGroups: [""] + resources: ["events"] + verbs: ["get", "create", "update", "patch"] + - apiGroups: ["admissionregistration.k8s.io"] + resources: ["validatingwebhookconfigurations", "mutatingwebhookconfigurations"] + verbs: ["get", "list", "watch", "update"] + - apiGroups: ["apiregistration.k8s.io"] + resources: ["apiservices"] + verbs: ["get", "list", "watch", "update"] + - apiGroups: ["apiextensions.k8s.io"] + resources: ["customresourcedefinitions"] + verbs: ["get", "list", "watch", "update"] +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "cainjector.fullname" . }} + labels: + app: {{ include "cainjector.name" . }} + app.kubernetes.io/name: {{ include "cainjector.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cainjector" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "cainjector.fullname" . }} +subjects: + - name: {{ template "cainjector.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + kind: ServiceAccount + +--- +# leader election rules +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ template "cainjector.fullname" . }}:leaderelection + namespace: {{ .Values.global.leaderElection.namespace }} + labels: + app: {{ include "cainjector.name" . }} + app.kubernetes.io/name: {{ include "cainjector.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cainjector" + {{- include "labels" . | nindent 4 }} +rules: + # Used for leader election by the controller + # cert-manager-cainjector-leader-election is used by the CertificateBased injector controller + # see cmd/cainjector/start.go#L113 + # cert-manager-cainjector-leader-election-core is used by the SecretBased injector controller + # see cmd/cainjector/start.go#L137 + - apiGroups: ["coordination.k8s.io"] + resources: ["leases"] + resourceNames: ["cert-manager-cainjector-leader-election", "cert-manager-cainjector-leader-election-core"] + verbs: ["get", "update", "patch"] + - apiGroups: ["coordination.k8s.io"] + resources: ["leases"] + verbs: ["create"] + +--- + +# grant cert-manager permission to manage the leaderelection configmap in the +# leader election namespace +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "cainjector.fullname" . }}:leaderelection + namespace: {{ .Values.global.leaderElection.namespace }} + labels: + app: {{ include "cainjector.name" . }} + app.kubernetes.io/name: {{ include "cainjector.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cainjector" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ template "cainjector.fullname" . }}:leaderelection +subjects: + - kind: ServiceAccount + name: {{ template "cainjector.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-serviceaccount.yaml new file mode 100644 index 0000000..6457b9e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/cainjector-serviceaccount.yaml @@ -0,0 +1,27 @@ +{{- if .Values.cainjector.enabled }} +{{- if .Values.cainjector.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +automountServiceAccountToken: {{ .Values.cainjector.serviceAccount.automountServiceAccountToken }} +metadata: + name: {{ template "cainjector.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + {{- with .Values.cainjector.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + app: {{ include "cainjector.name" . }} + app.kubernetes.io/name: {{ include "cainjector.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cainjector" + {{- include "labels" . | nindent 4 }} + {{- with .Values.cainjector.serviceAccount.labels }} + {{ toYaml . | nindent 4 }} + {{- end }} +{{- with .Values.global.imagePullSecrets }} +imagePullSecrets: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/crds.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/crds.yaml new file mode 100644 index 0000000..afea0de --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/crds.yaml @@ -0,0 +1,4280 @@ +{{- if .Values.installCRDs }} +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + name: certificaterequests.cert-manager.io + labels: + app: '{{ template "cert-manager.name" . }}' + app.kubernetes.io/name: '{{ template "cert-manager.name" . }}' + app.kubernetes.io/instance: '{{ .Release.Name }}' + # Generated labels {{- include "labels" . | nindent 4 }} +spec: + group: cert-manager.io + names: + kind: CertificateRequest + listKind: CertificateRequestList + plural: certificaterequests + shortNames: + - cr + - crs + singular: certificaterequest + categories: + - cert-manager + scope: Namespaced + versions: + - name: v1 + subresources: + status: {} + additionalPrinterColumns: + - jsonPath: .status.conditions[?(@.type=="Approved")].status + name: Approved + type: string + - jsonPath: .status.conditions[?(@.type=="Denied")].status + name: Denied + type: string + - jsonPath: .status.conditions[?(@.type=="Ready")].status + name: Ready + type: string + - jsonPath: .spec.issuerRef.name + name: Issuer + type: string + - jsonPath: .spec.username + name: Requestor + type: string + - jsonPath: .status.conditions[?(@.type=="Ready")].message + name: Status + priority: 1 + type: string + - jsonPath: .metadata.creationTimestamp + description: CreationTimestamp is a timestamp representing the server time when this object was created. It is not guaranteed to be set in happens-before order across separate operations. Clients may not set this value. It is represented in RFC3339 form and is in UTC. + name: Age + type: date + schema: + openAPIV3Schema: + description: "A CertificateRequest is used to request a signed certificate from one of the configured issuers. \n All fields within the CertificateRequest's `spec` are immutable after creation. A CertificateRequest will either succeed or fail, as denoted by its `status.state` field. \n A CertificateRequest is a one-shot resource, meaning it represents a single point in time request for a certificate and cannot be re-used." + type: object + required: + - spec + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Desired state of the CertificateRequest resource. + type: object + required: + - issuerRef + - request + properties: + duration: + description: The requested 'duration' (i.e. lifetime) of the Certificate. This option may be ignored/overridden by some issuer types. + type: string + extra: + description: Extra contains extra attributes of the user that created the CertificateRequest. Populated by the cert-manager webhook on creation and immutable. + type: object + additionalProperties: + type: array + items: + type: string + groups: + description: Groups contains group membership of the user that created the CertificateRequest. Populated by the cert-manager webhook on creation and immutable. + type: array + items: + type: string + x-kubernetes-list-type: atomic + isCA: + description: IsCA will request to mark the certificate as valid for certificate signing when submitting to the issuer. This will automatically add the `cert sign` usage to the list of `usages`. + type: boolean + issuerRef: + description: IssuerRef is a reference to the issuer for this CertificateRequest. If the `kind` field is not set, or set to `Issuer`, an Issuer resource with the given name in the same namespace as the CertificateRequest will be used. If the `kind` field is set to `ClusterIssuer`, a ClusterIssuer with the provided name will be used. The `name` field in this stanza is required at all times. The group field refers to the API group of the issuer which defaults to `cert-manager.io` if empty. + type: object + required: + - name + properties: + group: + description: Group of the resource being referred to. + type: string + kind: + description: Kind of the resource being referred to. + type: string + name: + description: Name of the resource being referred to. + type: string + request: + description: The PEM-encoded x509 certificate signing request to be submitted to the CA for signing. + type: string + format: byte + uid: + description: UID contains the uid of the user that created the CertificateRequest. Populated by the cert-manager webhook on creation and immutable. + type: string + usages: + description: Usages is the set of x509 usages that are requested for the certificate. If usages are set they SHOULD be encoded inside the CSR spec Defaults to `digital signature` and `key encipherment` if not specified. + type: array + items: + description: 'KeyUsage specifies valid usage contexts for keys. See: https://tools.ietf.org/html/rfc5280#section-4.2.1.3 https://tools.ietf.org/html/rfc5280#section-4.2.1.12 Valid KeyUsage values are as follows: "signing", "digital signature", "content commitment", "key encipherment", "key agreement", "data encipherment", "cert sign", "crl sign", "encipher only", "decipher only", "any", "server auth", "client auth", "code signing", "email protection", "s/mime", "ipsec end system", "ipsec tunnel", "ipsec user", "timestamping", "ocsp signing", "microsoft sgc", "netscape sgc"' + type: string + enum: + - signing + - digital signature + - content commitment + - key encipherment + - key agreement + - data encipherment + - cert sign + - crl sign + - encipher only + - decipher only + - any + - server auth + - client auth + - code signing + - email protection + - s/mime + - ipsec end system + - ipsec tunnel + - ipsec user + - timestamping + - ocsp signing + - microsoft sgc + - netscape sgc + username: + description: Username contains the name of the user that created the CertificateRequest. Populated by the cert-manager webhook on creation and immutable. + type: string + status: + description: Status of the CertificateRequest. This is set and managed automatically. + type: object + properties: + ca: + description: The PEM encoded x509 certificate of the signer, also known as the CA (Certificate Authority). This is set on a best-effort basis by different issuers. If not set, the CA is assumed to be unknown/not available. + type: string + format: byte + certificate: + description: The PEM encoded x509 certificate resulting from the certificate signing request. If not set, the CertificateRequest has either not been completed or has failed. More information on failure can be found by checking the `conditions` field. + type: string + format: byte + conditions: + description: List of status conditions to indicate the status of a CertificateRequest. Known condition types are `Ready` and `InvalidRequest`. + type: array + items: + description: CertificateRequestCondition contains condition information for a CertificateRequest. + type: object + required: + - status + - type + properties: + lastTransitionTime: + description: LastTransitionTime is the timestamp corresponding to the last status change of this condition. + type: string + format: date-time + message: + description: Message is a human readable description of the details of the last transition, complementing reason. + type: string + reason: + description: Reason is a brief machine readable explanation for the condition's last transition. + type: string + status: + description: Status of the condition, one of (`True`, `False`, `Unknown`). + type: string + enum: + - "True" + - "False" + - Unknown + type: + description: Type of the condition, known values are (`Ready`, `InvalidRequest`, `Approved`, `Denied`). + type: string + x-kubernetes-list-map-keys: + - type + x-kubernetes-list-type: map + failureTime: + description: FailureTime stores the time that this CertificateRequest failed. This is used to influence garbage collection and back-off. + type: string + format: date-time + served: true + storage: true +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + name: certificates.cert-manager.io + labels: + app: '{{ template "cert-manager.name" . }}' + app.kubernetes.io/name: '{{ template "cert-manager.name" . }}' + app.kubernetes.io/instance: '{{ .Release.Name }}' + # Generated labels {{- include "labels" . | nindent 4 }} +spec: + group: cert-manager.io + names: + kind: Certificate + listKind: CertificateList + plural: certificates + shortNames: + - cert + - certs + singular: certificate + categories: + - cert-manager + scope: Namespaced + versions: + - name: v1 + subresources: + status: {} + additionalPrinterColumns: + - jsonPath: .status.conditions[?(@.type=="Ready")].status + name: Ready + type: string + - jsonPath: .spec.secretName + name: Secret + type: string + - jsonPath: .spec.issuerRef.name + name: Issuer + priority: 1 + type: string + - jsonPath: .status.conditions[?(@.type=="Ready")].message + name: Status + priority: 1 + type: string + - jsonPath: .metadata.creationTimestamp + description: CreationTimestamp is a timestamp representing the server time when this object was created. It is not guaranteed to be set in happens-before order across separate operations. Clients may not set this value. It is represented in RFC3339 form and is in UTC. + name: Age + type: date + schema: + openAPIV3Schema: + description: "A Certificate resource should be created to ensure an up to date and signed x509 certificate is stored in the Kubernetes Secret resource named in `spec.secretName`. \n The stored certificate will be renewed before it expires (as configured by `spec.renewBefore`)." + type: object + required: + - spec + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Desired state of the Certificate resource. + type: object + required: + - issuerRef + - secretName + properties: + additionalOutputFormats: + description: AdditionalOutputFormats defines extra output formats of the private key and signed certificate chain to be written to this Certificate's target Secret. This is an Alpha Feature and is only enabled with the `--feature-gates=AdditionalCertificateOutputFormats=true` option on both the controller and webhook components. + type: array + items: + description: CertificateAdditionalOutputFormat defines an additional output format of a Certificate resource. These contain supplementary data formats of the signed certificate chain and paired private key. + type: object + required: + - type + properties: + type: + description: Type is the name of the format type that should be written to the Certificate's target Secret. + type: string + enum: + - DER + - CombinedPEM + commonName: + description: 'CommonName is a common name to be used on the Certificate. The CommonName should have a length of 64 characters or fewer to avoid generating invalid CSRs. This value is ignored by TLS clients when any subject alt name is set. This is x509 behaviour: https://tools.ietf.org/html/rfc6125#section-6.4.4' + type: string + dnsNames: + description: DNSNames is a list of DNS subjectAltNames to be set on the Certificate. + type: array + items: + type: string + duration: + description: The requested 'duration' (i.e. lifetime) of the Certificate. This option may be ignored/overridden by some issuer types. If unset this defaults to 90 days. Certificate will be renewed either 2/3 through its duration or `renewBefore` period before its expiry, whichever is later. Minimum accepted duration is 1 hour. Value must be in units accepted by Go time.ParseDuration https://golang.org/pkg/time/#ParseDuration + type: string + emailAddresses: + description: EmailAddresses is a list of email subjectAltNames to be set on the Certificate. + type: array + items: + type: string + encodeUsagesInRequest: + description: EncodeUsagesInRequest controls whether key usages should be present in the CertificateRequest + type: boolean + ipAddresses: + description: IPAddresses is a list of IP address subjectAltNames to be set on the Certificate. + type: array + items: + type: string + isCA: + description: IsCA will mark this Certificate as valid for certificate signing. This will automatically add the `cert sign` usage to the list of `usages`. + type: boolean + issuerRef: + description: IssuerRef is a reference to the issuer for this certificate. If the `kind` field is not set, or set to `Issuer`, an Issuer resource with the given name in the same namespace as the Certificate will be used. If the `kind` field is set to `ClusterIssuer`, a ClusterIssuer with the provided name will be used. The `name` field in this stanza is required at all times. + type: object + required: + - name + properties: + group: + description: Group of the resource being referred to. + type: string + kind: + description: Kind of the resource being referred to. + type: string + name: + description: Name of the resource being referred to. + type: string + keystores: + description: Keystores configures additional keystore output formats stored in the `secretName` Secret resource. + type: object + properties: + jks: + description: JKS configures options for storing a JKS keystore in the `spec.secretName` Secret resource. + type: object + required: + - create + - passwordSecretRef + properties: + create: + description: Create enables JKS keystore creation for the Certificate. If true, a file named `keystore.jks` will be created in the target Secret resource, encrypted using the password stored in `passwordSecretRef`. The keystore file will only be updated upon re-issuance. A file named `truststore.jks` will also be created in the target Secret resource, encrypted using the password stored in `passwordSecretRef` containing the issuing Certificate Authority + type: boolean + passwordSecretRef: + description: PasswordSecretRef is a reference to a key in a Secret resource containing the password used to encrypt the JKS keystore. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + pkcs12: + description: PKCS12 configures options for storing a PKCS12 keystore in the `spec.secretName` Secret resource. + type: object + required: + - create + - passwordSecretRef + properties: + create: + description: Create enables PKCS12 keystore creation for the Certificate. If true, a file named `keystore.p12` will be created in the target Secret resource, encrypted using the password stored in `passwordSecretRef`. The keystore file will only be updated upon re-issuance. A file named `truststore.p12` will also be created in the target Secret resource, encrypted using the password stored in `passwordSecretRef` containing the issuing Certificate Authority + type: boolean + passwordSecretRef: + description: PasswordSecretRef is a reference to a key in a Secret resource containing the password used to encrypt the PKCS12 keystore. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + privateKey: + description: Options to control private keys used for the Certificate. + type: object + properties: + algorithm: + description: Algorithm is the private key algorithm of the corresponding private key for this certificate. If provided, allowed values are either `RSA`,`Ed25519` or `ECDSA` If `algorithm` is specified and `size` is not provided, key size of 256 will be used for `ECDSA` key algorithm and key size of 2048 will be used for `RSA` key algorithm. key size is ignored when using the `Ed25519` key algorithm. + type: string + enum: + - RSA + - ECDSA + - Ed25519 + encoding: + description: The private key cryptography standards (PKCS) encoding for this certificate's private key to be encoded in. If provided, allowed values are `PKCS1` and `PKCS8` standing for PKCS#1 and PKCS#8, respectively. Defaults to `PKCS1` if not specified. + type: string + enum: + - PKCS1 + - PKCS8 + rotationPolicy: + description: RotationPolicy controls how private keys should be regenerated when a re-issuance is being processed. If set to Never, a private key will only be generated if one does not already exist in the target `spec.secretName`. If one does exists but it does not have the correct algorithm or size, a warning will be raised to await user intervention. If set to Always, a private key matching the specified requirements will be generated whenever a re-issuance occurs. Default is 'Never' for backward compatibility. + type: string + enum: + - Never + - Always + size: + description: Size is the key bit size of the corresponding private key for this certificate. If `algorithm` is set to `RSA`, valid values are `2048`, `4096` or `8192`, and will default to `2048` if not specified. If `algorithm` is set to `ECDSA`, valid values are `256`, `384` or `521`, and will default to `256` if not specified. If `algorithm` is set to `Ed25519`, Size is ignored. No other values are allowed. + type: integer + renewBefore: + description: How long before the currently issued certificate's expiry cert-manager should renew the certificate. The default is 2/3 of the issued certificate's duration. Minimum accepted value is 5 minutes. Value must be in units accepted by Go time.ParseDuration https://golang.org/pkg/time/#ParseDuration + type: string + revisionHistoryLimit: + description: revisionHistoryLimit is the maximum number of CertificateRequest revisions that are maintained in the Certificate's history. Each revision represents a single `CertificateRequest` created by this Certificate, either when it was created, renewed, or Spec was changed. Revisions will be removed by oldest first if the number of revisions exceeds this number. If set, revisionHistoryLimit must be a value of `1` or greater. If unset (`nil`), revisions will not be garbage collected. Default value is `nil`. + type: integer + format: int32 + secretName: + description: SecretName is the name of the secret resource that will be automatically created and managed by this Certificate resource. It will be populated with a private key and certificate, signed by the denoted issuer. + type: string + secretTemplate: + description: SecretTemplate defines annotations and labels to be copied to the Certificate's Secret. Labels and annotations on the Secret will be changed as they appear on the SecretTemplate when added or removed. SecretTemplate annotations are added in conjunction with, and cannot overwrite, the base set of annotations cert-manager sets on the Certificate's Secret. + type: object + properties: + annotations: + description: Annotations is a key value map to be copied to the target Kubernetes Secret. + type: object + additionalProperties: + type: string + labels: + description: Labels is a key value map to be copied to the target Kubernetes Secret. + type: object + additionalProperties: + type: string + subject: + description: Full X509 name specification (https://golang.org/pkg/crypto/x509/pkix/#Name). + type: object + properties: + countries: + description: Countries to be used on the Certificate. + type: array + items: + type: string + localities: + description: Cities to be used on the Certificate. + type: array + items: + type: string + organizationalUnits: + description: Organizational Units to be used on the Certificate. + type: array + items: + type: string + organizations: + description: Organizations to be used on the Certificate. + type: array + items: + type: string + postalCodes: + description: Postal codes to be used on the Certificate. + type: array + items: + type: string + provinces: + description: State/Provinces to be used on the Certificate. + type: array + items: + type: string + serialNumber: + description: Serial number to be used on the Certificate. + type: string + streetAddresses: + description: Street addresses to be used on the Certificate. + type: array + items: + type: string + uris: + description: URIs is a list of URI subjectAltNames to be set on the Certificate. + type: array + items: + type: string + usages: + description: Usages is the set of x509 usages that are requested for the certificate. Defaults to `digital signature` and `key encipherment` if not specified. + type: array + items: + description: 'KeyUsage specifies valid usage contexts for keys. See: https://tools.ietf.org/html/rfc5280#section-4.2.1.3 https://tools.ietf.org/html/rfc5280#section-4.2.1.12 Valid KeyUsage values are as follows: "signing", "digital signature", "content commitment", "key encipherment", "key agreement", "data encipherment", "cert sign", "crl sign", "encipher only", "decipher only", "any", "server auth", "client auth", "code signing", "email protection", "s/mime", "ipsec end system", "ipsec tunnel", "ipsec user", "timestamping", "ocsp signing", "microsoft sgc", "netscape sgc"' + type: string + enum: + - signing + - digital signature + - content commitment + - key encipherment + - key agreement + - data encipherment + - cert sign + - crl sign + - encipher only + - decipher only + - any + - server auth + - client auth + - code signing + - email protection + - s/mime + - ipsec end system + - ipsec tunnel + - ipsec user + - timestamping + - ocsp signing + - microsoft sgc + - netscape sgc + status: + description: Status of the Certificate. This is set and managed automatically. + type: object + properties: + conditions: + description: List of status conditions to indicate the status of certificates. Known condition types are `Ready` and `Issuing`. + type: array + items: + description: CertificateCondition contains condition information for an Certificate. + type: object + required: + - status + - type + properties: + lastTransitionTime: + description: LastTransitionTime is the timestamp corresponding to the last status change of this condition. + type: string + format: date-time + message: + description: Message is a human readable description of the details of the last transition, complementing reason. + type: string + observedGeneration: + description: If set, this represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.condition[x].observedGeneration is 9, the condition is out of date with respect to the current state of the Certificate. + type: integer + format: int64 + reason: + description: Reason is a brief machine readable explanation for the condition's last transition. + type: string + status: + description: Status of the condition, one of (`True`, `False`, `Unknown`). + type: string + enum: + - "True" + - "False" + - Unknown + type: + description: Type of the condition, known values are (`Ready`, `Issuing`). + type: string + x-kubernetes-list-map-keys: + - type + x-kubernetes-list-type: map + failedIssuanceAttempts: + description: The number of continuous failed issuance attempts up till now. This field gets removed (if set) on a successful issuance and gets set to 1 if unset and an issuance has failed. If an issuance has failed, the delay till the next issuance will be calculated using formula time.Hour * 2 ^ (failedIssuanceAttempts - 1). + type: integer + lastFailureTime: + description: LastFailureTime is the time as recorded by the Certificate controller of the most recent failure to complete a CertificateRequest for this Certificate resource. If set, cert-manager will not re-request another Certificate until 1 hour has elapsed from this time. + type: string + format: date-time + nextPrivateKeySecretName: + description: The name of the Secret resource containing the private key to be used for the next certificate iteration. The keymanager controller will automatically set this field if the `Issuing` condition is set to `True`. It will automatically unset this field when the Issuing condition is not set or False. + type: string + notAfter: + description: The expiration time of the certificate stored in the secret named by this resource in `spec.secretName`. + type: string + format: date-time + notBefore: + description: The time after which the certificate stored in the secret named by this resource in spec.secretName is valid. + type: string + format: date-time + renewalTime: + description: RenewalTime is the time at which the certificate will be next renewed. If not set, no upcoming renewal is scheduled. + type: string + format: date-time + revision: + description: "The current 'revision' of the certificate as issued. \n When a CertificateRequest resource is created, it will have the `cert-manager.io/certificate-revision` set to one greater than the current value of this field. \n Upon issuance, this field will be set to the value of the annotation on the CertificateRequest resource used to issue the certificate. \n Persisting the value on the CertificateRequest resource allows the certificates controller to know whether a request is part of an old issuance or if it is part of the ongoing revision's issuance by checking if the revision value in the annotation is greater than this field." + type: integer + served: true + storage: true +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + name: challenges.acme.cert-manager.io + labels: + app: '{{ template "cert-manager.name" . }}' + app.kubernetes.io/name: '{{ template "cert-manager.name" . }}' + app.kubernetes.io/instance: '{{ .Release.Name }}' + # Generated labels {{- include "labels" . | nindent 4 }} +spec: + group: acme.cert-manager.io + names: + kind: Challenge + listKind: ChallengeList + plural: challenges + singular: challenge + categories: + - cert-manager + - cert-manager-acme + scope: Namespaced + versions: + - additionalPrinterColumns: + - jsonPath: .status.state + name: State + type: string + - jsonPath: .spec.dnsName + name: Domain + type: string + - jsonPath: .status.reason + name: Reason + priority: 1 + type: string + - description: CreationTimestamp is a timestamp representing the server time when this object was created. It is not guaranteed to be set in happens-before order across separate operations. Clients may not set this value. It is represented in RFC3339 form and is in UTC. + jsonPath: .metadata.creationTimestamp + name: Age + type: date + name: v1 + schema: + openAPIV3Schema: + description: Challenge is a type to represent a Challenge request with an ACME server + type: object + required: + - metadata + - spec + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + type: object + required: + - authorizationURL + - dnsName + - issuerRef + - key + - solver + - token + - type + - url + properties: + authorizationURL: + description: The URL to the ACME Authorization resource that this challenge is a part of. + type: string + dnsName: + description: dnsName is the identifier that this challenge is for, e.g. example.com. If the requested DNSName is a 'wildcard', this field MUST be set to the non-wildcard domain, e.g. for `*.example.com`, it must be `example.com`. + type: string + issuerRef: + description: References a properly configured ACME-type Issuer which should be used to create this Challenge. If the Issuer does not exist, processing will be retried. If the Issuer is not an 'ACME' Issuer, an error will be returned and the Challenge will be marked as failed. + type: object + required: + - name + properties: + group: + description: Group of the resource being referred to. + type: string + kind: + description: Kind of the resource being referred to. + type: string + name: + description: Name of the resource being referred to. + type: string + key: + description: 'The ACME challenge key for this challenge For HTTP01 challenges, this is the value that must be responded with to complete the HTTP01 challenge in the format: `.`. For DNS01 challenges, this is the base64 encoded SHA256 sum of the `.` text that must be set as the TXT record content.' + type: string + solver: + description: Contains the domain solving configuration that should be used to solve this challenge resource. + type: object + properties: + dns01: + description: Configures cert-manager to attempt to complete authorizations by performing the DNS01 challenge flow. + type: object + properties: + acmeDNS: + description: Use the 'ACME DNS' (https://github.com/joohoi/acme-dns) API to manage DNS01 challenge records. + type: object + required: + - accountSecretRef + - host + properties: + accountSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + host: + type: string + akamai: + description: Use the Akamai DNS zone management API to manage DNS01 challenge records. + type: object + required: + - accessTokenSecretRef + - clientSecretSecretRef + - clientTokenSecretRef + - serviceConsumerDomain + properties: + accessTokenSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + clientSecretSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + clientTokenSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + serviceConsumerDomain: + type: string + azureDNS: + description: Use the Microsoft Azure DNS API to manage DNS01 challenge records. + type: object + required: + - resourceGroupName + - subscriptionID + properties: + clientID: + description: if both this and ClientSecret are left unset MSI will be used + type: string + clientSecretSecretRef: + description: if both this and ClientID are left unset MSI will be used + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + environment: + description: name of the Azure environment (default AzurePublicCloud) + type: string + enum: + - AzurePublicCloud + - AzureChinaCloud + - AzureGermanCloud + - AzureUSGovernmentCloud + hostedZoneName: + description: name of the DNS zone that should be used + type: string + managedIdentity: + description: managed identity configuration, can not be used at the same time as clientID, clientSecretSecretRef or tenantID + type: object + properties: + clientID: + description: client ID of the managed identity, can not be used at the same time as resourceID + type: string + resourceID: + description: resource ID of the managed identity, can not be used at the same time as clientID + type: string + resourceGroupName: + description: resource group the DNS zone is located in + type: string + subscriptionID: + description: ID of the Azure subscription + type: string + tenantID: + description: when specifying ClientID and ClientSecret then this field is also needed + type: string + cloudDNS: + description: Use the Google Cloud DNS API to manage DNS01 challenge records. + type: object + required: + - project + properties: + hostedZoneName: + description: HostedZoneName is an optional field that tells cert-manager in which Cloud DNS zone the challenge record has to be created. If left empty cert-manager will automatically choose a zone. + type: string + project: + type: string + serviceAccountSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + cloudflare: + description: Use the Cloudflare API to manage DNS01 challenge records. + type: object + properties: + apiKeySecretRef: + description: 'API key to use to authenticate with Cloudflare. Note: using an API token to authenticate is now the recommended method as it allows greater control of permissions.' + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + apiTokenSecretRef: + description: API token used to authenticate with Cloudflare. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + email: + description: Email of the account, only required when using API key based authentication. + type: string + cnameStrategy: + description: CNAMEStrategy configures how the DNS01 provider should handle CNAME records when found in DNS zones. + type: string + enum: + - None + - Follow + digitalocean: + description: Use the DigitalOcean DNS API to manage DNS01 challenge records. + type: object + required: + - tokenSecretRef + properties: + tokenSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + rfc2136: + description: Use RFC2136 ("Dynamic Updates in the Domain Name System") (https://datatracker.ietf.org/doc/rfc2136/) to manage DNS01 challenge records. + type: object + required: + - nameserver + properties: + nameserver: + description: The IP address or hostname of an authoritative DNS server supporting RFC2136 in the form host:port. If the host is an IPv6 address it must be enclosed in square brackets (e.g [2001:db8::1]) ; port is optional. This field is required. + type: string + tsigAlgorithm: + description: 'The TSIG Algorithm configured in the DNS supporting RFC2136. Used only when ``tsigSecretSecretRef`` and ``tsigKeyName`` are defined. Supported values are (case-insensitive): ``HMACMD5`` (default), ``HMACSHA1``, ``HMACSHA256`` or ``HMACSHA512``.' + type: string + tsigKeyName: + description: The TSIG Key name configured in the DNS. If ``tsigSecretSecretRef`` is defined, this field is required. + type: string + tsigSecretSecretRef: + description: The name of the secret containing the TSIG value. If ``tsigKeyName`` is defined, this field is required. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + route53: + description: Use the AWS Route53 API to manage DNS01 challenge records. + type: object + required: + - region + properties: + accessKeyID: + description: 'The AccessKeyID is used for authentication. If not set we fall-back to using env vars, shared credentials file or AWS Instance metadata see: https://docs.aws.amazon.com/sdk-for-go/v1/developer-guide/configuring-sdk.html#specifying-credentials' + type: string + hostedZoneID: + description: If set, the provider will manage only this zone in Route53 and will not do an lookup using the route53:ListHostedZonesByName api call. + type: string + region: + description: Always set the region when using AccessKeyID and SecretAccessKey + type: string + role: + description: Role is a Role ARN which the Route53 provider will assume using either the explicit credentials AccessKeyID/SecretAccessKey or the inferred credentials from environment variables, shared credentials file or AWS Instance metadata + type: string + secretAccessKeySecretRef: + description: The SecretAccessKey is used for authentication. If not set we fall-back to using env vars, shared credentials file or AWS Instance metadata https://docs.aws.amazon.com/sdk-for-go/v1/developer-guide/configuring-sdk.html#specifying-credentials + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + webhook: + description: Configure an external webhook based DNS01 challenge solver to manage DNS01 challenge records. + type: object + required: + - groupName + - solverName + properties: + config: + description: Additional configuration that should be passed to the webhook apiserver when challenges are processed. This can contain arbitrary JSON data. Secret values should not be specified in this stanza. If secret values are needed (e.g. credentials for a DNS service), you should use a SecretKeySelector to reference a Secret resource. For details on the schema of this field, consult the webhook provider implementation's documentation. + x-kubernetes-preserve-unknown-fields: true + groupName: + description: The API group name that should be used when POSTing ChallengePayload resources to the webhook apiserver. This should be the same as the GroupName specified in the webhook provider implementation. + type: string + solverName: + description: The name of the solver to use, as defined in the webhook provider implementation. This will typically be the name of the provider, e.g. 'cloudflare'. + type: string + http01: + description: Configures cert-manager to attempt to complete authorizations by performing the HTTP01 challenge flow. It is not possible to obtain certificates for wildcard domain names (e.g. `*.example.com`) using the HTTP01 challenge mechanism. + type: object + properties: + gatewayHTTPRoute: + description: The Gateway API is a sig-network community API that models service networking in Kubernetes (https://gateway-api.sigs.k8s.io/). The Gateway solver will create HTTPRoutes with the specified labels in the same namespace as the challenge. This solver is experimental, and fields / behaviour may change in the future. + type: object + properties: + labels: + description: Custom labels that will be applied to HTTPRoutes created by cert-manager while solving HTTP-01 challenges. + type: object + additionalProperties: + type: string + parentRefs: + description: 'When solving an HTTP-01 challenge, cert-manager creates an HTTPRoute. cert-manager needs to know which parentRefs should be used when creating the HTTPRoute. Usually, the parentRef references a Gateway. See: https://gateway-api.sigs.k8s.io/v1alpha2/api-types/httproute/#attaching-to-gateways' + type: array + items: + description: "ParentRef identifies an API object (usually a Gateway) that can be considered a parent of this resource (usually a route). The only kind of parent resource with \"Core\" support is Gateway. This API may be extended in the future to support additional kinds of parent resources, such as HTTPRoute. \n The API object must be valid in the cluster; the Group and Kind must be registered in the cluster for this reference to be valid. \n References to objects with invalid Group and Kind are not valid, and must be rejected by the implementation, with appropriate Conditions set on the containing object." + type: object + required: + - name + properties: + group: + description: "Group is the group of the referent. \n Support: Core" + type: string + default: gateway.networking.k8s.io + maxLength: 253 + pattern: ^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ + kind: + description: "Kind is kind of the referent. \n Support: Core (Gateway) Support: Custom (Other Resources)" + type: string + default: Gateway + maxLength: 63 + minLength: 1 + pattern: ^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$ + name: + description: "Name is the name of the referent. \n Support: Core" + type: string + maxLength: 253 + minLength: 1 + namespace: + description: "Namespace is the namespace of the referent. When unspecified (or empty string), this refers to the local namespace of the Route. \n Support: Core" + type: string + maxLength: 63 + minLength: 1 + pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ + sectionName: + description: "SectionName is the name of a section within the target resource. In the following resources, SectionName is interpreted as the following: \n * Gateway: Listener Name \n Implementations MAY choose to support attaching Routes to other resources. If that is the case, they MUST clearly document how SectionName is interpreted. \n When unspecified (empty string), this will reference the entire resource. For the purpose of status, an attachment is considered successful if at least one section in the parent resource accepts it. For example, Gateway listeners can restrict which Routes can attach to them by Route kind, namespace, or hostname. If 1 of 2 Gateway listeners accept attachment from the referencing Route, the Route MUST be considered successfully attached. If no Gateway listeners accept attachment from this Route, the Route MUST be considered detached from the Gateway. \n Support: Core" + type: string + maxLength: 253 + minLength: 1 + pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ + serviceType: + description: Optional service type for Kubernetes solver service. Supported values are NodePort or ClusterIP. If unset, defaults to NodePort. + type: string + ingress: + description: The ingress based HTTP01 challenge solver will solve challenges by creating or modifying Ingress resources in order to route requests for '/.well-known/acme-challenge/XYZ' to 'challenge solver' pods that are provisioned by cert-manager for each Challenge to be completed. + type: object + properties: + class: + description: The ingress class to use when creating Ingress resources to solve ACME challenges that use this challenge solver. Only one of 'class' or 'name' may be specified. + type: string + ingressTemplate: + description: Optional ingress template used to configure the ACME challenge solver ingress used for HTTP01 challenges. + type: object + properties: + metadata: + description: ObjectMeta overrides for the ingress used to solve HTTP01 challenges. Only the 'labels' and 'annotations' fields may be set. If labels or annotations overlap with in-built values, the values here will override the in-built values. + type: object + properties: + annotations: + description: Annotations that should be added to the created ACME HTTP01 solver ingress. + type: object + additionalProperties: + type: string + labels: + description: Labels that should be added to the created ACME HTTP01 solver ingress. + type: object + additionalProperties: + type: string + name: + description: The name of the ingress resource that should have ACME challenge solving routes inserted into it in order to solve HTTP01 challenges. This is typically used in conjunction with ingress controllers like ingress-gce, which maintains a 1:1 mapping between external IPs and ingress resources. + type: string + podTemplate: + description: Optional pod template used to configure the ACME challenge solver pods used for HTTP01 challenges. + type: object + properties: + metadata: + description: ObjectMeta overrides for the pod used to solve HTTP01 challenges. Only the 'labels' and 'annotations' fields may be set. If labels or annotations overlap with in-built values, the values here will override the in-built values. + type: object + properties: + annotations: + description: Annotations that should be added to the create ACME HTTP01 solver pods. + type: object + additionalProperties: + type: string + labels: + description: Labels that should be added to the created ACME HTTP01 solver pods. + type: object + additionalProperties: + type: string + spec: + description: PodSpec defines overrides for the HTTP01 challenge solver pod. Only the 'priorityClassName', 'nodeSelector', 'affinity', 'serviceAccountName' and 'tolerations' fields are supported currently. All other fields will be ignored. + type: object + properties: + affinity: + description: If specified, the pod's scheduling constraints + type: object + properties: + nodeAffinity: + description: Describes node affinity scheduling rules for the pod. + type: object + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. + type: array + items: + description: An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). + type: object + required: + - preference + - weight + properties: + preference: + description: A node selector term, associated with the corresponding weight. + type: object + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + type: array + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchFields: + description: A list of node selector requirements by node's fields. + type: array + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + type: array + items: + type: string + weight: + description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. + type: integer + format: int32 + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. + type: object + required: + - nodeSelectorTerms + properties: + nodeSelectorTerms: + description: Required. A list of node selector terms. The terms are ORed. + type: array + items: + description: A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. + type: object + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + type: array + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchFields: + description: A list of node selector requirements by node's fields. + type: array + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + type: array + items: + type: string + podAffinity: + description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). + type: object + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + type: array + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + type: object + required: + - podAffinityTerm + - weight + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + type: object + required: + - topologyKey + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. This field is beta-level and is only honored when PodAffinityNamespaceSelector feature is enabled. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace" + type: array + items: + type: string + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + type: integer + format: int32 + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + type: array + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + type: object + required: + - topologyKey + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. This field is beta-level and is only honored when PodAffinityNamespaceSelector feature is enabled. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace" + type: array + items: + type: string + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + podAntiAffinity: + description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). + type: object + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + type: array + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + type: object + required: + - podAffinityTerm + - weight + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + type: object + required: + - topologyKey + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. This field is beta-level and is only honored when PodAffinityNamespaceSelector feature is enabled. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace" + type: array + items: + type: string + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + type: integer + format: int32 + requiredDuringSchedulingIgnoredDuringExecution: + description: If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + type: array + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + type: object + required: + - topologyKey + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. This field is beta-level and is only honored when PodAffinityNamespaceSelector feature is enabled. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace" + type: array + items: + type: string + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + nodeSelector: + description: 'NodeSelector is a selector which must be true for the pod to fit on a node. Selector which must match a node''s labels for the pod to be scheduled on that node. More info: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/' + type: object + additionalProperties: + type: string + priorityClassName: + description: If specified, the pod's priorityClassName. + type: string + serviceAccountName: + description: If specified, the pod's service account + type: string + tolerations: + description: If specified, the pod's tolerations. + type: array + items: + description: The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . + type: object + properties: + effect: + description: Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. + type: string + key: + description: Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. + type: string + operator: + description: Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. + type: string + tolerationSeconds: + description: TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. + type: integer + format: int64 + value: + description: Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. + type: string + serviceType: + description: Optional service type for Kubernetes solver service. Supported values are NodePort or ClusterIP. If unset, defaults to NodePort. + type: string + selector: + description: Selector selects a set of DNSNames on the Certificate resource that should be solved using this challenge solver. If not specified, the solver will be treated as the 'default' solver with the lowest priority, i.e. if any other solver has a more specific match, it will be used instead. + type: object + properties: + dnsNames: + description: List of DNSNames that this solver will be used to solve. If specified and a match is found, a dnsNames selector will take precedence over a dnsZones selector. If multiple solvers match with the same dnsNames value, the solver with the most matching labels in matchLabels will be selected. If neither has more matches, the solver defined earlier in the list will be selected. + type: array + items: + type: string + dnsZones: + description: List of DNSZones that this solver will be used to solve. The most specific DNS zone match specified here will take precedence over other DNS zone matches, so a solver specifying sys.example.com will be selected over one specifying example.com for the domain www.sys.example.com. If multiple solvers match with the same dnsZones value, the solver with the most matching labels in matchLabels will be selected. If neither has more matches, the solver defined earlier in the list will be selected. + type: array + items: + type: string + matchLabels: + description: A label selector that is used to refine the set of certificate's that this challenge solver will apply to. + type: object + additionalProperties: + type: string + token: + description: The ACME challenge token for this challenge. This is the raw value returned from the ACME server. + type: string + type: + description: The type of ACME challenge this resource represents. One of "HTTP-01" or "DNS-01". + type: string + enum: + - HTTP-01 + - DNS-01 + url: + description: The URL of the ACME Challenge resource for this challenge. This can be used to lookup details about the status of this challenge. + type: string + wildcard: + description: wildcard will be true if this challenge is for a wildcard identifier, for example '*.example.com'. + type: boolean + status: + type: object + properties: + presented: + description: presented will be set to true if the challenge values for this challenge are currently 'presented'. This *does not* imply the self check is passing. Only that the values have been 'submitted' for the appropriate challenge mechanism (i.e. the DNS01 TXT record has been presented, or the HTTP01 configuration has been configured). + type: boolean + processing: + description: Used to denote whether this challenge should be processed or not. This field will only be set to true by the 'scheduling' component. It will only be set to false by the 'challenges' controller, after the challenge has reached a final state or timed out. If this field is set to false, the challenge controller will not take any more action. + type: boolean + reason: + description: Contains human readable information on why the Challenge is in the current state. + type: string + state: + description: Contains the current 'state' of the challenge. If not set, the state of the challenge is unknown. + type: string + enum: + - valid + - ready + - pending + - processing + - invalid + - expired + - errored + served: true + storage: true + subresources: + status: {} +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + name: clusterissuers.cert-manager.io + labels: + app: '{{ template "cert-manager.name" . }}' + app.kubernetes.io/name: '{{ template "cert-manager.name" . }}' + app.kubernetes.io/instance: '{{ .Release.Name }}' + # Generated labels {{- include "labels" . | nindent 4 }} +spec: + group: cert-manager.io + names: + kind: ClusterIssuer + listKind: ClusterIssuerList + plural: clusterissuers + singular: clusterissuer + categories: + - cert-manager + scope: Cluster + versions: + - name: v1 + subresources: + status: {} + additionalPrinterColumns: + - jsonPath: .status.conditions[?(@.type=="Ready")].status + name: Ready + type: string + - jsonPath: .status.conditions[?(@.type=="Ready")].message + name: Status + priority: 1 + type: string + - jsonPath: .metadata.creationTimestamp + description: CreationTimestamp is a timestamp representing the server time when this object was created. It is not guaranteed to be set in happens-before order across separate operations. Clients may not set this value. It is represented in RFC3339 form and is in UTC. + name: Age + type: date + schema: + openAPIV3Schema: + description: A ClusterIssuer represents a certificate issuing authority which can be referenced as part of `issuerRef` fields. It is similar to an Issuer, however it is cluster-scoped and therefore can be referenced by resources that exist in *any* namespace, not just the same namespace as the referent. + type: object + required: + - spec + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Desired state of the ClusterIssuer resource. + type: object + properties: + acme: + description: ACME configures this issuer to communicate with a RFC8555 (ACME) server to obtain signed x509 certificates. + type: object + required: + - privateKeySecretRef + - server + properties: + disableAccountKeyGeneration: + description: Enables or disables generating a new ACME account key. If true, the Issuer resource will *not* request a new account but will expect the account key to be supplied via an existing secret. If false, the cert-manager system will generate a new ACME account key for the Issuer. Defaults to false. + type: boolean + email: + description: Email is the email address to be associated with the ACME account. This field is optional, but it is strongly recommended to be set. It will be used to contact you in case of issues with your account or certificates, including expiry notification emails. This field may be updated after the account is initially registered. + type: string + enableDurationFeature: + description: Enables requesting a Not After date on certificates that matches the duration of the certificate. This is not supported by all ACME servers like Let's Encrypt. If set to true when the ACME server does not support it it will create an error on the Order. Defaults to false. + type: boolean + externalAccountBinding: + description: ExternalAccountBinding is a reference to a CA external account of the ACME server. If set, upon registration cert-manager will attempt to associate the given external account credentials with the registered ACME account. + type: object + required: + - keyID + - keySecretRef + properties: + keyAlgorithm: + description: 'Deprecated: keyAlgorithm field exists for historical compatibility reasons and should not be used. The algorithm is now hardcoded to HS256 in golang/x/crypto/acme.' + type: string + enum: + - HS256 + - HS384 + - HS512 + keyID: + description: keyID is the ID of the CA key that the External Account is bound to. + type: string + keySecretRef: + description: keySecretRef is a Secret Key Selector referencing a data item in a Kubernetes Secret which holds the symmetric MAC key of the External Account Binding. The `key` is the index string that is paired with the key data in the Secret and should not be confused with the key data itself, or indeed with the External Account Binding keyID above. The secret key stored in the Secret **must** be un-padded, base64 URL encoded data. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + preferredChain: + description: 'PreferredChain is the chain to use if the ACME server outputs multiple. PreferredChain is no guarantee that this one gets delivered by the ACME endpoint. For example, for Let''s Encrypt''s DST crosssign you would use: "DST Root CA X3" or "ISRG Root X1" for the newer Let''s Encrypt root CA. This value picks the first certificate bundle in the ACME alternative chains that has a certificate with this value as its issuer''s CN' + type: string + maxLength: 64 + privateKeySecretRef: + description: PrivateKey is the name of a Kubernetes Secret resource that will be used to store the automatically generated ACME account private key. Optionally, a `key` may be specified to select a specific entry within the named Secret resource. If `key` is not specified, a default of `tls.key` will be used. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + server: + description: 'Server is the URL used to access the ACME server''s ''directory'' endpoint. For example, for Let''s Encrypt''s staging endpoint, you would use: "https://acme-staging-v02.api.letsencrypt.org/directory". Only ACME v2 endpoints (i.e. RFC 8555) are supported.' + type: string + skipTLSVerify: + description: Enables or disables validation of the ACME server TLS certificate. If true, requests to the ACME server will not have their TLS certificate validated (i.e. insecure connections will be allowed). Only enable this option in development environments. The cert-manager system installed roots will be used to verify connections to the ACME server if this is false. Defaults to false. + type: boolean + solvers: + description: 'Solvers is a list of challenge solvers that will be used to solve ACME challenges for the matching domains. Solver configurations must be provided in order to obtain certificates from an ACME server. For more information, see: https://cert-manager.io/docs/configuration/acme/' + type: array + items: + description: An ACMEChallengeSolver describes how to solve ACME challenges for the issuer it is part of. A selector may be provided to use different solving strategies for different DNS names. Only one of HTTP01 or DNS01 must be provided. + type: object + properties: + dns01: + description: Configures cert-manager to attempt to complete authorizations by performing the DNS01 challenge flow. + type: object + properties: + acmeDNS: + description: Use the 'ACME DNS' (https://github.com/joohoi/acme-dns) API to manage DNS01 challenge records. + type: object + required: + - accountSecretRef + - host + properties: + accountSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + host: + type: string + akamai: + description: Use the Akamai DNS zone management API to manage DNS01 challenge records. + type: object + required: + - accessTokenSecretRef + - clientSecretSecretRef + - clientTokenSecretRef + - serviceConsumerDomain + properties: + accessTokenSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + clientSecretSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + clientTokenSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + serviceConsumerDomain: + type: string + azureDNS: + description: Use the Microsoft Azure DNS API to manage DNS01 challenge records. + type: object + required: + - resourceGroupName + - subscriptionID + properties: + clientID: + description: if both this and ClientSecret are left unset MSI will be used + type: string + clientSecretSecretRef: + description: if both this and ClientID are left unset MSI will be used + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + environment: + description: name of the Azure environment (default AzurePublicCloud) + type: string + enum: + - AzurePublicCloud + - AzureChinaCloud + - AzureGermanCloud + - AzureUSGovernmentCloud + hostedZoneName: + description: name of the DNS zone that should be used + type: string + managedIdentity: + description: managed identity configuration, can not be used at the same time as clientID, clientSecretSecretRef or tenantID + type: object + properties: + clientID: + description: client ID of the managed identity, can not be used at the same time as resourceID + type: string + resourceID: + description: resource ID of the managed identity, can not be used at the same time as clientID + type: string + resourceGroupName: + description: resource group the DNS zone is located in + type: string + subscriptionID: + description: ID of the Azure subscription + type: string + tenantID: + description: when specifying ClientID and ClientSecret then this field is also needed + type: string + cloudDNS: + description: Use the Google Cloud DNS API to manage DNS01 challenge records. + type: object + required: + - project + properties: + hostedZoneName: + description: HostedZoneName is an optional field that tells cert-manager in which Cloud DNS zone the challenge record has to be created. If left empty cert-manager will automatically choose a zone. + type: string + project: + type: string + serviceAccountSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + cloudflare: + description: Use the Cloudflare API to manage DNS01 challenge records. + type: object + properties: + apiKeySecretRef: + description: 'API key to use to authenticate with Cloudflare. Note: using an API token to authenticate is now the recommended method as it allows greater control of permissions.' + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + apiTokenSecretRef: + description: API token used to authenticate with Cloudflare. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + email: + description: Email of the account, only required when using API key based authentication. + type: string + cnameStrategy: + description: CNAMEStrategy configures how the DNS01 provider should handle CNAME records when found in DNS zones. + type: string + enum: + - None + - Follow + digitalocean: + description: Use the DigitalOcean DNS API to manage DNS01 challenge records. + type: object + required: + - tokenSecretRef + properties: + tokenSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + rfc2136: + description: Use RFC2136 ("Dynamic Updates in the Domain Name System") (https://datatracker.ietf.org/doc/rfc2136/) to manage DNS01 challenge records. + type: object + required: + - nameserver + properties: + nameserver: + description: The IP address or hostname of an authoritative DNS server supporting RFC2136 in the form host:port. If the host is an IPv6 address it must be enclosed in square brackets (e.g [2001:db8::1]) ; port is optional. This field is required. + type: string + tsigAlgorithm: + description: 'The TSIG Algorithm configured in the DNS supporting RFC2136. Used only when ``tsigSecretSecretRef`` and ``tsigKeyName`` are defined. Supported values are (case-insensitive): ``HMACMD5`` (default), ``HMACSHA1``, ``HMACSHA256`` or ``HMACSHA512``.' + type: string + tsigKeyName: + description: The TSIG Key name configured in the DNS. If ``tsigSecretSecretRef`` is defined, this field is required. + type: string + tsigSecretSecretRef: + description: The name of the secret containing the TSIG value. If ``tsigKeyName`` is defined, this field is required. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + route53: + description: Use the AWS Route53 API to manage DNS01 challenge records. + type: object + required: + - region + properties: + accessKeyID: + description: 'The AccessKeyID is used for authentication. If not set we fall-back to using env vars, shared credentials file or AWS Instance metadata see: https://docs.aws.amazon.com/sdk-for-go/v1/developer-guide/configuring-sdk.html#specifying-credentials' + type: string + hostedZoneID: + description: If set, the provider will manage only this zone in Route53 and will not do an lookup using the route53:ListHostedZonesByName api call. + type: string + region: + description: Always set the region when using AccessKeyID and SecretAccessKey + type: string + role: + description: Role is a Role ARN which the Route53 provider will assume using either the explicit credentials AccessKeyID/SecretAccessKey or the inferred credentials from environment variables, shared credentials file or AWS Instance metadata + type: string + secretAccessKeySecretRef: + description: The SecretAccessKey is used for authentication. If not set we fall-back to using env vars, shared credentials file or AWS Instance metadata https://docs.aws.amazon.com/sdk-for-go/v1/developer-guide/configuring-sdk.html#specifying-credentials + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + webhook: + description: Configure an external webhook based DNS01 challenge solver to manage DNS01 challenge records. + type: object + required: + - groupName + - solverName + properties: + config: + description: Additional configuration that should be passed to the webhook apiserver when challenges are processed. This can contain arbitrary JSON data. Secret values should not be specified in this stanza. If secret values are needed (e.g. credentials for a DNS service), you should use a SecretKeySelector to reference a Secret resource. For details on the schema of this field, consult the webhook provider implementation's documentation. + x-kubernetes-preserve-unknown-fields: true + groupName: + description: The API group name that should be used when POSTing ChallengePayload resources to the webhook apiserver. This should be the same as the GroupName specified in the webhook provider implementation. + type: string + solverName: + description: The name of the solver to use, as defined in the webhook provider implementation. This will typically be the name of the provider, e.g. 'cloudflare'. + type: string + http01: + description: Configures cert-manager to attempt to complete authorizations by performing the HTTP01 challenge flow. It is not possible to obtain certificates for wildcard domain names (e.g. `*.example.com`) using the HTTP01 challenge mechanism. + type: object + properties: + gatewayHTTPRoute: + description: The Gateway API is a sig-network community API that models service networking in Kubernetes (https://gateway-api.sigs.k8s.io/). The Gateway solver will create HTTPRoutes with the specified labels in the same namespace as the challenge. This solver is experimental, and fields / behaviour may change in the future. + type: object + properties: + labels: + description: Custom labels that will be applied to HTTPRoutes created by cert-manager while solving HTTP-01 challenges. + type: object + additionalProperties: + type: string + parentRefs: + description: 'When solving an HTTP-01 challenge, cert-manager creates an HTTPRoute. cert-manager needs to know which parentRefs should be used when creating the HTTPRoute. Usually, the parentRef references a Gateway. See: https://gateway-api.sigs.k8s.io/v1alpha2/api-types/httproute/#attaching-to-gateways' + type: array + items: + description: "ParentRef identifies an API object (usually a Gateway) that can be considered a parent of this resource (usually a route). The only kind of parent resource with \"Core\" support is Gateway. This API may be extended in the future to support additional kinds of parent resources, such as HTTPRoute. \n The API object must be valid in the cluster; the Group and Kind must be registered in the cluster for this reference to be valid. \n References to objects with invalid Group and Kind are not valid, and must be rejected by the implementation, with appropriate Conditions set on the containing object." + type: object + required: + - name + properties: + group: + description: "Group is the group of the referent. \n Support: Core" + type: string + default: gateway.networking.k8s.io + maxLength: 253 + pattern: ^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ + kind: + description: "Kind is kind of the referent. \n Support: Core (Gateway) Support: Custom (Other Resources)" + type: string + default: Gateway + maxLength: 63 + minLength: 1 + pattern: ^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$ + name: + description: "Name is the name of the referent. \n Support: Core" + type: string + maxLength: 253 + minLength: 1 + namespace: + description: "Namespace is the namespace of the referent. When unspecified (or empty string), this refers to the local namespace of the Route. \n Support: Core" + type: string + maxLength: 63 + minLength: 1 + pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ + sectionName: + description: "SectionName is the name of a section within the target resource. In the following resources, SectionName is interpreted as the following: \n * Gateway: Listener Name \n Implementations MAY choose to support attaching Routes to other resources. If that is the case, they MUST clearly document how SectionName is interpreted. \n When unspecified (empty string), this will reference the entire resource. For the purpose of status, an attachment is considered successful if at least one section in the parent resource accepts it. For example, Gateway listeners can restrict which Routes can attach to them by Route kind, namespace, or hostname. If 1 of 2 Gateway listeners accept attachment from the referencing Route, the Route MUST be considered successfully attached. If no Gateway listeners accept attachment from this Route, the Route MUST be considered detached from the Gateway. \n Support: Core" + type: string + maxLength: 253 + minLength: 1 + pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ + serviceType: + description: Optional service type for Kubernetes solver service. Supported values are NodePort or ClusterIP. If unset, defaults to NodePort. + type: string + ingress: + description: The ingress based HTTP01 challenge solver will solve challenges by creating or modifying Ingress resources in order to route requests for '/.well-known/acme-challenge/XYZ' to 'challenge solver' pods that are provisioned by cert-manager for each Challenge to be completed. + type: object + properties: + class: + description: The ingress class to use when creating Ingress resources to solve ACME challenges that use this challenge solver. Only one of 'class' or 'name' may be specified. + type: string + ingressTemplate: + description: Optional ingress template used to configure the ACME challenge solver ingress used for HTTP01 challenges. + type: object + properties: + metadata: + description: ObjectMeta overrides for the ingress used to solve HTTP01 challenges. Only the 'labels' and 'annotations' fields may be set. If labels or annotations overlap with in-built values, the values here will override the in-built values. + type: object + properties: + annotations: + description: Annotations that should be added to the created ACME HTTP01 solver ingress. + type: object + additionalProperties: + type: string + labels: + description: Labels that should be added to the created ACME HTTP01 solver ingress. + type: object + additionalProperties: + type: string + name: + description: The name of the ingress resource that should have ACME challenge solving routes inserted into it in order to solve HTTP01 challenges. This is typically used in conjunction with ingress controllers like ingress-gce, which maintains a 1:1 mapping between external IPs and ingress resources. + type: string + podTemplate: + description: Optional pod template used to configure the ACME challenge solver pods used for HTTP01 challenges. + type: object + properties: + metadata: + description: ObjectMeta overrides for the pod used to solve HTTP01 challenges. Only the 'labels' and 'annotations' fields may be set. If labels or annotations overlap with in-built values, the values here will override the in-built values. + type: object + properties: + annotations: + description: Annotations that should be added to the create ACME HTTP01 solver pods. + type: object + additionalProperties: + type: string + labels: + description: Labels that should be added to the created ACME HTTP01 solver pods. + type: object + additionalProperties: + type: string + spec: + description: PodSpec defines overrides for the HTTP01 challenge solver pod. Only the 'priorityClassName', 'nodeSelector', 'affinity', 'serviceAccountName' and 'tolerations' fields are supported currently. All other fields will be ignored. + type: object + properties: + affinity: + description: If specified, the pod's scheduling constraints + type: object + properties: + nodeAffinity: + description: Describes node affinity scheduling rules for the pod. + type: object + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. + type: array + items: + description: An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). + type: object + required: + - preference + - weight + properties: + preference: + description: A node selector term, associated with the corresponding weight. + type: object + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + type: array + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchFields: + description: A list of node selector requirements by node's fields. + type: array + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + type: array + items: + type: string + weight: + description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. + type: integer + format: int32 + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. + type: object + required: + - nodeSelectorTerms + properties: + nodeSelectorTerms: + description: Required. A list of node selector terms. The terms are ORed. + type: array + items: + description: A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. + type: object + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + type: array + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchFields: + description: A list of node selector requirements by node's fields. + type: array + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + type: array + items: + type: string + podAffinity: + description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). + type: object + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + type: array + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + type: object + required: + - podAffinityTerm + - weight + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + type: object + required: + - topologyKey + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. This field is beta-level and is only honored when PodAffinityNamespaceSelector feature is enabled. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace" + type: array + items: + type: string + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + type: integer + format: int32 + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + type: array + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + type: object + required: + - topologyKey + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. This field is beta-level and is only honored when PodAffinityNamespaceSelector feature is enabled. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace" + type: array + items: + type: string + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + podAntiAffinity: + description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). + type: object + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + type: array + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + type: object + required: + - podAffinityTerm + - weight + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + type: object + required: + - topologyKey + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. This field is beta-level and is only honored when PodAffinityNamespaceSelector feature is enabled. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace" + type: array + items: + type: string + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + type: integer + format: int32 + requiredDuringSchedulingIgnoredDuringExecution: + description: If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + type: array + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + type: object + required: + - topologyKey + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. This field is beta-level and is only honored when PodAffinityNamespaceSelector feature is enabled. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace" + type: array + items: + type: string + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + nodeSelector: + description: 'NodeSelector is a selector which must be true for the pod to fit on a node. Selector which must match a node''s labels for the pod to be scheduled on that node. More info: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/' + type: object + additionalProperties: + type: string + priorityClassName: + description: If specified, the pod's priorityClassName. + type: string + serviceAccountName: + description: If specified, the pod's service account + type: string + tolerations: + description: If specified, the pod's tolerations. + type: array + items: + description: The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . + type: object + properties: + effect: + description: Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. + type: string + key: + description: Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. + type: string + operator: + description: Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. + type: string + tolerationSeconds: + description: TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. + type: integer + format: int64 + value: + description: Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. + type: string + serviceType: + description: Optional service type for Kubernetes solver service. Supported values are NodePort or ClusterIP. If unset, defaults to NodePort. + type: string + selector: + description: Selector selects a set of DNSNames on the Certificate resource that should be solved using this challenge solver. If not specified, the solver will be treated as the 'default' solver with the lowest priority, i.e. if any other solver has a more specific match, it will be used instead. + type: object + properties: + dnsNames: + description: List of DNSNames that this solver will be used to solve. If specified and a match is found, a dnsNames selector will take precedence over a dnsZones selector. If multiple solvers match with the same dnsNames value, the solver with the most matching labels in matchLabels will be selected. If neither has more matches, the solver defined earlier in the list will be selected. + type: array + items: + type: string + dnsZones: + description: List of DNSZones that this solver will be used to solve. The most specific DNS zone match specified here will take precedence over other DNS zone matches, so a solver specifying sys.example.com will be selected over one specifying example.com for the domain www.sys.example.com. If multiple solvers match with the same dnsZones value, the solver with the most matching labels in matchLabels will be selected. If neither has more matches, the solver defined earlier in the list will be selected. + type: array + items: + type: string + matchLabels: + description: A label selector that is used to refine the set of certificate's that this challenge solver will apply to. + type: object + additionalProperties: + type: string + ca: + description: CA configures this issuer to sign certificates using a signing CA keypair stored in a Secret resource. This is used to build internal PKIs that are managed by cert-manager. + type: object + required: + - secretName + properties: + crlDistributionPoints: + description: The CRL distribution points is an X.509 v3 certificate extension which identifies the location of the CRL from which the revocation of this certificate can be checked. If not set, certificates will be issued without distribution points set. + type: array + items: + type: string + ocspServers: + description: The OCSP server list is an X.509 v3 extension that defines a list of URLs of OCSP responders. The OCSP responders can be queried for the revocation status of an issued certificate. If not set, the certificate will be issued with no OCSP servers set. For example, an OCSP server URL could be "http://ocsp.int-x3.letsencrypt.org". + type: array + items: + type: string + secretName: + description: SecretName is the name of the secret used to sign Certificates issued by this Issuer. + type: string + selfSigned: + description: SelfSigned configures this issuer to 'self sign' certificates using the private key used to create the CertificateRequest object. + type: object + properties: + crlDistributionPoints: + description: The CRL distribution points is an X.509 v3 certificate extension which identifies the location of the CRL from which the revocation of this certificate can be checked. If not set certificate will be issued without CDP. Values are strings. + type: array + items: + type: string + vault: + description: Vault configures this issuer to sign certificates using a HashiCorp Vault PKI backend. + type: object + required: + - auth + - path + - server + properties: + auth: + description: Auth configures how cert-manager authenticates with the Vault server. + type: object + properties: + appRole: + description: AppRole authenticates with Vault using the App Role auth mechanism, with the role and secret stored in a Kubernetes Secret resource. + type: object + required: + - path + - roleId + - secretRef + properties: + path: + description: 'Path where the App Role authentication backend is mounted in Vault, e.g: "approle"' + type: string + roleId: + description: RoleID configured in the App Role authentication backend when setting up the authentication backend in Vault. + type: string + secretRef: + description: Reference to a key in a Secret that contains the App Role secret used to authenticate with Vault. The `key` field must be specified and denotes which entry within the Secret resource is used as the app role secret. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + kubernetes: + description: Kubernetes authenticates with Vault by passing the ServiceAccount token stored in the named Secret resource to the Vault server. + type: object + required: + - role + - secretRef + properties: + mountPath: + description: The Vault mountPath here is the mount path to use when authenticating with Vault. For example, setting a value to `/v1/auth/foo`, will use the path `/v1/auth/foo/login` to authenticate with Vault. If unspecified, the default value "/v1/auth/kubernetes" will be used. + type: string + role: + description: A required field containing the Vault Role to assume. A Role binds a Kubernetes ServiceAccount with a set of Vault policies. + type: string + secretRef: + description: The required Secret field containing a Kubernetes ServiceAccount JWT used for authenticating with Vault. Use of 'ambient credentials' is not supported. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + tokenSecretRef: + description: TokenSecretRef authenticates with Vault by presenting a token. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + caBundle: + description: PEM-encoded CA bundle (base64-encoded) used to validate Vault server certificate. Only used if the Server URL is using HTTPS protocol. This parameter is ignored for plain HTTP protocol connection. If not set the system root certificates are used to validate the TLS connection. + type: string + format: byte + namespace: + description: 'Name of the vault namespace. Namespaces is a set of features within Vault Enterprise that allows Vault environments to support Secure Multi-tenancy. e.g: "ns1" More about namespaces can be found here https://www.vaultproject.io/docs/enterprise/namespaces' + type: string + path: + description: 'Path is the mount path of the Vault PKI backend''s `sign` endpoint, e.g: "my_pki_mount/sign/my-role-name".' + type: string + server: + description: 'Server is the connection address for the Vault server, e.g: "https://vault.example.com:8200".' + type: string + venafi: + description: Venafi configures this issuer to sign certificates using a Venafi TPP or Venafi Cloud policy zone. + type: object + required: + - zone + properties: + cloud: + description: Cloud specifies the Venafi cloud configuration settings. Only one of TPP or Cloud may be specified. + type: object + required: + - apiTokenSecretRef + properties: + apiTokenSecretRef: + description: APITokenSecretRef is a secret key selector for the Venafi Cloud API token. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + url: + description: URL is the base URL for Venafi Cloud. Defaults to "https://api.venafi.cloud/v1". + type: string + tpp: + description: TPP specifies Trust Protection Platform configuration settings. Only one of TPP or Cloud may be specified. + type: object + required: + - credentialsRef + - url + properties: + caBundle: + description: CABundle is a PEM encoded TLS certificate to use to verify connections to the TPP instance. If specified, system roots will not be used and the issuing CA for the TPP instance must be verifiable using the provided root. If not specified, the connection will be verified using the cert-manager system root certificates. + type: string + format: byte + credentialsRef: + description: CredentialsRef is a reference to a Secret containing the username and password for the TPP server. The secret must contain two keys, 'username' and 'password'. + type: object + required: + - name + properties: + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + url: + description: 'URL is the base URL for the vedsdk endpoint of the Venafi TPP instance, for example: "https://tpp.example.com/vedsdk".' + type: string + zone: + description: Zone is the Venafi Policy Zone to use for this issuer. All requests made to the Venafi platform will be restricted by the named zone policy. This field is required. + type: string + status: + description: Status of the ClusterIssuer. This is set and managed automatically. + type: object + properties: + acme: + description: ACME specific status options. This field should only be set if the Issuer is configured to use an ACME server to issue certificates. + type: object + properties: + lastRegisteredEmail: + description: LastRegisteredEmail is the email associated with the latest registered ACME account, in order to track changes made to registered account associated with the Issuer + type: string + uri: + description: URI is the unique account identifier, which can also be used to retrieve account details from the CA + type: string + conditions: + description: List of status conditions to indicate the status of a CertificateRequest. Known condition types are `Ready`. + type: array + items: + description: IssuerCondition contains condition information for an Issuer. + type: object + required: + - status + - type + properties: + lastTransitionTime: + description: LastTransitionTime is the timestamp corresponding to the last status change of this condition. + type: string + format: date-time + message: + description: Message is a human readable description of the details of the last transition, complementing reason. + type: string + observedGeneration: + description: If set, this represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.condition[x].observedGeneration is 9, the condition is out of date with respect to the current state of the Issuer. + type: integer + format: int64 + reason: + description: Reason is a brief machine readable explanation for the condition's last transition. + type: string + status: + description: Status of the condition, one of (`True`, `False`, `Unknown`). + type: string + enum: + - "True" + - "False" + - Unknown + type: + description: Type of the condition, known values are (`Ready`). + type: string + x-kubernetes-list-map-keys: + - type + x-kubernetes-list-type: map + served: true + storage: true +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + name: issuers.cert-manager.io + annotations: + cert-manager.io/inject-ca-from-secret: '{{ template "webhook.caRef" . }}' + labels: + app: '{{ template "cert-manager.name" . }}' + app.kubernetes.io/name: '{{ template "cert-manager.name" . }}' + app.kubernetes.io/instance: '{{ .Release.Name }}' + # Generated labels {{- include "labels" . | nindent 4 }} +spec: + group: cert-manager.io + names: + kind: Issuer + listKind: IssuerList + plural: issuers + singular: issuer + categories: + - cert-manager + scope: Namespaced + versions: + - name: v1 + subresources: + status: {} + additionalPrinterColumns: + - jsonPath: .status.conditions[?(@.type=="Ready")].status + name: Ready + type: string + - jsonPath: .status.conditions[?(@.type=="Ready")].message + name: Status + priority: 1 + type: string + - jsonPath: .metadata.creationTimestamp + description: CreationTimestamp is a timestamp representing the server time when this object was created. It is not guaranteed to be set in happens-before order across separate operations. Clients may not set this value. It is represented in RFC3339 form and is in UTC. + name: Age + type: date + schema: + openAPIV3Schema: + description: An Issuer represents a certificate issuing authority which can be referenced as part of `issuerRef` fields. It is scoped to a single namespace and can therefore only be referenced by resources within the same namespace. + type: object + required: + - spec + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Desired state of the Issuer resource. + type: object + properties: + acme: + description: ACME configures this issuer to communicate with a RFC8555 (ACME) server to obtain signed x509 certificates. + type: object + required: + - privateKeySecretRef + - server + properties: + disableAccountKeyGeneration: + description: Enables or disables generating a new ACME account key. If true, the Issuer resource will *not* request a new account but will expect the account key to be supplied via an existing secret. If false, the cert-manager system will generate a new ACME account key for the Issuer. Defaults to false. + type: boolean + email: + description: Email is the email address to be associated with the ACME account. This field is optional, but it is strongly recommended to be set. It will be used to contact you in case of issues with your account or certificates, including expiry notification emails. This field may be updated after the account is initially registered. + type: string + enableDurationFeature: + description: Enables requesting a Not After date on certificates that matches the duration of the certificate. This is not supported by all ACME servers like Let's Encrypt. If set to true when the ACME server does not support it it will create an error on the Order. Defaults to false. + type: boolean + externalAccountBinding: + description: ExternalAccountBinding is a reference to a CA external account of the ACME server. If set, upon registration cert-manager will attempt to associate the given external account credentials with the registered ACME account. + type: object + required: + - keyID + - keySecretRef + properties: + keyAlgorithm: + description: 'Deprecated: keyAlgorithm field exists for historical compatibility reasons and should not be used. The algorithm is now hardcoded to HS256 in golang/x/crypto/acme.' + type: string + enum: + - HS256 + - HS384 + - HS512 + keyID: + description: keyID is the ID of the CA key that the External Account is bound to. + type: string + keySecretRef: + description: keySecretRef is a Secret Key Selector referencing a data item in a Kubernetes Secret which holds the symmetric MAC key of the External Account Binding. The `key` is the index string that is paired with the key data in the Secret and should not be confused with the key data itself, or indeed with the External Account Binding keyID above. The secret key stored in the Secret **must** be un-padded, base64 URL encoded data. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + preferredChain: + description: 'PreferredChain is the chain to use if the ACME server outputs multiple. PreferredChain is no guarantee that this one gets delivered by the ACME endpoint. For example, for Let''s Encrypt''s DST crosssign you would use: "DST Root CA X3" or "ISRG Root X1" for the newer Let''s Encrypt root CA. This value picks the first certificate bundle in the ACME alternative chains that has a certificate with this value as its issuer''s CN' + type: string + maxLength: 64 + privateKeySecretRef: + description: PrivateKey is the name of a Kubernetes Secret resource that will be used to store the automatically generated ACME account private key. Optionally, a `key` may be specified to select a specific entry within the named Secret resource. If `key` is not specified, a default of `tls.key` will be used. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + server: + description: 'Server is the URL used to access the ACME server''s ''directory'' endpoint. For example, for Let''s Encrypt''s staging endpoint, you would use: "https://acme-staging-v02.api.letsencrypt.org/directory". Only ACME v2 endpoints (i.e. RFC 8555) are supported.' + type: string + skipTLSVerify: + description: Enables or disables validation of the ACME server TLS certificate. If true, requests to the ACME server will not have their TLS certificate validated (i.e. insecure connections will be allowed). Only enable this option in development environments. The cert-manager system installed roots will be used to verify connections to the ACME server if this is false. Defaults to false. + type: boolean + solvers: + description: 'Solvers is a list of challenge solvers that will be used to solve ACME challenges for the matching domains. Solver configurations must be provided in order to obtain certificates from an ACME server. For more information, see: https://cert-manager.io/docs/configuration/acme/' + type: array + items: + description: An ACMEChallengeSolver describes how to solve ACME challenges for the issuer it is part of. A selector may be provided to use different solving strategies for different DNS names. Only one of HTTP01 or DNS01 must be provided. + type: object + properties: + dns01: + description: Configures cert-manager to attempt to complete authorizations by performing the DNS01 challenge flow. + type: object + properties: + acmeDNS: + description: Use the 'ACME DNS' (https://github.com/joohoi/acme-dns) API to manage DNS01 challenge records. + type: object + required: + - accountSecretRef + - host + properties: + accountSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + host: + type: string + akamai: + description: Use the Akamai DNS zone management API to manage DNS01 challenge records. + type: object + required: + - accessTokenSecretRef + - clientSecretSecretRef + - clientTokenSecretRef + - serviceConsumerDomain + properties: + accessTokenSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + clientSecretSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + clientTokenSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + serviceConsumerDomain: + type: string + azureDNS: + description: Use the Microsoft Azure DNS API to manage DNS01 challenge records. + type: object + required: + - resourceGroupName + - subscriptionID + properties: + clientID: + description: if both this and ClientSecret are left unset MSI will be used + type: string + clientSecretSecretRef: + description: if both this and ClientID are left unset MSI will be used + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + environment: + description: name of the Azure environment (default AzurePublicCloud) + type: string + enum: + - AzurePublicCloud + - AzureChinaCloud + - AzureGermanCloud + - AzureUSGovernmentCloud + hostedZoneName: + description: name of the DNS zone that should be used + type: string + managedIdentity: + description: managed identity configuration, can not be used at the same time as clientID, clientSecretSecretRef or tenantID + type: object + properties: + clientID: + description: client ID of the managed identity, can not be used at the same time as resourceID + type: string + resourceID: + description: resource ID of the managed identity, can not be used at the same time as clientID + type: string + resourceGroupName: + description: resource group the DNS zone is located in + type: string + subscriptionID: + description: ID of the Azure subscription + type: string + tenantID: + description: when specifying ClientID and ClientSecret then this field is also needed + type: string + cloudDNS: + description: Use the Google Cloud DNS API to manage DNS01 challenge records. + type: object + required: + - project + properties: + hostedZoneName: + description: HostedZoneName is an optional field that tells cert-manager in which Cloud DNS zone the challenge record has to be created. If left empty cert-manager will automatically choose a zone. + type: string + project: + type: string + serviceAccountSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + cloudflare: + description: Use the Cloudflare API to manage DNS01 challenge records. + type: object + properties: + apiKeySecretRef: + description: 'API key to use to authenticate with Cloudflare. Note: using an API token to authenticate is now the recommended method as it allows greater control of permissions.' + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + apiTokenSecretRef: + description: API token used to authenticate with Cloudflare. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + email: + description: Email of the account, only required when using API key based authentication. + type: string + cnameStrategy: + description: CNAMEStrategy configures how the DNS01 provider should handle CNAME records when found in DNS zones. + type: string + enum: + - None + - Follow + digitalocean: + description: Use the DigitalOcean DNS API to manage DNS01 challenge records. + type: object + required: + - tokenSecretRef + properties: + tokenSecretRef: + description: A reference to a specific 'key' within a Secret resource. In some instances, `key` is a required field. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + rfc2136: + description: Use RFC2136 ("Dynamic Updates in the Domain Name System") (https://datatracker.ietf.org/doc/rfc2136/) to manage DNS01 challenge records. + type: object + required: + - nameserver + properties: + nameserver: + description: The IP address or hostname of an authoritative DNS server supporting RFC2136 in the form host:port. If the host is an IPv6 address it must be enclosed in square brackets (e.g [2001:db8::1]) ; port is optional. This field is required. + type: string + tsigAlgorithm: + description: 'The TSIG Algorithm configured in the DNS supporting RFC2136. Used only when ``tsigSecretSecretRef`` and ``tsigKeyName`` are defined. Supported values are (case-insensitive): ``HMACMD5`` (default), ``HMACSHA1``, ``HMACSHA256`` or ``HMACSHA512``.' + type: string + tsigKeyName: + description: The TSIG Key name configured in the DNS. If ``tsigSecretSecretRef`` is defined, this field is required. + type: string + tsigSecretSecretRef: + description: The name of the secret containing the TSIG value. If ``tsigKeyName`` is defined, this field is required. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + route53: + description: Use the AWS Route53 API to manage DNS01 challenge records. + type: object + required: + - region + properties: + accessKeyID: + description: 'The AccessKeyID is used for authentication. If not set we fall-back to using env vars, shared credentials file or AWS Instance metadata see: https://docs.aws.amazon.com/sdk-for-go/v1/developer-guide/configuring-sdk.html#specifying-credentials' + type: string + hostedZoneID: + description: If set, the provider will manage only this zone in Route53 and will not do an lookup using the route53:ListHostedZonesByName api call. + type: string + region: + description: Always set the region when using AccessKeyID and SecretAccessKey + type: string + role: + description: Role is a Role ARN which the Route53 provider will assume using either the explicit credentials AccessKeyID/SecretAccessKey or the inferred credentials from environment variables, shared credentials file or AWS Instance metadata + type: string + secretAccessKeySecretRef: + description: The SecretAccessKey is used for authentication. If not set we fall-back to using env vars, shared credentials file or AWS Instance metadata https://docs.aws.amazon.com/sdk-for-go/v1/developer-guide/configuring-sdk.html#specifying-credentials + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + webhook: + description: Configure an external webhook based DNS01 challenge solver to manage DNS01 challenge records. + type: object + required: + - groupName + - solverName + properties: + config: + description: Additional configuration that should be passed to the webhook apiserver when challenges are processed. This can contain arbitrary JSON data. Secret values should not be specified in this stanza. If secret values are needed (e.g. credentials for a DNS service), you should use a SecretKeySelector to reference a Secret resource. For details on the schema of this field, consult the webhook provider implementation's documentation. + x-kubernetes-preserve-unknown-fields: true + groupName: + description: The API group name that should be used when POSTing ChallengePayload resources to the webhook apiserver. This should be the same as the GroupName specified in the webhook provider implementation. + type: string + solverName: + description: The name of the solver to use, as defined in the webhook provider implementation. This will typically be the name of the provider, e.g. 'cloudflare'. + type: string + http01: + description: Configures cert-manager to attempt to complete authorizations by performing the HTTP01 challenge flow. It is not possible to obtain certificates for wildcard domain names (e.g. `*.example.com`) using the HTTP01 challenge mechanism. + type: object + properties: + gatewayHTTPRoute: + description: The Gateway API is a sig-network community API that models service networking in Kubernetes (https://gateway-api.sigs.k8s.io/). The Gateway solver will create HTTPRoutes with the specified labels in the same namespace as the challenge. This solver is experimental, and fields / behaviour may change in the future. + type: object + properties: + labels: + description: Custom labels that will be applied to HTTPRoutes created by cert-manager while solving HTTP-01 challenges. + type: object + additionalProperties: + type: string + parentRefs: + description: 'When solving an HTTP-01 challenge, cert-manager creates an HTTPRoute. cert-manager needs to know which parentRefs should be used when creating the HTTPRoute. Usually, the parentRef references a Gateway. See: https://gateway-api.sigs.k8s.io/v1alpha2/api-types/httproute/#attaching-to-gateways' + type: array + items: + description: "ParentRef identifies an API object (usually a Gateway) that can be considered a parent of this resource (usually a route). The only kind of parent resource with \"Core\" support is Gateway. This API may be extended in the future to support additional kinds of parent resources, such as HTTPRoute. \n The API object must be valid in the cluster; the Group and Kind must be registered in the cluster for this reference to be valid. \n References to objects with invalid Group and Kind are not valid, and must be rejected by the implementation, with appropriate Conditions set on the containing object." + type: object + required: + - name + properties: + group: + description: "Group is the group of the referent. \n Support: Core" + type: string + default: gateway.networking.k8s.io + maxLength: 253 + pattern: ^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ + kind: + description: "Kind is kind of the referent. \n Support: Core (Gateway) Support: Custom (Other Resources)" + type: string + default: Gateway + maxLength: 63 + minLength: 1 + pattern: ^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$ + name: + description: "Name is the name of the referent. \n Support: Core" + type: string + maxLength: 253 + minLength: 1 + namespace: + description: "Namespace is the namespace of the referent. When unspecified (or empty string), this refers to the local namespace of the Route. \n Support: Core" + type: string + maxLength: 63 + minLength: 1 + pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$ + sectionName: + description: "SectionName is the name of a section within the target resource. In the following resources, SectionName is interpreted as the following: \n * Gateway: Listener Name \n Implementations MAY choose to support attaching Routes to other resources. If that is the case, they MUST clearly document how SectionName is interpreted. \n When unspecified (empty string), this will reference the entire resource. For the purpose of status, an attachment is considered successful if at least one section in the parent resource accepts it. For example, Gateway listeners can restrict which Routes can attach to them by Route kind, namespace, or hostname. If 1 of 2 Gateway listeners accept attachment from the referencing Route, the Route MUST be considered successfully attached. If no Gateway listeners accept attachment from this Route, the Route MUST be considered detached from the Gateway. \n Support: Core" + type: string + maxLength: 253 + minLength: 1 + pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$ + serviceType: + description: Optional service type for Kubernetes solver service. Supported values are NodePort or ClusterIP. If unset, defaults to NodePort. + type: string + ingress: + description: The ingress based HTTP01 challenge solver will solve challenges by creating or modifying Ingress resources in order to route requests for '/.well-known/acme-challenge/XYZ' to 'challenge solver' pods that are provisioned by cert-manager for each Challenge to be completed. + type: object + properties: + class: + description: The ingress class to use when creating Ingress resources to solve ACME challenges that use this challenge solver. Only one of 'class' or 'name' may be specified. + type: string + ingressTemplate: + description: Optional ingress template used to configure the ACME challenge solver ingress used for HTTP01 challenges. + type: object + properties: + metadata: + description: ObjectMeta overrides for the ingress used to solve HTTP01 challenges. Only the 'labels' and 'annotations' fields may be set. If labels or annotations overlap with in-built values, the values here will override the in-built values. + type: object + properties: + annotations: + description: Annotations that should be added to the created ACME HTTP01 solver ingress. + type: object + additionalProperties: + type: string + labels: + description: Labels that should be added to the created ACME HTTP01 solver ingress. + type: object + additionalProperties: + type: string + name: + description: The name of the ingress resource that should have ACME challenge solving routes inserted into it in order to solve HTTP01 challenges. This is typically used in conjunction with ingress controllers like ingress-gce, which maintains a 1:1 mapping between external IPs and ingress resources. + type: string + podTemplate: + description: Optional pod template used to configure the ACME challenge solver pods used for HTTP01 challenges. + type: object + properties: + metadata: + description: ObjectMeta overrides for the pod used to solve HTTP01 challenges. Only the 'labels' and 'annotations' fields may be set. If labels or annotations overlap with in-built values, the values here will override the in-built values. + type: object + properties: + annotations: + description: Annotations that should be added to the create ACME HTTP01 solver pods. + type: object + additionalProperties: + type: string + labels: + description: Labels that should be added to the created ACME HTTP01 solver pods. + type: object + additionalProperties: + type: string + spec: + description: PodSpec defines overrides for the HTTP01 challenge solver pod. Only the 'priorityClassName', 'nodeSelector', 'affinity', 'serviceAccountName' and 'tolerations' fields are supported currently. All other fields will be ignored. + type: object + properties: + affinity: + description: If specified, the pod's scheduling constraints + type: object + properties: + nodeAffinity: + description: Describes node affinity scheduling rules for the pod. + type: object + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. + type: array + items: + description: An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). + type: object + required: + - preference + - weight + properties: + preference: + description: A node selector term, associated with the corresponding weight. + type: object + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + type: array + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchFields: + description: A list of node selector requirements by node's fields. + type: array + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + type: array + items: + type: string + weight: + description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. + type: integer + format: int32 + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. + type: object + required: + - nodeSelectorTerms + properties: + nodeSelectorTerms: + description: Required. A list of node selector terms. The terms are ORed. + type: array + items: + description: A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. + type: object + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + type: array + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchFields: + description: A list of node selector requirements by node's fields. + type: array + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + type: array + items: + type: string + podAffinity: + description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). + type: object + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + type: array + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + type: object + required: + - podAffinityTerm + - weight + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + type: object + required: + - topologyKey + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. This field is beta-level and is only honored when PodAffinityNamespaceSelector feature is enabled. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace" + type: array + items: + type: string + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + type: integer + format: int32 + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + type: array + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + type: object + required: + - topologyKey + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. This field is beta-level and is only honored when PodAffinityNamespaceSelector feature is enabled. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace" + type: array + items: + type: string + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + podAntiAffinity: + description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). + type: object + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + type: array + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + type: object + required: + - podAffinityTerm + - weight + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + type: object + required: + - topologyKey + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. This field is beta-level and is only honored when PodAffinityNamespaceSelector feature is enabled. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace" + type: array + items: + type: string + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + type: integer + format: int32 + requiredDuringSchedulingIgnoredDuringExecution: + description: If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + type: array + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + type: object + required: + - topologyKey + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. This field is beta-level and is only honored when PodAffinityNamespaceSelector feature is enabled. + type: object + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + type: array + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + type: object + required: + - key + - operator + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + type: array + items: + type: string + matchLabels: + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + additionalProperties: + type: string + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace" + type: array + items: + type: string + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + nodeSelector: + description: 'NodeSelector is a selector which must be true for the pod to fit on a node. Selector which must match a node''s labels for the pod to be scheduled on that node. More info: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/' + type: object + additionalProperties: + type: string + priorityClassName: + description: If specified, the pod's priorityClassName. + type: string + serviceAccountName: + description: If specified, the pod's service account + type: string + tolerations: + description: If specified, the pod's tolerations. + type: array + items: + description: The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . + type: object + properties: + effect: + description: Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. + type: string + key: + description: Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. + type: string + operator: + description: Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. + type: string + tolerationSeconds: + description: TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. + type: integer + format: int64 + value: + description: Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. + type: string + serviceType: + description: Optional service type for Kubernetes solver service. Supported values are NodePort or ClusterIP. If unset, defaults to NodePort. + type: string + selector: + description: Selector selects a set of DNSNames on the Certificate resource that should be solved using this challenge solver. If not specified, the solver will be treated as the 'default' solver with the lowest priority, i.e. if any other solver has a more specific match, it will be used instead. + type: object + properties: + dnsNames: + description: List of DNSNames that this solver will be used to solve. If specified and a match is found, a dnsNames selector will take precedence over a dnsZones selector. If multiple solvers match with the same dnsNames value, the solver with the most matching labels in matchLabels will be selected. If neither has more matches, the solver defined earlier in the list will be selected. + type: array + items: + type: string + dnsZones: + description: List of DNSZones that this solver will be used to solve. The most specific DNS zone match specified here will take precedence over other DNS zone matches, so a solver specifying sys.example.com will be selected over one specifying example.com for the domain www.sys.example.com. If multiple solvers match with the same dnsZones value, the solver with the most matching labels in matchLabels will be selected. If neither has more matches, the solver defined earlier in the list will be selected. + type: array + items: + type: string + matchLabels: + description: A label selector that is used to refine the set of certificate's that this challenge solver will apply to. + type: object + additionalProperties: + type: string + ca: + description: CA configures this issuer to sign certificates using a signing CA keypair stored in a Secret resource. This is used to build internal PKIs that are managed by cert-manager. + type: object + required: + - secretName + properties: + crlDistributionPoints: + description: The CRL distribution points is an X.509 v3 certificate extension which identifies the location of the CRL from which the revocation of this certificate can be checked. If not set, certificates will be issued without distribution points set. + type: array + items: + type: string + ocspServers: + description: The OCSP server list is an X.509 v3 extension that defines a list of URLs of OCSP responders. The OCSP responders can be queried for the revocation status of an issued certificate. If not set, the certificate will be issued with no OCSP servers set. For example, an OCSP server URL could be "http://ocsp.int-x3.letsencrypt.org". + type: array + items: + type: string + secretName: + description: SecretName is the name of the secret used to sign Certificates issued by this Issuer. + type: string + selfSigned: + description: SelfSigned configures this issuer to 'self sign' certificates using the private key used to create the CertificateRequest object. + type: object + properties: + crlDistributionPoints: + description: The CRL distribution points is an X.509 v3 certificate extension which identifies the location of the CRL from which the revocation of this certificate can be checked. If not set certificate will be issued without CDP. Values are strings. + type: array + items: + type: string + vault: + description: Vault configures this issuer to sign certificates using a HashiCorp Vault PKI backend. + type: object + required: + - auth + - path + - server + properties: + auth: + description: Auth configures how cert-manager authenticates with the Vault server. + type: object + properties: + appRole: + description: AppRole authenticates with Vault using the App Role auth mechanism, with the role and secret stored in a Kubernetes Secret resource. + type: object + required: + - path + - roleId + - secretRef + properties: + path: + description: 'Path where the App Role authentication backend is mounted in Vault, e.g: "approle"' + type: string + roleId: + description: RoleID configured in the App Role authentication backend when setting up the authentication backend in Vault. + type: string + secretRef: + description: Reference to a key in a Secret that contains the App Role secret used to authenticate with Vault. The `key` field must be specified and denotes which entry within the Secret resource is used as the app role secret. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + kubernetes: + description: Kubernetes authenticates with Vault by passing the ServiceAccount token stored in the named Secret resource to the Vault server. + type: object + required: + - role + - secretRef + properties: + mountPath: + description: The Vault mountPath here is the mount path to use when authenticating with Vault. For example, setting a value to `/v1/auth/foo`, will use the path `/v1/auth/foo/login` to authenticate with Vault. If unspecified, the default value "/v1/auth/kubernetes" will be used. + type: string + role: + description: A required field containing the Vault Role to assume. A Role binds a Kubernetes ServiceAccount with a set of Vault policies. + type: string + secretRef: + description: The required Secret field containing a Kubernetes ServiceAccount JWT used for authenticating with Vault. Use of 'ambient credentials' is not supported. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + tokenSecretRef: + description: TokenSecretRef authenticates with Vault by presenting a token. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + caBundle: + description: PEM-encoded CA bundle (base64-encoded) used to validate Vault server certificate. Only used if the Server URL is using HTTPS protocol. This parameter is ignored for plain HTTP protocol connection. If not set the system root certificates are used to validate the TLS connection. + type: string + format: byte + namespace: + description: 'Name of the vault namespace. Namespaces is a set of features within Vault Enterprise that allows Vault environments to support Secure Multi-tenancy. e.g: "ns1" More about namespaces can be found here https://www.vaultproject.io/docs/enterprise/namespaces' + type: string + path: + description: 'Path is the mount path of the Vault PKI backend''s `sign` endpoint, e.g: "my_pki_mount/sign/my-role-name".' + type: string + server: + description: 'Server is the connection address for the Vault server, e.g: "https://vault.example.com:8200".' + type: string + venafi: + description: Venafi configures this issuer to sign certificates using a Venafi TPP or Venafi Cloud policy zone. + type: object + required: + - zone + properties: + cloud: + description: Cloud specifies the Venafi cloud configuration settings. Only one of TPP or Cloud may be specified. + type: object + required: + - apiTokenSecretRef + properties: + apiTokenSecretRef: + description: APITokenSecretRef is a secret key selector for the Venafi Cloud API token. + type: object + required: + - name + properties: + key: + description: The key of the entry in the Secret resource's `data` field to be used. Some instances of this field may be defaulted, in others it may be required. + type: string + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + url: + description: URL is the base URL for Venafi Cloud. Defaults to "https://api.venafi.cloud/v1". + type: string + tpp: + description: TPP specifies Trust Protection Platform configuration settings. Only one of TPP or Cloud may be specified. + type: object + required: + - credentialsRef + - url + properties: + caBundle: + description: CABundle is a PEM encoded TLS certificate to use to verify connections to the TPP instance. If specified, system roots will not be used and the issuing CA for the TPP instance must be verifiable using the provided root. If not specified, the connection will be verified using the cert-manager system root certificates. + type: string + format: byte + credentialsRef: + description: CredentialsRef is a reference to a Secret containing the username and password for the TPP server. The secret must contain two keys, 'username' and 'password'. + type: object + required: + - name + properties: + name: + description: 'Name of the resource being referred to. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + url: + description: 'URL is the base URL for the vedsdk endpoint of the Venafi TPP instance, for example: "https://tpp.example.com/vedsdk".' + type: string + zone: + description: Zone is the Venafi Policy Zone to use for this issuer. All requests made to the Venafi platform will be restricted by the named zone policy. This field is required. + type: string + status: + description: Status of the Issuer. This is set and managed automatically. + type: object + properties: + acme: + description: ACME specific status options. This field should only be set if the Issuer is configured to use an ACME server to issue certificates. + type: object + properties: + lastRegisteredEmail: + description: LastRegisteredEmail is the email associated with the latest registered ACME account, in order to track changes made to registered account associated with the Issuer + type: string + uri: + description: URI is the unique account identifier, which can also be used to retrieve account details from the CA + type: string + conditions: + description: List of status conditions to indicate the status of a CertificateRequest. Known condition types are `Ready`. + type: array + items: + description: IssuerCondition contains condition information for an Issuer. + type: object + required: + - status + - type + properties: + lastTransitionTime: + description: LastTransitionTime is the timestamp corresponding to the last status change of this condition. + type: string + format: date-time + message: + description: Message is a human readable description of the details of the last transition, complementing reason. + type: string + observedGeneration: + description: If set, this represents the .metadata.generation that the condition was set based upon. For instance, if .metadata.generation is currently 12, but the .status.condition[x].observedGeneration is 9, the condition is out of date with respect to the current state of the Issuer. + type: integer + format: int64 + reason: + description: Reason is a brief machine readable explanation for the condition's last transition. + type: string + status: + description: Status of the condition, one of (`True`, `False`, `Unknown`). + type: string + enum: + - "True" + - "False" + - Unknown + type: + description: Type of the condition, known values are (`Ready`). + type: string + x-kubernetes-list-map-keys: + - type + x-kubernetes-list-type: map + served: true + storage: true +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + name: orders.acme.cert-manager.io + annotations: + cert-manager.io/inject-ca-from-secret: '{{ template "webhook.caRef" . }}' + labels: + app: '{{ template "cert-manager.name" . }}' + app.kubernetes.io/name: '{{ template "cert-manager.name" . }}' + app.kubernetes.io/instance: '{{ .Release.Name }}' + # Generated labels {{- include "labels" . | nindent 4 }} +spec: + group: acme.cert-manager.io + names: + kind: Order + listKind: OrderList + plural: orders + singular: order + categories: + - cert-manager + - cert-manager-acme + scope: Namespaced + versions: + - name: v1 + subresources: + status: {} + additionalPrinterColumns: + - jsonPath: .status.state + name: State + type: string + - jsonPath: .spec.issuerRef.name + name: Issuer + priority: 1 + type: string + - jsonPath: .status.reason + name: Reason + priority: 1 + type: string + - jsonPath: .metadata.creationTimestamp + description: CreationTimestamp is a timestamp representing the server time when this object was created. It is not guaranteed to be set in happens-before order across separate operations. Clients may not set this value. It is represented in RFC3339 form and is in UTC. + name: Age + type: date + schema: + openAPIV3Schema: + description: Order is a type to represent an Order with an ACME server + type: object + required: + - metadata + - spec + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + type: object + required: + - issuerRef + - request + properties: + commonName: + description: CommonName is the common name as specified on the DER encoded CSR. If specified, this value must also be present in `dnsNames` or `ipAddresses`. This field must match the corresponding field on the DER encoded CSR. + type: string + dnsNames: + description: DNSNames is a list of DNS names that should be included as part of the Order validation process. This field must match the corresponding field on the DER encoded CSR. + type: array + items: + type: string + duration: + description: Duration is the duration for the not after date for the requested certificate. this is set on order creation as pe the ACME spec. + type: string + ipAddresses: + description: IPAddresses is a list of IP addresses that should be included as part of the Order validation process. This field must match the corresponding field on the DER encoded CSR. + type: array + items: + type: string + issuerRef: + description: IssuerRef references a properly configured ACME-type Issuer which should be used to create this Order. If the Issuer does not exist, processing will be retried. If the Issuer is not an 'ACME' Issuer, an error will be returned and the Order will be marked as failed. + type: object + required: + - name + properties: + group: + description: Group of the resource being referred to. + type: string + kind: + description: Kind of the resource being referred to. + type: string + name: + description: Name of the resource being referred to. + type: string + request: + description: Certificate signing request bytes in DER encoding. This will be used when finalizing the order. This field must be set on the order. + type: string + format: byte + status: + type: object + properties: + authorizations: + description: Authorizations contains data returned from the ACME server on what authorizations must be completed in order to validate the DNS names specified on the Order. + type: array + items: + description: ACMEAuthorization contains data returned from the ACME server on an authorization that must be completed in order validate a DNS name on an ACME Order resource. + type: object + required: + - url + properties: + challenges: + description: Challenges specifies the challenge types offered by the ACME server. One of these challenge types will be selected when validating the DNS name and an appropriate Challenge resource will be created to perform the ACME challenge process. + type: array + items: + description: Challenge specifies a challenge offered by the ACME server for an Order. An appropriate Challenge resource can be created to perform the ACME challenge process. + type: object + required: + - token + - type + - url + properties: + token: + description: Token is the token that must be presented for this challenge. This is used to compute the 'key' that must also be presented. + type: string + type: + description: Type is the type of challenge being offered, e.g. 'http-01', 'dns-01', 'tls-sni-01', etc. This is the raw value retrieved from the ACME server. Only 'http-01' and 'dns-01' are supported by cert-manager, other values will be ignored. + type: string + url: + description: URL is the URL of this challenge. It can be used to retrieve additional metadata about the Challenge from the ACME server. + type: string + identifier: + description: Identifier is the DNS name to be validated as part of this authorization + type: string + initialState: + description: InitialState is the initial state of the ACME authorization when first fetched from the ACME server. If an Authorization is already 'valid', the Order controller will not create a Challenge resource for the authorization. This will occur when working with an ACME server that enables 'authz reuse' (such as Let's Encrypt's production endpoint). If not set and 'identifier' is set, the state is assumed to be pending and a Challenge will be created. + type: string + enum: + - valid + - ready + - pending + - processing + - invalid + - expired + - errored + url: + description: URL is the URL of the Authorization that must be completed + type: string + wildcard: + description: Wildcard will be true if this authorization is for a wildcard DNS name. If this is true, the identifier will be the *non-wildcard* version of the DNS name. For example, if '*.example.com' is the DNS name being validated, this field will be 'true' and the 'identifier' field will be 'example.com'. + type: boolean + certificate: + description: Certificate is a copy of the PEM encoded certificate for this Order. This field will be populated after the order has been successfully finalized with the ACME server, and the order has transitioned to the 'valid' state. + type: string + format: byte + failureTime: + description: FailureTime stores the time that this order failed. This is used to influence garbage collection and back-off. + type: string + format: date-time + finalizeURL: + description: FinalizeURL of the Order. This is used to obtain certificates for this order once it has been completed. + type: string + reason: + description: Reason optionally provides more information about a why the order is in the current state. + type: string + state: + description: State contains the current state of this Order resource. States 'success' and 'expired' are 'final' + type: string + enum: + - valid + - ready + - pending + - processing + - invalid + - expired + - errored + url: + description: URL of the Order. This will initially be empty when the resource is first created. The Order controller will populate this field when the Order is first processed. This field will be immutable after it is initially set. + type: string + served: true + storage: true +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/deployment.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/deployment.yaml new file mode 100644 index 0000000..b7f549e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/deployment.yaml @@ -0,0 +1,170 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ template "cert-manager.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "cert-manager.name" . }} + app.kubernetes.io/name: {{ template "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} + {{- with .Values.deploymentAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.replicaCount }} + selector: + matchLabels: + app.kubernetes.io/name: {{ template "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- with .Values.strategy }} + strategy: + {{- toYaml . | nindent 4 }} + {{- end }} + template: + metadata: + labels: + app: {{ template "cert-manager.name" . }} + app.kubernetes.io/name: {{ template "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 8 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.podAnnotations }} + annotations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if and .Values.prometheus.enabled (not .Values.prometheus.servicemonitor.enabled) }} + {{- if not .Values.podAnnotations }} + annotations: + {{- end }} + prometheus.io/path: "/metrics" + prometheus.io/scrape: 'true' + prometheus.io/port: '9402' + {{- end }} + spec: + serviceAccountName: {{ template "cert-manager.serviceAccountName" . }} + {{- with .Values.global.priorityClassName }} + priorityClassName: {{ . | quote }} + {{- end }} + {{- $enabledDefined := gt (len (keys (pick .Values.securityContext "enabled"))) 0 }} + {{- $legacyEnabledExplicitlyOff := and $enabledDefined (not .Values.securityContext.enabled) }} + {{- if and .Values.securityContext (not $legacyEnabledExplicitlyOff) }} + securityContext: + {{- if .Values.securityContext.enabled }} + {{/* support legacy securityContext.enabled and its two parameters */}} + fsGroup: {{ default 1001 .Values.securityContext.fsGroup }} + runAsUser: {{ default 1001 .Values.securityContext.runAsUser }} + {{- else }} + {{/* this is the way forward: support an arbitrary yaml block */}} + {{- toYaml .Values.securityContext | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.volumes }} + volumes: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: {{ .Chart.Name }} + {{- with .Values.image }} + image: "{{- if .registry -}}{{ .registry }}/{{- end -}}{{ .repository }}{{- if (.digest) -}} @{{ .digest }}{{- else -}}:{{ default $.Chart.AppVersion .tag }} {{- end -}}" + {{- end }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + {{- if .Values.global.logLevel }} + - --v={{ .Values.global.logLevel }} + {{- end }} + {{- if .Values.clusterResourceNamespace }} + - --cluster-resource-namespace={{ .Values.clusterResourceNamespace }} + {{- else }} + - --cluster-resource-namespace=$(POD_NAMESPACE) + {{- end }} + {{- with .Values.global.leaderElection }} + - --leader-election-namespace={{ .namespace }} + {{- if .leaseDuration }} + - --leader-election-lease-duration={{ .leaseDuration }} + {{- end }} + {{- if .renewDeadline }} + - --leader-election-renew-deadline={{ .renewDeadline }} + {{- end }} + {{- if .retryPeriod }} + - --leader-election-retry-period={{ .retryPeriod }} + {{- end }} + {{- end }} + {{- with .Values.extraArgs }} + {{- toYaml . | nindent 10 }} + {{- end }} + {{- with .Values.ingressShim }} + {{- if .defaultIssuerName }} + - --default-issuer-name={{ .defaultIssuerName }} + {{- end }} + {{- if .defaultIssuerKind }} + - --default-issuer-kind={{ .defaultIssuerKind }} + {{- end }} + {{- if .defaultIssuerGroup }} + - --default-issuer-group={{ .defaultIssuerGroup }} + {{- end }} + {{- end }} + {{- if .Values.featureGates }} + - --feature-gates={{ .Values.featureGates }} + {{- end }} + ports: + - containerPort: 9402 + name: http-metrics + protocol: TCP + {{- with .Values.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.volumeMounts }} + volumeMounts: + {{- toYaml . | nindent 12 }} + {{- end }} + env: + - name: POD_NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + {{- with .Values.extraEnv }} + {{- toYaml . | nindent 10 }} + {{- end }} + {{- with .Values.http_proxy }} + - name: HTTP_PROXY + value: {{ . }} + {{- end }} + {{- with .Values.https_proxy }} + - name: HTTPS_PROXY + value: {{ . }} + {{- end }} + {{- with .Values.no_proxy }} + - name: NO_PROXY + value: {{ . }} + {{- end }} + {{- with .Values.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.podDnsPolicy }} + dnsPolicy: {{ . }} + {{- end }} + {{- with .Values.podDnsConfig }} + dnsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/psp-clusterrole.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/psp-clusterrole.yaml new file mode 100644 index 0000000..1d40a02 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/psp-clusterrole.yaml @@ -0,0 +1,18 @@ +{{- if .Values.global.podSecurityPolicy.enabled }} +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ template "cert-manager.fullname" . }}-psp + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +rules: +- apiGroups: ['policy'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ template "cert-manager.fullname" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/psp-clusterrolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/psp-clusterrolebinding.yaml new file mode 100644 index 0000000..1da89c8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/psp-clusterrolebinding.yaml @@ -0,0 +1,20 @@ +{{- if .Values.global.podSecurityPolicy.enabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "cert-manager.fullname" . }}-psp + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "cert-manager.fullname" . }}-psp +subjects: + - kind: ServiceAccount + name: {{ template "cert-manager.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/psp.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/psp.yaml new file mode 100644 index 0000000..9e99f5c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/psp.yaml @@ -0,0 +1,49 @@ +{{- if .Values.global.podSecurityPolicy.enabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "cert-manager.fullname" . }} + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} + annotations: + seccomp.security.alpha.kubernetes.io/allowedProfileNames: 'docker/default' + seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default' + {{- if .Values.global.podSecurityPolicy.useAppArmor }} + apparmor.security.beta.kubernetes.io/allowedProfileNames: 'runtime/default' + apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default' + {{- end }} +spec: + privileged: false + allowPrivilegeEscalation: false + allowedCapabilities: [] # default set of capabilities are implicitly allowed + volumes: + - 'configMap' + - 'emptyDir' + - 'projected' + - 'secret' + - 'downwardAPI' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + rule: 'MustRunAs' + ranges: + - min: 1000 + max: 1000 + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + - min: 1000 + max: 1000 + fsGroup: + rule: 'MustRunAs' + ranges: + - min: 1000 + max: 1000 +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/rbac.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/rbac.yaml new file mode 100644 index 0000000..f8ead0c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/rbac.yaml @@ -0,0 +1,545 @@ +{{- if .Values.global.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ template "cert-manager.fullname" . }}:leaderelection + namespace: {{ .Values.global.leaderElection.namespace }} + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +rules: + - apiGroups: ["coordination.k8s.io"] + resources: ["leases"] + resourceNames: ["cert-manager-controller"] + verbs: ["get", "update", "patch"] + - apiGroups: ["coordination.k8s.io"] + resources: ["leases"] + verbs: ["create"] + +--- + +# grant cert-manager permission to manage the leaderelection configmap in the +# leader election namespace +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "cert-manager.fullname" . }}:leaderelection + namespace: {{ .Values.global.leaderElection.namespace }} + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ template "cert-manager.fullname" . }}:leaderelection +subjects: + - apiGroup: "" + kind: ServiceAccount + name: {{ template "cert-manager.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} + +--- + +# Issuer controller role +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-issuers + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +rules: + - apiGroups: ["cert-manager.io"] + resources: ["issuers", "issuers/status"] + verbs: ["update", "patch"] + - apiGroups: ["cert-manager.io"] + resources: ["issuers"] + verbs: ["get", "list", "watch"] + - apiGroups: [""] + resources: ["secrets"] + verbs: ["get", "list", "watch", "create", "update", "delete"] + - apiGroups: [""] + resources: ["events"] + verbs: ["create", "patch"] + +--- + +# ClusterIssuer controller role +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-clusterissuers + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +rules: + - apiGroups: ["cert-manager.io"] + resources: ["clusterissuers", "clusterissuers/status"] + verbs: ["update", "patch"] + - apiGroups: ["cert-manager.io"] + resources: ["clusterissuers"] + verbs: ["get", "list", "watch"] + - apiGroups: [""] + resources: ["secrets"] + verbs: ["get", "list", "watch", "create", "update", "delete"] + - apiGroups: [""] + resources: ["events"] + verbs: ["create", "patch"] + +--- + +# Certificates controller role +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-certificates + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +rules: + - apiGroups: ["cert-manager.io"] + resources: ["certificates", "certificates/status", "certificaterequests", "certificaterequests/status"] + verbs: ["update", "patch"] + - apiGroups: ["cert-manager.io"] + resources: ["certificates", "certificaterequests", "clusterissuers", "issuers"] + verbs: ["get", "list", "watch"] + # We require these rules to support users with the OwnerReferencesPermissionEnforcement + # admission controller enabled: + # https://kubernetes.io/docs/reference/access-authn-authz/admission-controllers/#ownerreferencespermissionenforcement + - apiGroups: ["cert-manager.io"] + resources: ["certificates/finalizers", "certificaterequests/finalizers"] + verbs: ["update"] + - apiGroups: ["acme.cert-manager.io"] + resources: ["orders"] + verbs: ["create", "delete", "get", "list", "watch"] + - apiGroups: [""] + resources: ["secrets"] + verbs: ["get", "list", "watch", "create", "update", "delete", "patch"] + - apiGroups: [""] + resources: ["events"] + verbs: ["create", "patch"] + +--- + +# Orders controller role +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-orders + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +rules: + - apiGroups: ["acme.cert-manager.io"] + resources: ["orders", "orders/status"] + verbs: ["update", "patch"] + - apiGroups: ["acme.cert-manager.io"] + resources: ["orders", "challenges"] + verbs: ["get", "list", "watch"] + - apiGroups: ["cert-manager.io"] + resources: ["clusterissuers", "issuers"] + verbs: ["get", "list", "watch"] + - apiGroups: ["acme.cert-manager.io"] + resources: ["challenges"] + verbs: ["create", "delete"] + # We require these rules to support users with the OwnerReferencesPermissionEnforcement + # admission controller enabled: + # https://kubernetes.io/docs/reference/access-authn-authz/admission-controllers/#ownerreferencespermissionenforcement + - apiGroups: ["acme.cert-manager.io"] + resources: ["orders/finalizers"] + verbs: ["update"] + - apiGroups: [""] + resources: ["secrets"] + verbs: ["get", "list", "watch"] + - apiGroups: [""] + resources: ["events"] + verbs: ["create", "patch"] + +--- + +# Challenges controller role +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-challenges + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +rules: + # Use to update challenge resource status + - apiGroups: ["acme.cert-manager.io"] + resources: ["challenges", "challenges/status"] + verbs: ["update", "patch"] + # Used to watch challenge resources + - apiGroups: ["acme.cert-manager.io"] + resources: ["challenges"] + verbs: ["get", "list", "watch"] + # Used to watch challenges, issuer and clusterissuer resources + - apiGroups: ["cert-manager.io"] + resources: ["issuers", "clusterissuers"] + verbs: ["get", "list", "watch"] + # Need to be able to retrieve ACME account private key to complete challenges + - apiGroups: [""] + resources: ["secrets"] + verbs: ["get", "list", "watch"] + # Used to create events + - apiGroups: [""] + resources: ["events"] + verbs: ["create", "patch"] + # HTTP01 rules + - apiGroups: [""] + resources: ["pods", "services"] + verbs: ["get", "list", "watch", "create", "delete"] + - apiGroups: ["networking.k8s.io"] + resources: ["ingresses"] + verbs: ["get", "list", "watch", "create", "delete", "update"] + - apiGroups: [ "gateway.networking.k8s.io" ] + resources: [ "httproutes" ] + verbs: ["get", "list", "watch", "create", "delete", "update"] + # We require the ability to specify a custom hostname when we are creating + # new ingress resources. + # See: https://github.com/openshift/origin/blob/21f191775636f9acadb44fa42beeb4f75b255532/pkg/route/apiserver/admission/ingress_admission.go#L84-L148 + - apiGroups: ["route.openshift.io"] + resources: ["routes/custom-host"] + verbs: ["create"] + # We require these rules to support users with the OwnerReferencesPermissionEnforcement + # admission controller enabled: + # https://kubernetes.io/docs/reference/access-authn-authz/admission-controllers/#ownerreferencespermissionenforcement + - apiGroups: ["acme.cert-manager.io"] + resources: ["challenges/finalizers"] + verbs: ["update"] + # DNS01 rules (duplicated above) + - apiGroups: [""] + resources: ["secrets"] + verbs: ["get", "list", "watch"] + +--- + +# ingress-shim controller role +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-ingress-shim + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +rules: + - apiGroups: ["cert-manager.io"] + resources: ["certificates", "certificaterequests"] + verbs: ["create", "update", "delete"] + - apiGroups: ["cert-manager.io"] + resources: ["certificates", "certificaterequests", "issuers", "clusterissuers"] + verbs: ["get", "list", "watch"] + - apiGroups: ["networking.k8s.io"] + resources: ["ingresses"] + verbs: ["get", "list", "watch"] + # We require these rules to support users with the OwnerReferencesPermissionEnforcement + # admission controller enabled: + # https://kubernetes.io/docs/reference/access-authn-authz/admission-controllers/#ownerreferencespermissionenforcement + - apiGroups: ["networking.k8s.io"] + resources: ["ingresses/finalizers"] + verbs: ["update"] + - apiGroups: ["gateway.networking.k8s.io"] + resources: ["gateways", "httproutes"] + verbs: ["get", "list", "watch"] + - apiGroups: ["gateway.networking.k8s.io"] + resources: ["gateways/finalizers", "httproutes/finalizers"] + verbs: ["update"] + - apiGroups: [""] + resources: ["events"] + verbs: ["create", "patch"] + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-issuers + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "cert-manager.fullname" . }}-controller-issuers +subjects: + - name: {{ template "cert-manager.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + kind: ServiceAccount + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-clusterissuers + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "cert-manager.fullname" . }}-controller-clusterissuers +subjects: + - name: {{ template "cert-manager.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + kind: ServiceAccount + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-certificates + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "cert-manager.fullname" . }}-controller-certificates +subjects: + - name: {{ template "cert-manager.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + kind: ServiceAccount + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-orders + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "cert-manager.fullname" . }}-controller-orders +subjects: + - name: {{ template "cert-manager.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + kind: ServiceAccount + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-challenges + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "cert-manager.fullname" . }}-controller-challenges +subjects: + - name: {{ template "cert-manager.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + kind: ServiceAccount + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-ingress-shim + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "cert-manager.fullname" . }}-controller-ingress-shim +subjects: + - name: {{ template "cert-manager.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + kind: ServiceAccount + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "cert-manager.fullname" . }}-view + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} + {{- if .Values.global.rbac.aggregateClusterRoles }} + rbac.authorization.k8s.io/aggregate-to-view: "true" + rbac.authorization.k8s.io/aggregate-to-edit: "true" + rbac.authorization.k8s.io/aggregate-to-admin: "true" + {{- end }} +rules: + - apiGroups: ["cert-manager.io"] + resources: ["certificates", "certificaterequests", "issuers"] + verbs: ["get", "list", "watch"] + - apiGroups: ["acme.cert-manager.io"] + resources: ["challenges", "orders"] + verbs: ["get", "list", "watch"] + + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "cert-manager.fullname" . }}-edit + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} + {{- if .Values.global.rbac.aggregateClusterRoles }} + rbac.authorization.k8s.io/aggregate-to-edit: "true" + rbac.authorization.k8s.io/aggregate-to-admin: "true" + {{- end }} +rules: + - apiGroups: ["cert-manager.io"] + resources: ["certificates", "certificaterequests", "issuers"] + verbs: ["create", "delete", "deletecollection", "patch", "update"] + - apiGroups: ["cert-manager.io"] + resources: ["certificates/status"] + verbs: ["update"] + - apiGroups: ["acme.cert-manager.io"] + resources: ["challenges", "orders"] + verbs: ["create", "delete", "deletecollection", "patch", "update"] + +--- + +# Permission to approve CertificateRequests referencing cert-manager.io Issuers and ClusterIssuers +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-approve:cert-manager-io + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cert-manager" + {{- include "labels" . | nindent 4 }} +rules: + - apiGroups: ["cert-manager.io"] + resources: ["signers"] + verbs: ["approve"] + resourceNames: ["issuers.cert-manager.io/*", "clusterissuers.cert-manager.io/*"] + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-approve:cert-manager-io + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cert-manager" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "cert-manager.fullname" . }}-controller-approve:cert-manager-io +subjects: + - name: {{ template "cert-manager.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + kind: ServiceAccount + +--- + +# Permission to: +# - Update and sign CertificatSigningeRequests referencing cert-manager.io Issuers and ClusterIssuers +# - Perform SubjectAccessReviews to test whether users are able to reference Namespaced Issuers +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-certificatesigningrequests + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cert-manager" + {{- include "labels" . | nindent 4 }} +rules: + - apiGroups: ["certificates.k8s.io"] + resources: ["certificatesigningrequests"] + verbs: ["get", "list", "watch", "update"] + - apiGroups: ["certificates.k8s.io"] + resources: ["certificatesigningrequests/status"] + verbs: ["update", "patch"] + - apiGroups: ["certificates.k8s.io"] + resources: ["signers"] + resourceNames: ["issuers.cert-manager.io/*", "clusterissuers.cert-manager.io/*"] + verbs: ["sign"] + - apiGroups: ["authorization.k8s.io"] + resources: ["subjectaccessreviews"] + verbs: ["create"] + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "cert-manager.fullname" . }}-controller-certificatesigningrequests + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "cert-manager" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "cert-manager.fullname" . }}-controller-certificatesigningrequests +subjects: + - name: {{ template "cert-manager.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + kind: ServiceAccount +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/service.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/service.yaml new file mode 100644 index 0000000..8ad24ca --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/service.yaml @@ -0,0 +1,31 @@ +{{- if .Values.prometheus.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "cert-manager.fullname" . }} + namespace: {{ .Release.Namespace | quote }} +{{- with .Values.serviceAnnotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} + {{- with .Values.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + ports: + - protocol: TCP + port: 9402 + name: tcp-prometheus-servicemonitor + targetPort: {{ .Values.prometheus.servicemonitor.targetPort }} + selector: + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/serviceaccount.yaml new file mode 100644 index 0000000..6e53f78 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/serviceaccount.yaml @@ -0,0 +1,25 @@ +{{- if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +{{- with .Values.global.imagePullSecrets }} +imagePullSecrets: + {{- toYaml . | nindent 2 }} +{{- end }} +automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }} +metadata: + name: {{ template "cert-manager.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + {{- with .Values.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} + {{- with .Values.serviceAccount.labels }} + {{ toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/servicemonitor.yaml new file mode 100644 index 0000000..f962c6b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/servicemonitor.yaml @@ -0,0 +1,39 @@ +{{- if and .Values.prometheus.enabled .Values.prometheus.servicemonitor.enabled (.Capabilities.APIVersions.Has "monitoring.coreos.com/v1") }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "cert-manager.fullname" . }} +{{- if .Values.prometheus.servicemonitor.namespace }} + namespace: {{ .Values.prometheus.servicemonitor.namespace }} +{{- else }} + namespace: {{ .Release.Namespace | quote }} +{{- end }} + labels: + app: {{ include "cert-manager.name" . }} + app.kubernetes.io/name: {{ include "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" + {{- include "labels" . | nindent 4 }} + prometheus: {{ .Values.prometheus.servicemonitor.prometheusInstance }} + {{- with .Values.prometheus.servicemonitor.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + jobLabel: {{ template "cert-manager.fullname" . }} + selector: + matchLabels: + app.kubernetes.io/name: {{ template "cert-manager.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "controller" +{{- if .Values.prometheus.servicemonitor.namespace }} + namespaceSelector: + matchNames: + - {{ .Release.Namespace }} +{{- end }} + endpoints: + - targetPort: {{ .Values.prometheus.servicemonitor.targetPort }} + path: {{ .Values.prometheus.servicemonitor.path }} + interval: {{ .Values.prometheus.servicemonitor.interval }} + scrapeTimeout: {{ .Values.prometheus.servicemonitor.scrapeTimeout }} + honorLabels: {{ .Values.prometheus.servicemonitor.honorLabels }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-job.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-job.yaml new file mode 100644 index 0000000..66db004 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-job.yaml @@ -0,0 +1,77 @@ +{{- if .Values.startupapicheck.enabled }} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ include "startupapicheck.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ include "startupapicheck.name" . }} + app.kubernetes.io/name: {{ include "startupapicheck.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "startupapicheck" + {{- include "labels" . | nindent 4 }} + {{- with .Values.startupapicheck.jobAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + backoffLimit: {{ .Values.startupapicheck.backoffLimit }} + template: + metadata: + labels: + app: {{ include "startupapicheck.name" . }} + app.kubernetes.io/name: {{ include "startupapicheck.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "startupapicheck" + {{- include "labels" . | nindent 8 }} + {{- with .Values.startupapicheck.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.startupapicheck.podAnnotations }} + annotations: + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + restartPolicy: OnFailure + serviceAccountName: {{ template "startupapicheck.serviceAccountName" . }} + {{- with .Values.global.priorityClassName }} + priorityClassName: {{ . | quote }} + {{- end }} + {{- with .Values.startupapicheck.securityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: {{ .Chart.Name }} + {{- with .Values.startupapicheck.image }} + image: "{{- if .registry -}}{{ .registry }}/{{- end -}}{{ .repository }}{{- if (.digest) -}} @{{ .digest }}{{- else -}}:{{ default $.Chart.AppVersion .tag }} {{- end -}}" + {{- end }} + imagePullPolicy: {{ .Values.startupapicheck.image.pullPolicy }} + args: + - check + - api + - --wait={{ .Values.startupapicheck.timeout }} + {{- with .Values.startupapicheck.extraArgs }} + {{- toYaml . | nindent 10 }} + {{- end }} + {{- with .Values.startupapicheck.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.startupapicheck.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.startupapicheck.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.startupapicheck.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.startupapicheck.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-psp-clusterrole.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-psp-clusterrole.yaml new file mode 100644 index 0000000..dacd4be --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-psp-clusterrole.yaml @@ -0,0 +1,24 @@ +{{- if .Values.startupapicheck.enabled }} +{{- if .Values.global.podSecurityPolicy.enabled }} +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ template "startupapicheck.fullname" . }}-psp + labels: + app: {{ include "startupapicheck.name" . }} + app.kubernetes.io/name: {{ include "startupapicheck.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "startupapicheck" + {{- include "labels" . | nindent 4 }} + {{- with .Values.startupapicheck.rbac.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +rules: +- apiGroups: ['policy'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ template "startupapicheck.fullname" . }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-psp-clusterrolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-psp-clusterrolebinding.yaml new file mode 100644 index 0000000..d19fa84 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-psp-clusterrolebinding.yaml @@ -0,0 +1,26 @@ +{{- if .Values.startupapicheck.enabled }} +{{- if .Values.global.podSecurityPolicy.enabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "startupapicheck.fullname" . }}-psp + labels: + app: {{ include "startupapicheck.name" . }} + app.kubernetes.io/name: {{ include "startupapicheck.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "startupapicheck" + {{- include "labels" . | nindent 4 }} + {{- with .Values.startupapicheck.rbac.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "startupapicheck.fullname" . }}-psp +subjects: + - kind: ServiceAccount + name: {{ template "startupapicheck.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-psp.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-psp.yaml new file mode 100644 index 0000000..f09d60d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-psp.yaml @@ -0,0 +1,51 @@ +{{- if .Values.startupapicheck.enabled }} +{{- if .Values.global.podSecurityPolicy.enabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "startupapicheck.fullname" . }} + labels: + app: {{ include "startupapicheck.name" . }} + app.kubernetes.io/name: {{ include "startupapicheck.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "startupapicheck" + {{- include "labels" . | nindent 4 }} + annotations: + seccomp.security.alpha.kubernetes.io/allowedProfileNames: 'docker/default' + seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default' + {{- if .Values.global.podSecurityPolicy.useAppArmor }} + apparmor.security.beta.kubernetes.io/allowedProfileNames: 'runtime/default' + apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default' + {{- end }} + {{- with .Values.startupapicheck.rbac.annotations }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + privileged: false + allowPrivilegeEscalation: false + allowedCapabilities: [] # default set of capabilities are implicitly allowed + volumes: + - 'projected' + - 'secret' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + rule: 'MustRunAs' + ranges: + - min: 1000 + max: 1000 + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + - min: 1000 + max: 1000 + fsGroup: + rule: 'MustRunAs' + ranges: + - min: 1000 + max: 1000 +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-rbac.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-rbac.yaml new file mode 100644 index 0000000..a6be7b9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-rbac.yaml @@ -0,0 +1,48 @@ +{{- if .Values.startupapicheck.enabled }} +{{- if .Values.global.rbac.create }} +# create certificate role +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ template "startupapicheck.fullname" . }}:create-cert + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ include "startupapicheck.name" . }} + app.kubernetes.io/name: {{ include "startupapicheck.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "startupapicheck" + {{- include "labels" . | nindent 4 }} + {{- with .Values.startupapicheck.rbac.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +rules: + - apiGroups: ["cert-manager.io"] + resources: ["certificates"] + verbs: ["create"] +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "startupapicheck.fullname" . }}:create-cert + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ include "startupapicheck.name" . }} + app.kubernetes.io/name: {{ include "startupapicheck.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "startupapicheck" + {{- include "labels" . | nindent 4 }} + {{- with .Values.startupapicheck.rbac.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ template "startupapicheck.fullname" . }}:create-cert +subjects: + - kind: ServiceAccount + name: {{ template "startupapicheck.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-serviceaccount.yaml new file mode 100644 index 0000000..46262d5 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/startupapicheck-serviceaccount.yaml @@ -0,0 +1,27 @@ +{{- if .Values.startupapicheck.enabled }} +{{- if .Values.startupapicheck.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +automountServiceAccountToken: {{ .Values.startupapicheck.serviceAccount.automountServiceAccountToken }} +metadata: + name: {{ template "startupapicheck.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + {{- with .Values.startupapicheck.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + app: {{ include "startupapicheck.name" . }} + app.kubernetes.io/name: {{ include "startupapicheck.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "startupapicheck" + {{- include "labels" . | nindent 4 }} + {{- with .Values.startupapicheck.serviceAccount.labels }} + {{ toYaml . | nindent 4 }} + {{- end }} +{{- with .Values.global.imagePullSecrets }} +imagePullSecrets: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-config.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-config.yaml new file mode 100644 index 0000000..29558e9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-config.yaml @@ -0,0 +1,24 @@ +{{- if .Values.webhook.config -}} + {{- if not .Values.webhook.config.apiVersion -}} + {{- fail "webhook.config.apiVersion must be set" -}} + {{- end -}} + + {{- if not .Values.webhook.config.kind -}} + {{- fail "webhook.config.kind must be set" -}} + {{- end -}} +{{- end -}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "webhook.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" +data: + {{- if .Values.webhook.config }} + config.yaml: | + {{ .Values.webhook.config | toYaml | nindent 4 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-deployment.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-deployment.yaml new file mode 100644 index 0000000..0de1df2 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-deployment.yaml @@ -0,0 +1,153 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "webhook.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 4 }} + {{- with .Values.webhook.deploymentAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.webhook.replicaCount }} + selector: + matchLabels: + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- with .Values.webhook.strategy }} + strategy: + {{- toYaml . | nindent 4 }} + {{- end }} + template: + metadata: + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 8 }} + {{- with .Values.webhook.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.webhook.podAnnotations }} + annotations: + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + serviceAccountName: {{ template "webhook.serviceAccountName" . }} + {{- with .Values.global.priorityClassName }} + priorityClassName: {{ . | quote }} + {{- end }} + {{- with .Values.webhook.securityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.webhook.hostNetwork }} + hostNetwork: true + {{- end }} + containers: + - name: {{ .Chart.Name }} + {{- with .Values.webhook.image }} + image: "{{- if .registry -}}{{ .registry }}/{{- end -}}{{ .repository }}{{- if (.digest) -}} @{{ .digest }}{{- else -}}:{{ default $.Chart.AppVersion .tag }} {{- end -}}" + {{- end }} + imagePullPolicy: {{ .Values.webhook.image.pullPolicy }} + args: + {{- if .Values.global.logLevel }} + - --v={{ .Values.global.logLevel }} + {{- end }} + {{- if .Values.webhook.config }} + - --config=/var/cert-manager/config/config.yaml + {{- end }} + {{- $config := default .Values.webhook.config "" }} + {{ if not $config.securePort -}} + - --secure-port={{ .Values.webhook.securePort }} + {{- end }} + {{- $tlsConfig := default $config.tlsConfig "" }} + {{ if or (not $config.tlsConfig) (and (not $tlsConfig.dynamic) (not $tlsConfig.filesystem) ) -}} + - --dynamic-serving-ca-secret-namespace=$(POD_NAMESPACE) + - --dynamic-serving-ca-secret-name={{ template "webhook.fullname" . }}-ca + - --dynamic-serving-dns-names={{ template "webhook.fullname" . }},{{ template "webhook.fullname" . }}.{{ .Release.Namespace }},{{ template "webhook.fullname" . }}.{{ .Release.Namespace }}.svc{{ if .Values.webhook.url.host }},{{ .Values.webhook.url.host }}{{ end }} + {{- end }} + {{- with .Values.webhook.extraArgs }} + {{- toYaml . | nindent 10 }} + {{- end }} + ports: + - name: https + protocol: TCP + {{- if $config.securePort }} + containerPort: {{ $config.securePort }} + {{- else if .Values.webhook.securePort }} + containerPort: {{ .Values.webhook.securePort }} + {{- else }} + containerPort: 6443 + {{- end }} + livenessProbe: + httpGet: + path: /livez + {{- if $config.healthzPort }} + port: {{ $config.healthzPort }} + {{- else }} + port: 6080 + {{- end }} + scheme: HTTP + initialDelaySeconds: {{ .Values.webhook.livenessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.webhook.livenessProbe.periodSeconds }} + timeoutSeconds: {{ .Values.webhook.livenessProbe.timeoutSeconds }} + successThreshold: {{ .Values.webhook.livenessProbe.successThreshold }} + failureThreshold: {{ .Values.webhook.livenessProbe.failureThreshold }} + readinessProbe: + httpGet: + path: /healthz + {{- if $config.healthzPort }} + port: {{ $config.healthzPort }} + {{- else }} + port: 6080 + {{- end }} + scheme: HTTP + initialDelaySeconds: {{ .Values.webhook.readinessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.webhook.readinessProbe.periodSeconds }} + timeoutSeconds: {{ .Values.webhook.readinessProbe.timeoutSeconds }} + successThreshold: {{ .Values.webhook.readinessProbe.successThreshold }} + failureThreshold: {{ .Values.webhook.readinessProbe.failureThreshold }} + {{- with .Values.webhook.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + env: + - name: POD_NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + {{- with .Values.webhook.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.webhook.config }} + volumeMounts: + - name: config + mountPath: /var/cert-manager/config + {{- end }} + {{- with .Values.webhook.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.webhook.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.webhook.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.webhook.config }} + volumes: + - name: config + configMap: + name: {{ include "webhook.fullname" . }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-mutating-webhook.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-mutating-webhook.yaml new file mode 100644 index 0000000..fb8b795 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-mutating-webhook.yaml @@ -0,0 +1,46 @@ +apiVersion: admissionregistration.k8s.io/v1 +kind: MutatingWebhookConfiguration +metadata: + name: {{ include "webhook.fullname" . }} + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 4 }} + annotations: + cert-manager.io/inject-ca-from-secret: "{{ .Release.Namespace }}/{{ template "webhook.fullname" . }}-ca" + {{- with .Values.webhook.mutatingWebhookConfigurationAnnotations }} + {{- toYaml . | nindent 4 }} + {{- end }} +webhooks: + - name: webhook.cert-manager.io + rules: + - apiGroups: + - "cert-manager.io" + - "acme.cert-manager.io" + apiVersions: + - "v1" + operations: + - CREATE + - UPDATE + resources: + - "*/*" + admissionReviewVersions: ["v1"] + # This webhook only accepts v1 cert-manager resources. + # Equivalent matchPolicy ensures that non-v1 resource requests are sent to + # this webhook (after the resources have been converted to v1). + matchPolicy: Equivalent + timeoutSeconds: {{ .Values.webhook.timeoutSeconds }} + failurePolicy: Fail + # Only include 'sideEffects' field in Kubernetes 1.12+ + sideEffects: None + clientConfig: + {{- if .Values.webhook.url.host }} + url: https://{{ .Values.webhook.url.host }}/mutate + {{- else }} + service: + name: {{ template "webhook.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + path: /mutate + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-psp-clusterrole.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-psp-clusterrole.yaml new file mode 100644 index 0000000..2a8808e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-psp-clusterrole.yaml @@ -0,0 +1,18 @@ +{{- if .Values.global.podSecurityPolicy.enabled }} +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ template "webhook.fullname" . }}-psp + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 4 }} +rules: +- apiGroups: ['policy'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ template "webhook.fullname" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-psp-clusterrolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-psp-clusterrolebinding.yaml new file mode 100644 index 0000000..e8e1bb2 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-psp-clusterrolebinding.yaml @@ -0,0 +1,20 @@ +{{- if .Values.global.podSecurityPolicy.enabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "webhook.fullname" . }}-psp + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "webhook.fullname" . }}-psp +subjects: + - kind: ServiceAccount + name: {{ template "webhook.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-psp.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-psp.yaml new file mode 100644 index 0000000..4d5d959 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-psp.yaml @@ -0,0 +1,54 @@ +{{- if .Values.global.podSecurityPolicy.enabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "webhook.fullname" . }} + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 4 }} + annotations: + seccomp.security.alpha.kubernetes.io/allowedProfileNames: 'docker/default' + seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default' + {{- if .Values.global.podSecurityPolicy.useAppArmor }} + apparmor.security.beta.kubernetes.io/allowedProfileNames: 'runtime/default' + apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default' + {{- end }} +spec: + privileged: false + allowPrivilegeEscalation: false + allowedCapabilities: [] # default set of capabilities are implicitly allowed + volumes: + - 'configMap' + - 'emptyDir' + - 'projected' + - 'secret' + - 'downwardAPI' + hostNetwork: {{ .Values.webhook.hostNetwork }} + {{- if .Values.webhook.hostNetwork }} + hostPorts: + - max: {{ .Values.webhook.securePort }} + min: {{ .Values.webhook.securePort }} + {{- end }} + hostIPC: false + hostPID: false + runAsUser: + rule: 'MustRunAs' + ranges: + - min: 1000 + max: 1000 + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + - min: 1000 + max: 1000 + fsGroup: + rule: 'MustRunAs' + ranges: + - min: 1000 + max: 1000 +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-rbac.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-rbac.yaml new file mode 100644 index 0000000..1070333 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-rbac.yaml @@ -0,0 +1,83 @@ +{{- if .Values.global.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ template "webhook.fullname" . }}:dynamic-serving + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 4 }} +rules: +- apiGroups: [""] + resources: ["secrets"] + resourceNames: + - '{{ template "webhook.fullname" . }}-ca' + verbs: ["get", "list", "watch", "update"] +# It's not possible to grant CREATE permission on a single resourceName. +- apiGroups: [""] + resources: ["secrets"] + verbs: ["create"] +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ template "webhook.fullname" . }}:dynamic-serving + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ template "webhook.fullname" . }}:dynamic-serving +subjects: +- apiGroup: "" + kind: ServiceAccount + name: {{ template "webhook.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ template "webhook.fullname" . }}:subjectaccessreviews + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 4 }} +rules: +- apiGroups: ["authorization.k8s.io"] + resources: ["subjectaccessreviews"] + verbs: ["create"] +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ template "webhook.fullname" . }}:subjectaccessreviews + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ template "webhook.fullname" . }}:subjectaccessreviews +subjects: +- apiGroup: "" + kind: ServiceAccount + name: {{ template "webhook.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-service.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-service.yaml new file mode 100644 index 0000000..ed0278a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-service.yaml @@ -0,0 +1,32 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ template "webhook.fullname" . }} + namespace: {{ .Release.Namespace | quote }} +{{- with .Values.webhook.serviceAnnotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 4 }} + {{- with .Values.webhook.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.webhook.serviceType }} + {{- with .Values.webhook.loadBalancerIP }} + loadBalancerIP: {{ . }} + {{- end }} + ports: + - name: https + port: 443 + protocol: TCP + targetPort: "https" + selector: + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-serviceaccount.yaml new file mode 100644 index 0000000..2792a43 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-serviceaccount.yaml @@ -0,0 +1,25 @@ +{{- if .Values.webhook.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +automountServiceAccountToken: {{ .Values.webhook.serviceAccount.automountServiceAccountToken }} +metadata: + name: {{ template "webhook.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + {{- with .Values.webhook.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 4 }} + {{- with .Values.webhook.serviceAccount.labels }} + {{ toYaml . | nindent 4 }} + {{- end }} +{{- with .Values.global.imagePullSecrets }} +imagePullSecrets: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-validating-webhook.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-validating-webhook.yaml new file mode 100644 index 0000000..2ca6403 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/templates/webhook-validating-webhook.yaml @@ -0,0 +1,55 @@ +apiVersion: admissionregistration.k8s.io/v1 +kind: ValidatingWebhookConfiguration +metadata: + name: {{ include "webhook.fullname" . }} + labels: + app: {{ include "webhook.name" . }} + app.kubernetes.io/name: {{ include "webhook.name" . }} + app.kubernetes.io/instance: {{ .Release.Name }} + app.kubernetes.io/component: "webhook" + {{- include "labels" . | nindent 4 }} + annotations: + cert-manager.io/inject-ca-from-secret: "{{ .Release.Namespace }}/{{ template "webhook.fullname" . }}-ca" + {{- with .Values.webhook.validatingWebhookConfigurationAnnotations }} + {{- toYaml . | nindent 4 }} + {{- end }} +webhooks: + - name: webhook.cert-manager.io + namespaceSelector: + matchExpressions: + - key: "cert-manager.io/disable-validation" + operator: "NotIn" + values: + - "true" + - key: "name" + operator: "NotIn" + values: + - {{ .Release.Namespace }} + rules: + - apiGroups: + - "cert-manager.io" + - "acme.cert-manager.io" + apiVersions: + - "v1" + operations: + - CREATE + - UPDATE + resources: + - "*/*" + admissionReviewVersions: ["v1"] + # This webhook only accepts v1 cert-manager resources. + # Equivalent matchPolicy ensures that non-v1 resource requests are sent to + # this webhook (after the resources have been converted to v1). + matchPolicy: Equivalent + timeoutSeconds: {{ .Values.webhook.timeoutSeconds }} + failurePolicy: Fail + sideEffects: None + clientConfig: + {{- if .Values.webhook.url.host }} + url: https://{{ .Values.webhook.url.host }}/validate + {{- else }} + service: + name: {{ template "webhook.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + path: /validate + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/cert-manager/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/values.yaml new file mode 100644 index 0000000..3a21b15 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/cert-manager/values.yaml @@ -0,0 +1,543 @@ +# Default values for cert-manager. +# This is a YAML-formatted file. +# Declare variables to be passed into your templates. +global: + ## Reference to one or more secrets to be used when pulling images + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## + imagePullSecrets: [] + # - name: "image-pull-secret" + + # Optional priority class to be used for the cert-manager pods + priorityClassName: "" + rbac: + create: true + # Aggregate ClusterRoles to Kubernetes default user-facing roles. Ref: https://kubernetes.io/docs/reference/access-authn-authz/rbac/#user-facing-roles + aggregateClusterRoles: true + + podSecurityPolicy: + enabled: false + useAppArmor: true + + # Set the verbosity of cert-manager. Range of 0 - 6 with 6 being the most verbose. + logLevel: 2 + + leaderElection: + # Override the namespace used to store the ConfigMap for leader election + namespace: "kube-system" + + # The duration that non-leader candidates will wait after observing a + # leadership renewal until attempting to acquire leadership of a led but + # unrenewed leader slot. This is effectively the maximum duration that a + # leader can be stopped before it is replaced by another candidate. + # leaseDuration: 60s + + # The interval between attempts by the acting master to renew a leadership + # slot before it stops leading. This must be less than or equal to the + # lease duration. + # renewDeadline: 40s + + # The duration the clients should wait between attempting acquisition and + # renewal of a leadership. + # retryPeriod: 15s + +installCRDs: false + +replicaCount: 1 + +strategy: {} + # type: RollingUpdate + # rollingUpdate: + # maxSurge: 0 + # maxUnavailable: 1 + +# Comma separated list of feature gates that should be enabled on the +# controller pod. +featureGates: "" + +image: + repository: quay.io/jetstack/cert-manager-controller + # You can manage a registry with + # registry: quay.io + # repository: jetstack/cert-manager-controller + + # Override the image tag to deploy by setting this variable. + # If no value is set, the chart's appVersion will be used. + # tag: canary + + # Setting a digest will override any tag + # digest: sha256:0e072dddd1f7f8fc8909a2ca6f65e76c5f0d2fcfb8be47935ae3457e8bbceb20 + pullPolicy: IfNotPresent + +# Override the namespace used to store DNS provider credentials etc. for ClusterIssuer +# resources. By default, the same namespace as cert-manager is deployed within is +# used. This namespace will not be automatically created by the Helm chart. +clusterResourceNamespace: "" + +serviceAccount: + # Specifies whether a service account should be created + create: true + # The name of the service account to use. + # If not set and create is true, a name is generated using the fullname template + # name: "" + # Optional additional annotations to add to the controller's ServiceAccount + # annotations: {} + # Automount API credentials for a Service Account. + # Optional additional labels to add to the controller's ServiceAccount + # labels: {} + automountServiceAccountToken: true + +# Additional command line flags to pass to cert-manager controller binary. +# To see all available flags run docker run quay.io/jetstack/cert-manager-controller: --help +extraArgs: [] + # When this flag is enabled, secrets will be automatically removed when the certificate resource is deleted + # - --enable-certificate-owner-ref=true + # Use this flag to enabled or disable arbitrary controllers, for example, disable the CertificiateRequests approver + # - --controllers=*,-certificaterequests-approver + +extraEnv: [] +# - name: SOME_VAR +# value: 'some value' + +resources: {} + # requests: + # cpu: 10m + # memory: 32Mi + +# Pod Security Context +# ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ +securityContext: + runAsNonRoot: true +# legacy securityContext parameter format: if enabled is set to true, only fsGroup and runAsUser are supported +# securityContext: +# enabled: false +# fsGroup: 1001 +# runAsUser: 1001 +# to support additional securityContext parameters, omit the `enabled` parameter and simply specify the parameters +# you want to set, e.g. +# securityContext: +# fsGroup: 1000 +# runAsUser: 1000 +# runAsNonRoot: true + +# Container Security Context to be set on the controller component container +# ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ +containerSecurityContext: + allowPrivilegeEscalation: false + # capabilities: + # drop: + # - ALL + # readOnlyRootFilesystem: true + # runAsNonRoot: true + + +volumes: [] + +volumeMounts: [] + +# Optional additional annotations to add to the controller Deployment +# deploymentAnnotations: {} + +# Optional additional annotations to add to the controller Pods +# podAnnotations: {} + +podLabels: {} + +# Optional annotations to add to the controller Service +# serviceAnnotations: {} + +# Optional additional labels to add to the controller Service +# serviceLabels: {} + +# Optional DNS settings, useful if you have a public and private DNS zone for +# the same domain on Route 53. What follows is an example of ensuring +# cert-manager can access an ingress or DNS TXT records at all times. +# NOTE: This requires Kubernetes 1.10 or `CustomPodDNS` feature gate enabled for +# the cluster to work. +# podDnsPolicy: "None" +# podDnsConfig: +# nameservers: +# - "1.1.1.1" +# - "8.8.8.8" + +nodeSelector: + kubernetes.io/os: linux + +ingressShim: {} + # defaultIssuerName: "" + # defaultIssuerKind: "" + # defaultIssuerGroup: "" + +prometheus: + enabled: true + servicemonitor: + enabled: false + prometheusInstance: default + targetPort: 9402 + path: /metrics + interval: 60s + scrapeTimeout: 30s + labels: {} + honorLabels: false + +# Use these variables to configure the HTTP_PROXY environment variables +# http_proxy: "http://proxy:8080" +# https_proxy: "https://proxy:8080" +# no_proxy: 127.0.0.1,localhost + +# expects input structure as per specification https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.11/#affinity-v1-core +# for example: +# affinity: +# nodeAffinity: +# requiredDuringSchedulingIgnoredDuringExecution: +# nodeSelectorTerms: +# - matchExpressions: +# - key: foo.bar.com/role +# operator: In +# values: +# - master +affinity: {} + +# expects input structure as per specification https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.11/#toleration-v1-core +# for example: +# tolerations: +# - key: foo.bar.com/role +# operator: Equal +# value: master +# effect: NoSchedule +tolerations: [] + +webhook: + replicaCount: 1 + timeoutSeconds: 10 + + # Used to configure options for the webhook pod. + # This allows setting options that'd usually be provided via flags. + # An APIVersion and Kind must be specified in your values.yaml file. + # Flags will override options that are set here. + config: + # apiVersion: webhook.config.cert-manager.io/v1alpha1 + # kind: WebhookConfiguration + + # The port that the webhook should listen on for requests. + # In GKE private clusters, by default kubernetes apiservers are allowed to + # talk to the cluster nodes only on 443 and 10250. so configuring + # securePort: 10250, will work out of the box without needing to add firewall + # rules or requiring NET_BIND_SERVICE capabilities to bind port numbers <1000. + # This should be uncommented and set as a default by the chart once we graduate + # the apiVersion of WebhookConfiguration past v1alpha1. + # securePort: 10250 + + strategy: {} + # type: RollingUpdate + # rollingUpdate: + # maxSurge: 0 + # maxUnavailable: 1 + + # Pod Security Context to be set on the webhook component Pod + # ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ + securityContext: + runAsNonRoot: true + + # Container Security Context to be set on the webhook component container + # ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ + containerSecurityContext: + allowPrivilegeEscalation: false + # capabilities: + # drop: + # - ALL + # readOnlyRootFilesystem: true + # runAsNonRoot: true + + # Optional additional annotations to add to the webhook Deployment + # deploymentAnnotations: {} + + # Optional additional annotations to add to the webhook Pods + # podAnnotations: {} + + # Optional additional annotations to add to the webhook Service + # serviceAnnotations: {} + + # Optional additional annotations to add to the webhook MutatingWebhookConfiguration + # mutatingWebhookConfigurationAnnotations: {} + + # Optional additional annotations to add to the webhook ValidatingWebhookConfiguration + # validatingWebhookConfigurationAnnotations: {} + + # Additional command line flags to pass to cert-manager webhook binary. + # To see all available flags run docker run quay.io/jetstack/cert-manager-webhook: --help + extraArgs: [] + # Path to a file containing a WebhookConfiguration object used to configure the webhook + # - --config= + + resources: {} + # requests: + # cpu: 10m + # memory: 32Mi + + ## Liveness and readiness probe values + ## Ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#container-probes + ## + livenessProbe: + failureThreshold: 3 + initialDelaySeconds: 60 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + readinessProbe: + failureThreshold: 3 + initialDelaySeconds: 5 + periodSeconds: 5 + successThreshold: 1 + timeoutSeconds: 1 + + nodeSelector: + kubernetes.io/os: linux + + affinity: {} + + tolerations: [] + + # Optional additional labels to add to the Webhook Pods + podLabels: {} + + # Optional additional labels to add to the Webhook Service + serviceLabels: {} + + image: + repository: quay.io/jetstack/cert-manager-webhook + # You can manage a registry with + # registry: quay.io + # repository: jetstack/cert-manager-webhook + + # Override the image tag to deploy by setting this variable. + # If no value is set, the chart's appVersion will be used. + # tag: canary + + # Setting a digest will override any tag + # digest: sha256:0e072dddd1f7f8fc8909a2ca6f65e76c5f0d2fcfb8be47935ae3457e8bbceb20 + + pullPolicy: IfNotPresent + + serviceAccount: + # Specifies whether a service account should be created + create: true + # The name of the service account to use. + # If not set and create is true, a name is generated using the fullname template + # name: "" + # Optional additional annotations to add to the controller's ServiceAccount + # annotations: {} + # Optional additional labels to add to the webhook's ServiceAccount + # labels: {} + # Automount API credentials for a Service Account. + automountServiceAccountToken: true + + # The port that the webhook should listen on for requests. + # In GKE private clusters, by default kubernetes apiservers are allowed to + # talk to the cluster nodes only on 443 and 10250. so configuring + # securePort: 10250, will work out of the box without needing to add firewall + # rules or requiring NET_BIND_SERVICE capabilities to bind port numbers <1000 + securePort: 10250 + + # Specifies if the webhook should be started in hostNetwork mode. + # + # Required for use in some managed kubernetes clusters (such as AWS EKS) with custom + # CNI (such as calico), because control-plane managed by AWS cannot communicate + # with pods' IP CIDR and admission webhooks are not working + # + # Since the default port for the webhook conflicts with kubelet on the host + # network, `webhook.securePort` should be changed to an available port if + # running in hostNetwork mode. + hostNetwork: false + + # Specifies how the service should be handled. Useful if you want to expose the + # webhook to outside of the cluster. In some cases, the control plane cannot + # reach internal services. + serviceType: ClusterIP + # loadBalancerIP: + + # Overrides the mutating webhook and validating webhook so they reach the webhook + # service using the `url` field instead of a service. + url: {} + # host: + +cainjector: + enabled: true + replicaCount: 1 + + strategy: {} + # type: RollingUpdate + # rollingUpdate: + # maxSurge: 0 + # maxUnavailable: 1 + + # Pod Security Context to be set on the cainjector component Pod + # ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ + securityContext: + runAsNonRoot: true + + # Container Security Context to be set on the cainjector component container + # ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ + containerSecurityContext: + allowPrivilegeEscalation: false + # capabilities: + # drop: + # - ALL + # readOnlyRootFilesystem: true + # runAsNonRoot: true + + + # Optional additional annotations to add to the cainjector Deployment + # deploymentAnnotations: {} + + # Optional additional annotations to add to the cainjector Pods + # podAnnotations: {} + + # Additional command line flags to pass to cert-manager cainjector binary. + # To see all available flags run docker run quay.io/jetstack/cert-manager-cainjector: --help + extraArgs: [] + # Enable profiling for cainjector + # - --enable-profiling=true + + resources: {} + # requests: + # cpu: 10m + # memory: 32Mi + + nodeSelector: + kubernetes.io/os: linux + + affinity: {} + + tolerations: [] + + # Optional additional labels to add to the CA Injector Pods + podLabels: {} + + image: + repository: quay.io/jetstack/cert-manager-cainjector + # You can manage a registry with + # registry: quay.io + # repository: jetstack/cert-manager-cainjector + + # Override the image tag to deploy by setting this variable. + # If no value is set, the chart's appVersion will be used. + # tag: canary + + # Setting a digest will override any tag + # digest: sha256:0e072dddd1f7f8fc8909a2ca6f65e76c5f0d2fcfb8be47935ae3457e8bbceb20 + + pullPolicy: IfNotPresent + + serviceAccount: + # Specifies whether a service account should be created + create: true + # The name of the service account to use. + # If not set and create is true, a name is generated using the fullname template + # name: "" + # Optional additional annotations to add to the controller's ServiceAccount + # annotations: {} + # Automount API credentials for a Service Account. + # Optional additional labels to add to the cainjector's ServiceAccount + # labels: {} + automountServiceAccountToken: true + +# This startupapicheck is a Helm post-install hook that waits for the webhook +# endpoints to become available. +# The check is implemented using a Kubernetes Job- if you are injecting mesh +# sidecar proxies into cert-manager pods, you probably want to ensure that they +# are not injected into this Job's pod. Otherwise the installation may time out +# due to the Job never being completed because the sidecar proxy does not exit. +# See https://github.com/cert-manager/cert-manager/pull/4414 for context. +startupapicheck: + enabled: true + + # Pod Security Context to be set on the startupapicheck component Pod + # ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ + securityContext: + runAsNonRoot: true + + # Container Security Context to be set on the controller component container + # ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ + containerSecurityContext: + allowPrivilegeEscalation: false + # capabilities: + # drop: + # - ALL + # readOnlyRootFilesystem: true + # runAsNonRoot: true + + # Timeout for 'kubectl check api' command + timeout: 1m + + # Job backoffLimit + backoffLimit: 4 + + # Optional additional annotations to add to the startupapicheck Job + jobAnnotations: + helm.sh/hook: post-install + helm.sh/hook-weight: "1" + helm.sh/hook-delete-policy: before-hook-creation,hook-succeeded + + # Optional additional annotations to add to the startupapicheck Pods + # podAnnotations: {} + + # Additional command line flags to pass to startupapicheck binary. + # To see all available flags run docker run quay.io/jetstack/cert-manager-ctl: --help + extraArgs: [] + + resources: {} + # requests: + # cpu: 10m + # memory: 32Mi + + nodeSelector: {} + + affinity: {} + + tolerations: [] + + # Optional additional labels to add to the startupapicheck Pods + podLabels: {} + + image: + repository: quay.io/jetstack/cert-manager-ctl + # You can manage a registry with + # registry: quay.io + # repository: jetstack/cert-manager-ctl + + # Override the image tag to deploy by setting this variable. + # If no value is set, the chart's appVersion will be used. + # tag: canary + + # Setting a digest will override any tag + # digest: sha256:0e072dddd1f7f8fc8909a2ca6f65e76c5f0d2fcfb8be47935ae3457e8bbceb20 + + pullPolicy: IfNotPresent + + rbac: + # annotations for the startup API Check job RBAC and PSP resources + annotations: + helm.sh/hook: post-install + helm.sh/hook-weight: "-5" + helm.sh/hook-delete-policy: before-hook-creation,hook-succeeded + + serviceAccount: + # Specifies whether a service account should be created + create: true + + # The name of the service account to use. + # If not set and create is true, a name is generated using the fullname template + # name: "" + + # Optional additional annotations to add to the Job's ServiceAccount + annotations: + helm.sh/hook: post-install + helm.sh/hook-weight: "-5" + helm.sh/hook-delete-policy: before-hook-creation,hook-succeeded + + # Automount API credentials for a Service Account. + automountServiceAccountToken: true + + # Optional additional labels to add to the startupapicheck's ServiceAccount + # labels: {} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/grafana/.helmignore new file mode 100644 index 0000000..8cade13 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/.helmignore @@ -0,0 +1,23 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.vscode +.project +.idea/ +*.tmproj +OWNERS diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/Chart.yaml new file mode 100644 index 0000000..e022cdf --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/Chart.yaml @@ -0,0 +1,29 @@ +annotations: + artifacthub.io/links: | + - name: Chart Source + url: https://github.com/grafana/helm-charts + - name: Upstream Project + url: https://github.com/grafana/grafana +apiVersion: v2 +appVersion: 9.5.3 +description: The leading tool for querying and visualizing time series and metrics. +home: https://grafana.net +icon: https://raw.githubusercontent.com/grafana/grafana/master/public/img/logo_transparent_400x.png +kubeVersion: ^1.8.0-0 +maintainers: +- email: zanhsieh@gmail.com + name: zanhsieh +- email: rluckie@cisco.com + name: rtluckie +- email: maor.friedman@redhat.com + name: maorfr +- email: miroslav.hadzhiev@gmail.com + name: Xtigyro +- email: mail@torstenwalter.de + name: torstenwalter +name: grafana +sources: +- https://github.com/grafana/grafana +- https://github.com/grafana/helm-charts +type: application +version: 6.57.1 diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/README.md b/observability/lgtm-distributed/charts/oncall/charts/grafana/README.md new file mode 100644 index 0000000..0da2569 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/README.md @@ -0,0 +1,685 @@ +# Grafana Helm Chart + +* Installs the web dashboarding system [Grafana](http://grafana.org/) + +## Get Repo Info + +```console +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update +``` + +_See [helm repo](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```console +helm install my-release grafana/grafana +``` + +## Uninstalling the Chart + +To uninstall/delete the my-release deployment: + +```console +helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + +## Upgrading an existing Release to a new major version + +A major chart version change (like v1.2.3 -> v2.0.0) indicates that there is an +incompatible breaking change needing manual actions. + +### To 4.0.0 (And 3.12.1) + +This version requires Helm >= 2.12.0. + +### To 5.0.0 + +You have to add --force to your helm upgrade command as the labels of the chart have changed. + +### To 6.0.0 + +This version requires Helm >= 3.1.0. + +## Configuration + +| Parameter | Description | Default | +|-------------------------------------------|-----------------------------------------------|---------------------------------------------------------| +| `replicas` | Number of nodes | `1` | +| `podDisruptionBudget.minAvailable` | Pod disruption minimum available | `nil` | +| `podDisruptionBudget.maxUnavailable` | Pod disruption maximum unavailable | `nil` | +| `deploymentStrategy` | Deployment strategy | `{ "type": "RollingUpdate" }` | +| `livenessProbe` | Liveness Probe settings | `{ "httpGet": { "path": "/api/health", "port": 3000 } "initialDelaySeconds": 60, "timeoutSeconds": 30, "failureThreshold": 10 }` | +| `readinessProbe` | Readiness Probe settings | `{ "httpGet": { "path": "/api/health", "port": 3000 } }`| +| `securityContext` | Deployment securityContext | `{"runAsUser": 472, "runAsGroup": 472, "fsGroup": 472}` | +| `priorityClassName` | Name of Priority Class to assign pods | `nil` | +| `image.repository` | Image repository | `grafana/grafana` | +| `image.tag` | Overrides the Grafana image tag whose default is the chart appVersion (`Must be >= 5.0.0`) | `` | +| `image.sha` | Image sha (optional) | `` | +| `image.pullPolicy` | Image pull policy | `IfNotPresent` | +| `image.pullSecrets` | Image pull secrets (can be templated) | `[]` | +| `service.enabled` | Enable grafana service | `true` | +| `service.type` | Kubernetes service type | `ClusterIP` | +| `service.port` | Kubernetes port where service is exposed | `80` | +| `service.portName` | Name of the port on the service | `service` | +| `service.appProtocol` | Adds the appProtocol field to the service | `` | +| `service.targetPort` | Internal service is port | `3000` | +| `service.nodePort` | Kubernetes service nodePort | `nil` | +| `service.annotations` | Service annotations (can be templated) | `{}` | +| `service.labels` | Custom labels | `{}` | +| `service.clusterIP` | internal cluster service IP | `nil` | +| `service.loadBalancerIP` | IP address to assign to load balancer (if supported) | `nil` | +| `service.loadBalancerSourceRanges` | list of IP CIDRs allowed access to lb (if supported) | `[]` | +| `service.externalIPs` | service external IP addresses | `[]` | +| `headlessService` | Create a headless service | `false` | +| `extraExposePorts` | Additional service ports for sidecar containers| `[]` | +| `hostAliases` | adds rules to the pod's /etc/hosts | `[]` | +| `ingress.enabled` | Enables Ingress | `false` | +| `ingress.annotations` | Ingress annotations (values are templated) | `{}` | +| `ingress.labels` | Custom labels | `{}` | +| `ingress.path` | Ingress accepted path | `/` | +| `ingress.pathType` | Ingress type of path | `Prefix` | +| `ingress.hosts` | Ingress accepted hostnames | `["chart-example.local"]` | +| `ingress.extraPaths` | Ingress extra paths to prepend to every host configuration. Useful when configuring [custom actions with AWS ALB Ingress Controller](https://kubernetes-sigs.github.io/aws-alb-ingress-controller/guide/ingress/annotation/#actions). Requires `ingress.hosts` to have one or more host entries. | `[]` | +| `ingress.tls` | Ingress TLS configuration | `[]` | +| `ingress.ingressClassName` | Ingress Class Name. MAY be required for Kubernetes versions >= 1.18 | `""` | +| `resources` | CPU/Memory resource requests/limits | `{}` | +| `nodeSelector` | Node labels for pod assignment | `{}` | +| `tolerations` | Toleration labels for pod assignment | `[]` | +| `affinity` | Affinity settings for pod assignment | `{}` | +| `extraInitContainers` | Init containers to add to the grafana pod | `{}` | +| `extraContainers` | Sidecar containers to add to the grafana pod | `""` | +| `extraContainerVolumes` | Volumes that can be mounted in sidecar containers | `[]` | +| `extraLabels` | Custom labels for all manifests | `{}` | +| `schedulerName` | Name of the k8s scheduler (other than default) | `nil` | +| `persistence.enabled` | Use persistent volume to store data | `false` | +| `persistence.type` | Type of persistence (`pvc` or `statefulset`) | `pvc` | +| `persistence.size` | Size of persistent volume claim | `10Gi` | +| `persistence.existingClaim` | Use an existing PVC to persist data (can be templated) | `nil` | +| `persistence.storageClassName` | Type of persistent volume claim | `nil` | +| `persistence.accessModes` | Persistence access modes | `[ReadWriteOnce]` | +| `persistence.annotations` | PersistentVolumeClaim annotations | `{}` | +| `persistence.finalizers` | PersistentVolumeClaim finalizers | `[ "kubernetes.io/pvc-protection" ]` | +| `persistence.extraPvcLabels` | Extra labels to apply to a PVC. | `{}` | +| `persistence.subPath` | Mount a sub dir of the persistent volume (can be templated) | `nil` | +| `persistence.inMemory.enabled` | If persistence is not enabled, whether to mount the local storage in-memory to improve performance | `false` | +| `persistence.inMemory.sizeLimit` | SizeLimit for the in-memory local storage | `nil` | +| `initChownData.enabled` | If false, don't reset data ownership at startup | true | +| `initChownData.image.repository` | init-chown-data container image repository | `busybox` | +| `initChownData.image.tag` | init-chown-data container image tag | `1.31.1` | +| `initChownData.image.sha` | init-chown-data container image sha (optional)| `""` | +| `initChownData.image.pullPolicy` | init-chown-data container image pull policy | `IfNotPresent` | +| `initChownData.resources` | init-chown-data pod resource requests & limits | `{}` | +| `schedulerName` | Alternate scheduler name | `nil` | +| `env` | Extra environment variables passed to pods | `{}` | +| `envValueFrom` | Environment variables from alternate sources. See the API docs on [EnvVarSource](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.17/#envvarsource-v1-core) for format details. Can be templated | `{}` | +| `envFromSecret` | Name of a Kubernetes secret (must be manually created in the same namespace) containing values to be added to the environment. Can be templated | `""` | +| `envFromSecrets` | List of Kubernetes secrets (must be manually created in the same namespace) containing values to be added to the environment. Can be templated | `[]` | +| `envFromConfigMaps` | List of Kubernetes ConfigMaps (must be manually created in the same namespace) containing values to be added to the environment. Can be templated | `[]` | +| `envRenderSecret` | Sensible environment variables passed to pods and stored as secret. (passed through [tpl](https://helm.sh/docs/howto/charts_tips_and_tricks/#using-the-tpl-function)) | `{}` | +| `enableServiceLinks` | Inject Kubernetes services as environment variables. | `true` | +| `extraSecretMounts` | Additional grafana server secret mounts | `[]` | +| `extraVolumeMounts` | Additional grafana server volume mounts | `[]` | +| `createConfigmap` | Enable creating the grafana configmap | `true` | +| `extraConfigmapMounts` | Additional grafana server configMap volume mounts (values are templated) | `[]` | +| `extraEmptyDirMounts` | Additional grafana server emptyDir volume mounts | `[]` | +| `plugins` | Plugins to be loaded along with Grafana | `[]` | +| `datasources` | Configure grafana datasources (passed through tpl) | `{}` | +| `alerting` | Configure grafana alerting (passed through tpl) | `{}` | +| `notifiers` | Configure grafana notifiers | `{}` | +| `dashboardProviders` | Configure grafana dashboard providers | `{}` | +| `dashboards` | Dashboards to import | `{}` | +| `dashboardsConfigMaps` | ConfigMaps reference that contains dashboards | `{}` | +| `grafana.ini` | Grafana's primary configuration | `{}` | +| `global.imagePullSecrets` | Global image pull secrets (can be templated). Allows either an array of {name: pullSecret} maps (k8s-style), or an array of strings (more common helm-style). | `[]` | +| `ldap.enabled` | Enable LDAP authentication | `false` | +| `ldap.existingSecret` | The name of an existing secret containing the `ldap.toml` file, this must have the key `ldap-toml`. | `""` | +| `ldap.config` | Grafana's LDAP configuration | `""` | +| `annotations` | Deployment annotations | `{}` | +| `labels` | Deployment labels | `{}` | +| `podAnnotations` | Pod annotations | `{}` | +| `podLabels` | Pod labels | `{}` | +| `podPortName` | Name of the grafana port on the pod | `grafana` | +| `lifecycleHooks` | Lifecycle hooks for podStart and preStop [Example](https://kubernetes.io/docs/tasks/configure-pod-container/attach-handler-lifecycle-event/#define-poststart-and-prestop-handlers) | `{}` | +| `sidecar.image.repository` | Sidecar image repository | `quay.io/kiwigrid/k8s-sidecar` | +| `sidecar.image.tag` | Sidecar image tag | `1.24.3` | +| `sidecar.image.sha` | Sidecar image sha (optional) | `""` | +| `sidecar.imagePullPolicy` | Sidecar image pull policy | `IfNotPresent` | +| `sidecar.resources` | Sidecar resources | `{}` | +| `sidecar.securityContext` | Sidecar securityContext | `{}` | +| `sidecar.enableUniqueFilenames` | Sets the kiwigrid/k8s-sidecar UNIQUE_FILENAMES environment variable. If set to `true` the sidecar will create unique filenames where duplicate data keys exist between ConfigMaps and/or Secrets within the same or multiple Namespaces. | `false` | +| `sidecar.alerts.enabled` | Enables the cluster wide search for alerts and adds/updates/deletes them in grafana |`false` | +| `sidecar.alerts.label` | Label that config maps with alerts should have to be added | `grafana_alert` | +| `sidecar.alerts.labelValue` | Label value that config maps with alerts should have to be added | `""` | +| `sidecar.alerts.searchNamespace` | Namespaces list. If specified, the sidecar will search for alerts config-maps inside these namespaces. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces. | `nil` | +| `sidecar.alerts.watchMethod` | Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. | `WATCH` | +| `sidecar.alerts.resource` | Should the sidecar looks into secrets, configmaps or both. | `both` | +| `sidecar.alerts.reloadURL` | Full url of datasource configuration reload API endpoint, to invoke after a config-map change | `"http://localhost:3000/api/admin/provisioning/alerting/reload"` | +| `sidecar.alerts.skipReload` | Enabling this omits defining the REQ_URL and REQ_METHOD environment variables | `false` | +| `sidecar.alerts.initDatasources` | Set to true to deploy the datasource sidecar as an initContainer in addition to a container. This is needed if skipReload is true, to load any alerts defined at startup time. | `false` | +| `sidecar.dashboards.enabled` | Enables the cluster wide search for dashboards and adds/updates/deletes them in grafana | `false` | +| `sidecar.dashboards.SCProvider` | Enables creation of sidecar provider | `true` | +| `sidecar.dashboards.provider.name` | Unique name of the grafana provider | `sidecarProvider` | +| `sidecar.dashboards.provider.orgid` | Id of the organisation, to which the dashboards should be added | `1` | +| `sidecar.dashboards.provider.folder` | Logical folder in which grafana groups dashboards | `""` | +| `sidecar.dashboards.provider.disableDelete` | Activate to avoid the deletion of imported dashboards | `false` | +| `sidecar.dashboards.provider.allowUiUpdates` | Allow updating provisioned dashboards from the UI | `false` | +| `sidecar.dashboards.provider.type` | Provider type | `file` | +| `sidecar.dashboards.provider.foldersFromFilesStructure` | Allow Grafana to replicate dashboard structure from filesystem. | `false` | +| `sidecar.dashboards.watchMethod` | Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. | `WATCH` | +| `sidecar.skipTlsVerify` | Set to true to skip tls verification for kube api calls | `nil` | +| `sidecar.dashboards.label` | Label that config maps with dashboards should have to be added | `grafana_dashboard` | +| `sidecar.dashboards.labelValue` | Label value that config maps with dashboards should have to be added | `""` | +| `sidecar.dashboards.folder` | Folder in the pod that should hold the collected dashboards (unless `sidecar.dashboards.defaultFolderName` is set). This path will be mounted. | `/tmp/dashboards` | +| `sidecar.dashboards.folderAnnotation` | The annotation the sidecar will look for in configmaps to override the destination folder for files | `nil` | +| `sidecar.dashboards.defaultFolderName` | The default folder name, it will create a subfolder under the `sidecar.dashboards.folder` and put dashboards in there instead | `nil` | +| `sidecar.dashboards.searchNamespace` | Namespaces list. If specified, the sidecar will search for dashboards config-maps inside these namespaces. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces. | `nil` | +| `sidecar.dashboards.script` | Absolute path to shell script to execute after a configmap got reloaded. | `nil` | +| `sidecar.dashboards.reloadURL` | Full url of dashboards configuration reload API endpoint, to invoke after a config-map change | `"http://localhost:3000/api/admin/provisioning/dashboards/reload"` | +| `sidecar.dashboards.skipReload` | Enabling this omits defining the REQ_URL and REQ_METHOD environment variables | `false` | +| `sidecar.dashboards.resource` | Should the sidecar looks into secrets, configmaps or both. | `both` | +| `sidecar.dashboards.extraMounts` | Additional dashboard sidecar volume mounts. | `[]` | +| `sidecar.datasources.enabled` | Enables the cluster wide search for datasources and adds/updates/deletes them in grafana |`false` | +| `sidecar.datasources.label` | Label that config maps with datasources should have to be added | `grafana_datasource` | +| `sidecar.datasources.labelValue` | Label value that config maps with datasources should have to be added | `""` | +| `sidecar.datasources.searchNamespace` | Namespaces list. If specified, the sidecar will search for datasources config-maps inside these namespaces. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces. | `nil` | +| `sidecar.datasources.watchMethod` | Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. | `WATCH` | +| `sidecar.datasources.resource` | Should the sidecar looks into secrets, configmaps or both. | `both` | +| `sidecar.datasources.reloadURL` | Full url of datasource configuration reload API endpoint, to invoke after a config-map change | `"http://localhost:3000/api/admin/provisioning/datasources/reload"` | +| `sidecar.datasources.skipReload` | Enabling this omits defining the REQ_URL and REQ_METHOD environment variables | `false` | +| `sidecar.datasources.initDatasources` | Set to true to deploy the datasource sidecar as an initContainer in addition to a container. This is needed if skipReload is true, to load any datasources defined at startup time. | `false` | +| `sidecar.notifiers.enabled` | Enables the cluster wide search for notifiers and adds/updates/deletes them in grafana | `false` | +| `sidecar.notifiers.label` | Label that config maps with notifiers should have to be added | `grafana_notifier` | +| `sidecar.notifiers.labelValue` | Label value that config maps with notifiers should have to be added | `""` | +| `sidecar.notifiers.searchNamespace` | Namespaces list. If specified, the sidecar will search for notifiers config-maps (or secrets) inside these namespaces. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces. | `nil` | +| `sidecar.notifiers.watchMethod` | Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. | `WATCH` | +| `sidecar.notifiers.resource` | Should the sidecar looks into secrets, configmaps or both. | `both` | +| `sidecar.notifiers.reloadURL` | Full url of notifier configuration reload API endpoint, to invoke after a config-map change | `"http://localhost:3000/api/admin/provisioning/notifications/reload"` | +| `sidecar.notifiers.skipReload` | Enabling this omits defining the REQ_URL and REQ_METHOD environment variables | `false` | +| `sidecar.notifiers.initNotifiers` | Set to true to deploy the notifier sidecar as an initContainer in addition to a container. This is needed if skipReload is true, to load any notifiers defined at startup time. | `false` | +| `smtp.existingSecret` | The name of an existing secret containing the SMTP credentials. | `""` | +| `smtp.userKey` | The key in the existing SMTP secret containing the username. | `"user"` | +| `smtp.passwordKey` | The key in the existing SMTP secret containing the password. | `"password"` | +| `admin.existingSecret` | The name of an existing secret containing the admin credentials (can be templated). | `""` | +| `admin.userKey` | The key in the existing admin secret containing the username. | `"admin-user"` | +| `admin.passwordKey` | The key in the existing admin secret containing the password. | `"admin-password"` | +| `serviceAccount.autoMount` | Automount the service account token in the pod| `true` | +| `serviceAccount.annotations` | ServiceAccount annotations | | +| `serviceAccount.create` | Create service account | `true` | +| `serviceAccount.labels` | ServiceAccount labels | `{}` | +| `serviceAccount.name` | Service account name to use, when empty will be set to created account if `serviceAccount.create` is set else to `default` | `` | +| `serviceAccount.nameTest` | Service account name to use for test, when empty will be set to created account if `serviceAccount.create` is set else to `default` | `nil` | +| `rbac.create` | Create and use RBAC resources | `true` | +| `rbac.namespaced` | Creates Role and Rolebinding instead of the default ClusterRole and ClusteRoleBindings for the grafana instance | `false` | +| `rbac.useExistingRole` | Set to a rolename to use existing role - skipping role creating - but still doing serviceaccount and rolebinding to the rolename set here. | `nil` | +| `rbac.pspEnabled` | Create PodSecurityPolicy (with `rbac.create`, grant roles permissions as well) | `false` | +| `rbac.pspUseAppArmor` | Enforce AppArmor in created PodSecurityPolicy (requires `rbac.pspEnabled`) | `false` | +| `rbac.extraRoleRules` | Additional rules to add to the Role | [] | +| `rbac.extraClusterRoleRules` | Additional rules to add to the ClusterRole | [] | +| `command` | Define command to be executed by grafana container at startup | `nil` | +| `args` | Define additional args if command is used | `nil` | +| `testFramework.enabled` | Whether to create test-related resources | `true` | +| `testFramework.image` | `test-framework` image repository. | `bats/bats` | +| `testFramework.tag` | `test-framework` image tag. | `v1.4.1` | +| `testFramework.imagePullPolicy` | `test-framework` image pull policy. | `IfNotPresent` | +| `testFramework.securityContext` | `test-framework` securityContext | `{}` | +| `downloadDashboards.env` | Environment variables to be passed to the `download-dashboards` container | `{}` | +| `downloadDashboards.envFromSecret` | Name of a Kubernetes secret (must be manually created in the same namespace) containing values to be added to the environment. Can be templated | `""` | +| `downloadDashboards.resources` | Resources of `download-dashboards` container | `{}` | +| `downloadDashboardsImage.repository` | Curl docker image repo | `curlimages/curl` | +| `downloadDashboardsImage.tag` | Curl docker image tag | `7.73.0` | +| `downloadDashboardsImage.sha` | Curl docker image sha (optional) | `""` | +| `downloadDashboardsImage.pullPolicy` | Curl docker image pull policy | `IfNotPresent` | +| `namespaceOverride` | Override the deployment namespace | `""` (`Release.Namespace`) | +| `serviceMonitor.enabled` | Use servicemonitor from prometheus operator | `false` | +| `serviceMonitor.namespace` | Namespace this servicemonitor is installed in | | +| `serviceMonitor.interval` | How frequently Prometheus should scrape | `1m` | +| `serviceMonitor.path` | Path to scrape | `/metrics` | +| `serviceMonitor.scheme` | Scheme to use for metrics scraping | `http` | +| `serviceMonitor.tlsConfig` | TLS configuration block for the endpoint | `{}` | +| `serviceMonitor.labels` | Labels for the servicemonitor passed to Prometheus Operator | `{}` | +| `serviceMonitor.scrapeTimeout` | Timeout after which the scrape is ended | `30s` | +| `serviceMonitor.relabelings` | MetricRelabelConfigs to apply to samples before ingestion. | `[]` | +| `revisionHistoryLimit` | Number of old ReplicaSets to retain | `10` | +| `imageRenderer.enabled` | Enable the image-renderer deployment & service | `false` | +| `imageRenderer.image.repository` | image-renderer Image repository | `grafana/grafana-image-renderer` | +| `imageRenderer.image.tag` | image-renderer Image tag | `latest` | +| `imageRenderer.image.sha` | image-renderer Image sha (optional) | `""` | +| `imageRenderer.image.pullPolicy` | image-renderer ImagePullPolicy | `Always` | +| `imageRenderer.env` | extra env-vars for image-renderer | `{}` | +| `imageRenderer.envValueFrom` | Environment variables for image-renderer from alternate sources. See the API docs on [EnvVarSource](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.17/#envvarsource-v1-core) for format details. Can be templated | `{}` | +| `imageRenderer.serviceAccountName` | image-renderer deployment serviceAccountName | `""` | +| `imageRenderer.securityContext` | image-renderer deployment securityContext | `{}` | +| `imageRenderer.hostAliases` | image-renderer deployment Host Aliases | `[]` | +| `imageRenderer.priorityClassName` | image-renderer deployment priority class | `''` | +| `imageRenderer.service.enabled` | Enable the image-renderer service | `true` | +| `imageRenderer.service.portName` | image-renderer service port name | `http` | +| `imageRenderer.service.port` | image-renderer port used by deployment | `8081` | +| `imageRenderer.service.targetPort` | image-renderer service port used by service | `8081` | +| `imageRenderer.appProtocol` | Adds the appProtocol field to the service | `` | +| `imageRenderer.grafanaSubPath` | Grafana sub path to use for image renderer callback url | `''` | +| `imageRenderer.podPortName` | name of the image-renderer port on the pod | `http` | +| `imageRenderer.revisionHistoryLimit` | number of image-renderer replica sets to keep | `10` | +| `imageRenderer.networkPolicy.limitIngress` | Enable a NetworkPolicy to limit inbound traffic from only the created grafana pods | `true` | +| `imageRenderer.networkPolicy.limitEgress` | Enable a NetworkPolicy to limit outbound traffic to only the created grafana pods | `false` | +| `imageRenderer.resources` | Set resource limits for image-renderer pdos | `{}` | +| `imageRenderer.nodeSelector` | Node labels for pod assignment | `{}` | +| `imageRenderer.tolerations` | Toleration labels for pod assignment | `[]` | +| `imageRenderer.affinity` | Affinity settings for pod assignment | `{}` | +| `networkPolicy.enabled` | Enable creation of NetworkPolicy resources. | `false` | +| `networkPolicy.allowExternal` | Don't require client label for connections | `true` | +| `networkPolicy.explicitNamespacesSelector` | A Kubernetes LabelSelector to explicitly select namespaces from which traffic could be allowed | `{}` | +| `networkPolicy.ingress` | Enable the creation of an ingress network policy | `true` | +| `networkPolicy.egress.enabled` | Enable the creation of an egress network policy | `false` | +| `networkPolicy.egress.ports` | An array of ports to allow for the egress | `[]` | +| `enableKubeBackwardCompatibility` | Enable backward compatibility of kubernetes where pod's defintion version below 1.13 doesn't have the enableServiceLinks option | `false` | + +### Example ingress with path + +With grafana 6.3 and above + +```yaml +grafana.ini: + server: + domain: monitoring.example.com + root_url: "%(protocol)s://%(domain)s/grafana" + serve_from_sub_path: true +ingress: + enabled: true + hosts: + - "monitoring.example.com" + path: "/grafana" +``` + +### Example of extraVolumeMounts + +Volume can be type persistentVolumeClaim or hostPath but not both at same time. +If neither existingClaim or hostPath argument is given then type is emptyDir. + +```yaml +- extraVolumeMounts: + - name: plugins + mountPath: /var/lib/grafana/plugins + subPath: configs/grafana/plugins + existingClaim: existing-grafana-claim + readOnly: false + - name: dashboards + mountPath: /var/lib/grafana/dashboards + hostPath: /usr/shared/grafana/dashboards + readOnly: false +``` + +## Import dashboards + +There are a few methods to import dashboards to Grafana. Below are some examples and explanations as to how to use each method: + +```yaml +dashboards: + default: + some-dashboard: + json: | + { + "annotations": + + ... + # Complete json file here + ... + + "title": "Some Dashboard", + "uid": "abcd1234", + "version": 1 + } + custom-dashboard: + # This is a path to a file inside the dashboards directory inside the chart directory + file: dashboards/custom-dashboard.json + prometheus-stats: + # Ref: https://grafana.com/dashboards/2 + gnetId: 2 + revision: 2 + datasource: Prometheus + loki-dashboard-quick-search: + gnetId: 12019 + revision: 2 + datasource: + - name: DS_PROMETHEUS + value: Prometheus + - name: DS_LOKI + value: Loki + local-dashboard: + url: https://raw.githubusercontent.com/user/repository/master/dashboards/dashboard.json +``` + +## BASE64 dashboards + +Dashboards could be stored on a server that does not return JSON directly and instead of it returns a Base64 encoded file (e.g. Gerrit) +A new parameter has been added to the url use case so if you specify a b64content value equals to true after the url entry a Base64 decoding is applied before save the file to disk. +If this entry is not set or is equals to false not decoding is applied to the file before saving it to disk. + +### Gerrit use case + +Gerrit API for download files has the following schema: where {project-name} and +{file-id} usually has '/' in their values and so they MUST be replaced by %2F so if project-name is user/repo, branch-id is master and file-id is equals to dir1/dir2/dashboard +the url value is + +## Sidecar for dashboards + +If the parameter `sidecar.dashboards.enabled` is set, a sidecar container is deployed in the grafana +pod. This container watches all configmaps (or secrets) in the cluster and filters out the ones with +a label as defined in `sidecar.dashboards.label`. The files defined in those configmaps are written +to a folder and accessed by grafana. Changes to the configmaps are monitored and the imported +dashboards are deleted/updated. + +A recommendation is to use one configmap per dashboard, as a reduction of multiple dashboards inside +one configmap is currently not properly mirrored in grafana. + +Example dashboard config: + +```yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: sample-grafana-dashboard + labels: + grafana_dashboard: "1" +data: + k8s-dashboard.json: |- + [...] +``` + +## Sidecar for datasources + +If the parameter `sidecar.datasources.enabled` is set, an init container is deployed in the grafana +pod. This container lists all secrets (or configmaps, though not recommended) in the cluster and +filters out the ones with a label as defined in `sidecar.datasources.label`. The files defined in +those secrets are written to a folder and accessed by grafana on startup. Using these yaml files, +the data sources in grafana can be imported. + +Should you aim for reloading datasources in Grafana each time the config is changed, set `sidecar.datasources.skipReload: false` and adjust `sidecar.datasources.reloadURL` to `http://..svc.cluster.local/api/admin/provisioning/datasources/reload`. + +Secrets are recommended over configmaps for this usecase because datasources usually contain private +data like usernames and passwords. Secrets are the more appropriate cluster resource to manage those. + +Example values to add a postgres datasource as a kubernetes secret: +```yaml +apiVersion: v1 +kind: Secret +metadata: + name: grafana-datasources + labels: + grafana_datasource: 'true' # default value for: sidecar.datasources.label +stringData: + pg-db.yaml: |- + apiVersion: 1 + datasources: + - name: My pg db datasource + type: postgres + url: my-postgresql-db:5432 + user: db-readonly-user + secureJsonData: + password: 'SUperSEcretPa$$word' + jsonData: + database: my_datase + sslmode: 'disable' # disable/require/verify-ca/verify-full + maxOpenConns: 0 # Grafana v5.4+ + maxIdleConns: 2 # Grafana v5.4+ + connMaxLifetime: 14400 # Grafana v5.4+ + postgresVersion: 1000 # 903=9.3, 904=9.4, 905=9.5, 906=9.6, 1000=10 + timescaledb: false + # allow users to edit datasources from the UI. + editable: false +``` + +Example values to add a datasource adapted from [Grafana](http://docs.grafana.org/administration/provisioning/#example-datasource-config-file): + +```yaml +datasources: + datasources.yaml: + apiVersion: 1 + datasources: + # name of the datasource. Required + - name: Graphite + # datasource type. Required + type: graphite + # access mode. proxy or direct (Server or Browser in the UI). Required + access: proxy + # org id. will default to orgId 1 if not specified + orgId: 1 + # url + url: http://localhost:8080 + # database password, if used + password: + # database user, if used + user: + # database name, if used + database: + # enable/disable basic auth + basicAuth: + # basic auth username + basicAuthUser: + # basic auth password + basicAuthPassword: + # enable/disable with credentials headers + withCredentials: + # mark as default datasource. Max one per org + isDefault: + # fields that will be converted to json and stored in json_data + jsonData: + graphiteVersion: "1.1" + tlsAuth: true + tlsAuthWithCACert: true + # json object of data that will be encrypted. + secureJsonData: + tlsCACert: "..." + tlsClientCert: "..." + tlsClientKey: "..." + version: 1 + # allow users to edit datasources from the UI. + editable: false +``` + +## Sidecar for notifiers + +If the parameter `sidecar.notifiers.enabled` is set, an init container is deployed in the grafana +pod. This container lists all secrets (or configmaps, though not recommended) in the cluster and +filters out the ones with a label as defined in `sidecar.notifiers.label`. The files defined in +those secrets are written to a folder and accessed by grafana on startup. Using these yaml files, +the notification channels in grafana can be imported. The secrets must be created before +`helm install` so that the notifiers init container can list the secrets. + +Secrets are recommended over configmaps for this usecase because alert notification channels usually contain +private data like SMTP usernames and passwords. Secrets are the more appropriate cluster resource to manage those. + +Example datasource config adapted from [Grafana](https://grafana.com/docs/grafana/latest/administration/provisioning/#alert-notification-channels): + +```yaml +notifiers: + - name: notification-channel-1 + type: slack + uid: notifier1 + # either + org_id: 2 + # or + org_name: Main Org. + is_default: true + send_reminder: true + frequency: 1h + disable_resolve_message: false + # See `Supported Settings` section for settings supporter for each + # alert notification type. + settings: + recipient: 'XXX' + token: 'xoxb' + uploadImage: true + url: https://slack.com + +delete_notifiers: + - name: notification-channel-1 + uid: notifier1 + org_id: 2 + - name: notification-channel-2 + # default org_id: 1 +``` + +## Provision alert rules, contact points, notification policies and notification templates + +There are two methods to provision alerting configuration in Grafana. Below are some examples and explanations as to how to use each method: + +```yaml +alerting: + team1-alert-rules.yaml: + file: alerting/team1/rules.yaml + team2-alert-rules.yaml: + file: alerting/team2/rules.yaml + team3-alert-rules.yaml: + file: alerting/team3/rules.yaml + notification-policies.yaml: + file: alerting/shared/notification-policies.yaml + notification-templates.yaml: + file: alerting/shared/notification-templates.yaml + contactpoints.yaml: + apiVersion: 1 + contactPoints: + - orgId: 1 + name: Slack channel + receivers: + - uid: default-receiver + type: slack + settings: + # Webhook URL to be filled in + url: "" + # We need to escape double curly braces for the tpl function. + text: '{{ `{{ template "default.message" . }}` }}' + title: '{{ `{{ template "default.title" . }}` }}' +``` + +There are two possibilities: + +* Inlining the file contents as described in the example `values.yaml` and the official [Grafana documentation](https://grafana.com/docs/grafana/next/alerting/set-up/provision-alerting-resources/file-provisioning/). +* Importing a file using a relative path starting from the chart root directory. + +### Important notes on file provisioning + +* The chart supports importing YAML and JSON files. +* The filename must be unique, otherwise one volume mount will overwrite the other. +* In case of inlining, double curly braces that arise from the Grafana configuration format and are not intended as templates for the chart must be escaped. +* The number of total files under `alerting:` is not limited. Each file will end up as a volume mount in the corresponding provisioning folder of the deployed Grafana instance. +* The file size for each import is limited by what the function `.Files.Get` can handle, which suffices for most cases. + +## How to serve Grafana with a path prefix (/grafana) + +In order to serve Grafana with a prefix (e.g., ), add the following to your values.yaml. + +```yaml +ingress: + enabled: true + annotations: + kubernetes.io/ingress.class: "nginx" + nginx.ingress.kubernetes.io/rewrite-target: /$1 + nginx.ingress.kubernetes.io/use-regex: "true" + + path: /grafana/?(.*) + hosts: + - k8s.example.dev + +grafana.ini: + server: + root_url: http://localhost:3000/grafana # this host can be localhost +``` + +## How to securely reference secrets in grafana.ini + +This example uses Grafana [file providers](https://grafana.com/docs/grafana/latest/administration/configuration/#file-provider) for secret values and the `extraSecretMounts` configuration flag (Additional grafana server secret mounts) to mount the secrets. + +In grafana.ini: + +```yaml +grafana.ini: + [auth.generic_oauth] + enabled = true + client_id = $__file{/etc/secrets/auth_generic_oauth/client_id} + client_secret = $__file{/etc/secrets/auth_generic_oauth/client_secret} +``` + +Existing secret, or created along with helm: + +```yaml +--- +apiVersion: v1 +kind: Secret +metadata: + name: auth-generic-oauth-secret +type: Opaque +stringData: + client_id: + client_secret: +``` + +Include in the `extraSecretMounts` configuration flag: + +```yaml +- extraSecretMounts: + - name: auth-generic-oauth-secret-mount + secretName: auth-generic-oauth-secret + defaultMode: 0440 + mountPath: /etc/secrets/auth_generic_oauth + readOnly: true +``` + +### extraSecretMounts using a Container Storage Interface (CSI) provider + +This example uses a CSI driver e.g. retrieving secrets using [Azure Key Vault Provider](https://github.com/Azure/secrets-store-csi-driver-provider-azure) + +```yaml +- extraSecretMounts: + - name: secrets-store-inline + mountPath: /run/secrets + readOnly: true + csi: + driver: secrets-store.csi.k8s.io + readOnly: true + volumeAttributes: + secretProviderClass: "my-provider" + nodePublishSecretRef: + name: akv-creds +``` + +## Image Renderer Plug-In + +This chart supports enabling [remote image rendering](https://github.com/grafana/grafana-image-renderer/blob/master/README.md#run-in-docker) + +```yaml +imageRenderer: + enabled: true +``` + +### Image Renderer NetworkPolicy + +By default the image-renderer pods will have a network policy which only allows ingress traffic from the created grafana instance + +### High Availability for unified alerting + +If you want to run Grafana in a high availability cluster you need to enable +the headless service by setting `headlessService: true` in your `values.yaml` +file. + +As next step you have to setup the `grafana.ini` in your `values.yaml` in a way +that it will make use of the headless service to obtain all the IPs of the +cluster. You should replace ``{{ Name }}`` with the name of your helm deployment. + +```yaml +grafana.ini: + ... + unified_alerting: + enabled: true + ha_peers: {{ Name }}-headless:9094 + ha_listen_address: ${POD_IP}:9094 + ha_advertise_address: ${POD_IP}:9094 + + alerting: + enabled: false +``` diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/default-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/default-values.yaml new file mode 100644 index 0000000..fc2ba60 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/default-values.yaml @@ -0,0 +1 @@ +# Leave this file empty to ensure that CI runs builds against the default configuration in values.yaml. diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-affinity-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-affinity-values.yaml new file mode 100644 index 0000000..f5b9b53 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-affinity-values.yaml @@ -0,0 +1,16 @@ +affinity: + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - podAffinityTerm: + labelSelector: + matchLabels: + app.kubernetes.io/instance: grafana-test + app.kubernetes.io/name: grafana + topologyKey: failure-domain.beta.kubernetes.io/zone + weight: 100 + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + app.kubernetes.io/instance: grafana-test + app.kubernetes.io/name: grafana + topologyKey: kubernetes.io/hostname diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-dashboard-json-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-dashboard-json-values.yaml new file mode 100644 index 0000000..e0c4e41 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-dashboard-json-values.yaml @@ -0,0 +1,53 @@ +dashboards: + my-provider: + my-awesome-dashboard: + # An empty but valid dashboard + json: | + { + "__inputs": [], + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "6.3.5" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "id": null, + "links": [], + "panels": [], + "schemaVersion": 19, + "style": "dark", + "tags": [], + "templating": { + "list": [] + }, + "time": { + "from": "now-6h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": ["5s"] + }, + "timezone": "", + "title": "Dummy Dashboard", + "uid": "IdcYQooWk", + "version": 1 + } + datasource: Prometheus diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-dashboard-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-dashboard-values.yaml new file mode 100644 index 0000000..7b662c5 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-dashboard-values.yaml @@ -0,0 +1,19 @@ +dashboards: + my-provider: + my-awesome-dashboard: + gnetId: 10000 + revision: 1 + datasource: Prometheus +dashboardProviders: + dashboardproviders.yaml: + apiVersion: 1 + providers: + - name: 'my-provider' + orgId: 1 + folder: '' + type: file + updateIntervalSeconds: 10 + disableDeletion: true + editable: true + options: + path: /var/lib/grafana/dashboards/my-provider diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-extraconfigmapmounts-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-extraconfigmapmounts-values.yaml new file mode 100644 index 0000000..5cc44a0 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-extraconfigmapmounts-values.yaml @@ -0,0 +1,7 @@ +extraConfigmapMounts: + - name: '{{ include "grafana.fullname" . }}' + configMap: '{{ include "grafana.fullname" . }}' + mountPath: /var/lib/grafana/dashboards/test-dashboard.json + # This is not a realistic test, but for this we only care about extraConfigmapMounts not being empty and pointing to an existing ConfigMap + subPath: grafana.ini + readOnly: true diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-image-renderer-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-image-renderer-values.yaml new file mode 100644 index 0000000..32f3074 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-image-renderer-values.yaml @@ -0,0 +1,19 @@ +podLabels: + customLableA: Aaaaa +imageRenderer: + enabled: true + env: + RENDERING_ARGS: --disable-gpu,--window-size=1280x758 + RENDERING_MODE: clustered + podLabels: + customLableB: Bbbbb + networkPolicy: + limitIngress: true + limitEgress: true + resources: + limits: + cpu: 1000m + memory: 1000Mi + requests: + cpu: 500m + memory: 50Mi diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-persistence.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-persistence.yaml new file mode 100644 index 0000000..b92ca02 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/ci/with-persistence.yaml @@ -0,0 +1,3 @@ +persistence: + type: pvc + enabled: true diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/dashboards/custom-dashboard.json b/observability/lgtm-distributed/charts/oncall/charts/grafana/dashboards/custom-dashboard.json new file mode 100644 index 0000000..9e26dfe --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/dashboards/custom-dashboard.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/NOTES.txt new file mode 100644 index 0000000..d86419f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/NOTES.txt @@ -0,0 +1,55 @@ +1. Get your '{{ .Values.adminUser }}' user password by running: + + kubectl get secret --namespace {{ include "grafana.namespace" . }} {{ .Values.admin.existingSecret | default (include "grafana.fullname" .) }} -o jsonpath="{.data.{{ .Values.admin.passwordKey | default "admin-password" }}}" | base64 --decode ; echo + + +2. The Grafana server can be accessed via port {{ .Values.service.port }} on the following DNS name from within your cluster: + + {{ include "grafana.fullname" . }}.{{ include "grafana.namespace" . }}.svc.cluster.local +{{ if .Values.ingress.enabled }} + If you bind grafana to 80, please update values in values.yaml and reinstall: + ``` + securityContext: + runAsUser: 0 + runAsGroup: 0 + fsGroup: 0 + + command: + - "setcap" + - "'cap_net_bind_service=+ep'" + - "/usr/sbin/grafana-server &&" + - "sh" + - "/run.sh" + ``` + Details refer to https://grafana.com/docs/installation/configuration/#http-port. + Or grafana would always crash. + + From outside the cluster, the server URL(s) are: + {{- range .Values.ingress.hosts }} + http://{{ . }} + {{- end }} +{{- else }} + Get the Grafana URL to visit by running these commands in the same shell: + {{- if contains "NodePort" .Values.service.type }} + export NODE_PORT=$(kubectl get --namespace {{ include "grafana.namespace" . }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "grafana.fullname" . }}) + export NODE_IP=$(kubectl get nodes --namespace {{ include "grafana.namespace" . }} -o jsonpath="{.items[0].status.addresses[0].address}") + echo http://$NODE_IP:$NODE_PORT + {{- else if contains "LoadBalancer" .Values.service.type }} + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + You can watch the status of by running 'kubectl get svc --namespace {{ include "grafana.namespace" . }} -w {{ include "grafana.fullname" . }}' + export SERVICE_IP=$(kubectl get svc --namespace {{ include "grafana.namespace" . }} {{ include "grafana.fullname" . }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}') + http://$SERVICE_IP:{{ .Values.service.port -}} + {{- else if contains "ClusterIP" .Values.service.type }} + export POD_NAME=$(kubectl get pods --namespace {{ include "grafana.namespace" . }} -l "app.kubernetes.io/name={{ include "grafana.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") + kubectl --namespace {{ include "grafana.namespace" . }} port-forward $POD_NAME 3000 + {{- end }} +{{- end }} + +3. Login with the password from step 1 and the username: {{ .Values.adminUser }} + +{{- if not .Values.persistence.enabled }} +################################################################################# +###### WARNING: Persistence is disabled!!! You will lose your data when ##### +###### the Grafana pod is terminated. ##### +################################################################################# +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/_helpers.tpl new file mode 100644 index 0000000..8307e10 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/_helpers.tpl @@ -0,0 +1,201 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "grafana.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "grafana.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default .Chart.Name .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "grafana.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create the name of the service account +*/}} +{{- define "grafana.serviceAccountName" -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "grafana.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} + +{{- define "grafana.serviceAccountNameTest" -}} +{{- if .Values.serviceAccount.create }} +{{- default (print (include "grafana.fullname" .) "-test") .Values.serviceAccount.nameTest }} +{{- else }} +{{- default "default" .Values.serviceAccount.nameTest }} +{{- end }} +{{- end }} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts +*/}} +{{- define "grafana.namespace" -}} +{{- if .Values.namespaceOverride }} +{{- .Values.namespaceOverride }} +{{- else }} +{{- .Release.Namespace }} +{{- end }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "grafana.labels" -}} +helm.sh/chart: {{ include "grafana.chart" . }} +{{ include "grafana.selectorLabels" . }} +{{- if or .Chart.AppVersion .Values.image.tag }} +app.kubernetes.io/version: {{ mustRegexReplaceAllLiteral "@sha.*" .Values.image.tag "" | default .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- with .Values.extraLabels }} +{{ toYaml . }} +{{- end }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "grafana.selectorLabels" -}} +app.kubernetes.io/name: {{ include "grafana.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "grafana.imageRenderer.labels" -}} +helm.sh/chart: {{ include "grafana.chart" . }} +{{ include "grafana.imageRenderer.selectorLabels" . }} +{{- if or .Chart.AppVersion .Values.image.tag }} +app.kubernetes.io/version: {{ mustRegexReplaceAllLiteral "@sha.*" .Values.image.tag "" | default .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end }} + +{{/* +Selector labels ImageRenderer +*/}} +{{- define "grafana.imageRenderer.selectorLabels" -}} +app.kubernetes.io/name: {{ include "grafana.name" . }}-image-renderer +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Looks if there's an existing secret and reuse its password. If not it generates +new password and use it. +*/}} +{{- define "grafana.password" -}} +{{- $secret := (lookup "v1" "Secret" (include "grafana.namespace" .) (include "grafana.fullname" .) ) }} +{{- if $secret }} +{{- index $secret "data" "admin-password" }} +{{- else }} +{{- (randAlphaNum 40) | b64enc | quote }} +{{- end }} +{{- end }} + +{{/* +Return the appropriate apiVersion for rbac. +*/}} +{{- define "grafana.rbac.apiVersion" -}} +{{- if $.Capabilities.APIVersions.Has "rbac.authorization.k8s.io/v1" }} +{{- print "rbac.authorization.k8s.io/v1" }} +{{- else }} +{{- print "rbac.authorization.k8s.io/v1beta1" }} +{{- end }} +{{- end }} + +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "grafana.ingress.apiVersion" -}} +{{- if and ($.Capabilities.APIVersions.Has "networking.k8s.io/v1") (semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version) }} +{{- print "networking.k8s.io/v1" }} +{{- else if $.Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" }} +{{- print "networking.k8s.io/v1beta1" }} +{{- else }} +{{- print "extensions/v1beta1" }} +{{- end }} +{{- end }} + +{{/* +Return the appropriate apiVersion for Horizontal Pod Autoscaler. +*/}} +{{- define "grafana.hpa.apiVersion" -}} +{{- if $.Capabilities.APIVersions.Has "autoscaling/v2/HorizontalPodAutoscaler" }} +{{- print "autoscaling/v2" }} +{{- else if $.Capabilities.APIVersions.Has "autoscaling/v2beta2/HorizontalPodAutoscaler" }} +{{- print "autoscaling/v2beta2" }} +{{- else }} +{{- print "autoscaling/v2beta1" }} +{{- end }} +{{- end }} + +{{/* +Return the appropriate apiVersion for podDisruptionBudget. +*/}} +{{- define "grafana.podDisruptionBudget.apiVersion" -}} +{{- if $.Capabilities.APIVersions.Has "policy/v1/PodDisruptionBudget" }} +{{- print "policy/v1" }} +{{- else }} +{{- print "policy/v1beta1" }} +{{- end }} +{{- end }} + +{{/* +Return if ingress is stable. +*/}} +{{- define "grafana.ingress.isStable" -}} +{{- eq (include "grafana.ingress.apiVersion" .) "networking.k8s.io/v1" }} +{{- end }} + +{{/* +Return if ingress supports ingressClassName. +*/}} +{{- define "grafana.ingress.supportsIngressClassName" -}} +{{- or (eq (include "grafana.ingress.isStable" .) "true") (and (eq (include "grafana.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) }} +{{- end }} + +{{/* +Return if ingress supports pathType. +*/}} +{{- define "grafana.ingress.supportsPathType" -}} +{{- or (eq (include "grafana.ingress.isStable" .) "true") (and (eq (include "grafana.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) }} +{{- end }} + +{{/* +Formats imagePullSecrets. Input is (dict "root" . "imagePullSecrets" .{specific imagePullSecrets}) +*/}} +{{- define "grafana.imagePullSecrets" -}} +{{- $root := .root }} +{{- range (concat .root.Values.global.imagePullSecrets .imagePullSecrets) }} +{{- if eq (typeOf .) "map[string]interface {}" }} +- {{ toYaml (dict "name" (tpl .name $root)) | trim }} +{{- else }} +- name: {{ tpl . $root }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/_pod.tpl b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/_pod.tpl new file mode 100644 index 0000000..762603d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/_pod.tpl @@ -0,0 +1,1159 @@ +{{- define "grafana.pod" -}} +{{- $sts := list "sts" "StatefulSet" "statefulset" -}} +{{- $root := . -}} +{{- with .Values.schedulerName }} +schedulerName: "{{ . }}" +{{- end }} +serviceAccountName: {{ include "grafana.serviceAccountName" . }} +automountServiceAccountToken: {{ .Values.serviceAccount.autoMount }} +{{- with .Values.securityContext }} +securityContext: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.hostAliases }} +hostAliases: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.priorityClassName }} +priorityClassName: {{ . }} +{{- end }} +{{- if ( or .Values.persistence.enabled .Values.dashboards .Values.extraInitContainers (and .Values.sidecar.datasources.enabled .Values.sidecar.datasources.initDatasources) (and .Values.sidecar.notifiers.enabled .Values.sidecar.notifiers.initNotifiers)) }} +initContainers: +{{- end }} +{{- if ( and .Values.persistence.enabled .Values.initChownData.enabled ) }} + - name: init-chown-data + {{- if .Values.initChownData.image.sha }} + image: "{{ .Values.initChownData.image.repository }}:{{ .Values.initChownData.image.tag }}@sha256:{{ .Values.initChownData.image.sha }}" + {{- else }} + image: "{{ .Values.initChownData.image.repository }}:{{ .Values.initChownData.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.initChownData.image.pullPolicy }} + {{- with .Values.initChownData.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + command: + - chown + - -R + - {{ .Values.securityContext.runAsUser }}:{{ .Values.securityContext.runAsGroup }} + - /var/lib/grafana + {{- with .Values.initChownData.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: storage + mountPath: "/var/lib/grafana" + {{- with .Values.persistence.subPath }} + subPath: {{ tpl . $root }} + {{- end }} +{{- end }} +{{- if .Values.dashboards }} + - name: download-dashboards + {{- if .Values.downloadDashboardsImage.sha }} + image: "{{ .Values.downloadDashboardsImage.repository }}:{{ .Values.downloadDashboardsImage.tag }}@sha256:{{ .Values.downloadDashboardsImage.sha }}" + {{- else }} + image: "{{ .Values.downloadDashboardsImage.repository }}:{{ .Values.downloadDashboardsImage.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.downloadDashboardsImage.pullPolicy }} + command: ["/bin/sh"] + args: [ "-c", "mkdir -p /var/lib/grafana/dashboards/default && /bin/sh -x /etc/grafana/download_dashboards.sh" ] + {{- with .Values.downloadDashboards.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + env: + {{- range $key, $value := .Values.downloadDashboards.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- range $key, $value := .Values.downloadDashboards.envValueFrom }} + - name: {{ $key | quote }} + valueFrom: + {{- tpl (toYaml $value) $ | nindent 10 }} + {{- end }} + {{- with .Values.downloadDashboards.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.downloadDashboards.envFromSecret }} + envFrom: + - secretRef: + name: {{ tpl . $root }} + {{- end }} + volumeMounts: + - name: config + mountPath: "/etc/grafana/download_dashboards.sh" + subPath: download_dashboards.sh + - name: storage + mountPath: "/var/lib/grafana" + {{- with .Values.persistence.subPath }} + subPath: {{ tpl . $root }} + {{- end }} + {{- range .Values.extraSecretMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + readOnly: {{ .readOnly }} + {{- end }} +{{- end }} +{{- if and .Values.sidecar.datasources.enabled .Values.sidecar.datasources.initDatasources }} + - name: {{ include "grafana.name" . }}-init-sc-datasources + {{- if .Values.sidecar.image.sha }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.datasources.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.datasources.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: "LIST" + - name: LABEL + value: "{{ .Values.sidecar.datasources.label }}" + {{- with .Values.sidecar.datasources.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.datasources.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.datasources.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/datasources" + - name: RESOURCE + value: {{ quote .Values.sidecar.datasources.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- if .Values.sidecar.datasources.searchNamespace }} + - name: NAMESPACE + value: "{{ tpl (.Values.sidecar.datasources.searchNamespace | join ",") . }}" + {{- end }} + {{- with .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-datasources-volume + mountPath: "/etc/grafana/provisioning/datasources" +{{- end }} +{{- if and .Values.sidecar.notifiers.enabled .Values.sidecar.notifiers.initNotifiers }} + - name: {{ include "grafana.name" . }}-init-sc-notifiers + {{- if .Values.sidecar.image.sha }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.notifiers.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.notifiers.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: LIST + - name: LABEL + value: "{{ .Values.sidecar.notifiers.label }}" + {{- with .Values.sidecar.notifiers.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.notifiers.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.notifiers.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/notifiers" + - name: RESOURCE + value: {{ quote .Values.sidecar.notifiers.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.notifiers.searchNamespace }} + - name: NAMESPACE + value: "{{ tpl (. | join ",") $root }}" + {{- end }} + {{- with .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-notifiers-volume + mountPath: "/etc/grafana/provisioning/notifiers" +{{- end}} +{{- with .Values.extraInitContainers }} + {{- tpl (toYaml .) $root | nindent 2 }} +{{- end }} +{{- if or .Values.image.pullSecrets .Values.global.imagePullSecrets }} +imagePullSecrets: + {{- include "grafana.imagePullSecrets" (dict "root" $root "imagePullSecrets" .Values.image.pullSecrets) | nindent 2 }} +{{- end }} +{{- if not .Values.enableKubeBackwardCompatibility }} +enableServiceLinks: {{ .Values.enableServiceLinks }} +{{- end }} +containers: +{{- if .Values.sidecar.alerts.enabled }} + - name: {{ include "grafana.name" . }}-sc-alerts + {{- if .Values.sidecar.image.sha }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.alerts.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.alerts.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: {{ .Values.sidecar.alerts.watchMethod }} + - name: LABEL + value: "{{ .Values.sidecar.alerts.label }}" + {{- with .Values.sidecar.alerts.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.alerts.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.alerts.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/alerting" + - name: RESOURCE + value: {{ quote .Values.sidecar.alerts.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.alerts.searchNamespace }} + - name: NAMESPACE + value: {{ . | join "," | quote }} + {{- end }} + {{- with .Values.sidecar.alerts.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: {{ quote . }} + {{- end }} + {{- with .Values.sidecar.alerts.script }} + - name: SCRIPT + value: {{ quote . }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + {{- if not .Values.sidecar.alerts.skipReload }} + - name: REQ_URL + value: {{ .Values.sidecar.alerts.reloadURL }} + - name: REQ_METHOD + value: POST + {{- end }} + {{- if .Values.sidecar.alerts.watchServerTimeout }} + {{- if ne .Values.sidecar.alerts.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.alerts.watchServerTimeout with .Values.sidecar.alerts.watchMethod %s" .Values.sidecar.alerts.watchMethod) }} + {{- end }} + - name: WATCH_SERVER_TIMEOUT + value: "{{ .Values.sidecar.alerts.watchServerTimeout }}" + {{- end }} + {{- if .Values.sidecar.alerts.watchClientTimeout }} + {{- if ne .Values.sidecar.alerts.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.alerts.watchClientTimeout with .Values.sidecar.alerts.watchMethod %s" .Values.sidecar.alerts.watchMethod) }} + {{- end }} + - name: WATCH_CLIENT_TIMEOUT + value: "{{ .Values.sidecar.alerts.watchClientTimeout }}" + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-alerts-volume + mountPath: "/etc/grafana/provisioning/alerting" +{{- end}} +{{- if .Values.sidecar.dashboards.enabled }} + - name: {{ include "grafana.name" . }}-sc-dashboard + {{- if .Values.sidecar.image.sha }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.dashboards.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.dashboards.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: {{ .Values.sidecar.dashboards.watchMethod }} + - name: LABEL + value: "{{ .Values.sidecar.dashboards.label }}" + {{- with .Values.sidecar.dashboards.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.dashboards.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.dashboards.logLevel }} + {{- end }} + - name: FOLDER + value: "{{ .Values.sidecar.dashboards.folder }}{{- with .Values.sidecar.dashboards.defaultFolderName }}/{{ . }}{{- end }}" + - name: RESOURCE + value: {{ quote .Values.sidecar.dashboards.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.dashboards.searchNamespace }} + - name: NAMESPACE + value: "{{ tpl (. | join ",") $root }}" + {{- end }} + {{- with .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.dashboards.folderAnnotation }} + - name: FOLDER_ANNOTATION + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.dashboards.script }} + - name: SCRIPT + value: "{{ . }}" + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + {{- if not .Values.sidecar.dashboards.skipReload }} + - name: REQ_URL + value: {{ .Values.sidecar.dashboards.reloadURL }} + - name: REQ_METHOD + value: POST + {{- end }} + {{- if .Values.sidecar.dashboards.watchServerTimeout }} + {{- if ne .Values.sidecar.dashboards.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.dashboards.watchServerTimeout with .Values.sidecar.dashboards.watchMethod %s" .Values.sidecar.dashboards.watchMethod) }} + {{- end }} + - name: WATCH_SERVER_TIMEOUT + value: "{{ .Values.sidecar.dashboards.watchServerTimeout }}" + {{- end }} + {{- if .Values.sidecar.dashboards.watchClientTimeout }} + {{- if ne .Values.sidecar.dashboards.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.dashboards.watchClientTimeout with .Values.sidecar.dashboards.watchMethod %s" .Values.sidecar.dashboards.watchMethod) }} + {{- end }} + - name: WATCH_CLIENT_TIMEOUT + value: {{ .Values.sidecar.dashboards.watchClientTimeout | quote }} + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-dashboard-volume + mountPath: {{ .Values.sidecar.dashboards.folder | quote }} + {{- with .Values.sidecar.dashboards.extraMounts }} + {{- toYaml . | trim | nindent 6 }} + {{- end }} +{{- end}} +{{- if .Values.sidecar.datasources.enabled }} + - name: {{ include "grafana.name" . }}-sc-datasources + {{- if .Values.sidecar.image.sha }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.datasources.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.datasources.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: {{ .Values.sidecar.datasources.watchMethod }} + - name: LABEL + value: "{{ .Values.sidecar.datasources.label }}" + {{- with .Values.sidecar.datasources.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.datasources.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.datasources.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/datasources" + - name: RESOURCE + value: {{ quote .Values.sidecar.datasources.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.datasources.searchNamespace }} + - name: NAMESPACE + value: "{{ tpl (. | join ",") $root }}" + {{- end }} + {{- if .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ .Values.sidecar.skipTlsVerify }}" + {{- end }} + {{- if .Values.sidecar.datasources.script }} + - name: SCRIPT + value: "{{ .Values.sidecar.datasources.script }}" + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + {{- if not .Values.sidecar.datasources.skipReload }} + - name: REQ_URL + value: {{ .Values.sidecar.datasources.reloadURL }} + - name: REQ_METHOD + value: POST + {{- end }} + {{- if .Values.sidecar.datasources.watchServerTimeout }} + {{- if ne .Values.sidecar.datasources.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.datasources.watchServerTimeout with .Values.sidecar.datasources.watchMethod %s" .Values.sidecar.datasources.watchMethod) }} + {{- end }} + - name: WATCH_SERVER_TIMEOUT + value: "{{ .Values.sidecar.datasources.watchServerTimeout }}" + {{- end }} + {{- if .Values.sidecar.datasources.watchClientTimeout }} + {{- if ne .Values.sidecar.datasources.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.datasources.watchClientTimeout with .Values.sidecar.datasources.watchMethod %s" .Values.sidecar.datasources.watchMethod) }} + {{- end }} + - name: WATCH_CLIENT_TIMEOUT + value: "{{ .Values.sidecar.datasources.watchClientTimeout }}" + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-datasources-volume + mountPath: "/etc/grafana/provisioning/datasources" +{{- end}} +{{- if .Values.sidecar.notifiers.enabled }} + - name: {{ include "grafana.name" . }}-sc-notifiers + {{- if .Values.sidecar.image.sha }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.notifiers.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.notifiers.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: {{ .Values.sidecar.notifiers.watchMethod }} + - name: LABEL + value: "{{ .Values.sidecar.notifiers.label }}" + {{- with .Values.sidecar.notifiers.labelValue }} + - name: LABEL_VALUE + value: {{ quote . }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.notifiers.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.notifiers.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/notifiers" + - name: RESOURCE + value: {{ quote .Values.sidecar.notifiers.resource }} + {{- if .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ .Values.sidecar.enableUniqueFilenames }}" + {{- end }} + {{- with .Values.sidecar.notifiers.searchNamespace }} + - name: NAMESPACE + value: "{{ tpl (. | join ",") $root }}" + {{- end }} + {{- with .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ . }}" + {{- end }} + {{- if .Values.sidecar.notifiers.script }} + - name: SCRIPT + value: "{{ .Values.sidecar.notifiers.script }}" + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + {{- if not .Values.sidecar.notifiers.skipReload }} + - name: REQ_URL + value: {{ .Values.sidecar.notifiers.reloadURL }} + - name: REQ_METHOD + value: POST + {{- end }} + {{- if .Values.sidecar.notifiers.watchServerTimeout }} + {{- if ne .Values.sidecar.notifiers.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.notifiers.watchServerTimeout with .Values.sidecar.notifiers.watchMethod %s" .Values.sidecar.notifiers.watchMethod) }} + {{- end }} + - name: WATCH_SERVER_TIMEOUT + value: "{{ .Values.sidecar.notifiers.watchServerTimeout }}" + {{- end }} + {{- if .Values.sidecar.notifiers.watchClientTimeout }} + {{- if ne .Values.sidecar.notifiers.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.notifiers.watchClientTimeout with .Values.sidecar.notifiers.watchMethod %s" .Values.sidecar.notifiers.watchMethod) }} + {{- end }} + - name: WATCH_CLIENT_TIMEOUT + value: "{{ .Values.sidecar.notifiers.watchClientTimeout }}" + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-notifiers-volume + mountPath: "/etc/grafana/provisioning/notifiers" +{{- end}} +{{- if .Values.sidecar.plugins.enabled }} + - name: {{ include "grafana.name" . }}-sc-plugins + {{- if .Values.sidecar.image.sha }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}@sha256:{{ .Values.sidecar.image.sha }}" + {{- else }} + image: "{{ .Values.sidecar.image.repository }}:{{ .Values.sidecar.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }} + env: + {{- range $key, $value := .Values.sidecar.plugins.env }} + - name: "{{ $key }}" + value: "{{ $value }}" + {{- end }} + {{- if .Values.sidecar.plugins.ignoreAlreadyProcessed }} + - name: IGNORE_ALREADY_PROCESSED + value: "true" + {{- end }} + - name: METHOD + value: {{ .Values.sidecar.plugins.watchMethod }} + - name: LABEL + value: "{{ .Values.sidecar.plugins.label }}" + {{- if .Values.sidecar.plugins.labelValue }} + - name: LABEL_VALUE + value: {{ quote .Values.sidecar.plugins.labelValue }} + {{- end }} + {{- if or .Values.sidecar.logLevel .Values.sidecar.plugins.logLevel }} + - name: LOG_LEVEL + value: {{ default .Values.sidecar.logLevel .Values.sidecar.plugins.logLevel }} + {{- end }} + - name: FOLDER + value: "/etc/grafana/provisioning/plugins" + - name: RESOURCE + value: {{ quote .Values.sidecar.plugins.resource }} + {{- with .Values.sidecar.enableUniqueFilenames }} + - name: UNIQUE_FILENAMES + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.plugins.searchNamespace }} + - name: NAMESPACE + value: "{{ tpl (. | join ",") $root }}" + {{- end }} + {{- with .Values.sidecar.plugins.script }} + - name: SCRIPT + value: "{{ . }}" + {{- end }} + {{- with .Values.sidecar.skipTlsVerify }} + - name: SKIP_TLS_VERIFY + value: "{{ . }}" + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + {{- if not .Values.sidecar.plugins.skipReload }} + - name: REQ_URL + value: {{ .Values.sidecar.plugins.reloadURL }} + - name: REQ_METHOD + value: POST + {{- end }} + {{- if .Values.sidecar.plugins.watchServerTimeout }} + {{- if ne .Values.sidecar.plugins.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.plugins.watchServerTimeout with .Values.sidecar.plugins.watchMethod %s" .Values.sidecar.plugins.watchMethod) }} + {{- end }} + - name: WATCH_SERVER_TIMEOUT + value: "{{ .Values.sidecar.plugins.watchServerTimeout }}" + {{- end }} + {{- if .Values.sidecar.plugins.watchClientTimeout }} + {{- if ne .Values.sidecar.plugins.watchMethod "WATCH" }} + {{- fail (printf "Cannot use .Values.sidecar.plugins.watchClientTimeout with .Values.sidecar.plugins.watchMethod %s" .Values.sidecar.plugins.watchMethod) }} + {{- end }} + - name: WATCH_CLIENT_TIMEOUT + value: "{{ .Values.sidecar.plugins.watchClientTimeout }}" + {{- end }} + {{- with .Values.sidecar.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.sidecar.securityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: sc-plugins-volume + mountPath: "/etc/grafana/provisioning/plugins" +{{- end}} + - name: {{ .Chart.Name }} + {{- if .Values.image.sha }} + image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}@sha256:{{ .Values.image.sha }}" + {{- else }} + image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" + {{- end }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + {{- if .Values.command }} + command: + {{- range .Values.command }} + - {{ . | quote }} + {{- end }} + {{- end }} + {{- if .Values.args }} + args: + {{- range .Values.args }} + - {{ . | quote }} + {{- end }} + {{- end }} + {{- with .Values.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: config + mountPath: "/etc/grafana/grafana.ini" + subPath: grafana.ini + {{- if .Values.ldap.enabled }} + - name: ldap + mountPath: "/etc/grafana/ldap.toml" + subPath: ldap.toml + {{- end }} + {{- range .Values.extraConfigmapMounts }} + - name: {{ tpl .name $root }} + mountPath: {{ tpl .mountPath $root }} + subPath: {{ tpl (.subPath | default "") $root }} + readOnly: {{ .readOnly }} + {{- end }} + - name: storage + mountPath: "/var/lib/grafana" + {{- with .Values.persistence.subPath }} + subPath: {{ tpl . $root }} + {{- end }} + {{- with .Values.dashboards }} + {{- range $provider, $dashboards := . }} + {{- range $key, $value := $dashboards }} + {{- if (or (hasKey $value "json") (hasKey $value "file")) }} + - name: dashboards-{{ $provider }} + mountPath: "/var/lib/grafana/dashboards/{{ $provider }}/{{ $key }}.json" + subPath: "{{ $key }}.json" + {{- end }} + {{- end }} + {{- end }} + {{- end }} + {{- with .Values.dashboardsConfigMaps }} + {{- range (keys . | sortAlpha) }} + - name: dashboards-{{ . }} + mountPath: "/var/lib/grafana/dashboards/{{ . }}" + {{- end }} + {{- end }} + {{- with .Values.datasources }} + {{- range (keys . | sortAlpha) }} + - name: config + mountPath: "/etc/grafana/provisioning/datasources/{{ . }}" + subPath: {{ . | quote }} + {{- end }} + {{- end }} + {{- with .Values.notifiers }} + {{- range (keys . | sortAlpha) }} + - name: config + mountPath: "/etc/grafana/provisioning/notifiers/{{ . }}" + subPath: {{ . | quote }} + {{- end }} + {{- end }} + {{- with .Values.alerting }} + {{- range (keys . | sortAlpha) }} + - name: config + mountPath: "/etc/grafana/provisioning/alerting/{{ . }}" + subPath: {{ . | quote }} + {{- end }} + {{- end }} + {{- with .Values.dashboardProviders }} + {{- range (keys . | sortAlpha) }} + - name: config + mountPath: "/etc/grafana/provisioning/dashboards/{{ . }}" + subPath: {{ . | quote }} + {{- end }} + {{- end }} + {{- with .Values.sidecar.alerts.enabled }} + - name: sc-alerts-volume + mountPath: "/etc/grafana/provisioning/alerting" + {{- end}} + {{- if .Values.sidecar.dashboards.enabled }} + - name: sc-dashboard-volume + mountPath: {{ .Values.sidecar.dashboards.folder | quote }} + {{- if .Values.sidecar.dashboards.SCProvider }} + - name: sc-dashboard-provider + mountPath: "/etc/grafana/provisioning/dashboards/sc-dashboardproviders.yaml" + subPath: provider.yaml + {{- end}} + {{- end}} + {{- if .Values.sidecar.datasources.enabled }} + - name: sc-datasources-volume + mountPath: "/etc/grafana/provisioning/datasources" + {{- end}} + {{- if .Values.sidecar.plugins.enabled }} + - name: sc-plugins-volume + mountPath: "/etc/grafana/provisioning/plugins" + {{- end}} + {{- if .Values.sidecar.notifiers.enabled }} + - name: sc-notifiers-volume + mountPath: "/etc/grafana/provisioning/notifiers" + {{- end}} + {{- range .Values.extraSecretMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + readOnly: {{ .readOnly }} + subPath: {{ .subPath | default "" }} + {{- end }} + {{- range .Values.extraVolumeMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath | default "" }} + readOnly: {{ .readOnly }} + {{- end }} + {{- range .Values.extraEmptyDirMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + {{- end }} + ports: + - name: {{ .Values.podPortName }} + containerPort: {{ .Values.service.targetPort }} + protocol: TCP + - name: {{ .Values.gossipPortName }}-tcp + containerPort: 9094 + protocol: TCP + - name: {{ .Values.gossipPortName }}-udp + containerPort: 9094 + protocol: UDP + env: + - name: POD_IP + valueFrom: + fieldRef: + fieldPath: status.podIP + {{- if and (not .Values.env.GF_SECURITY_ADMIN_USER) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: GF_SECURITY_ADMIN_USER + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.userKey | default "admin-user" }} + {{- end }} + {{- if and (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + - name: GF_SECURITY_ADMIN_PASSWORD + valueFrom: + secretKeyRef: + name: {{ (tpl .Values.admin.existingSecret .) | default (include "grafana.fullname" .) }} + key: {{ .Values.admin.passwordKey | default "admin-password" }} + {{- end }} + {{- if .Values.plugins }} + - name: GF_INSTALL_PLUGINS + valueFrom: + configMapKeyRef: + name: {{ include "grafana.fullname" . }} + key: plugins + {{- end }} + {{- if .Values.smtp.existingSecret }} + - name: GF_SMTP_USER + valueFrom: + secretKeyRef: + name: {{ .Values.smtp.existingSecret }} + key: {{ .Values.smtp.userKey | default "user" }} + - name: GF_SMTP_PASSWORD + valueFrom: + secretKeyRef: + name: {{ .Values.smtp.existingSecret }} + key: {{ .Values.smtp.passwordKey | default "password" }} + {{- end }} + {{- if .Values.imageRenderer.enabled }} + - name: GF_RENDERING_SERVER_URL + value: http://{{ include "grafana.fullname" . }}-image-renderer.{{ include "grafana.namespace" . }}:{{ .Values.imageRenderer.service.port }}/render + - name: GF_RENDERING_CALLBACK_URL + value: {{ .Values.imageRenderer.grafanaProtocol }}://{{ include "grafana.fullname" . }}.{{ include "grafana.namespace" . }}:{{ .Values.service.port }}/{{ .Values.imageRenderer.grafanaSubPath }} + {{- end }} + - name: GF_PATHS_DATA + value: {{ (get .Values "grafana.ini").paths.data }} + - name: GF_PATHS_LOGS + value: {{ (get .Values "grafana.ini").paths.logs }} + - name: GF_PATHS_PLUGINS + value: {{ (get .Values "grafana.ini").paths.plugins }} + - name: GF_PATHS_PROVISIONING + value: {{ (get .Values "grafana.ini").paths.provisioning }} + {{- range $key, $value := .Values.envValueFrom }} + - name: {{ $key | quote }} + valueFrom: + {{- tpl (toYaml $value) $ | nindent 10 }} + {{- end }} + {{- range $key, $value := .Values.env }} + - name: "{{ tpl $key $ }}" + value: "{{ tpl (print $value) $ }}" + {{- end }} + {{- if or .Values.envFromSecret (or .Values.envRenderSecret .Values.envFromSecrets) .Values.envFromConfigMaps }} + envFrom: + {{- if .Values.envFromSecret }} + - secretRef: + name: {{ tpl .Values.envFromSecret . }} + {{- end }} + {{- if .Values.envRenderSecret }} + - secretRef: + name: {{ include "grafana.fullname" . }}-env + {{- end }} + {{- range .Values.envFromSecrets }} + - secretRef: + name: {{ tpl .name $ }} + optional: {{ .optional | default false }} + {{- end }} + {{- range .Values.envFromConfigMaps }} + - configMapRef: + name: {{ tpl .name $ }} + optional: {{ .optional | default false }} + {{- end }} + {{- end }} + {{- with .Values.livenessProbe }} + livenessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.lifecycleHooks }} + lifecycle: + {{- tpl (toYaml .) $root | nindent 6 }} + {{- end }} + {{- with .Values.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} +{{- with .Values.extraContainers }} + {{- tpl . $ | nindent 2 }} +{{- end }} +{{- with .Values.nodeSelector }} +nodeSelector: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.affinity }} +affinity: + {{- tpl (toYaml .) $root | nindent 2 }} +{{- end }} +{{- with .Values.topologySpreadConstraints }} +topologySpreadConstraints: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.tolerations }} +tolerations: + {{- toYaml . | nindent 2 }} +{{- end }} +volumes: + - name: config + configMap: + name: {{ include "grafana.fullname" . }} + {{- range .Values.extraConfigmapMounts }} + - name: {{ tpl .name $root }} + configMap: + name: {{ tpl .configMap $root }} + {{- with .items }} + items: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + {{- if .Values.dashboards }} + {{- range (keys .Values.dashboards | sortAlpha) }} + - name: dashboards-{{ . }} + configMap: + name: {{ include "grafana.fullname" $ }}-dashboards-{{ . }} + {{- end }} + {{- end }} + {{- if .Values.dashboardsConfigMaps }} + {{- range $provider, $name := .Values.dashboardsConfigMaps }} + - name: dashboards-{{ $provider }} + configMap: + name: {{ tpl $name $root }} + {{- end }} + {{- end }} + {{- if .Values.ldap.enabled }} + - name: ldap + secret: + {{- if .Values.ldap.existingSecret }} + secretName: {{ .Values.ldap.existingSecret }} + {{- else }} + secretName: {{ include "grafana.fullname" . }} + {{- end }} + items: + - key: ldap-toml + path: ldap.toml + {{- end }} + {{- if and .Values.persistence.enabled (eq .Values.persistence.type "pvc") }} + - name: storage + persistentVolumeClaim: + claimName: {{ tpl (.Values.persistence.existingClaim | default (include "grafana.fullname" .)) . }} + {{- else if and .Values.persistence.enabled (has .Values.persistence.type $sts) }} + {{/* nothing */}} + {{- else }} + - name: storage + {{- if .Values.persistence.inMemory.enabled }} + emptyDir: + medium: Memory + {{- with .Values.persistence.inMemory.sizeLimit }} + sizeLimit: {{ . }} + {{- end }} + {{- else }} + emptyDir: {} + {{- end }} + {{- end }} + {{- if .Values.sidecar.alerts.enabled }} + - name: sc-alerts-volume + emptyDir: + {{- with .Values.sidecar.alerts.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- end }} + {{- if .Values.sidecar.dashboards.enabled }} + - name: sc-dashboard-volume + emptyDir: + {{- with .Values.sidecar.dashboards.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- if .Values.sidecar.dashboards.SCProvider }} + - name: sc-dashboard-provider + configMap: + name: {{ include "grafana.fullname" . }}-config-dashboards + {{- end }} + {{- end }} + {{- if .Values.sidecar.datasources.enabled }} + - name: sc-datasources-volume + emptyDir: + {{- with .Values.sidecar.datasources.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- end }} + {{- if .Values.sidecar.plugins.enabled }} + - name: sc-plugins-volume + emptyDir: + {{- with .Values.sidecar.plugins.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- end }} + {{- if .Values.sidecar.notifiers.enabled }} + - name: sc-notifiers-volume + emptyDir: + {{- with .Values.sidecar.notifiers.sizeLimit }} + sizeLimit: {{ . }} + {{- else }} + {} + {{- end }} + {{- end }} + {{- range .Values.extraSecretMounts }} + {{- if .secretName }} + - name: {{ .name }} + secret: + secretName: {{ .secretName }} + defaultMode: {{ .defaultMode }} + {{- with .items }} + items: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- else if .projected }} + - name: {{ .name }} + projected: + {{- toYaml .projected | nindent 6 }} + {{- else if .csi }} + - name: {{ .name }} + csi: + {{- toYaml .csi | nindent 6 }} + {{- end }} + {{- end }} + {{- range .Values.extraVolumeMounts }} + - name: {{ .name }} + {{- if .existingClaim }} + persistentVolumeClaim: + claimName: {{ .existingClaim }} + {{- else if .hostPath }} + hostPath: + path: {{ .hostPath }} + {{- else if .csi }} + csi: + {{- toYaml .data | nindent 6 }} + {{- else }} + emptyDir: {} + {{- end }} + {{- end }} + {{- range .Values.extraEmptyDirMounts }} + - name: {{ .name }} + emptyDir: {} + {{- end }} + {{- with .Values.extraContainerVolumes }} + {{- tpl (toYaml .) $root | nindent 2 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/clusterrole.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/clusterrole.yaml new file mode 100644 index 0000000..2c9a180 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/clusterrole.yaml @@ -0,0 +1,25 @@ +{{- if and .Values.rbac.create (or (not .Values.rbac.namespaced) .Values.rbac.extraClusterRoleRules) (not .Values.rbac.useExistingRole) }} +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "grafana.fullname" . }}-clusterrole +{{- if or .Values.sidecar.dashboards.enabled .Values.rbac.extraClusterRoleRules .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled .Values.sidecar.alerts.enabled }} +rules: + {{- if or .Values.sidecar.dashboards.enabled .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled .Values.sidecar.alerts.enabled }} + - apiGroups: [""] # "" indicates the core API group + resources: ["configmaps", "secrets"] + verbs: ["get", "watch", "list"] + {{- end}} + {{- with .Values.rbac.extraClusterRoleRules }} + {{- toYaml . | nindent 2 }} + {{- end}} +{{- else }} +rules: [] +{{- end}} +{{- end}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/clusterrolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/clusterrolebinding.yaml new file mode 100644 index 0000000..b848e8c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/clusterrolebinding.yaml @@ -0,0 +1,24 @@ +{{- if and .Values.rbac.create (or (not .Values.rbac.namespaced) .Values.rbac.extraClusterRoleRules) }} +kind: ClusterRoleBinding +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ include "grafana.fullname" . }}-clusterrolebinding + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +subjects: + - kind: ServiceAccount + name: {{ include "grafana.serviceAccountName" . }} + namespace: {{ include "grafana.namespace" . }} +roleRef: + kind: ClusterRole + {{- if .Values.rbac.useExistingRole }} + name: {{ .Values.rbac.useExistingRole }} + {{- else }} + name: {{ include "grafana.fullname" . }}-clusterrole + {{- end }} + apiGroup: rbac.authorization.k8s.io +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/configmap-dashboard-provider.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/configmap-dashboard-provider.yaml new file mode 100644 index 0000000..1f706a8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/configmap-dashboard-provider.yaml @@ -0,0 +1,29 @@ +{{- if and .Values.sidecar.dashboards.enabled .Values.sidecar.dashboards.SCProvider }} +apiVersion: v1 +kind: ConfigMap +metadata: + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "grafana.fullname" . }}-config-dashboards + namespace: {{ include "grafana.namespace" . }} +data: + provider.yaml: |- + apiVersion: 1 + providers: + - name: '{{ .Values.sidecar.dashboards.provider.name }}' + orgId: {{ .Values.sidecar.dashboards.provider.orgid }} + {{- if not .Values.sidecar.dashboards.provider.foldersFromFilesStructure }} + folder: '{{ .Values.sidecar.dashboards.provider.folder }}' + {{- end }} + type: {{ .Values.sidecar.dashboards.provider.type }} + disableDeletion: {{ .Values.sidecar.dashboards.provider.disableDelete }} + allowUiUpdates: {{ .Values.sidecar.dashboards.provider.allowUiUpdates }} + updateIntervalSeconds: {{ .Values.sidecar.dashboards.provider.updateIntervalSeconds | default 30 }} + options: + foldersFromFilesStructure: {{ .Values.sidecar.dashboards.provider.foldersFromFilesStructure }} + path: {{ .Values.sidecar.dashboards.folder }}{{- with .Values.sidecar.dashboards.defaultFolderName }}/{{ . }}{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/configmap.yaml new file mode 100644 index 0000000..b5f21e8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/configmap.yaml @@ -0,0 +1,138 @@ +{{- if .Values.createConfigmap }} +{{- $files := .Files }} +{{- $root := . -}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +data: + {{- with .Values.plugins }} + plugins: {{ join "," . }} + {{- end }} + grafana.ini: | + {{- range $elem, $elemVal := index .Values "grafana.ini" }} + {{- if not (kindIs "map" $elemVal) }} + {{- if kindIs "invalid" $elemVal }} + {{ $elem }} = + {{- else if kindIs "string" $elemVal }} + {{ $elem }} = {{ tpl $elemVal $ }} + {{- else }} + {{ $elem }} = {{ $elemVal }} + {{- end }} + {{- end }} + {{- end }} + {{- range $key, $value := index .Values "grafana.ini" }} + {{- if kindIs "map" $value }} + [{{ $key }}] + {{- range $elem, $elemVal := $value }} + {{- if kindIs "invalid" $elemVal }} + {{ $elem }} = + {{- else if kindIs "string" $elemVal }} + {{ $elem }} = {{ tpl $elemVal $ }} + {{- else }} + {{ $elem }} = {{ $elemVal }} + {{- end }} + {{- end }} + {{- end }} + {{- end }} + + {{- range $key, $value := .Values.datasources }} + {{- $key | nindent 2 }}: | + {{- tpl (toYaml $value | nindent 4) $root }} + {{- end }} + + {{- range $key, $value := .Values.notifiers }} + {{- $key | nindent 2 }}: | + {{- toYaml $value | nindent 4 }} + {{- end }} + + {{- range $key, $value := .Values.alerting }} + {{- if (hasKey $value "file") }} + {{- $key | nindent 2 }}: + {{- toYaml ( $files.Get $value.file ) | nindent 4}} + {{- else }} + {{- $key | nindent 2 }}: | + {{- tpl (toYaml $value | nindent 4) $root }} + {{- end }} + {{- end }} + + {{- range $key, $value := .Values.dashboardProviders }} + {{- $key | nindent 2 }}: | + {{- toYaml $value | nindent 4 }} + {{- end }} + +{{- if .Values.dashboards }} + download_dashboards.sh: | + #!/usr/bin/env sh + set -euf + {{- if .Values.dashboardProviders }} + {{- range $key, $value := .Values.dashboardProviders }} + {{- range $value.providers }} + mkdir -p {{ .options.path }} + {{- end }} + {{- end }} + {{- end }} + {{ $dashboardProviders := .Values.dashboardProviders }} + {{- range $provider, $dashboards := .Values.dashboards }} + {{- range $key, $value := $dashboards }} + {{- if (or (hasKey $value "gnetId") (hasKey $value "url")) }} + curl -skf \ + --connect-timeout 60 \ + --max-time 60 \ + {{- if not $value.b64content }} + {{- if not $value.acceptHeader }} + -H "Accept: application/json" \ + {{- else }} + -H "Accept: {{ $value.acceptHeader }}" \ + {{- end }} + {{- if $value.token }} + -H "Authorization: token {{ $value.token }}" \ + {{- end }} + {{- if $value.bearerToken }} + -H "Authorization: Bearer {{ $value.bearerToken }}" \ + {{- end }} + {{- if $value.basic }} + -H "Authorization: Basic {{ $value.basic }}" \ + {{- end }} + {{- if $value.gitlabToken }} + -H "PRIVATE-TOKEN: {{ $value.gitlabToken }}" \ + {{- end }} + -H "Content-Type: application/json;charset=UTF-8" \ + {{- end }} + {{- $dpPath := "" -}} + {{- range $kd := (index $dashboardProviders "dashboardproviders.yaml").providers }} + {{- if eq $kd.name $provider }} + {{- $dpPath = $kd.options.path }} + {{- end }} + {{- end }} + {{- if $value.url }} + "{{ $value.url }}" \ + {{- else }} + "https://grafana.com/api/dashboards/{{ $value.gnetId }}/revisions/{{- if $value.revision -}}{{ $value.revision }}{{- else -}}1{{- end -}}/download" \ + {{- end }} + {{- if $value.datasource }} + {{- if kindIs "string" $value.datasource }} + | sed '/-- .* --/! s/"datasource":.*,/"datasource": "{{ $value.datasource }}",/g' \ + {{- end }} + {{- if kindIs "slice" $value.datasource }} + {{- range $value.datasource }} + | sed '/-- .* --/! s/${{"{"}}{{ .name }}}/{{ .value }}/g' \ + {{- end }} + {{- end }} + {{- end }} + {{- if $value.b64content }} + | base64 -d \ + {{- end }} + > "{{- if $dpPath -}}{{ $dpPath }}{{- else -}}/var/lib/grafana/dashboards/{{ $provider }}{{- end -}}/{{ $key }}.json" + {{ end }} + {{- end }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/dashboards-json-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/dashboards-json-configmap.yaml new file mode 100644 index 0000000..df0ed0d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/dashboards-json-configmap.yaml @@ -0,0 +1,35 @@ +{{- if .Values.dashboards }} +{{ $files := .Files }} +{{- range $provider, $dashboards := .Values.dashboards }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "grafana.fullname" $ }}-dashboards-{{ $provider }} + namespace: {{ include "grafana.namespace" $ }} + labels: + {{- include "grafana.labels" $ | nindent 4 }} + dashboard-provider: {{ $provider }} +{{- if $dashboards }} +data: +{{- $dashboardFound := false }} +{{- range $key, $value := $dashboards }} +{{- if (or (hasKey $value "json") (hasKey $value "file")) }} +{{- $dashboardFound = true }} + {{- print $key | nindent 2 }}.json: + {{- if hasKey $value "json" }} + |- + {{- $value.json | nindent 6 }} + {{- end }} + {{- if hasKey $value "file" }} + {{- toYaml ( $files.Get $value.file ) | nindent 4}} + {{- end }} +{{- end }} +{{- end }} +{{- if not $dashboardFound }} + {} +{{- end }} +{{- end }} +--- +{{- end }} + +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/deployment.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/deployment.yaml new file mode 100644 index 0000000..bfa26bb --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/deployment.yaml @@ -0,0 +1,51 @@ +{{- if (and (not .Values.useStatefulSet) (or (not .Values.persistence.enabled) (eq .Values.persistence.type "pvc"))) }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if and (not .Values.autoscaling.enabled) (.Values.replicas) }} + replicas: {{ .Values.replicas }} + {{- end }} + revisionHistoryLimit: {{ .Values.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} + {{- with .Values.deploymentStrategy }} + strategy: + {{- toYaml . | trim | nindent 4 }} + {{- end }} + template: + metadata: + labels: + {{- include "grafana.selectorLabels" . | nindent 8 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + checksum/dashboards-json-config: {{ include (print $.Template.BasePath "/dashboards-json-configmap.yaml") . | sha256sum }} + checksum/sc-dashboard-provider-config: {{ include (print $.Template.BasePath "/configmap-dashboard-provider.yaml") . | sha256sum }} + {{- if and (or (and (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD)) (and .Values.ldap.enabled (not .Values.ldap.existingSecret))) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }} + {{- end }} + {{- if .Values.envRenderSecret }} + checksum/secret-env: {{ include (print $.Template.BasePath "/secret-env.yaml") . | sha256sum }} + {{- end }} + kubectl.kubernetes.io/default-container: {{ .Chart.Name }} + {{- with .Values.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- include "grafana.pod" . | nindent 6 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/extra-manifests.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/extra-manifests.yaml new file mode 100644 index 0000000..a9bb3b6 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/extra-manifests.yaml @@ -0,0 +1,4 @@ +{{ range .Values.extraObjects }} +--- +{{ tpl (toYaml .) $ }} +{{ end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/headless-service.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/headless-service.yaml new file mode 100644 index 0000000..3028589 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/headless-service.yaml @@ -0,0 +1,22 @@ +{{- $sts := list "sts" "StatefulSet" "statefulset" -}} +{{- if or .Values.headlessService (and .Values.persistence.enabled (not .Values.persistence.existingClaim) (has .Values.persistence.type $sts)) }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "grafana.fullname" . }}-headless + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + clusterIP: None + selector: + {{- include "grafana.selectorLabels" . | nindent 4 }} + type: ClusterIP + ports: + - name: {{ .Values.gossipPortName }}-tcp + port: 9094 +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/hpa.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/hpa.yaml new file mode 100644 index 0000000..46bbcb4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/hpa.yaml @@ -0,0 +1,52 @@ +{{- $sts := list "sts" "StatefulSet" "statefulset" -}} +{{- if .Values.autoscaling.enabled }} +apiVersion: {{ include "grafana.hpa.apiVersion" . }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + app.kubernetes.io/name: {{ include "grafana.name" . }} + helm.sh/chart: {{ include "grafana.chart" . }} + app.kubernetes.io/managed-by: {{ .Release.Service }} + app.kubernetes.io/instance: {{ .Release.Name }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + {{- if has .Values.persistence.type $sts }} + kind: StatefulSet + {{- else }} + kind: Deployment + {{- end }} + name: {{ include "grafana.fullname" . }} + minReplicas: {{ .Values.autoscaling.minReplicas }} + maxReplicas: {{ .Values.autoscaling.maxReplicas }} + metrics: + {{- if .Values.autoscaling.targetMemory }} + - type: Resource + resource: + name: memory + {{- if eq (include "grafana.hpa.apiVersion" .) "autoscaling/v2beta1" }} + targetAverageUtilization: {{ .Values.autoscaling.targetMemory }} + {{- else }} + target: + type: Utilization + averageUtilization: {{ .Values.autoscaling.targetMemory }} + {{- end }} + {{- end }} + {{- if .Values.autoscaling.targetCPU }} + - type: Resource + resource: + name: cpu + {{- if eq (include "grafana.hpa.apiVersion" .) "autoscaling/v2beta1" }} + targetAverageUtilization: {{ .Values.autoscaling.targetCPU }} + {{- else }} + target: + type: Utilization + averageUtilization: {{ .Values.autoscaling.targetCPU }} + {{- end }} + {{- end }} + {{- if .Values.autoscaling.behavior }} + behavior: {{ toYaml .Values.autoscaling.behavior | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-deployment.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-deployment.yaml new file mode 100644 index 0000000..93d20e8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-deployment.yaml @@ -0,0 +1,130 @@ +{{ if .Values.imageRenderer.enabled }} +{{- $root := . -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "grafana.fullname" . }}-image-renderer + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.imageRenderer.labels" . | nindent 4 }} + {{- with .Values.imageRenderer.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.imageRenderer.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if and (not .Values.imageRenderer.autoscaling.enabled) (.Values.imageRenderer.replicas) }} + replicas: {{ .Values.imageRenderer.replicas }} + {{- end }} + revisionHistoryLimit: {{ .Values.imageRenderer.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 6 }} + + {{- with .Values.imageRenderer.deploymentStrategy }} + strategy: + {{- toYaml . | trim | nindent 4 }} + {{- end }} + template: + metadata: + labels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 8 }} + {{- with .Values.imageRenderer.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + {{- with .Values.imageRenderer.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- with .Values.imageRenderer.schedulerName }} + schedulerName: "{{ . }}" + {{- end }} + {{- with .Values.imageRenderer.serviceAccountName }} + serviceAccountName: "{{ . }}" + {{- end }} + {{- with .Values.imageRenderer.securityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.imageRenderer.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.imageRenderer.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.imageRenderer.image.pullSecrets }} + imagePullSecrets: + {{- range . }} + - name: {{ tpl . $root }} + {{- end}} + {{- end }} + containers: + - name: {{ .Chart.Name }}-image-renderer + {{- if .Values.imageRenderer.image.sha }} + image: "{{ .Values.imageRenderer.image.repository }}:{{ .Values.imageRenderer.image.tag }}@sha256:{{ .Values.imageRenderer.image.sha }}" + {{- else }} + image: "{{ .Values.imageRenderer.image.repository }}:{{ .Values.imageRenderer.image.tag }}" + {{- end }} + imagePullPolicy: {{ .Values.imageRenderer.image.pullPolicy }} + {{- if .Values.imageRenderer.command }} + command: + {{- range .Values.imageRenderer.command }} + - {{ . }} + {{- end }} + {{- end}} + ports: + - name: {{ .Values.imageRenderer.service.portName }} + containerPort: {{ .Values.imageRenderer.service.targetPort }} + protocol: TCP + livenessProbe: + httpGet: + path: / + port: {{ .Values.imageRenderer.service.portName }} + env: + - name: HTTP_PORT + value: {{ .Values.imageRenderer.service.targetPort | quote }} + {{- if .Values.imageRenderer.serviceMonitor.enabled }} + - name: ENABLE_METRICS + value: "true" + {{- end }} + {{- range $key, $value := .Values.imageRenderer.envValueFrom }} + - name: {{ $key | quote }} + valueFrom: + {{- tpl (toYaml $value) $ | nindent 16 }} + {{- end }} + {{- range $key, $value := .Values.imageRenderer.env }} + - name: {{ $key | quote }} + value: {{ $value | quote }} + {{- end }} + {{- with .Values.imageRenderer.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - mountPath: /tmp + name: image-renderer-tmpfs + {{- with .Values.imageRenderer.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.imageRenderer.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.imageRenderer.affinity }} + affinity: + {{- tpl (toYaml .) $root | nindent 8 }} + {{- end }} + {{- with .Values.imageRenderer.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: image-renderer-tmpfs + emptyDir: {} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-hpa.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-hpa.yaml new file mode 100644 index 0000000..b0f0059 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-hpa.yaml @@ -0,0 +1,47 @@ +{{- if and .Values.imageRenderer.enabled .Values.imageRenderer.autoscaling.enabled }} +apiVersion: {{ include "grafana.hpa.apiVersion" . }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "grafana.fullname" . }}-image-renderer + namespace: {{ include "grafana.namespace" . }} + labels: + app.kubernetes.io/name: {{ include "grafana.name" . }}-image-renderer + helm.sh/chart: {{ include "grafana.chart" . }} + app.kubernetes.io/managed-by: {{ .Release.Service }} + app.kubernetes.io/instance: {{ .Release.Name }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "grafana.fullname" . }}-image-renderer + minReplicas: {{ .Values.imageRenderer.autoscaling.minReplicas }} + maxReplicas: {{ .Values.imageRenderer.autoscaling.maxReplicas }} + metrics: + {{- if .Values.imageRenderer.autoscaling.targetMemory }} + - type: Resource + resource: + name: memory + {{- if eq (include "grafana.hpa.apiVersion" .) "autoscaling/v2beta1" }} + targetAverageUtilization: {{ .Values.imageRenderer.autoscaling.targetMemory }} + {{- else }} + target: + type: Utilization + averageUtilization: {{ .Values.imageRenderer.autoscaling.targetMemory }} + {{- end }} + {{- end }} + {{- if .Values.imageRenderer.autoscaling.targetCPU }} + - type: Resource + resource: + name: cpu + {{- if eq (include "grafana.hpa.apiVersion" .) "autoscaling/v2beta1" }} + targetAverageUtilization: {{ .Values.imageRenderer.autoscaling.targetCPU }} + {{- else }} + target: + type: Utilization + averageUtilization: {{ .Values.imageRenderer.autoscaling.targetCPU }} + {{- end }} + {{- end }} + {{- if .Values.imageRenderer.autoscaling.behavior }} + behavior: {{ toYaml .Values.imageRenderer.autoscaling.behavior | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-network-policy.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-network-policy.yaml new file mode 100644 index 0000000..d1a0eb3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-network-policy.yaml @@ -0,0 +1,79 @@ +{{- if and .Values.imageRenderer.enabled .Values.imageRenderer.networkPolicy.limitIngress }} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "grafana.fullname" . }}-image-renderer-ingress + namespace: {{ include "grafana.namespace" . }} + annotations: + comment: Limit image-renderer ingress traffic from grafana +spec: + podSelector: + matchLabels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 6 }} + {{- with .Values.imageRenderer.podLabels }} + {{- toYaml . | nindent 6 }} + {{- end }} + + policyTypes: + - Ingress + ingress: + - ports: + - port: {{ .Values.imageRenderer.service.targetPort }} + protocol: TCP + from: + - namespaceSelector: + matchLabels: + kubernetes.io/metadata.name: {{ include "grafana.namespace" . }} + podSelector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 14 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 14 }} + {{- end }} + {{- with .Values.imageRenderer.networkPolicy.extraIngressSelectors -}} + {{ toYaml . | nindent 8 }} + {{- end }} +{{- end }} + +{{- if and .Values.imageRenderer.enabled .Values.imageRenderer.networkPolicy.limitEgress }} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "grafana.fullname" . }}-image-renderer-egress + namespace: {{ include "grafana.namespace" . }} + annotations: + comment: Limit image-renderer egress traffic to grafana +spec: + podSelector: + matchLabels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 6 }} + {{- with .Values.imageRenderer.podLabels }} + {{- toYaml . | nindent 6 }} + {{- end }} + + policyTypes: + - Egress + egress: + # allow dns resolution + - ports: + - port: 53 + protocol: UDP + - port: 53 + protocol: TCP + # talk only to grafana + - ports: + - port: {{ .Values.service.targetPort }} + protocol: TCP + to: + - namespaceSelector: + matchLabels: + name: {{ include "grafana.namespace" . }} + podSelector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 14 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 14 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-service.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-service.yaml new file mode 100644 index 0000000..f8da127 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-service.yaml @@ -0,0 +1,31 @@ +{{- if and .Values.imageRenderer.enabled .Values.imageRenderer.service.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "grafana.fullname" . }}-image-renderer + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.imageRenderer.labels" . | nindent 4 }} + {{- with .Values.imageRenderer.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.imageRenderer.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + {{- with .Values.imageRenderer.service.clusterIP }} + clusterIP: {{ . }} + {{- end }} + ports: + - name: {{ .Values.imageRenderer.service.portName }} + port: {{ .Values.imageRenderer.service.port }} + protocol: TCP + targetPort: {{ .Values.imageRenderer.service.targetPort }} + {{- with .Values.imageRenderer.appProtocol }} + appProtocol: {{ . }} + {{- end }} + selector: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-servicemonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-servicemonitor.yaml new file mode 100644 index 0000000..5d9f09d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/image-renderer-servicemonitor.yaml @@ -0,0 +1,48 @@ +{{- if .Values.imageRenderer.serviceMonitor.enabled }} +--- +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "grafana.fullname" . }}-image-renderer + {{- if .Values.imageRenderer.serviceMonitor.namespace }} + namespace: {{ tpl .Values.imageRenderer.serviceMonitor.namespace . }} + {{- else }} + namespace: {{ include "grafana.namespace" . }} + {{- end }} + labels: + {{- include "grafana.imageRenderer.labels" . | nindent 4 }} + {{- with .Values.imageRenderer.serviceMonitor.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + endpoints: + - port: {{ .Values.imageRenderer.service.portName }} + {{- with .Values.imageRenderer.serviceMonitor.interval }} + interval: {{ . }} + {{- end }} + {{- with .Values.imageRenderer.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + honorLabels: true + path: {{ .Values.imageRenderer.serviceMonitor.path }} + scheme: {{ .Values.imageRenderer.serviceMonitor.scheme }} + {{- with .Values.imageRenderer.serviceMonitor.tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.imageRenderer.serviceMonitor.relabelings }} + relabelings: + {{- toYaml . | nindent 6 }} + {{- end }} + jobLabel: "{{ .Release.Name }}-image-renderer" + selector: + matchLabels: + {{- include "grafana.imageRenderer.selectorLabels" . | nindent 6 }} + namespaceSelector: + matchNames: + - {{ include "grafana.namespace" . }} + {{- with .Values.imageRenderer.serviceMonitor.targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/ingress.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/ingress.yaml new file mode 100644 index 0000000..063cdfa --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/ingress.yaml @@ -0,0 +1,78 @@ +{{- if .Values.ingress.enabled -}} +{{- $ingressApiIsStable := eq (include "grafana.ingress.isStable" .) "true" -}} +{{- $ingressSupportsIngressClassName := eq (include "grafana.ingress.supportsIngressClassName" .) "true" -}} +{{- $ingressSupportsPathType := eq (include "grafana.ingress.supportsPathType" .) "true" -}} +{{- $fullName := include "grafana.fullname" . -}} +{{- $servicePort := .Values.service.port -}} +{{- $ingressPath := .Values.ingress.path -}} +{{- $ingressPathType := .Values.ingress.pathType -}} +{{- $extraPaths := .Values.ingress.extraPaths -}} +apiVersion: {{ include "grafana.ingress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ $fullName }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.ingress.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.ingress.annotations }} + annotations: + {{- range $key, $value := . }} + {{ $key }}: {{ tpl $value $ | quote }} + {{- end }} + {{- end }} +spec: + {{- if and $ingressSupportsIngressClassName .Values.ingress.ingressClassName }} + ingressClassName: {{ .Values.ingress.ingressClassName }} + {{- end -}} + {{- with .Values.ingress.tls }} + tls: + {{- tpl (toYaml .) $ | nindent 4 }} + {{- end }} + rules: + {{- if .Values.ingress.hosts }} + {{- range .Values.ingress.hosts }} + - host: {{ tpl . $ }} + http: + paths: + {{- with $extraPaths }} + {{- toYaml . | nindent 10 }} + {{- end }} + - path: {{ $ingressPath }} + {{- if $ingressSupportsPathType }} + pathType: {{ $ingressPathType }} + {{- end }} + backend: + {{- if $ingressApiIsStable }} + service: + name: {{ $fullName }} + port: + number: {{ $servicePort }} + {{- else }} + serviceName: {{ $fullName }} + servicePort: {{ $servicePort }} + {{- end }} + {{- end }} + {{- else }} + - http: + paths: + - backend: + {{- if $ingressApiIsStable }} + service: + name: {{ $fullName }} + port: + number: {{ $servicePort }} + {{- else }} + serviceName: {{ $fullName }} + servicePort: {{ $servicePort }} + {{- end }} + {{- with $ingressPath }} + path: {{ . }} + {{- end }} + {{- if $ingressSupportsPathType }} + pathType: {{ $ingressPathType }} + {{- end }} + {{- end -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/networkpolicy.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/networkpolicy.yaml new file mode 100644 index 0000000..ea4578b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/networkpolicy.yaml @@ -0,0 +1,52 @@ +{{- if .Values.networkPolicy.enabled }} +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + policyTypes: + {{- if .Values.networkPolicy.ingress }} + - Ingress + {{- end }} + {{- if .Values.networkPolicy.egress.enabled }} + - Egress + {{- end }} + podSelector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} + + {{- if .Values.networkPolicy.egress.enabled }} + egress: + - ports: + {{ .Values.networkPolicy.egress.ports | toJson }} + {{- end }} + {{- if .Values.networkPolicy.ingress }} + ingress: + - ports: + - port: {{ .Values.service.targetPort }} + {{- if not .Values.networkPolicy.allowExternal }} + from: + - podSelector: + matchLabels: + {{ include "grafana.fullname" . }}-client: "true" + {{- with .Values.networkPolicy.explicitNamespacesSelector }} + - namespaceSelector: + {{- toYaml . | nindent 12 }} + {{- end }} + - podSelector: + matchLabels: + {{- include "grafana.labels" . | nindent 14 }} + role: read + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/poddisruptionbudget.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/poddisruptionbudget.yaml new file mode 100644 index 0000000..0525121 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/poddisruptionbudget.yaml @@ -0,0 +1,22 @@ +{{- if .Values.podDisruptionBudget }} +apiVersion: {{ include "grafana.podDisruptionBudget.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .Values.podDisruptionBudget.minAvailable }} + minAvailable: {{ . }} + {{- end }} + {{- with .Values.podDisruptionBudget.maxUnavailable }} + maxUnavailable: {{ . }} + {{- end }} + selector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/podsecuritypolicy.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/podsecuritypolicy.yaml new file mode 100644 index 0000000..eed7af9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/podsecuritypolicy.yaml @@ -0,0 +1,49 @@ +{{- if and .Values.rbac.pspEnabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "grafana.fullname" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + annotations: + seccomp.security.alpha.kubernetes.io/allowedProfileNames: 'docker/default,runtime/default' + seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default' + {{- if .Values.rbac.pspUseAppArmor }} + apparmor.security.beta.kubernetes.io/allowedProfileNames: 'runtime/default' + apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default' + {{- end }} +spec: + privileged: false + allowPrivilegeEscalation: false + requiredDropCapabilities: + # Default set from Docker, with DAC_OVERRIDE and CHOWN + - ALL + volumes: + - 'configMap' + - 'emptyDir' + - 'projected' + - 'csi' + - 'secret' + - 'downwardAPI' + - 'persistentVolumeClaim' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + rule: 'RunAsAny' + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 1 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 1 + max: 65535 + readOnlyRootFilesystem: false +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/pvc.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/pvc.yaml new file mode 100644 index 0000000..eb8f87f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/pvc.yaml @@ -0,0 +1,36 @@ +{{- if and .Values.persistence.enabled (not .Values.persistence.existingClaim) (eq .Values.persistence.type "pvc")}} +apiVersion: v1 +kind: PersistentVolumeClaim +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.persistence.extraPvcLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.persistence.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.persistence.finalizers }} + finalizers: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + accessModes: + {{- range .Values.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + resources: + requests: + storage: {{ .Values.persistence.size | quote }} + {{- with .Values.persistence.storageClassName }} + storageClassName: {{ . }} + {{- end }} + {{- with .Values.persistence.selectorLabels }} + selector: + matchLabels: + {{- toYaml . | nindent 6 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/role.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/role.yaml new file mode 100644 index 0000000..df8ac9a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/role.yaml @@ -0,0 +1,32 @@ +{{- if and .Values.rbac.create (not .Values.rbac.useExistingRole) -}} +apiVersion: {{ include "grafana.rbac.apiVersion" . }} +kind: Role +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- if or .Values.rbac.pspEnabled (and .Values.rbac.namespaced (or .Values.sidecar.dashboards.enabled .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled .Values.rbac.extraRoleRules)) }} +rules: + {{- if and .Values.rbac.pspEnabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} + - apiGroups: ['extensions'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: [{{ include "grafana.fullname" . }}] + {{- end }} + {{- if and .Values.rbac.namespaced (or .Values.sidecar.dashboards.enabled .Values.sidecar.datasources.enabled .Values.sidecar.plugins.enabled) }} + - apiGroups: [""] # "" indicates the core API group + resources: ["configmaps", "secrets"] + verbs: ["get", "watch", "list"] + {{- end }} + {{- with .Values.rbac.extraRoleRules }} + {{- toYaml . | nindent 2 }} + {{- end}} +{{- else }} +rules: [] +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/rolebinding.yaml new file mode 100644 index 0000000..cc07bd9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/rolebinding.yaml @@ -0,0 +1,25 @@ +{{- if .Values.rbac.create }} +apiVersion: {{ include "grafana.rbac.apiVersion" . }} +kind: RoleBinding +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + {{- if .Values.rbac.useExistingRole }} + name: {{ .Values.rbac.useExistingRole }} + {{- else }} + name: {{ include "grafana.fullname" . }} + {{- end }} +subjects: +- kind: ServiceAccount + name: {{ include "grafana.serviceAccountName" . }} + namespace: {{ include "grafana.namespace" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/secret-env.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/secret-env.yaml new file mode 100644 index 0000000..eb14aac --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/secret-env.yaml @@ -0,0 +1,14 @@ +{{- if .Values.envRenderSecret }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "grafana.fullname" . }}-env + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} +type: Opaque +data: +{{- range $key, $val := .Values.envRenderSecret }} + {{ $key }}: {{ tpl ($val | toString) $ | b64enc | quote }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/secret.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/secret.yaml new file mode 100644 index 0000000..5cbd527 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/secret.yaml @@ -0,0 +1,26 @@ +{{- if or (and (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION)) (and .Values.ldap.enabled (not .Values.ldap.existingSecret)) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +type: Opaque +data: + {{- if and (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD) }} + admin-user: {{ .Values.adminUser | b64enc | quote }} + {{- if .Values.adminPassword }} + admin-password: {{ .Values.adminPassword | b64enc | quote }} + {{- else }} + admin-password: {{ include "grafana.password" . }} + {{- end }} + {{- end }} + {{- if not .Values.ldap.existingSecret }} + ldap-toml: {{ tpl .Values.ldap.config $ | b64enc | quote }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/service.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/service.yaml new file mode 100644 index 0000000..43d360b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/service.yaml @@ -0,0 +1,55 @@ +{{- if .Values.service.enabled }} +{{- $root := . }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.service.annotations }} + annotations: + {{- tpl (toYaml . | nindent 4) $root }} + {{- end }} +spec: + {{- if (or (eq .Values.service.type "ClusterIP") (empty .Values.service.type)) }} + type: ClusterIP + {{- with .Values.service.clusterIP }} + clusterIP: {{ . }} + {{- end }} + {{- else if eq .Values.service.type "LoadBalancer" }} + type: {{ .Values.service.type }} + {{- with .Values.service.loadBalancerIP }} + loadBalancerIP: {{ . }} + {{- end }} + {{- with .Values.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- else }} + type: {{ .Values.service.type }} + {{- end }} + {{- with .Values.service.externalIPs }} + externalIPs: + {{- toYaml . | nindent 4 }} + {{- end }} + ports: + - name: {{ .Values.service.portName }} + port: {{ .Values.service.port }} + protocol: TCP + targetPort: {{ .Values.service.targetPort }} + {{- with .Values.service.appProtocol }} + appProtocol: {{ . }} + {{- end }} + {{- if (and (eq .Values.service.type "NodePort") (not (empty .Values.service.nodePort))) }} + nodePort: {{ .Values.service.nodePort }} + {{- end }} + {{- with .Values.extraExposePorts }} + {{- tpl (toYaml . | nindent 4) $root }} + {{- end }} + selector: + {{- include "grafana.selectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/serviceaccount.yaml new file mode 100644 index 0000000..784e71b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/serviceaccount.yaml @@ -0,0 +1,17 @@ +{{- if .Values.serviceAccount.create }} +{{- $root := . -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.serviceAccount.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.serviceAccount.annotations }} + annotations: + {{- tpl (toYaml . | nindent 4) $root }} + {{- end }} + name: {{ include "grafana.serviceAccountName" . }} + namespace: {{ include "grafana.namespace" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/servicemonitor.yaml new file mode 100644 index 0000000..a4e9f00 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/servicemonitor.yaml @@ -0,0 +1,48 @@ +{{- if .Values.serviceMonitor.enabled }} +--- +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "grafana.fullname" . }} + {{- if .Values.serviceMonitor.namespace }} + namespace: {{ tpl .Values.serviceMonitor.namespace . }} + {{- else }} + namespace: {{ include "grafana.namespace" . }} + {{- end }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.serviceMonitor.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + endpoints: + - port: {{ .Values.service.portName }} + {{- with .Values.serviceMonitor.interval }} + interval: {{ . }} + {{- end }} + {{- with .Values.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + honorLabels: true + path: {{ .Values.serviceMonitor.path }} + scheme: {{ .Values.serviceMonitor.scheme }} + {{- with .Values.serviceMonitor.tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.serviceMonitor.relabelings }} + relabelings: + {{- toYaml . | nindent 6 }} + {{- end }} + jobLabel: "{{ .Release.Name }}" + selector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} + namespaceSelector: + matchNames: + - {{ include "grafana.namespace" . }} + {{- with .Values.serviceMonitor.targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/statefulset.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/statefulset.yaml new file mode 100644 index 0000000..e6c944a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/statefulset.yaml @@ -0,0 +1,56 @@ +{{- $sts := list "sts" "StatefulSet" "statefulset" -}} +{{- if (or (.Values.useStatefulSet) (and .Values.persistence.enabled (not .Values.persistence.existingClaim) (has .Values.persistence.type $sts)))}} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "grafana.fullname" . }} + namespace: {{ include "grafana.namespace" . }} + labels: + {{- include "grafana.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.replicas }} + selector: + matchLabels: + {{- include "grafana.selectorLabels" . | nindent 6 }} + serviceName: {{ include "grafana.fullname" . }}-headless + template: + metadata: + labels: + {{- include "grafana.selectorLabels" . | nindent 8 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + checksum/dashboards-json-config: {{ include (print $.Template.BasePath "/dashboards-json-configmap.yaml") . | sha256sum }} + checksum/sc-dashboard-provider-config: {{ include (print $.Template.BasePath "/configmap-dashboard-provider.yaml") . | sha256sum }} + {{- if and (or (and (not .Values.admin.existingSecret) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD__FILE) (not .Values.env.GF_SECURITY_ADMIN_PASSWORD)) (and .Values.ldap.enabled (not .Values.ldap.existingSecret))) (not .Values.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION) }} + checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }} + {{- end }} + kubectl.kubernetes.io/default-container: {{ .Chart.Name }} + {{- with .Values.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- include "grafana.pod" . | nindent 6 }} + {{- if .Values.persistence.enabled}} + volumeClaimTemplates: + - metadata: + name: storage + spec: + accessModes: {{ .Values.persistence.accessModes }} + storageClassName: {{ .Values.persistence.storageClassName }} + resources: + requests: + storage: {{ .Values.persistence.size }} + {{- with .Values.persistence.selectorLabels }} + selector: + matchLabels: + {{- toYaml . | nindent 10 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-configmap.yaml new file mode 100644 index 0000000..01c96c9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-configmap.yaml @@ -0,0 +1,20 @@ +{{- if .Values.testFramework.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "grafana.fullname" . }}-test + namespace: {{ include "grafana.namespace" . }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" + labels: + {{- include "grafana.labels" . | nindent 4 }} +data: + run.sh: |- + @test "Test Health" { + url="http://{{ include "grafana.fullname" . }}/api/health" + + code=$(wget --server-response --spider --timeout 90 --tries 10 ${url} 2>&1 | awk '/^ HTTP/{print $2}') + [ "$code" == "200" ] + } +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-podsecuritypolicy.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-podsecuritypolicy.yaml new file mode 100644 index 0000000..1821772 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-podsecuritypolicy.yaml @@ -0,0 +1,32 @@ +{{- if and (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") .Values.testFramework.enabled .Values.rbac.pspEnabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "grafana.fullname" . }}-test + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" + labels: + {{- include "grafana.labels" . | nindent 4 }} +spec: + allowPrivilegeEscalation: true + privileged: false + hostNetwork: false + hostIPC: false + hostPID: false + fsGroup: + rule: RunAsAny + seLinux: + rule: RunAsAny + supplementalGroups: + rule: RunAsAny + runAsUser: + rule: RunAsAny + volumes: + - configMap + - downwardAPI + - emptyDir + - projected + - csi + - secret +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-role.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-role.yaml new file mode 100644 index 0000000..cb4c782 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-role.yaml @@ -0,0 +1,17 @@ +{{- if and (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") .Values.testFramework.enabled .Values.rbac.pspEnabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ include "grafana.fullname" . }}-test + namespace: {{ include "grafana.namespace" . }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" + labels: + {{- include "grafana.labels" . | nindent 4 }} +rules: + - apiGroups: ['policy'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: [{{ include "grafana.fullname" . }}-test] +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-rolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-rolebinding.yaml new file mode 100644 index 0000000..f40d791 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-rolebinding.yaml @@ -0,0 +1,20 @@ +{{- if and (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") .Values.testFramework.enabled .Values.rbac.pspEnabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "grafana.fullname" . }}-test + namespace: {{ include "grafana.namespace" . }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" + labels: + {{- include "grafana.labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "grafana.fullname" . }}-test +subjects: + - kind: ServiceAccount + name: {{ include "grafana.serviceAccountNameTest" . }} + namespace: {{ include "grafana.namespace" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-serviceaccount.yaml new file mode 100644 index 0000000..38fba35 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test-serviceaccount.yaml @@ -0,0 +1,12 @@ +{{- if and .Values.testFramework.enabled .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + {{- include "grafana.labels" . | nindent 4 }} + name: {{ include "grafana.serviceAccountNameTest" . }} + namespace: {{ include "grafana.namespace" . }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test.yaml new file mode 100644 index 0000000..9fb8842 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/templates/tests/test.yaml @@ -0,0 +1,49 @@ +{{- if .Values.testFramework.enabled }} +{{- $root := . }} +apiVersion: v1 +kind: Pod +metadata: + name: {{ include "grafana.fullname" . }}-test + labels: + {{- include "grafana.labels" . | nindent 4 }} + annotations: + "helm.sh/hook": test-success + "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" + namespace: {{ include "grafana.namespace" . }} +spec: + serviceAccountName: {{ include "grafana.serviceAccountNameTest" . }} + {{- with .Values.testFramework.securityContext }} + securityContext: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- if or .Values.image.pullSecrets .Values.global.imagePullSecrets }} + imagePullSecrets: + {{- include "grafana.imagePullSecrets" (dict "root" $root "imagePullSecrets" .Values.image.pullSecrets) | nindent 4 }} + {{- end }} + {{- with .Values.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.affinity }} + affinity: + {{- tpl (toYaml .) $root | nindent 4 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: + {{- toYaml . | nindent 4 }} + {{- end }} + containers: + - name: {{ .Release.Name }}-test + image: "{{ .Values.testFramework.image}}:{{ .Values.testFramework.tag }}" + imagePullPolicy: "{{ .Values.testFramework.imagePullPolicy}}" + command: ["/opt/bats/bin/bats", "-t", "/tests/run.sh"] + volumeMounts: + - mountPath: /tests + name: tests + readOnly: true + volumes: + - name: tests + configMap: + name: {{ include "grafana.fullname" . }}-test + restartPolicy: Never +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/grafana/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/grafana/values.yaml new file mode 100644 index 0000000..c1ba7df --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/grafana/values.yaml @@ -0,0 +1,1242 @@ +global: + # To help compatibility with other charts which use global.imagePullSecrets. + # Allow either an array of {name: pullSecret} maps (k8s-style), or an array of strings (more common helm-style). + # Can be tempalted. + # global: + # imagePullSecrets: + # - name: pullSecret1 + # - name: pullSecret2 + # or + # global: + # imagePullSecrets: + # - pullSecret1 + # - pullSecret2 + imagePullSecrets: [] + +rbac: + create: true + ## Use an existing ClusterRole/Role (depending on rbac.namespaced false/true) + # useExistingRole: name-of-some-(cluster)role + pspEnabled: false + pspUseAppArmor: false + namespaced: false + extraRoleRules: [] + # - apiGroups: [] + # resources: [] + # verbs: [] + extraClusterRoleRules: [] + # - apiGroups: [] + # resources: [] + # verbs: [] +serviceAccount: + create: true + name: + nameTest: + ## ServiceAccount labels. + labels: {} +## Service account annotations. Can be templated. +# annotations: +# eks.amazonaws.com/role-arn: arn:aws:iam::123456789000:role/iam-role-name-here + autoMount: true + +replicas: 1 + +## Create a headless service for the deployment +headlessService: false + +## Create HorizontalPodAutoscaler object for deployment type +# +autoscaling: + enabled: false + minReplicas: 1 + maxReplicas: 5 + targetCPU: "60" + targetMemory: "" + behavior: {} + +## See `kubectl explain poddisruptionbudget.spec` for more +## ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/ +podDisruptionBudget: {} +# minAvailable: 1 +# maxUnavailable: 1 + +## See `kubectl explain deployment.spec.strategy` for more +## ref: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy +deploymentStrategy: + type: RollingUpdate + +readinessProbe: + httpGet: + path: /api/health + port: 3000 + +livenessProbe: + httpGet: + path: /api/health + port: 3000 + initialDelaySeconds: 60 + timeoutSeconds: 30 + failureThreshold: 10 + +## Use an alternate scheduler, e.g. "stork". +## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ +## +# schedulerName: "default-scheduler" + +image: + repository: docker.io/grafana/grafana + # Overrides the Grafana image tag whose default is the chart appVersion + tag: "" + sha: "" + pullPolicy: IfNotPresent + + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## Can be templated. + ## + pullSecrets: [] + # - myRegistrKeySecretName + +testFramework: + enabled: true + image: docker.io/bats/bats + tag: "v1.4.1" + imagePullPolicy: IfNotPresent + securityContext: {} + +securityContext: + runAsNonRoot: true + runAsUser: 472 + runAsGroup: 472 + fsGroup: 472 + +containerSecurityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + +# Enable creating the grafana configmap +createConfigmap: true + +# Extra configmaps to mount in grafana pods +# Values are templated. +extraConfigmapMounts: [] + # - name: certs-configmap + # mountPath: /etc/grafana/ssl/ + # subPath: certificates.crt # (optional) + # configMap: certs-configmap + # readOnly: true + + +extraEmptyDirMounts: [] + # - name: provisioning-notifiers + # mountPath: /etc/grafana/provisioning/notifiers + + +# Apply extra labels to common labels. +extraLabels: {} + +## Assign a PriorityClassName to pods if set +# priorityClassName: + +downloadDashboardsImage: + repository: docker.io/curlimages/curl + tag: 7.85.0 + sha: "" + pullPolicy: IfNotPresent + +downloadDashboards: + env: {} + envFromSecret: "" + resources: {} + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + envValueFrom: {} + # ENV_NAME: + # configMapKeyRef: + # name: configmap-name + # key: value_key + +## Pod Annotations +# podAnnotations: {} + +## Pod Labels +# podLabels: {} + +podPortName: grafana +gossipPortName: gossip +## Deployment annotations +# annotations: {} + +## Expose the grafana service to be accessed from outside the cluster (LoadBalancer service). +## or access it from within the cluster (ClusterIP service). Set the service type and the port to serve it. +## ref: http://kubernetes.io/docs/user-guide/services/ +## +service: + enabled: true + type: ClusterIP + port: 80 + targetPort: 3000 + # targetPort: 4181 To be used with a proxy extraContainer + ## Service annotations. Can be templated. + annotations: {} + labels: {} + portName: service + # Adds the appProtocol field to the service. This allows to work with istio protocol selection. Ex: "http" or "tcp" + appProtocol: "" + +serviceMonitor: + ## If true, a ServiceMonitor CRD is created for a prometheus operator + ## https://github.com/coreos/prometheus-operator + ## + enabled: false + path: /metrics + # namespace: monitoring (defaults to use the namespace this chart is deployed to) + labels: {} + interval: 1m + scheme: http + tlsConfig: {} + scrapeTimeout: 30s + relabelings: [] + targetLabels: [] + +extraExposePorts: [] + # - name: keycloak + # port: 8080 + # targetPort: 8080 + # type: ClusterIP + +# overrides pod.spec.hostAliases in the grafana deployment's pods +hostAliases: [] + # - ip: "1.2.3.4" + # hostnames: + # - "my.host.com" + +ingress: + enabled: false + # For Kubernetes >= 1.18 you should specify the ingress-controller via the field ingressClassName + # See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#specifying-the-class-of-an-ingress + # ingressClassName: nginx + # Values can be templated + annotations: {} + # kubernetes.io/ingress.class: nginx + # kubernetes.io/tls-acme: "true" + labels: {} + path: / + + # pathType is only for k8s >= 1.1= + pathType: Prefix + + hosts: + - chart-example.local + ## Extra paths to prepend to every host configuration. This is useful when working with annotation based services. + extraPaths: [] + # - path: /* + # backend: + # serviceName: ssl-redirect + # servicePort: use-annotation + ## Or for k8s > 1.19 + # - path: /* + # pathType: Prefix + # backend: + # service: + # name: ssl-redirect + # port: + # name: use-annotation + + + tls: [] + # - secretName: chart-example-tls + # hosts: + # - chart-example.local + +resources: {} +# limits: +# cpu: 100m +# memory: 128Mi +# requests: +# cpu: 100m +# memory: 128Mi + +## Node labels for pod assignment +## ref: https://kubernetes.io/docs/user-guide/node-selection/ +# +nodeSelector: {} + +## Tolerations for pod assignment +## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ +## +tolerations: [] + +## Affinity for pod assignment (evaluated as template) +## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity +## +affinity: {} + +## Topology Spread Constraints +## ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ +## +topologySpreadConstraints: [] + +## Additional init containers (evaluated as template) +## ref: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/ +## +extraInitContainers: [] + +## Enable an Specify container in extraContainers. This is meant to allow adding an authentication proxy to a grafana pod +extraContainers: "" +# extraContainers: | +# - name: proxy +# image: quay.io/gambol99/keycloak-proxy:latest +# args: +# - -provider=github +# - -client-id= +# - -client-secret= +# - -github-org= +# - -email-domain=* +# - -cookie-secret= +# - -http-address=http://0.0.0.0:4181 +# - -upstream-url=http://127.0.0.1:3000 +# ports: +# - name: proxy-web +# containerPort: 4181 + +## Volumes that can be used in init containers that will not be mounted to deployment pods +extraContainerVolumes: [] +# - name: volume-from-secret +# secret: +# secretName: secret-to-mount +# - name: empty-dir-volume +# emptyDir: {} + +## Enable persistence using Persistent Volume Claims +## ref: http://kubernetes.io/docs/user-guide/persistent-volumes/ +## +persistence: + type: pvc + enabled: false + # storageClassName: default + accessModes: + - ReadWriteOnce + size: 10Gi + # annotations: {} + finalizers: + - kubernetes.io/pvc-protection + # selectorLabels: {} + ## Sub-directory of the PV to mount. Can be templated. + # subPath: "" + ## Name of an existing PVC. Can be templated. + # existingClaim: + ## Extra labels to apply to a PVC. + extraPvcLabels: {} + + ## If persistence is not enabled, this allows to mount the + ## local storage in-memory to improve performance + ## + inMemory: + enabled: false + ## The maximum usage on memory medium EmptyDir would be + ## the minimum value between the SizeLimit specified + ## here and the sum of memory limits of all containers in a pod + ## + # sizeLimit: 300Mi + +initChownData: + ## If false, data ownership will not be reset at startup + ## This allows the grafana-server to be run with an arbitrary user + ## + enabled: true + + ## initChownData container image + ## + image: + repository: docker.io/library/busybox + tag: "1.31.1" + sha: "" + pullPolicy: IfNotPresent + + ## initChownData resource requests and limits + ## Ref: http://kubernetes.io/docs/user-guide/compute-resources/ + ## + resources: {} + # limits: + # cpu: 100m + # memory: 128Mi + # requests: + # cpu: 100m + # memory: 128Mi + securityContext: + runAsNonRoot: false + runAsUser: 0 + seccompProfile: + type: RuntimeDefault + capabilities: + add: + - CHOWN + +# Administrator credentials when not using an existing secret (see below) +adminUser: admin +# adminPassword: strongpassword + +# Use an existing secret for the admin user. +admin: + ## Name of the secret. Can be templated. + existingSecret: "" + userKey: admin-user + passwordKey: admin-password + +## Define command to be executed at startup by grafana container +## Needed if using `vault-env` to manage secrets (ref: https://banzaicloud.com/blog/inject-secrets-into-pods-vault/) +## Default is "run.sh" as defined in grafana's Dockerfile +# command: +# - "sh" +# - "/run.sh" + +## Optionally define args if command is used +## Needed if using `hashicorp/envconsul` to manage secrets +## By default no arguments are set +# args: +# - "-secret" +# - "secret/grafana" +# - "./grafana" + +## Extra environment variables that will be pass onto deployment pods +## +## to provide grafana with access to CloudWatch on AWS EKS: +## 1. create an iam role of type "Web identity" with provider oidc.eks.* (note the provider for later) +## 2. edit the "Trust relationships" of the role, add a line inside the StringEquals clause using the +## same oidc eks provider as noted before (same as the existing line) +## also, replace NAMESPACE and prometheus-operator-grafana with the service account namespace and name +## +## "oidc.eks.us-east-1.amazonaws.com/id/XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX:sub": "system:serviceaccount:NAMESPACE:prometheus-operator-grafana", +## +## 3. attach a policy to the role, you can use a built in policy called CloudWatchReadOnlyAccess +## 4. use the following env: (replace 123456789000 and iam-role-name-here with your aws account number and role name) +## +## env: +## AWS_ROLE_ARN: arn:aws:iam::123456789000:role/iam-role-name-here +## AWS_WEB_IDENTITY_TOKEN_FILE: /var/run/secrets/eks.amazonaws.com/serviceaccount/token +## AWS_REGION: us-east-1 +## +## 5. uncomment the EKS section in extraSecretMounts: below +## 6. uncomment the annotation section in the serviceAccount: above +## make sure to replace arn:aws:iam::123456789000:role/iam-role-name-here with your role arn + +env: {} + +## "valueFrom" environment variable references that will be added to deployment pods. Name is templated. +## ref: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.19/#envvarsource-v1-core +## Renders in container spec as: +## env: +## ... +## - name: +## valueFrom: +## +envValueFrom: {} + # ENV_NAME: + # configMapKeyRef: + # name: configmap-name + # key: value_key + +## The name of a secret in the same kubernetes namespace which contain values to be added to the environment +## This can be useful for auth tokens, etc. Value is templated. +envFromSecret: "" + +## Sensible environment variables that will be rendered as new secret object +## This can be useful for auth tokens, etc. +## If the secret values contains "{{", they'll need to be properly escaped so that they are not interpreted by Helm +## ref: https://helm.sh/docs/howto/charts_tips_and_tricks/#using-the-tpl-function +envRenderSecret: {} + +## The names of secrets in the same kubernetes namespace which contain values to be added to the environment +## Each entry should contain a name key, and can optionally specify whether the secret must be defined with an optional key. +## Name is templated. +envFromSecrets: [] +## - name: secret-name +## optional: true + +## The names of conifgmaps in the same kubernetes namespace which contain values to be added to the environment +## Each entry should contain a name key, and can optionally specify whether the configmap must be defined with an optional key. +## Name is templated. +## ref: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#configmapenvsource-v1-core +envFromConfigMaps: [] +## - name: configmap-name +## optional: true + +# Inject Kubernetes services as environment variables. +# See https://kubernetes.io/docs/concepts/services-networking/connect-applications-service/#environment-variables +enableServiceLinks: true + +## Additional grafana server secret mounts +# Defines additional mounts with secrets. Secrets must be manually created in the namespace. +extraSecretMounts: [] + # - name: secret-files + # mountPath: /etc/secrets + # secretName: grafana-secret-files + # readOnly: true + # subPath: "" + # + # for AWS EKS (cloudwatch) use the following (see also instruction in env: above) + # - name: aws-iam-token + # mountPath: /var/run/secrets/eks.amazonaws.com/serviceaccount + # readOnly: true + # projected: + # defaultMode: 420 + # sources: + # - serviceAccountToken: + # audience: sts.amazonaws.com + # expirationSeconds: 86400 + # path: token + # + # for CSI e.g. Azure Key Vault use the following + # - name: secrets-store-inline + # mountPath: /run/secrets + # readOnly: true + # csi: + # driver: secrets-store.csi.k8s.io + # readOnly: true + # volumeAttributes: + # secretProviderClass: "akv-grafana-spc" + # nodePublishSecretRef: # Only required when using service principal mode + # name: grafana-akv-creds # Only required when using service principal mode + +## Additional grafana server volume mounts +# Defines additional volume mounts. +extraVolumeMounts: [] + # - name: extra-volume-0 + # mountPath: /mnt/volume0 + # readOnly: true + # existingClaim: volume-claim + # - name: extra-volume-1 + # mountPath: /mnt/volume1 + # readOnly: true + # hostPath: /usr/shared/ + # - name: grafana-secrets + # csi: true + # data: + # driver: secrets-store.csi.k8s.io + # readOnly: true + # volumeAttributes: + # secretProviderClass: "grafana-env-spc" + +## Container Lifecycle Hooks. Execute a specific bash command or make an HTTP request +lifecycleHooks: {} + # postStart: + # exec: + # command: [] + +## Pass the plugins you want installed as a list. +## +plugins: [] + # - digrich-bubblechart-panel + # - grafana-clock-panel + ## You can also use other plugin download URL, as long as they are valid zip files, + ## and specify the name of the plugin after the semicolon. Like this: + # - https://grafana.com/api/plugins/marcusolsson-json-datasource/versions/1.3.2/download;marcusolsson-json-datasource + +## Configure grafana datasources +## ref: http://docs.grafana.org/administration/provisioning/#datasources +## +datasources: {} +# datasources.yaml: +# apiVersion: 1 +# datasources: +# - name: Prometheus +# type: prometheus +# url: http://prometheus-prometheus-server +# access: proxy +# isDefault: true +# - name: CloudWatch +# type: cloudwatch +# access: proxy +# uid: cloudwatch +# editable: false +# jsonData: +# authType: default +# defaultRegion: us-east-1 + +## Configure grafana alerting (can be templated) +## ref: http://docs.grafana.org/administration/provisioning/#alerting +## +alerting: {} + # rules.yaml: + # apiVersion: 1 + # groups: + # - orgId: 1 + # name: '{{ .Chart.Name }}_my_rule_group' + # folder: my_first_folder + # interval: 60s + # rules: + # - uid: my_id_1 + # title: my_first_rule + # condition: A + # data: + # - refId: A + # datasourceUid: '-100' + # model: + # conditions: + # - evaluator: + # params: + # - 3 + # type: gt + # operator: + # type: and + # query: + # params: + # - A + # reducer: + # type: last + # type: query + # datasource: + # type: __expr__ + # uid: '-100' + # expression: 1==0 + # intervalMs: 1000 + # maxDataPoints: 43200 + # refId: A + # type: math + # dashboardUid: my_dashboard + # panelId: 123 + # noDataState: Alerting + # for: 60s + # annotations: + # some_key: some_value + # labels: + # team: sre_team_1 + # contactpoints.yaml: + # apiVersion: 1 + # contactPoints: + # - orgId: 1 + # name: cp_1 + # receivers: + # - uid: first_uid + # type: pagerduty + # settings: + # integrationKey: XXX + # severity: critical + # class: ping failure + # component: Grafana + # group: app-stack + # summary: | + # {{ `{{ include "default.message" . }}` }} + +## Configure notifiers +## ref: http://docs.grafana.org/administration/provisioning/#alert-notification-channels +## +notifiers: {} +# notifiers.yaml: +# notifiers: +# - name: email-notifier +# type: email +# uid: email1 +# # either: +# org_id: 1 +# # or +# org_name: Main Org. +# is_default: true +# settings: +# addresses: an_email_address@example.com +# delete_notifiers: + +## Configure grafana dashboard providers +## ref: http://docs.grafana.org/administration/provisioning/#dashboards +## +## `path` must be /var/lib/grafana/dashboards/ +## +dashboardProviders: {} +# dashboardproviders.yaml: +# apiVersion: 1 +# providers: +# - name: 'default' +# orgId: 1 +# folder: '' +# type: file +# disableDeletion: false +# editable: true +# options: +# path: /var/lib/grafana/dashboards/default + +## Configure grafana dashboard to import +## NOTE: To use dashboards you must also enable/configure dashboardProviders +## ref: https://grafana.com/dashboards +## +## dashboards per provider, use provider name as key. +## +dashboards: {} + # default: + # some-dashboard: + # json: | + # $RAW_JSON + # custom-dashboard: + # file: dashboards/custom-dashboard.json + # prometheus-stats: + # gnetId: 2 + # revision: 2 + # datasource: Prometheus + # local-dashboard: + # url: https://example.com/repository/test.json + # token: '' + # local-dashboard-base64: + # url: https://example.com/repository/test-b64.json + # token: '' + # b64content: true + # local-dashboard-gitlab: + # url: https://example.com/repository/test-gitlab.json + # gitlabToken: '' + # local-dashboard-bitbucket: + # url: https://example.com/repository/test-bitbucket.json + # bearerToken: '' + # local-dashboard-azure: + # url: https://example.com/repository/test-azure.json + # basic: '' + # acceptHeader: '*/*' + +## Reference to external ConfigMap per provider. Use provider name as key and ConfigMap name as value. +## A provider dashboards must be defined either by external ConfigMaps or in values.yaml, not in both. +## ConfigMap data example: +## +## data: +## example-dashboard.json: | +## RAW_JSON +## +dashboardsConfigMaps: {} +# default: "" + +## Grafana's primary configuration +## NOTE: values in map will be converted to ini format +## ref: http://docs.grafana.org/installation/configuration/ +## +grafana.ini: + paths: + data: /var/lib/grafana/ + logs: /var/log/grafana + plugins: /var/lib/grafana/plugins + provisioning: /etc/grafana/provisioning + analytics: + check_for_updates: true + log: + mode: console + grafana_net: + url: https://grafana.net + server: + domain: "{{ if (and .Values.ingress.enabled .Values.ingress.hosts) }}{{ .Values.ingress.hosts | first }}{{ else }}''{{ end }}" +## grafana Authentication can be enabled with the following values on grafana.ini + # server: + # The full public facing url you use in browser, used for redirects and emails + # root_url: + # https://grafana.com/docs/grafana/latest/auth/github/#enable-github-in-grafana + # auth.github: + # enabled: false + # allow_sign_up: false + # scopes: user:email,read:org + # auth_url: https://github.com/login/oauth/authorize + # token_url: https://github.com/login/oauth/access_token + # api_url: https://api.github.com/user + # team_ids: + # allowed_organizations: + # client_id: + # client_secret: +## LDAP Authentication can be enabled with the following values on grafana.ini +## NOTE: Grafana will fail to start if the value for ldap.toml is invalid + # auth.ldap: + # enabled: true + # allow_sign_up: true + # config_file: /etc/grafana/ldap.toml + +## Grafana's LDAP configuration +## Templated by the template in _helpers.tpl +## NOTE: To enable the grafana.ini must be configured with auth.ldap.enabled +## ref: http://docs.grafana.org/installation/configuration/#auth-ldap +## ref: http://docs.grafana.org/installation/ldap/#configuration +ldap: + enabled: false + # `existingSecret` is a reference to an existing secret containing the ldap configuration + # for Grafana in a key `ldap-toml`. + existingSecret: "" + # `config` is the content of `ldap.toml` that will be stored in the created secret + config: "" + # config: |- + # verbose_logging = true + + # [[servers]] + # host = "my-ldap-server" + # port = 636 + # use_ssl = true + # start_tls = false + # ssl_skip_verify = false + # bind_dn = "uid=%s,ou=users,dc=myorg,dc=com" + +## Grafana's SMTP configuration +## NOTE: To enable, grafana.ini must be configured with smtp.enabled +## ref: http://docs.grafana.org/installation/configuration/#smtp +smtp: + # `existingSecret` is a reference to an existing secret containing the smtp configuration + # for Grafana. + existingSecret: "" + userKey: "user" + passwordKey: "password" + +## Sidecars that collect the configmaps with specified label and stores the included files them into the respective folders +## Requires at least Grafana 5 to work and can't be used together with parameters dashboardProviders, datasources and dashboards +sidecar: + image: + repository: quay.io/kiwigrid/k8s-sidecar + tag: 1.24.3 + sha: "" + imagePullPolicy: IfNotPresent + resources: {} +# limits: +# cpu: 100m +# memory: 100Mi +# requests: +# cpu: 50m +# memory: 50Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + # skipTlsVerify Set to true to skip tls verification for kube api calls + # skipTlsVerify: true + enableUniqueFilenames: false + readinessProbe: {} + livenessProbe: {} + # Log level default for all sidecars. Can be one of: DEBUG, INFO, WARN, ERROR, CRITICAL. Defaults to INFO + # logLevel: INFO + alerts: + enabled: false + # Additional environment variables for the alerts sidecar + env: {} + # Do not reprocess already processed unchanged resources on k8s API reconnect. + # ignoreAlreadyProcessed: true + # label that the configmaps with alert are marked with + label: grafana_alert + # value of label that the configmaps with alert are set to + labelValue: "" + # Log level. Can be one of: DEBUG, INFO, WARN, ERROR, CRITICAL. + # logLevel: INFO + # If specified, the sidecar will search for alert config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: null + # Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. + watchMethod: WATCH + # search in configmap, secret or both + resource: both + # watchServerTimeout: request to the server, asking it to cleanly close the connection after that. + # defaults to 60sec; much higher values like 3600 seconds (1h) are feasible for non-Azure K8S + # watchServerTimeout: 3600 + # + # watchClientTimeout: is a client-side timeout, configuring your local socket. + # If you have a network outage dropping all packets with no RST/FIN, + # this is how long your client waits before realizing & dropping the connection. + # defaults to 66sec (sic!) + # watchClientTimeout: 60 + # + # Endpoint to send request to reload alerts + reloadURL: "http://localhost:3000/api/admin/provisioning/alerting/reload" + # Absolute path to shell script to execute after a alert got reloaded + script: null + skipReload: false + # Deploy the alert sidecar as an initContainer in addition to a container. + # Sets the size limit of the alert sidecar emptyDir volume + sizeLimit: {} + dashboards: + enabled: false + # Additional environment variables for the dashboards sidecar + env: {} + # Do not reprocess already processed unchanged resources on k8s API reconnect. + # ignoreAlreadyProcessed: true + SCProvider: true + # label that the configmaps with dashboards are marked with + label: grafana_dashboard + # value of label that the configmaps with dashboards are set to + labelValue: "" + # Log level. Can be one of: DEBUG, INFO, WARN, ERROR, CRITICAL. + # logLevel: INFO + # folder in the pod that should hold the collected dashboards (unless `defaultFolderName` is set) + folder: /tmp/dashboards + # The default folder name, it will create a subfolder under the `folder` and put dashboards in there instead + defaultFolderName: null + # Namespaces list. If specified, the sidecar will search for config-maps/secrets inside these namespaces. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces. + searchNamespace: null + # Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. + watchMethod: WATCH + # search in configmap, secret or both + resource: both + # If specified, the sidecar will look for annotation with this name to create folder and put graph here. + # You can use this parameter together with `provider.foldersFromFilesStructure`to annotate configmaps and create folder structure. + folderAnnotation: null + # Endpoint to send request to reload alerts + reloadURL: "http://localhost:3000/api/admin/provisioning/dashboards/reload" + # Absolute path to shell script to execute after a configmap got reloaded + script: null + skipReload: false + # watchServerTimeout: request to the server, asking it to cleanly close the connection after that. + # defaults to 60sec; much higher values like 3600 seconds (1h) are feasible for non-Azure K8S + # watchServerTimeout: 3600 + # + # watchClientTimeout: is a client-side timeout, configuring your local socket. + # If you have a network outage dropping all packets with no RST/FIN, + # this is how long your client waits before realizing & dropping the connection. + # defaults to 66sec (sic!) + # watchClientTimeout: 60 + # + # provider configuration that lets grafana manage the dashboards + provider: + # name of the provider, should be unique + name: sidecarProvider + # orgid as configured in grafana + orgid: 1 + # folder in which the dashboards should be imported in grafana + folder: '' + # type of the provider + type: file + # disableDelete to activate a import-only behaviour + disableDelete: false + # allow updating provisioned dashboards from the UI + allowUiUpdates: false + # allow Grafana to replicate dashboard structure from filesystem + foldersFromFilesStructure: false + # Additional dashboard sidecar volume mounts + extraMounts: [] + # Sets the size limit of the dashboard sidecar emptyDir volume + sizeLimit: {} + datasources: + enabled: false + # Additional environment variables for the datasourcessidecar + env: {} + # Do not reprocess already processed unchanged resources on k8s API reconnect. + # ignoreAlreadyProcessed: true + # label that the configmaps with datasources are marked with + label: grafana_datasource + # value of label that the configmaps with datasources are set to + labelValue: "" + # Log level. Can be one of: DEBUG, INFO, WARN, ERROR, CRITICAL. + # logLevel: INFO + # If specified, the sidecar will search for datasource config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: null + # Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. + watchMethod: WATCH + # search in configmap, secret or both + resource: both + # watchServerTimeout: request to the server, asking it to cleanly close the connection after that. + # defaults to 60sec; much higher values like 3600 seconds (1h) are feasible for non-Azure K8S + # watchServerTimeout: 3600 + # + # watchClientTimeout: is a client-side timeout, configuring your local socket. + # If you have a network outage dropping all packets with no RST/FIN, + # this is how long your client waits before realizing & dropping the connection. + # defaults to 66sec (sic!) + # watchClientTimeout: 60 + # + # Endpoint to send request to reload datasources + reloadURL: "http://localhost:3000/api/admin/provisioning/datasources/reload" + # Absolute path to shell script to execute after a datasource got reloaded + script: null + skipReload: false + # Deploy the datasource sidecar as an initContainer in addition to a container. + # This is needed if skipReload is true, to load any datasources defined at startup time. + initDatasources: false + # Sets the size limit of the datasource sidecar emptyDir volume + sizeLimit: {} + plugins: + enabled: false + # Additional environment variables for the plugins sidecar + env: {} + # Do not reprocess already processed unchanged resources on k8s API reconnect. + # ignoreAlreadyProcessed: true + # label that the configmaps with plugins are marked with + label: grafana_plugin + # value of label that the configmaps with plugins are set to + labelValue: "" + # Log level. Can be one of: DEBUG, INFO, WARN, ERROR, CRITICAL. + # logLevel: INFO + # If specified, the sidecar will search for plugin config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: null + # Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. + watchMethod: WATCH + # search in configmap, secret or both + resource: both + # watchServerTimeout: request to the server, asking it to cleanly close the connection after that. + # defaults to 60sec; much higher values like 3600 seconds (1h) are feasible for non-Azure K8S + # watchServerTimeout: 3600 + # + # watchClientTimeout: is a client-side timeout, configuring your local socket. + # If you have a network outage dropping all packets with no RST/FIN, + # this is how long your client waits before realizing & dropping the connection. + # defaults to 66sec (sic!) + # watchClientTimeout: 60 + # + # Endpoint to send request to reload plugins + reloadURL: "http://localhost:3000/api/admin/provisioning/plugins/reload" + # Absolute path to shell script to execute after a plugin got reloaded + script: null + skipReload: false + # Deploy the datasource sidecar as an initContainer in addition to a container. + # This is needed if skipReload is true, to load any plugins defined at startup time. + initPlugins: false + # Sets the size limit of the plugin sidecar emptyDir volume + sizeLimit: {} + notifiers: + enabled: false + # Additional environment variables for the notifierssidecar + env: {} + # Do not reprocess already processed unchanged resources on k8s API reconnect. + # ignoreAlreadyProcessed: true + # label that the configmaps with notifiers are marked with + label: grafana_notifier + # value of label that the configmaps with notifiers are set to + labelValue: "" + # Log level. Can be one of: DEBUG, INFO, WARN, ERROR, CRITICAL. + # logLevel: INFO + # If specified, the sidecar will search for notifier config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: null + # Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds. + watchMethod: WATCH + # search in configmap, secret or both + resource: both + # watchServerTimeout: request to the server, asking it to cleanly close the connection after that. + # defaults to 60sec; much higher values like 3600 seconds (1h) are feasible for non-Azure K8S + # watchServerTimeout: 3600 + # + # watchClientTimeout: is a client-side timeout, configuring your local socket. + # If you have a network outage dropping all packets with no RST/FIN, + # this is how long your client waits before realizing & dropping the connection. + # defaults to 66sec (sic!) + # watchClientTimeout: 60 + # + # Endpoint to send request to reload notifiers + reloadURL: "http://localhost:3000/api/admin/provisioning/notifications/reload" + # Absolute path to shell script to execute after a notifier got reloaded + script: null + skipReload: false + # Deploy the notifier sidecar as an initContainer in addition to a container. + # This is needed if skipReload is true, to load any notifiers defined at startup time. + initNotifiers: false + # Sets the size limit of the notifier sidecar emptyDir volume + sizeLimit: {} + +## Override the deployment namespace +## +namespaceOverride: "" + +## Number of old ReplicaSets to retain +## +revisionHistoryLimit: 10 + +## Add a seperate remote image renderer deployment/service +imageRenderer: + deploymentStrategy: {} + # Enable the image-renderer deployment & service + enabled: false + replicas: 1 + autoscaling: + enabled: false + minReplicas: 1 + maxReplicas: 5 + targetCPU: "60" + targetMemory: "" + behavior: {} + image: + # image-renderer Image repository + repository: docker.io/grafana/grafana-image-renderer + # image-renderer Image tag + tag: latest + # image-renderer Image sha (optional) + sha: "" + # image-renderer ImagePullPolicy + pullPolicy: Always + # extra environment variables + env: + HTTP_HOST: "0.0.0.0" + # RENDERING_ARGS: --no-sandbox,--disable-gpu,--window-size=1280x758 + # RENDERING_MODE: clustered + # IGNORE_HTTPS_ERRORS: true + + ## "valueFrom" environment variable references that will be added to deployment pods. Name is templated. + ## ref: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.19/#envvarsource-v1-core + ## Renders in container spec as: + ## env: + ## ... + ## - name: + ## valueFrom: + ## + envValueFrom: {} + # ENV_NAME: + # configMapKeyRef: + # name: configmap-name + # key: value_key + + # image-renderer deployment serviceAccount + serviceAccountName: "" + # image-renderer deployment securityContext + securityContext: {} + # image-renderer deployment container securityContext + containerSecurityContext: + seccompProfile: + type: RuntimeDefault + capabilities: + drop: ['ALL'] + allowPrivilegeEscalation: false + readOnlyRootFilesystem: true + # image-renderer deployment Host Aliases + hostAliases: [] + # image-renderer deployment priority class + priorityClassName: '' + service: + # Enable the image-renderer service + enabled: true + # image-renderer service port name + portName: 'http' + # image-renderer service port used by both service and deployment + port: 8081 + targetPort: 8081 + # Adds the appProtocol field to the image-renderer service. This allows to work with istio protocol selection. Ex: "http" or "tcp" + appProtocol: "" + serviceMonitor: + ## If true, a ServiceMonitor CRD is created for a prometheus operator + ## https://github.com/coreos/prometheus-operator + ## + enabled: false + path: /metrics + # namespace: monitoring (defaults to use the namespace this chart is deployed to) + labels: {} + interval: 1m + scheme: http + tlsConfig: {} + scrapeTimeout: 30s + relabelings: [] + # See: https://doc.crds.dev/github.com/prometheus-operator/kube-prometheus/monitoring.coreos.com/ServiceMonitor/v1@v0.11.0#spec-targetLabels + targetLabels: [] + # - targetLabel1 + # - targetLabel2 + # If https is enabled in Grafana, this needs to be set as 'https' to correctly configure the callback used in Grafana + grafanaProtocol: http + # In case a sub_path is used this needs to be added to the image renderer callback + grafanaSubPath: "" + # name of the image-renderer port on the pod + podPortName: http + # number of image-renderer replica sets to keep + revisionHistoryLimit: 10 + networkPolicy: + # Enable a NetworkPolicy to limit inbound traffic to only the created grafana pods + limitIngress: true + # Enable a NetworkPolicy to limit outbound traffic to only the created grafana pods + limitEgress: false + # Allow additional services to access image-renderer (eg. Prometheus operator when ServiceMonitor is enabled) + extraIngressSelectors: [] + resources: {} +# limits: +# cpu: 100m +# memory: 100Mi +# requests: +# cpu: 50m +# memory: 50Mi + ## Node labels for pod assignment + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + # + nodeSelector: {} + + ## Tolerations for pod assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + ## + tolerations: [] + + ## Affinity for pod assignment (evaluated as template) + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + ## + affinity: {} + + ## Use an alternate scheduler, e.g. "stork". + ## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ + ## + # schedulerName: "default-scheduler" + +networkPolicy: + ## @param networkPolicy.enabled Enable creation of NetworkPolicy resources. Only Ingress traffic is filtered for now. + ## + enabled: false + ## @param networkPolicy.allowExternal Don't require client label for connections + ## The Policy model to apply. When set to false, only pods with the correct + ## client label will have network access to grafana port defined. + ## When true, grafana will accept connections from any source + ## (with the correct destination port). + ## + ingress: true + ## @param networkPolicy.ingress When true enables the creation + ## an ingress network policy + ## + allowExternal: true + ## @param networkPolicy.explicitNamespacesSelector A Kubernetes LabelSelector to explicitly select namespaces from which traffic could be allowed + ## If explicitNamespacesSelector is missing or set to {}, only client Pods that are in the networkPolicy's namespace + ## and that match other criteria, the ones that have the good label, can reach the grafana. + ## But sometimes, we want the grafana to be accessible to clients from other namespaces, in this case, we can use this + ## LabelSelector to select these namespaces, note that the networkPolicy's namespace should also be explicitly added. + ## + ## Example: + ## explicitNamespacesSelector: + ## matchLabels: + ## role: frontend + ## matchExpressions: + ## - {key: role, operator: In, values: [frontend]} + ## + explicitNamespacesSelector: {} + ## + ## + ## + ## + ## + ## + egress: + ## @param networkPolicy.egress.enabled When enabled, an egress network policy will be + ## created allowing grafana to connect to external data sources from kubernetes cluster. + enabled: false + ## + ## @param networkPolicy.egress.ports Add individual ports to be allowed by the egress + ports: [] + ## Add ports to the egress by specifying - port: + ## E.X. + ## ports: + ## - port: 80 + ## - port: 443 + ## + ## + ## + ## + ## + ## + +# Enable backward compatibility of kubernetes where version below 1.13 doesn't have the enableServiceLinks option +enableKubeBackwardCompatibility: false +useStatefulSet: false +# Create a dynamic manifests via values: +extraObjects: [] + # - apiVersion: "kubernetes-client.io/v1" + # kind: ExternalSecret + # metadata: + # name: grafana-secrets + # spec: + # backendType: gcpSecretsManager + # data: + # - key: grafana-admin-password + # name: adminPassword diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/.helmignore new file mode 100644 index 0000000..50af031 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/.helmignore @@ -0,0 +1,22 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/CHANGELOG.md b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/CHANGELOG.md new file mode 100644 index 0000000..201a4f0 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/CHANGELOG.md @@ -0,0 +1,398 @@ +# Changelog + +This file documents all notable changes to [ingress-nginx](https://github.com/kubernetes/ingress-nginx) Helm Chart. The release numbering uses [semantic versioning](http://semver.org). + +### 4.1.2 + +- "[8587](https://github.com/kubernetes/ingress-nginx/pull/8587) Add CAP_SYS_CHROOT to DS/PSP when needed" +- "[8458](https://github.com/kubernetes/ingress-nginx/pull/8458) Add portNamePreffix Helm chart parameter" +- "[8522](https://github.com/kubernetes/ingress-nginx/pull/8522) Add documentation for controller.service.loadBalancerIP in Helm chart" + +### 4.1.0 + +- "[8481](https://github.com/kubernetes/ingress-nginx/pull/8481) Fix log creation in chroot script" +- "[8479](https://github.com/kubernetes/ingress-nginx/pull/8479) changed nginx base img tag to img built with alpine3.14.6" +- "[8478](https://github.com/kubernetes/ingress-nginx/pull/8478) update base images and protobuf gomod" +- "[8468](https://github.com/kubernetes/ingress-nginx/pull/8468) Fallback to ngx.var.scheme for redirectScheme with use-forward-headers when X-Forwarded-Proto is empty" +- "[8456](https://github.com/kubernetes/ingress-nginx/pull/8456) Implement object deep inspector" +- "[8455](https://github.com/kubernetes/ingress-nginx/pull/8455) Update dependencies" +- "[8454](https://github.com/kubernetes/ingress-nginx/pull/8454) Update index.md" +- "[8447](https://github.com/kubernetes/ingress-nginx/pull/8447) typo fixing" +- "[8446](https://github.com/kubernetes/ingress-nginx/pull/8446) Fix suggested annotation-value-word-blocklist" +- "[8444](https://github.com/kubernetes/ingress-nginx/pull/8444) replace deprecated topology key in example with current one" +- "[8443](https://github.com/kubernetes/ingress-nginx/pull/8443) Add dependency review enforcement" +- "[8434](https://github.com/kubernetes/ingress-nginx/pull/8434) added new auth-tls-match-cn annotation" +- "[8426](https://github.com/kubernetes/ingress-nginx/pull/8426) Bump github.com/prometheus/common from 0.32.1 to 0.33.0" + +### 4.0.18 + +- "[8291](https://github.com/kubernetes/ingress-nginx/pull/8291) remove git tag env from cloud build" +- "[8286](https://github.com/kubernetes/ingress-nginx/pull/8286) Fix OpenTelemetry sidecar image build" +- "[8277](https://github.com/kubernetes/ingress-nginx/pull/8277) Add OpenSSF Best practices badge" +- "[8273](https://github.com/kubernetes/ingress-nginx/pull/8273) Issue#8241" +- "[8267](https://github.com/kubernetes/ingress-nginx/pull/8267) Add fsGroup value to admission-webhooks/job-patch charts" +- "[8262](https://github.com/kubernetes/ingress-nginx/pull/8262) Updated confusing error" +- "[8256](https://github.com/kubernetes/ingress-nginx/pull/8256) fix: deny locations with invalid auth-url annotation" +- "[8253](https://github.com/kubernetes/ingress-nginx/pull/8253) Add a certificate info metric" +- "[8236](https://github.com/kubernetes/ingress-nginx/pull/8236) webhook: remove useless code." +- "[8227](https://github.com/kubernetes/ingress-nginx/pull/8227) Update libraries in webhook image" +- "[8225](https://github.com/kubernetes/ingress-nginx/pull/8225) fix inconsistent-label-cardinality for prometheus metrics: nginx_ingress_controller_requests" +- "[8221](https://github.com/kubernetes/ingress-nginx/pull/8221) Do not validate ingresses with unknown ingress class in admission webhook endpoint" +- "[8210](https://github.com/kubernetes/ingress-nginx/pull/8210) Bump github.com/prometheus/client_golang from 1.11.0 to 1.12.1" +- "[8209](https://github.com/kubernetes/ingress-nginx/pull/8209) Bump google.golang.org/grpc from 1.43.0 to 1.44.0" +- "[8204](https://github.com/kubernetes/ingress-nginx/pull/8204) Add Artifact Hub lint" +- "[8203](https://github.com/kubernetes/ingress-nginx/pull/8203) Fix Indentation of example and link to cert-manager tutorial" +- "[8201](https://github.com/kubernetes/ingress-nginx/pull/8201) feat(metrics): add path and method labels to requests countera" +- "[8199](https://github.com/kubernetes/ingress-nginx/pull/8199) use functional options to reduce number of methods creating an EchoDeployment" +- "[8196](https://github.com/kubernetes/ingress-nginx/pull/8196) docs: fix inconsistent controller annotation" +- "[8191](https://github.com/kubernetes/ingress-nginx/pull/8191) Using Go install for misspell" +- "[8186](https://github.com/kubernetes/ingress-nginx/pull/8186) prometheus+grafana using servicemonitor" +- "[8185](https://github.com/kubernetes/ingress-nginx/pull/8185) Append elements on match, instead of removing for cors-annotations" +- "[8179](https://github.com/kubernetes/ingress-nginx/pull/8179) Bump github.com/opencontainers/runc from 1.0.3 to 1.1.0" +- "[8173](https://github.com/kubernetes/ingress-nginx/pull/8173) Adding annotations to the controller service account" +- "[8163](https://github.com/kubernetes/ingress-nginx/pull/8163) Update the $req_id placeholder description" +- "[8162](https://github.com/kubernetes/ingress-nginx/pull/8162) Versioned static manifests" +- "[8159](https://github.com/kubernetes/ingress-nginx/pull/8159) Adding some geoip variables and default values" +- "[8155](https://github.com/kubernetes/ingress-nginx/pull/8155) #7271 feat: avoid-pdb-creation-when-default-backend-disabled-and-replicas-gt-1" +- "[8151](https://github.com/kubernetes/ingress-nginx/pull/8151) Automatically generate helm docs" +- "[8143](https://github.com/kubernetes/ingress-nginx/pull/8143) Allow to configure delay before controller exits" +- "[8136](https://github.com/kubernetes/ingress-nginx/pull/8136) add ingressClass option to helm chart - back compatibility with ingress.class annotations" +- "[8126](https://github.com/kubernetes/ingress-nginx/pull/8126) Example for JWT" + + +### 4.0.15 + +- [8120] https://github.com/kubernetes/ingress-nginx/pull/8120 Update go in runner and release v1.1.1 +- [8119] https://github.com/kubernetes/ingress-nginx/pull/8119 Update to go v1.17.6 +- [8118] https://github.com/kubernetes/ingress-nginx/pull/8118 Remove deprecated libraries, update other libs +- [8117] https://github.com/kubernetes/ingress-nginx/pull/8117 Fix codegen errors +- [8115] https://github.com/kubernetes/ingress-nginx/pull/8115 chart/ghaction: set the correct permission to have access to push a release +- [8098] https://github.com/kubernetes/ingress-nginx/pull/8098 generating SHA for CA only certs in backend_ssl.go + comparision of P… +- [8088] https://github.com/kubernetes/ingress-nginx/pull/8088 Fix Edit this page link to use main branch +- [8072] https://github.com/kubernetes/ingress-nginx/pull/8072 Expose GeoIP2 Continent code as variable +- [8061] https://github.com/kubernetes/ingress-nginx/pull/8061 docs(charts): using helm-docs for chart +- [8058] https://github.com/kubernetes/ingress-nginx/pull/8058 Bump github.com/spf13/cobra from 1.2.1 to 1.3.0 +- [8054] https://github.com/kubernetes/ingress-nginx/pull/8054 Bump google.golang.org/grpc from 1.41.0 to 1.43.0 +- [8051] https://github.com/kubernetes/ingress-nginx/pull/8051 align bug report with feature request regarding kind documentation +- [8046] https://github.com/kubernetes/ingress-nginx/pull/8046 Report expired certificates (#8045) +- [8044] https://github.com/kubernetes/ingress-nginx/pull/8044 remove G109 check till gosec resolves issues +- [8042] https://github.com/kubernetes/ingress-nginx/pull/8042 docs_multiple_instances_one_cluster_ticket_7543 +- [8041] https://github.com/kubernetes/ingress-nginx/pull/8041 docs: fix typo'd executible name +- [8035] https://github.com/kubernetes/ingress-nginx/pull/8035 Comment busy owners +- [8029] https://github.com/kubernetes/ingress-nginx/pull/8029 Add stream-snippet as a ConfigMap and Annotation option +- [8023] https://github.com/kubernetes/ingress-nginx/pull/8023 fix nginx compilation flags +- [8021] https://github.com/kubernetes/ingress-nginx/pull/8021 Disable default modsecurity_rules_file if modsecurity-snippet is specified +- [8019] https://github.com/kubernetes/ingress-nginx/pull/8019 Revise main documentation page +- [8018] https://github.com/kubernetes/ingress-nginx/pull/8018 Preserve order of plugin invocation +- [8015] https://github.com/kubernetes/ingress-nginx/pull/8015 Add newline indenting to admission webhook annotations +- [8014] https://github.com/kubernetes/ingress-nginx/pull/8014 Add link to example error page manifest in docs +- [8009] https://github.com/kubernetes/ingress-nginx/pull/8009 Fix spelling in documentation and top-level files +- [8008] https://github.com/kubernetes/ingress-nginx/pull/8008 Add relabelings in controller-servicemonitor.yaml +- [8003] https://github.com/kubernetes/ingress-nginx/pull/8003 Minor improvements (formatting, consistency) in install guide +- [8001] https://github.com/kubernetes/ingress-nginx/pull/8001 fix: go-grpc Dockerfile +- [7999] https://github.com/kubernetes/ingress-nginx/pull/7999 images: use k8s-staging-test-infra/gcb-docker-gcloud +- [7996] https://github.com/kubernetes/ingress-nginx/pull/7996 doc: improvement +- [7983] https://github.com/kubernetes/ingress-nginx/pull/7983 Fix a couple of misspellings in the annotations documentation. +- [7979] https://github.com/kubernetes/ingress-nginx/pull/7979 allow set annotations for admission Jobs +- [7977] https://github.com/kubernetes/ingress-nginx/pull/7977 Add ssl_reject_handshake to defaul server +- [7975] https://github.com/kubernetes/ingress-nginx/pull/7975 add legacy version update v0.50.0 to main changelog +- [7972] https://github.com/kubernetes/ingress-nginx/pull/7972 updated service upstream definition + +### 4.0.14 + +- [8061] https://github.com/kubernetes/ingress-nginx/pull/8061 Using helm-docs to populate values table in README.md + +### 4.0.13 + +- [8008] https://github.com/kubernetes/ingress-nginx/pull/8008 Add relabelings in controller-servicemonitor.yaml + +### 4.0.12 + +- [7978] https://github.com/kubernetes/ingress-nginx/pull/7979 Support custom annotations in admissions Jobs + +### 4.0.11 + +- [7873] https://github.com/kubernetes/ingress-nginx/pull/7873 Makes the [appProtocol](https://kubernetes.io/docs/concepts/services-networking/_print/#application-protocol) field optional. + +### 4.0.10 + +- [7964] https://github.com/kubernetes/ingress-nginx/pull/7964 Update controller version to v1.1.0 + +### 4.0.9 + +- [6992] https://github.com/kubernetes/ingress-nginx/pull/6992 Add ability to specify labels for all resources + +### 4.0.7 + +- [7923] https://github.com/kubernetes/ingress-nginx/pull/7923 Release v1.0.5 of ingress-nginx +- [7806] https://github.com/kubernetes/ingress-nginx/pull/7806 Choice option for internal/external loadbalancer type service + +### 4.0.6 + +- [7804] https://github.com/kubernetes/ingress-nginx/pull/7804 Release v1.0.4 of ingress-nginx +- [7651] https://github.com/kubernetes/ingress-nginx/pull/7651 Support ipFamilyPolicy and ipFamilies fields in Helm Chart +- [7798] https://github.com/kubernetes/ingress-nginx/pull/7798 Exoscale: use HTTP Healthcheck mode +- [7793] https://github.com/kubernetes/ingress-nginx/pull/7793 Update kube-webhook-certgen to v1.1.1 + +### 4.0.5 + +- [7740] https://github.com/kubernetes/ingress-nginx/pull/7740 Release v1.0.3 of ingress-nginx + +### 4.0.3 + +- [7707] https://github.com/kubernetes/ingress-nginx/pull/7707 Release v1.0.2 of ingress-nginx + +### 4.0.2 + +- [7681] https://github.com/kubernetes/ingress-nginx/pull/7681 Release v1.0.1 of ingress-nginx + +### 4.0.1 + +- [7535] https://github.com/kubernetes/ingress-nginx/pull/7535 Release v1.0.0 ingress-nginx + +### 3.34.0 + +- [7256] https://github.com/kubernetes/ingress-nginx/pull/7256 Add namespace field in the namespace scoped resource templates + +### 3.33.0 + +- [7164] https://github.com/kubernetes/ingress-nginx/pull/7164 Update nginx to v1.20.1 + +### 3.32.0 + +- [7117] https://github.com/kubernetes/ingress-nginx/pull/7117 Add annotations for HPA + +### 3.31.0 + +- [7137] https://github.com/kubernetes/ingress-nginx/pull/7137 Add support for custom probes + +### 3.30.0 + +- [#7092](https://github.com/kubernetes/ingress-nginx/pull/7092) Removes the possibility of using localhost in ExternalNames as endpoints + +### 3.29.0 + +- [X] [#6945](https://github.com/kubernetes/ingress-nginx/pull/7020) Add option to specify job label for ServiceMonitor + +### 3.28.0 + +- [ ] [#6900](https://github.com/kubernetes/ingress-nginx/pull/6900) Support existing PSPs + +### 3.27.0 + +- Update ingress-nginx v0.45.0 + +### 3.26.0 + +- [X] [#6979](https://github.com/kubernetes/ingress-nginx/pull/6979) Changed servicePort value for metrics + +### 3.25.0 + +- [X] [#6957](https://github.com/kubernetes/ingress-nginx/pull/6957) Add ability to specify automountServiceAccountToken + +### 3.24.0 + +- [X] [#6908](https://github.com/kubernetes/ingress-nginx/pull/6908) Add volumes to default-backend deployment + +### 3.23.0 + +- Update ingress-nginx v0.44.0 + +### 3.22.0 + +- [X] [#6802](https://github.com/kubernetes/ingress-nginx/pull/6802) Add value for configuring a custom Diffie-Hellman parameters file +- [X] [#6815](https://github.com/kubernetes/ingress-nginx/pull/6815) Allow use of numeric namespaces in helm chart + +### 3.21.0 + +- [X] [#6783](https://github.com/kubernetes/ingress-nginx/pull/6783) Add custom annotations to ScaledObject +- [X] [#6761](https://github.com/kubernetes/ingress-nginx/pull/6761) Adding quotes in the serviceAccount name in Helm values +- [X] [#6767](https://github.com/kubernetes/ingress-nginx/pull/6767) Remove ClusterRole when scope option is enabled +- [X] [#6785](https://github.com/kubernetes/ingress-nginx/pull/6785) Update kube-webhook-certgen image to v1.5.1 + +### 3.20.1 + +- Do not create KEDA in case of DaemonSets. +- Fix KEDA v2 definition + +### 3.20.0 + +- [X] [#6730](https://github.com/kubernetes/ingress-nginx/pull/6730) Do not create HPA for defaultBackend if not enabled. + +### 3.19.0 + +- Update ingress-nginx v0.43.0 + +### 3.18.0 + +- [X] [#6688](https://github.com/kubernetes/ingress-nginx/pull/6688) Allow volume-type emptyDir in controller podsecuritypolicy +- [X] [#6691](https://github.com/kubernetes/ingress-nginx/pull/6691) Improve parsing of helm parameters + +### 3.17.0 + +- Update ingress-nginx v0.42.0 + +### 3.16.1 + +- Fix chart-releaser action + +### 3.16.0 + +- [X] [#6646](https://github.com/kubernetes/ingress-nginx/pull/6646) Added LoadBalancerIP value for internal service + +### 3.15.1 + +- Fix chart-releaser action + +### 3.15.0 + +- [X] [#6586](https://github.com/kubernetes/ingress-nginx/pull/6586) Fix 'maxmindLicenseKey' location in values.yaml + +### 3.14.0 + +- [X] [#6469](https://github.com/kubernetes/ingress-nginx/pull/6469) Allow custom service names for controller and backend + +### 3.13.0 + +- [X] [#6544](https://github.com/kubernetes/ingress-nginx/pull/6544) Fix default backend HPA name variable + +### 3.12.0 + +- [X] [#6514](https://github.com/kubernetes/ingress-nginx/pull/6514) Remove helm2 support and update docs + +### 3.11.1 + +- [X] [#6505](https://github.com/kubernetes/ingress-nginx/pull/6505) Reorder HPA resource list to work with GitOps tooling + +### 3.11.0 + +- Support Keda Autoscaling + +### 3.10.1 + +- Fix regression introduced in 0.41.0 with external authentication + +### 3.10.0 + +- Fix routing regression introduced in 0.41.0 with PathType Exact + +### 3.9.0 + +- [X] [#6423](https://github.com/kubernetes/ingress-nginx/pull/6423) Add Default backend HPA autoscaling + +### 3.8.0 + +- [X] [#6395](https://github.com/kubernetes/ingress-nginx/pull/6395) Update jettech/kube-webhook-certgen image +- [X] [#6377](https://github.com/kubernetes/ingress-nginx/pull/6377) Added loadBalancerSourceRanges for internal lbs +- [X] [#6356](https://github.com/kubernetes/ingress-nginx/pull/6356) Add securitycontext settings on defaultbackend +- [X] [#6401](https://github.com/kubernetes/ingress-nginx/pull/6401) Fix controller service annotations +- [X] [#6403](https://github.com/kubernetes/ingress-nginx/pull/6403) Initial helm chart changelog + +### 3.7.1 + +- [X] [#6326](https://github.com/kubernetes/ingress-nginx/pull/6326) Fix liveness and readiness probe path in daemonset chart + +### 3.7.0 + +- [X] [#6316](https://github.com/kubernetes/ingress-nginx/pull/6316) Numerals in podAnnotations in quotes [#6315](https://github.com/kubernetes/ingress-nginx/issues/6315) + +### 3.6.0 + +- [X] [#6305](https://github.com/kubernetes/ingress-nginx/pull/6305) Add default linux nodeSelector + +### 3.5.1 + +- [X] [#6299](https://github.com/kubernetes/ingress-nginx/pull/6299) Fix helm chart release + +### 3.5.0 + +- [X] [#6260](https://github.com/kubernetes/ingress-nginx/pull/6260) Allow Helm Chart to customize admission webhook's annotations, timeoutSeconds, namespaceSelector, objectSelector and cert files locations + +### 3.4.0 + +- [X] [#6268](https://github.com/kubernetes/ingress-nginx/pull/6268) Update to 0.40.2 in helm chart #6288 + +### 3.3.1 + +- [X] [#6259](https://github.com/kubernetes/ingress-nginx/pull/6259) Release helm chart +- [X] [#6258](https://github.com/kubernetes/ingress-nginx/pull/6258) Fix chart markdown link +- [X] [#6253](https://github.com/kubernetes/ingress-nginx/pull/6253) Release v0.40.0 + +### 3.3.1 + +- [X] [#6233](https://github.com/kubernetes/ingress-nginx/pull/6233) Add admission controller e2e test + +### 3.3.0 + +- [X] [#6203](https://github.com/kubernetes/ingress-nginx/pull/6203) Refactor parsing of key values +- [X] [#6162](https://github.com/kubernetes/ingress-nginx/pull/6162) Add helm chart options to expose metrics service as NodePort +- [X] [#6180](https://github.com/kubernetes/ingress-nginx/pull/6180) Fix helm chart admissionReviewVersions regression +- [X] [#6169](https://github.com/kubernetes/ingress-nginx/pull/6169) Fix Typo in example prometheus rules + +### 3.0.0 + +- [X] [#6167](https://github.com/kubernetes/ingress-nginx/pull/6167) Update chart requirements + +### 2.16.0 + +- [X] [#6154](https://github.com/kubernetes/ingress-nginx/pull/6154) add `topologySpreadConstraint` to controller + +### 2.15.0 + +- [X] [#6087](https://github.com/kubernetes/ingress-nginx/pull/6087) Adding parameter for externalTrafficPolicy in internal controller service spec + +### 2.14.0 + +- [X] [#6104](https://github.com/kubernetes/ingress-nginx/pull/6104) Misc fixes for nginx-ingress chart for better keel and prometheus-operator integration + +### 2.13.0 + +- [X] [#6093](https://github.com/kubernetes/ingress-nginx/pull/6093) Release v0.35.0 + +### 2.13.0 + +- [X] [#6093](https://github.com/kubernetes/ingress-nginx/pull/6093) Release v0.35.0 +- [X] [#6080](https://github.com/kubernetes/ingress-nginx/pull/6080) Switch images to k8s.gcr.io after Vanity Domain Flip + +### 2.12.1 + +- [X] [#6075](https://github.com/kubernetes/ingress-nginx/pull/6075) Sync helm chart affinity examples + +### 2.12.0 + +- [X] [#6039](https://github.com/kubernetes/ingress-nginx/pull/6039) Add configurable serviceMonitor metricRelabelling and targetLabels +- [X] [#6044](https://github.com/kubernetes/ingress-nginx/pull/6044) Fix YAML linting + +### 2.11.3 + +- [X] [#6038](https://github.com/kubernetes/ingress-nginx/pull/6038) Bump chart version PATCH + +### 2.11.2 + +- [X] [#5951](https://github.com/kubernetes/ingress-nginx/pull/5951) Bump chart patch version + +### 2.11.1 + +- [X] [#5900](https://github.com/kubernetes/ingress-nginx/pull/5900) Release helm chart for v0.34.1 + +### 2.11.0 + +- [X] [#5879](https://github.com/kubernetes/ingress-nginx/pull/5879) Update helm chart for v0.34.0 +- [X] [#5671](https://github.com/kubernetes/ingress-nginx/pull/5671) Make liveness probe more fault tolerant than readiness probe + +### 2.10.0 + +- [X] [#5843](https://github.com/kubernetes/ingress-nginx/pull/5843) Update jettech/kube-webhook-certgen image + +### 2.9.1 + +- [X] [#5823](https://github.com/kubernetes/ingress-nginx/pull/5823) Add quoting to sysctls because numeric values need to be presented as strings (#5823) + +### 2.9.0 + +- [X] [#5795](https://github.com/kubernetes/ingress-nginx/pull/5795) Use fully qualified images to avoid cri-o issues + + +### TODO + +Keep building the changelog using *git log charts* checking the tag diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/Chart.yaml new file mode 100644 index 0000000..78d7151 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/Chart.yaml @@ -0,0 +1,30 @@ +annotations: + artifacthub.io/changes: | + - "[8459](https://github.com/kubernetes/ingress-nginx/pull/8459) Update default allowed CORS headers" + - "[8202](https://github.com/kubernetes/ingress-nginx/pull/8202) disable modsecurity on error page" + - "[8178](https://github.com/kubernetes/ingress-nginx/pull/8178) Add header Host into mirror annotations" + - "[8213](https://github.com/kubernetes/ingress-nginx/pull/8213) feat: always set auth cookie" + - "[8548](https://github.com/kubernetes/ingress-nginx/pull/8548) Implement reporting status classes in metrics" + - "[8612](https://github.com/kubernetes/ingress-nginx/pull/8612) move so files under /etc/nginx/modules" + - "[8624](https://github.com/kubernetes/ingress-nginx/pull/8624) Add patch to remove root and alias directives" + - "[8623](https://github.com/kubernetes/ingress-nginx/pull/8623) Improve path rule" + artifacthub.io/prerelease: "false" +apiVersion: v2 +appVersion: 1.2.1 +description: Ingress controller for Kubernetes using NGINX as a reverse proxy and + load balancer +home: https://github.com/kubernetes/ingress-nginx +icon: https://upload.wikimedia.org/wikipedia/commons/thumb/c/c5/Nginx_logo.svg/500px-Nginx_logo.svg.png +keywords: +- ingress +- nginx +kubeVersion: '>=1.19.0-0' +maintainers: +- name: rikatz +- name: strongjz +- name: tao12345666333 +name: ingress-nginx +sources: +- https://github.com/kubernetes/ingress-nginx +type: application +version: 4.1.4 diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/OWNERS b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/OWNERS new file mode 100644 index 0000000..6b7e049 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/OWNERS @@ -0,0 +1,10 @@ +# See the OWNERS docs: https://github.com/kubernetes/community/blob/master/contributors/guide/owners.md + +approvers: +- ingress-nginx-helm-maintainers + +reviewers: +- ingress-nginx-helm-reviewers + +labels: +- area/helm diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/README.md b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/README.md new file mode 100644 index 0000000..c513f81 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/README.md @@ -0,0 +1,491 @@ +# ingress-nginx + +[ingress-nginx](https://github.com/kubernetes/ingress-nginx) Ingress controller for Kubernetes using NGINX as a reverse proxy and load balancer + +![Version: 4.1.4](https://img.shields.io/badge/Version-4.1.4-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 1.2.1](https://img.shields.io/badge/AppVersion-1.2.1-informational?style=flat-square) + +To use, add `ingressClassName: nginx` spec field or the `kubernetes.io/ingress.class: nginx` annotation to your Ingress resources. + +This chart bootstraps an ingress-nginx deployment on a [Kubernetes](http://kubernetes.io) cluster using the [Helm](https://helm.sh) package manager. + +## Prerequisites + +- Chart version 3.x.x: Kubernetes v1.16+ +- Chart version 4.x.x and above: Kubernetes v1.19+ + +## Get Repo Info + +```console +helm repo add ingress-nginx https://kubernetes.github.io/ingress-nginx +helm repo update +``` + +## Install Chart + +**Important:** only helm3 is supported + +```console +helm install [RELEASE_NAME] ingress-nginx/ingress-nginx +``` + +The command deploys ingress-nginx on the Kubernetes cluster in the default configuration. + +_See [configuration](#configuration) below._ + +_See [helm install](https://helm.sh/docs/helm/helm_install/) for command documentation._ + +## Uninstall Chart + +```console +helm uninstall [RELEASE_NAME] +``` + +This removes all the Kubernetes components associated with the chart and deletes the release. + +_See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall/) for command documentation._ + +## Upgrading Chart + +```console +helm upgrade [RELEASE_NAME] [CHART] --install +``` + +_See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documentation._ + +### Upgrading With Zero Downtime in Production + +By default the ingress-nginx controller has service interruptions whenever it's pods are restarted or redeployed. In order to fix that, see the excellent blog post by Lindsay Landry from Codecademy: [Kubernetes: Nginx and Zero Downtime in Production](https://medium.com/codecademy-engineering/kubernetes-nginx-and-zero-downtime-in-production-2c910c6a5ed8). + +### Migrating from stable/nginx-ingress + +There are two main ways to migrate a release from `stable/nginx-ingress` to `ingress-nginx/ingress-nginx` chart: + +1. For Nginx Ingress controllers used for non-critical services, the easiest method is to [uninstall](#uninstall-chart) the old release and [install](#install-chart) the new one +1. For critical services in production that require zero-downtime, you will want to: + 1. [Install](#install-chart) a second Ingress controller + 1. Redirect your DNS traffic from the old controller to the new controller + 1. Log traffic from both controllers during this changeover + 1. [Uninstall](#uninstall-chart) the old controller once traffic has fully drained from it + 1. For details on all of these steps see [Upgrading With Zero Downtime in Production](#upgrading-with-zero-downtime-in-production) + +Note that there are some different and upgraded configurations between the two charts, described by Rimas Mocevicius from JFrog in the "Upgrading to ingress-nginx Helm chart" section of [Migrating from Helm chart nginx-ingress to ingress-nginx](https://rimusz.net/migrating-to-ingress-nginx). As the `ingress-nginx/ingress-nginx` chart continues to update, you will want to check current differences by running [helm configuration](#configuration) commands on both charts. + +## Configuration + +See [Customizing the Chart Before Installing](https://helm.sh/docs/intro/using_helm/#customizing-the-chart-before-installing). To see all configurable options with detailed comments, visit the chart's [values.yaml](./values.yaml), or run these configuration commands: + +```console +helm show values ingress-nginx/ingress-nginx +``` + +### PodDisruptionBudget + +Note that the PodDisruptionBudget resource will only be defined if the replicaCount is greater than one, +else it would make it impossible to evacuate a node. See [gh issue #7127](https://github.com/helm/charts/issues/7127) for more info. + +### Prometheus Metrics + +The Nginx ingress controller can export Prometheus metrics, by setting `controller.metrics.enabled` to `true`. + +You can add Prometheus annotations to the metrics service using `controller.metrics.service.annotations`. +Alternatively, if you use the Prometheus Operator, you can enable ServiceMonitor creation using `controller.metrics.serviceMonitor.enabled`. And set `controller.metrics.serviceMonitor.additionalLabels.release="prometheus"`. "release=prometheus" should match the label configured in the prometheus servicemonitor ( see `kubectl get servicemonitor prometheus-kube-prom-prometheus -oyaml -n prometheus`) + +### ingress-nginx nginx\_status page/stats server + +Previous versions of this chart had a `controller.stats.*` configuration block, which is now obsolete due to the following changes in nginx ingress controller: + +- In [0.16.1](https://github.com/kubernetes/ingress-nginx/blob/main/Changelog.md#0161), the vts (virtual host traffic status) dashboard was removed +- In [0.23.0](https://github.com/kubernetes/ingress-nginx/blob/main/Changelog.md#0230), the status page at port 18080 is now a unix socket webserver only available at localhost. + You can use `curl --unix-socket /tmp/nginx-status-server.sock http://localhost/nginx_status` inside the controller container to access it locally, or use the snippet from [nginx-ingress changelog](https://github.com/kubernetes/ingress-nginx/blob/main/Changelog.md#0230) to re-enable the http server + +### ExternalDNS Service Configuration + +Add an [ExternalDNS](https://github.com/kubernetes-incubator/external-dns) annotation to the LoadBalancer service: + +```yaml +controller: + service: + annotations: + external-dns.alpha.kubernetes.io/hostname: kubernetes-example.com. +``` + +### AWS L7 ELB with SSL Termination + +Annotate the controller as shown in the [nginx-ingress l7 patch](https://github.com/kubernetes/ingress-nginx/blob/ab3a789caae65eec4ad6e3b46b19750b481b6bce/deploy/aws/l7/service-l7.yaml): + +```yaml +controller: + service: + targetPorts: + http: http + https: http + annotations: + service.beta.kubernetes.io/aws-load-balancer-ssl-cert: arn:aws:acm:XX-XXXX-X:XXXXXXXXX:certificate/XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXX + service.beta.kubernetes.io/aws-load-balancer-backend-protocol: "http" + service.beta.kubernetes.io/aws-load-balancer-ssl-ports: "https" + service.beta.kubernetes.io/aws-load-balancer-connection-idle-timeout: '3600' +``` + +### AWS route53-mapper + +To configure the LoadBalancer service with the [route53-mapper addon](https://github.com/kubernetes/kops/blob/be63d4f1a7a46daaf1c4c482527328236850f111/addons/route53-mapper/README.md), add the `domainName` annotation and `dns` label: + +```yaml +controller: + service: + labels: + dns: "route53" + annotations: + domainName: "kubernetes-example.com" +``` + +### Additional Internal Load Balancer + +This setup is useful when you need both external and internal load balancers but don't want to have multiple ingress controllers and multiple ingress objects per application. + +By default, the ingress object will point to the external load balancer address, but if correctly configured, you can make use of the internal one if the URL you are looking up resolves to the internal load balancer's URL. + +You'll need to set both the following values: + +`controller.service.internal.enabled` +`controller.service.internal.annotations` + +If one of them is missing the internal load balancer will not be deployed. Example you may have `controller.service.internal.enabled=true` but no annotations set, in this case no action will be taken. + +`controller.service.internal.annotations` varies with the cloud service you're using. + +Example for AWS: + +```yaml +controller: + service: + internal: + enabled: true + annotations: + # Create internal ELB + service.beta.kubernetes.io/aws-load-balancer-internal: "true" + # Any other annotation can be declared here. +``` + +Example for GCE: + +```yaml +controller: + service: + internal: + enabled: true + annotations: + # Create internal LB. More informations: https://cloud.google.com/kubernetes-engine/docs/how-to/internal-load-balancing + # For GKE versions 1.17 and later + networking.gke.io/load-balancer-type: "Internal" + # For earlier versions + # cloud.google.com/load-balancer-type: "Internal" + + # Any other annotation can be declared here. +``` + +Example for Azure: + +```yaml +controller: + service: + annotations: + # Create internal LB + service.beta.kubernetes.io/azure-load-balancer-internal: "true" + # Any other annotation can be declared here. +``` + +Example for Oracle Cloud Infrastructure: + +```yaml +controller: + service: + annotations: + # Create internal LB + service.beta.kubernetes.io/oci-load-balancer-internal: "true" + # Any other annotation can be declared here. +``` + +An use case for this scenario is having a split-view DNS setup where the public zone CNAME records point to the external balancer URL while the private zone CNAME records point to the internal balancer URL. This way, you only need one ingress kubernetes object. + +Optionally you can set `controller.service.loadBalancerIP` if you need a static IP for the resulting `LoadBalancer`. + +### Ingress Admission Webhooks + +With nginx-ingress-controller version 0.25+, the nginx ingress controller pod exposes an endpoint that will integrate with the `validatingwebhookconfiguration` Kubernetes feature to prevent bad ingress from being added to the cluster. +**This feature is enabled by default since 0.31.0.** + +With nginx-ingress-controller in 0.25.* work only with kubernetes 1.14+, 0.26 fix [this issue](https://github.com/kubernetes/ingress-nginx/pull/4521) + +### Helm Error When Upgrading: spec.clusterIP: Invalid value: "" + +If you are upgrading this chart from a version between 0.31.0 and 1.2.2 then you may get an error like this: + +```console +Error: UPGRADE FAILED: Service "?????-controller" is invalid: spec.clusterIP: Invalid value: "": field is immutable +``` + +Detail of how and why are in [this issue](https://github.com/helm/charts/pull/13646) but to resolve this you can set `xxxx.service.omitClusterIP` to `true` where `xxxx` is the service referenced in the error. + +As of version `1.26.0` of this chart, by simply not providing any clusterIP value, `invalid: spec.clusterIP: Invalid value: "": field is immutable` will no longer occur since `clusterIP: ""` will not be rendered. + +## Requirements + +Kubernetes: `>=1.19.0-0` + +## Values + +| Key | Type | Default | Description | +|-----|------|---------|-------------| +| commonLabels | object | `{}` | | +| controller.addHeaders | object | `{}` | Will add custom headers before sending response traffic to the client according to: https://kubernetes.github.io/ingress-nginx/user-guide/nginx-configuration/configmap/#add-headers | +| controller.admissionWebhooks.annotations | object | `{}` | | +| controller.admissionWebhooks.certificate | string | `"/usr/local/certificates/cert"` | | +| controller.admissionWebhooks.createSecretJob.resources | object | `{}` | | +| controller.admissionWebhooks.enabled | bool | `true` | | +| controller.admissionWebhooks.existingPsp | string | `""` | Use an existing PSP instead of creating one | +| controller.admissionWebhooks.failurePolicy | string | `"Fail"` | | +| controller.admissionWebhooks.key | string | `"/usr/local/certificates/key"` | | +| controller.admissionWebhooks.labels | object | `{}` | Labels to be added to admission webhooks | +| controller.admissionWebhooks.namespaceSelector | object | `{}` | | +| controller.admissionWebhooks.objectSelector | object | `{}` | | +| controller.admissionWebhooks.patch.enabled | bool | `true` | | +| controller.admissionWebhooks.patch.fsGroup | int | `2000` | | +| controller.admissionWebhooks.patch.image.digest | string | `"sha256:64d8c73dca984af206adf9d6d7e46aa550362b1d7a01f3a0a91b20cc67868660"` | | +| controller.admissionWebhooks.patch.image.image | string | `"ingress-nginx/kube-webhook-certgen"` | | +| controller.admissionWebhooks.patch.image.pullPolicy | string | `"IfNotPresent"` | | +| controller.admissionWebhooks.patch.image.registry | string | `"registry.k8s.io"` | | +| controller.admissionWebhooks.patch.image.tag | string | `"v1.1.1"` | | +| controller.admissionWebhooks.patch.labels | object | `{}` | Labels to be added to patch job resources | +| controller.admissionWebhooks.patch.nodeSelector."kubernetes.io/os" | string | `"linux"` | | +| controller.admissionWebhooks.patch.podAnnotations | object | `{}` | | +| controller.admissionWebhooks.patch.priorityClassName | string | `""` | Provide a priority class name to the webhook patching job | +| controller.admissionWebhooks.patch.runAsUser | int | `2000` | | +| controller.admissionWebhooks.patch.tolerations | list | `[]` | | +| controller.admissionWebhooks.patchWebhookJob.resources | object | `{}` | | +| controller.admissionWebhooks.port | int | `8443` | | +| controller.admissionWebhooks.service.annotations | object | `{}` | | +| controller.admissionWebhooks.service.externalIPs | list | `[]` | | +| controller.admissionWebhooks.service.loadBalancerSourceRanges | list | `[]` | | +| controller.admissionWebhooks.service.servicePort | int | `443` | | +| controller.admissionWebhooks.service.type | string | `"ClusterIP"` | | +| controller.affinity | object | `{}` | Affinity and anti-affinity rules for server scheduling to nodes | +| controller.allowSnippetAnnotations | bool | `true` | This configuration defines if Ingress Controller should allow users to set their own *-snippet annotations, otherwise this is forbidden / dropped when users add those annotations. Global snippets in ConfigMap are still respected | +| controller.annotations | object | `{}` | Annotations to be added to the controller Deployment or DaemonSet | +| controller.autoscaling.behavior | object | `{}` | | +| controller.autoscaling.enabled | bool | `false` | | +| controller.autoscaling.maxReplicas | int | `11` | | +| controller.autoscaling.minReplicas | int | `1` | | +| controller.autoscaling.targetCPUUtilizationPercentage | int | `50` | | +| controller.autoscaling.targetMemoryUtilizationPercentage | int | `50` | | +| controller.autoscalingTemplate | list | `[]` | | +| controller.config | object | `{}` | Will add custom configuration options to Nginx https://kubernetes.github.io/ingress-nginx/user-guide/nginx-configuration/configmap/ | +| controller.configAnnotations | object | `{}` | Annotations to be added to the controller config configuration configmap. | +| controller.configMapNamespace | string | `""` | Allows customization of the configmap / nginx-configmap namespace; defaults to $(POD_NAMESPACE) | +| controller.containerName | string | `"controller"` | Configures the controller container name | +| controller.containerPort | object | `{"http":80,"https":443}` | Configures the ports that the nginx-controller listens on | +| controller.customTemplate.configMapKey | string | `""` | | +| controller.customTemplate.configMapName | string | `""` | | +| controller.dnsConfig | object | `{}` | Optionally customize the pod dnsConfig. | +| controller.dnsPolicy | string | `"ClusterFirst"` | Optionally change this to ClusterFirstWithHostNet in case you have 'hostNetwork: true'. By default, while using host network, name resolution uses the host's DNS. If you wish nginx-controller to keep resolving names inside the k8s network, use ClusterFirstWithHostNet. | +| controller.electionID | string | `"ingress-controller-leader"` | Election ID to use for status update | +| controller.enableMimalloc | bool | `true` | Enable mimalloc as a drop-in replacement for malloc. | +| controller.existingPsp | string | `""` | Use an existing PSP instead of creating one | +| controller.extraArgs | object | `{}` | Additional command line arguments to pass to nginx-ingress-controller E.g. to specify the default SSL certificate you can use | +| controller.extraContainers | list | `[]` | Additional containers to be added to the controller pod. See https://github.com/lemonldap-ng-controller/lemonldap-ng-controller as example. | +| controller.extraEnvs | list | `[]` | Additional environment variables to set | +| controller.extraInitContainers | list | `[]` | Containers, which are run before the app containers are started. | +| controller.extraModules | list | `[]` | | +| controller.extraVolumeMounts | list | `[]` | Additional volumeMounts to the controller main container. | +| controller.extraVolumes | list | `[]` | Additional volumes to the controller pod. | +| controller.healthCheckHost | string | `""` | Address to bind the health check endpoint. It is better to set this option to the internal node address if the ingress nginx controller is running in the `hostNetwork: true` mode. | +| controller.healthCheckPath | string | `"/healthz"` | Path of the health check endpoint. All requests received on the port defined by the healthz-port parameter are forwarded internally to this path. | +| controller.hostNetwork | bool | `false` | Required for use with CNI based kubernetes installations (such as ones set up by kubeadm), since CNI and hostport don't mix yet. Can be deprecated once https://github.com/kubernetes/kubernetes/issues/23920 is merged | +| controller.hostPort.enabled | bool | `false` | Enable 'hostPort' or not | +| controller.hostPort.ports.http | int | `80` | 'hostPort' http port | +| controller.hostPort.ports.https | int | `443` | 'hostPort' https port | +| controller.hostname | object | `{}` | Optionally customize the pod hostname. | +| controller.image.allowPrivilegeEscalation | bool | `true` | | +| controller.image.chroot | bool | `false` | | +| controller.image.digest | string | `"sha256:5516d103a9c2ecc4f026efbd4b40662ce22dc1f824fb129ed121460aaa5c47f8"` | | +| controller.image.digestChroot | string | `"sha256:d301551cf62bc3fb75c69fa56f7aa1d9e87b5079333adaf38afe84d9b7439355"` | | +| controller.image.image | string | `"ingress-nginx/controller"` | | +| controller.image.pullPolicy | string | `"IfNotPresent"` | | +| controller.image.registry | string | `"registry.k8s.io"` | | +| controller.image.runAsUser | int | `101` | | +| controller.image.tag | string | `"v1.2.1"` | | +| controller.ingressClass | string | `"nginx"` | For backwards compatibility with ingress.class annotation, use ingressClass. Algorithm is as follows, first ingressClassName is considered, if not present, controller looks for ingress.class annotation | +| controller.ingressClassByName | bool | `false` | Process IngressClass per name (additionally as per spec.controller). | +| controller.ingressClassResource.controllerValue | string | `"k8s.io/ingress-nginx"` | Controller-value of the controller that is processing this ingressClass | +| controller.ingressClassResource.default | bool | `false` | Is this the default ingressClass for the cluster | +| controller.ingressClassResource.enabled | bool | `true` | Is this ingressClass enabled or not | +| controller.ingressClassResource.name | string | `"nginx"` | Name of the ingressClass | +| controller.ingressClassResource.parameters | object | `{}` | Parameters is a link to a custom resource containing additional configuration for the controller. This is optional if the controller does not require extra parameters. | +| controller.keda.apiVersion | string | `"keda.sh/v1alpha1"` | | +| controller.keda.behavior | object | `{}` | | +| controller.keda.cooldownPeriod | int | `300` | | +| controller.keda.enabled | bool | `false` | | +| controller.keda.maxReplicas | int | `11` | | +| controller.keda.minReplicas | int | `1` | | +| controller.keda.pollingInterval | int | `30` | | +| controller.keda.restoreToOriginalReplicaCount | bool | `false` | | +| controller.keda.scaledObject.annotations | object | `{}` | | +| controller.keda.triggers | list | `[]` | | +| controller.kind | string | `"Deployment"` | Use a `DaemonSet` or `Deployment` | +| controller.labels | object | `{}` | Labels to be added to the controller Deployment or DaemonSet and other resources that do not have option to specify labels | +| controller.lifecycle | object | `{"preStop":{"exec":{"command":["/wait-shutdown"]}}}` | Improve connection draining when ingress controller pod is deleted using a lifecycle hook: With this new hook, we increased the default terminationGracePeriodSeconds from 30 seconds to 300, allowing the draining of connections up to five minutes. If the active connections end before that, the pod will terminate gracefully at that time. To effectively take advantage of this feature, the Configmap feature worker-shutdown-timeout new value is 240s instead of 10s. | +| controller.livenessProbe.failureThreshold | int | `5` | | +| controller.livenessProbe.httpGet.path | string | `"/healthz"` | | +| controller.livenessProbe.httpGet.port | int | `10254` | | +| controller.livenessProbe.httpGet.scheme | string | `"HTTP"` | | +| controller.livenessProbe.initialDelaySeconds | int | `10` | | +| controller.livenessProbe.periodSeconds | int | `10` | | +| controller.livenessProbe.successThreshold | int | `1` | | +| controller.livenessProbe.timeoutSeconds | int | `1` | | +| controller.maxmindLicenseKey | string | `""` | Maxmind license key to download GeoLite2 Databases. | +| controller.metrics.enabled | bool | `false` | | +| controller.metrics.port | int | `10254` | | +| controller.metrics.prometheusRule.additionalLabels | object | `{}` | | +| controller.metrics.prometheusRule.enabled | bool | `false` | | +| controller.metrics.prometheusRule.rules | list | `[]` | | +| controller.metrics.service.annotations | object | `{}` | | +| controller.metrics.service.externalIPs | list | `[]` | List of IP addresses at which the stats-exporter service is available | +| controller.metrics.service.loadBalancerSourceRanges | list | `[]` | | +| controller.metrics.service.servicePort | int | `10254` | | +| controller.metrics.service.type | string | `"ClusterIP"` | | +| controller.metrics.serviceMonitor.additionalLabels | object | `{}` | | +| controller.metrics.serviceMonitor.enabled | bool | `false` | | +| controller.metrics.serviceMonitor.metricRelabelings | list | `[]` | | +| controller.metrics.serviceMonitor.namespace | string | `""` | | +| controller.metrics.serviceMonitor.namespaceSelector | object | `{}` | | +| controller.metrics.serviceMonitor.relabelings | list | `[]` | | +| controller.metrics.serviceMonitor.scrapeInterval | string | `"30s"` | | +| controller.metrics.serviceMonitor.targetLabels | list | `[]` | | +| controller.minAvailable | int | `1` | | +| controller.minReadySeconds | int | `0` | `minReadySeconds` to avoid killing pods before we are ready | +| controller.name | string | `"controller"` | | +| controller.nodeSelector | object | `{"kubernetes.io/os":"linux"}` | Node labels for controller pod assignment | +| controller.podAnnotations | object | `{}` | Annotations to be added to controller pods | +| controller.podLabels | object | `{}` | Labels to add to the pod container metadata | +| controller.podSecurityContext | object | `{}` | Security Context policies for controller pods | +| controller.priorityClassName | string | `""` | | +| controller.proxySetHeaders | object | `{}` | Will add custom headers before sending traffic to backends according to https://github.com/kubernetes/ingress-nginx/tree/main/docs/examples/customization/custom-headers | +| controller.publishService | object | `{"enabled":true,"pathOverride":""}` | Allows customization of the source of the IP address or FQDN to report in the ingress status field. By default, it reads the information provided by the service. If disable, the status field reports the IP address of the node or nodes where an ingress controller pod is running. | +| controller.publishService.enabled | bool | `true` | Enable 'publishService' or not | +| controller.publishService.pathOverride | string | `""` | Allows overriding of the publish service to bind to Must be / | +| controller.readinessProbe.failureThreshold | int | `3` | | +| controller.readinessProbe.httpGet.path | string | `"/healthz"` | | +| controller.readinessProbe.httpGet.port | int | `10254` | | +| controller.readinessProbe.httpGet.scheme | string | `"HTTP"` | | +| controller.readinessProbe.initialDelaySeconds | int | `10` | | +| controller.readinessProbe.periodSeconds | int | `10` | | +| controller.readinessProbe.successThreshold | int | `1` | | +| controller.readinessProbe.timeoutSeconds | int | `1` | | +| controller.replicaCount | int | `1` | | +| controller.reportNodeInternalIp | bool | `false` | Bare-metal considerations via the host network https://kubernetes.github.io/ingress-nginx/deploy/baremetal/#via-the-host-network Ingress status was blank because there is no Service exposing the NGINX Ingress controller in a configuration using the host network, the default --publish-service flag used in standard cloud setups does not apply | +| controller.resources.requests.cpu | string | `"100m"` | | +| controller.resources.requests.memory | string | `"90Mi"` | | +| controller.scope.enabled | bool | `false` | Enable 'scope' or not | +| controller.scope.namespace | string | `""` | Namespace to limit the controller to; defaults to $(POD_NAMESPACE) | +| controller.scope.namespaceSelector | string | `""` | When scope.enabled == false, instead of watching all namespaces, we watching namespaces whose labels only match with namespaceSelector. Format like foo=bar. Defaults to empty, means watching all namespaces. | +| controller.service.annotations | object | `{}` | | +| controller.service.appProtocol | bool | `true` | If enabled is adding an appProtocol option for Kubernetes service. An appProtocol field replacing annotations that were using for setting a backend protocol. Here is an example for AWS: service.beta.kubernetes.io/aws-load-balancer-backend-protocol: http It allows choosing the protocol for each backend specified in the Kubernetes service. See the following GitHub issue for more details about the purpose: https://github.com/kubernetes/kubernetes/issues/40244 Will be ignored for Kubernetes versions older than 1.20 | +| controller.service.enableHttp | bool | `true` | | +| controller.service.enableHttps | bool | `true` | | +| controller.service.enabled | bool | `true` | | +| controller.service.external.enabled | bool | `true` | | +| controller.service.externalIPs | list | `[]` | List of IP addresses at which the controller services are available | +| controller.service.internal.annotations | object | `{}` | Annotations are mandatory for the load balancer to come up. Varies with the cloud service. | +| controller.service.internal.enabled | bool | `false` | Enables an additional internal load balancer (besides the external one). | +| controller.service.internal.loadBalancerSourceRanges | list | `[]` | Restrict access For LoadBalancer service. Defaults to 0.0.0.0/0. | +| controller.service.ipFamilies | list | `["IPv4"]` | List of IP families (e.g. IPv4, IPv6) assigned to the service. This field is usually assigned automatically based on cluster configuration and the ipFamilyPolicy field. | +| controller.service.ipFamilyPolicy | string | `"SingleStack"` | Represents the dual-stack-ness requested or required by this Service. Possible values are SingleStack, PreferDualStack or RequireDualStack. The ipFamilies and clusterIPs fields depend on the value of this field. | +| controller.service.labels | object | `{}` | | +| controller.service.loadBalancerIP | string | `""` | Used by cloud providers to connect the resulting `LoadBalancer` to a pre-existing static IP according to https://kubernetes.io/docs/concepts/services-networking/service/#loadbalancer | +| controller.service.loadBalancerSourceRanges | list | `[]` | | +| controller.service.nodePorts.http | string | `""` | | +| controller.service.nodePorts.https | string | `""` | | +| controller.service.nodePorts.tcp | object | `{}` | | +| controller.service.nodePorts.udp | object | `{}` | | +| controller.service.ports.http | int | `80` | | +| controller.service.ports.https | int | `443` | | +| controller.service.targetPorts.http | string | `"http"` | | +| controller.service.targetPorts.https | string | `"https"` | | +| controller.service.type | string | `"LoadBalancer"` | | +| controller.shareProcessNamespace | bool | `false` | | +| controller.sysctls | object | `{}` | See https://kubernetes.io/docs/tasks/administer-cluster/sysctl-cluster/ for notes on enabling and using sysctls | +| controller.tcp.annotations | object | `{}` | Annotations to be added to the tcp config configmap | +| controller.tcp.configMapNamespace | string | `""` | Allows customization of the tcp-services-configmap; defaults to $(POD_NAMESPACE) | +| controller.terminationGracePeriodSeconds | int | `300` | `terminationGracePeriodSeconds` to avoid killing pods before we are ready | +| controller.tolerations | list | `[]` | Node tolerations for server scheduling to nodes with taints | +| controller.topologySpreadConstraints | list | `[]` | Topology spread constraints rely on node labels to identify the topology domain(s) that each Node is in. | +| controller.udp.annotations | object | `{}` | Annotations to be added to the udp config configmap | +| controller.udp.configMapNamespace | string | `""` | Allows customization of the udp-services-configmap; defaults to $(POD_NAMESPACE) | +| controller.updateStrategy | object | `{}` | The update strategy to apply to the Deployment or DaemonSet | +| controller.watchIngressWithoutClass | bool | `false` | Process Ingress objects without ingressClass annotation/ingressClassName field Overrides value for --watch-ingress-without-class flag of the controller binary Defaults to false | +| defaultBackend.affinity | object | `{}` | | +| defaultBackend.autoscaling.annotations | object | `{}` | | +| defaultBackend.autoscaling.enabled | bool | `false` | | +| defaultBackend.autoscaling.maxReplicas | int | `2` | | +| defaultBackend.autoscaling.minReplicas | int | `1` | | +| defaultBackend.autoscaling.targetCPUUtilizationPercentage | int | `50` | | +| defaultBackend.autoscaling.targetMemoryUtilizationPercentage | int | `50` | | +| defaultBackend.containerSecurityContext | object | `{}` | Security Context policies for controller main container. See https://kubernetes.io/docs/tasks/administer-cluster/sysctl-cluster/ for notes on enabling and using sysctls | +| defaultBackend.enabled | bool | `false` | | +| defaultBackend.existingPsp | string | `""` | Use an existing PSP instead of creating one | +| defaultBackend.extraArgs | object | `{}` | | +| defaultBackend.extraEnvs | list | `[]` | Additional environment variables to set for defaultBackend pods | +| defaultBackend.extraVolumeMounts | list | `[]` | | +| defaultBackend.extraVolumes | list | `[]` | | +| defaultBackend.image.allowPrivilegeEscalation | bool | `false` | | +| defaultBackend.image.image | string | `"defaultbackend-amd64"` | | +| defaultBackend.image.pullPolicy | string | `"IfNotPresent"` | | +| defaultBackend.image.readOnlyRootFilesystem | bool | `true` | | +| defaultBackend.image.registry | string | `"registry.k8s.io"` | | +| defaultBackend.image.runAsNonRoot | bool | `true` | | +| defaultBackend.image.runAsUser | int | `65534` | | +| defaultBackend.image.tag | string | `"1.5"` | | +| defaultBackend.labels | object | `{}` | Labels to be added to the default backend resources | +| defaultBackend.livenessProbe.failureThreshold | int | `3` | | +| defaultBackend.livenessProbe.initialDelaySeconds | int | `30` | | +| defaultBackend.livenessProbe.periodSeconds | int | `10` | | +| defaultBackend.livenessProbe.successThreshold | int | `1` | | +| defaultBackend.livenessProbe.timeoutSeconds | int | `5` | | +| defaultBackend.minAvailable | int | `1` | | +| defaultBackend.name | string | `"defaultbackend"` | | +| defaultBackend.nodeSelector | object | `{"kubernetes.io/os":"linux"}` | Node labels for default backend pod assignment | +| defaultBackend.podAnnotations | object | `{}` | Annotations to be added to default backend pods | +| defaultBackend.podLabels | object | `{}` | Labels to add to the pod container metadata | +| defaultBackend.podSecurityContext | object | `{}` | Security Context policies for controller pods See https://kubernetes.io/docs/tasks/administer-cluster/sysctl-cluster/ for notes on enabling and using sysctls | +| defaultBackend.port | int | `8080` | | +| defaultBackend.priorityClassName | string | `""` | | +| defaultBackend.readinessProbe.failureThreshold | int | `6` | | +| defaultBackend.readinessProbe.initialDelaySeconds | int | `0` | | +| defaultBackend.readinessProbe.periodSeconds | int | `5` | | +| defaultBackend.readinessProbe.successThreshold | int | `1` | | +| defaultBackend.readinessProbe.timeoutSeconds | int | `5` | | +| defaultBackend.replicaCount | int | `1` | | +| defaultBackend.resources | object | `{}` | | +| defaultBackend.service.annotations | object | `{}` | | +| defaultBackend.service.externalIPs | list | `[]` | List of IP addresses at which the default backend service is available | +| defaultBackend.service.loadBalancerSourceRanges | list | `[]` | | +| defaultBackend.service.servicePort | int | `80` | | +| defaultBackend.service.type | string | `"ClusterIP"` | | +| defaultBackend.serviceAccount.automountServiceAccountToken | bool | `true` | | +| defaultBackend.serviceAccount.create | bool | `true` | | +| defaultBackend.serviceAccount.name | string | `""` | | +| defaultBackend.tolerations | list | `[]` | Node tolerations for server scheduling to nodes with taints | +| dhParam | string | `nil` | A base64-encoded Diffie-Hellman parameter. This can be generated with: `openssl dhparam 4096 2> /dev/null | base64` | +| imagePullSecrets | list | `[]` | Optional array of imagePullSecrets containing private registry credentials | +| podSecurityPolicy.enabled | bool | `false` | | +| portNamePrefix | string | `""` | Prefix for TCP and UDP ports names in ingress controller service | +| rbac.create | bool | `true` | | +| rbac.scope | bool | `false` | | +| revisionHistoryLimit | int | `10` | Rollback limit | +| serviceAccount.annotations | object | `{}` | Annotations for the controller service account | +| serviceAccount.automountServiceAccountToken | bool | `true` | | +| serviceAccount.create | bool | `true` | | +| serviceAccount.name | string | `""` | | +| tcp | object | `{}` | TCP service key-value pairs | +| udp | object | `{}` | UDP service key-value pairs | + diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/README.md.gotmpl b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/README.md.gotmpl new file mode 100644 index 0000000..8959961 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/README.md.gotmpl @@ -0,0 +1,235 @@ +{{ template "chart.header" . }} +[ingress-nginx](https://github.com/kubernetes/ingress-nginx) Ingress controller for Kubernetes using NGINX as a reverse proxy and load balancer + +{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }} + +To use, add `ingressClassName: nginx` spec field or the `kubernetes.io/ingress.class: nginx` annotation to your Ingress resources. + +This chart bootstraps an ingress-nginx deployment on a [Kubernetes](http://kubernetes.io) cluster using the [Helm](https://helm.sh) package manager. + +## Prerequisites + +- Chart version 3.x.x: Kubernetes v1.16+ +- Chart version 4.x.x and above: Kubernetes v1.19+ + +## Get Repo Info + +```console +helm repo add ingress-nginx https://kubernetes.github.io/ingress-nginx +helm repo update +``` + +## Install Chart + +**Important:** only helm3 is supported + +```console +helm install [RELEASE_NAME] ingress-nginx/ingress-nginx +``` + +The command deploys ingress-nginx on the Kubernetes cluster in the default configuration. + +_See [configuration](#configuration) below._ + +_See [helm install](https://helm.sh/docs/helm/helm_install/) for command documentation._ + +## Uninstall Chart + +```console +helm uninstall [RELEASE_NAME] +``` + +This removes all the Kubernetes components associated with the chart and deletes the release. + +_See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall/) for command documentation._ + +## Upgrading Chart + +```console +helm upgrade [RELEASE_NAME] [CHART] --install +``` + +_See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documentation._ + +### Upgrading With Zero Downtime in Production + +By default the ingress-nginx controller has service interruptions whenever it's pods are restarted or redeployed. In order to fix that, see the excellent blog post by Lindsay Landry from Codecademy: [Kubernetes: Nginx and Zero Downtime in Production](https://medium.com/codecademy-engineering/kubernetes-nginx-and-zero-downtime-in-production-2c910c6a5ed8). + +### Migrating from stable/nginx-ingress + +There are two main ways to migrate a release from `stable/nginx-ingress` to `ingress-nginx/ingress-nginx` chart: + +1. For Nginx Ingress controllers used for non-critical services, the easiest method is to [uninstall](#uninstall-chart) the old release and [install](#install-chart) the new one +1. For critical services in production that require zero-downtime, you will want to: + 1. [Install](#install-chart) a second Ingress controller + 1. Redirect your DNS traffic from the old controller to the new controller + 1. Log traffic from both controllers during this changeover + 1. [Uninstall](#uninstall-chart) the old controller once traffic has fully drained from it + 1. For details on all of these steps see [Upgrading With Zero Downtime in Production](#upgrading-with-zero-downtime-in-production) + +Note that there are some different and upgraded configurations between the two charts, described by Rimas Mocevicius from JFrog in the "Upgrading to ingress-nginx Helm chart" section of [Migrating from Helm chart nginx-ingress to ingress-nginx](https://rimusz.net/migrating-to-ingress-nginx). As the `ingress-nginx/ingress-nginx` chart continues to update, you will want to check current differences by running [helm configuration](#configuration) commands on both charts. + +## Configuration + +See [Customizing the Chart Before Installing](https://helm.sh/docs/intro/using_helm/#customizing-the-chart-before-installing). To see all configurable options with detailed comments, visit the chart's [values.yaml](./values.yaml), or run these configuration commands: + +```console +helm show values ingress-nginx/ingress-nginx +``` + +### PodDisruptionBudget + +Note that the PodDisruptionBudget resource will only be defined if the replicaCount is greater than one, +else it would make it impossible to evacuate a node. See [gh issue #7127](https://github.com/helm/charts/issues/7127) for more info. + +### Prometheus Metrics + +The Nginx ingress controller can export Prometheus metrics, by setting `controller.metrics.enabled` to `true`. + +You can add Prometheus annotations to the metrics service using `controller.metrics.service.annotations`. +Alternatively, if you use the Prometheus Operator, you can enable ServiceMonitor creation using `controller.metrics.serviceMonitor.enabled`. And set `controller.metrics.serviceMonitor.additionalLabels.release="prometheus"`. "release=prometheus" should match the label configured in the prometheus servicemonitor ( see `kubectl get servicemonitor prometheus-kube-prom-prometheus -oyaml -n prometheus`) + +### ingress-nginx nginx\_status page/stats server + +Previous versions of this chart had a `controller.stats.*` configuration block, which is now obsolete due to the following changes in nginx ingress controller: + +- In [0.16.1](https://github.com/kubernetes/ingress-nginx/blob/main/Changelog.md#0161), the vts (virtual host traffic status) dashboard was removed +- In [0.23.0](https://github.com/kubernetes/ingress-nginx/blob/main/Changelog.md#0230), the status page at port 18080 is now a unix socket webserver only available at localhost. + You can use `curl --unix-socket /tmp/nginx-status-server.sock http://localhost/nginx_status` inside the controller container to access it locally, or use the snippet from [nginx-ingress changelog](https://github.com/kubernetes/ingress-nginx/blob/main/Changelog.md#0230) to re-enable the http server + +### ExternalDNS Service Configuration + +Add an [ExternalDNS](https://github.com/kubernetes-incubator/external-dns) annotation to the LoadBalancer service: + +```yaml +controller: + service: + annotations: + external-dns.alpha.kubernetes.io/hostname: kubernetes-example.com. +``` + +### AWS L7 ELB with SSL Termination + +Annotate the controller as shown in the [nginx-ingress l7 patch](https://github.com/kubernetes/ingress-nginx/blob/ab3a789caae65eec4ad6e3b46b19750b481b6bce/deploy/aws/l7/service-l7.yaml): + +```yaml +controller: + service: + targetPorts: + http: http + https: http + annotations: + service.beta.kubernetes.io/aws-load-balancer-ssl-cert: arn:aws:acm:XX-XXXX-X:XXXXXXXXX:certificate/XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXX + service.beta.kubernetes.io/aws-load-balancer-backend-protocol: "http" + service.beta.kubernetes.io/aws-load-balancer-ssl-ports: "https" + service.beta.kubernetes.io/aws-load-balancer-connection-idle-timeout: '3600' +``` + +### AWS route53-mapper + +To configure the LoadBalancer service with the [route53-mapper addon](https://github.com/kubernetes/kops/blob/be63d4f1a7a46daaf1c4c482527328236850f111/addons/route53-mapper/README.md), add the `domainName` annotation and `dns` label: + +```yaml +controller: + service: + labels: + dns: "route53" + annotations: + domainName: "kubernetes-example.com" +``` + +### Additional Internal Load Balancer + +This setup is useful when you need both external and internal load balancers but don't want to have multiple ingress controllers and multiple ingress objects per application. + +By default, the ingress object will point to the external load balancer address, but if correctly configured, you can make use of the internal one if the URL you are looking up resolves to the internal load balancer's URL. + +You'll need to set both the following values: + +`controller.service.internal.enabled` +`controller.service.internal.annotations` + +If one of them is missing the internal load balancer will not be deployed. Example you may have `controller.service.internal.enabled=true` but no annotations set, in this case no action will be taken. + +`controller.service.internal.annotations` varies with the cloud service you're using. + +Example for AWS: + +```yaml +controller: + service: + internal: + enabled: true + annotations: + # Create internal ELB + service.beta.kubernetes.io/aws-load-balancer-internal: "true" + # Any other annotation can be declared here. +``` + +Example for GCE: + +```yaml +controller: + service: + internal: + enabled: true + annotations: + # Create internal LB. More informations: https://cloud.google.com/kubernetes-engine/docs/how-to/internal-load-balancing + # For GKE versions 1.17 and later + networking.gke.io/load-balancer-type: "Internal" + # For earlier versions + # cloud.google.com/load-balancer-type: "Internal" + + # Any other annotation can be declared here. +``` + +Example for Azure: + +```yaml +controller: + service: + annotations: + # Create internal LB + service.beta.kubernetes.io/azure-load-balancer-internal: "true" + # Any other annotation can be declared here. +``` + +Example for Oracle Cloud Infrastructure: + +```yaml +controller: + service: + annotations: + # Create internal LB + service.beta.kubernetes.io/oci-load-balancer-internal: "true" + # Any other annotation can be declared here. +``` + +An use case for this scenario is having a split-view DNS setup where the public zone CNAME records point to the external balancer URL while the private zone CNAME records point to the internal balancer URL. This way, you only need one ingress kubernetes object. + +Optionally you can set `controller.service.loadBalancerIP` if you need a static IP for the resulting `LoadBalancer`. + +### Ingress Admission Webhooks + +With nginx-ingress-controller version 0.25+, the nginx ingress controller pod exposes an endpoint that will integrate with the `validatingwebhookconfiguration` Kubernetes feature to prevent bad ingress from being added to the cluster. +**This feature is enabled by default since 0.31.0.** + +With nginx-ingress-controller in 0.25.* work only with kubernetes 1.14+, 0.26 fix [this issue](https://github.com/kubernetes/ingress-nginx/pull/4521) + +### Helm Error When Upgrading: spec.clusterIP: Invalid value: "" + +If you are upgrading this chart from a version between 0.31.0 and 1.2.2 then you may get an error like this: + +```console +Error: UPGRADE FAILED: Service "?????-controller" is invalid: spec.clusterIP: Invalid value: "": field is immutable +``` + +Detail of how and why are in [this issue](https://github.com/helm/charts/pull/13646) but to resolve this you can set `xxxx.service.omitClusterIP` to `true` where `xxxx` is the service referenced in the error. + +As of version `1.26.0` of this chart, by simply not providing any clusterIP value, `invalid: spec.clusterIP: Invalid value: "": field is immutable` will no longer occur since `clusterIP: ""` will not be rendered. + +{{ template "chart.requirementsSection" . }} + +{{ template "chart.valuesSection" . }} + +{{ template "helm-docs.versionFooter" . }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/controller-custom-ingressclass-flags.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/controller-custom-ingressclass-flags.yaml new file mode 100644 index 0000000..b28a232 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/controller-custom-ingressclass-flags.yaml @@ -0,0 +1,7 @@ +controller: + watchIngressWithoutClass: true + ingressClassResource: + name: custom-nginx + enabled: true + default: true + controllerValue: "k8s.io/custom-nginx" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-customconfig-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-customconfig-values.yaml new file mode 100644 index 0000000..4393a5b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-customconfig-values.yaml @@ -0,0 +1,14 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + kind: DaemonSet + allowSnippetAnnotations: false + admissionWebhooks: + enabled: false + service: + type: ClusterIP + + config: + use-proxy-protocol: "true" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-customnodeport-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-customnodeport-values.yaml new file mode 100644 index 0000000..1d94be2 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-customnodeport-values.yaml @@ -0,0 +1,22 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + + service: + type: NodePort + nodePorts: + tcp: + 9000: 30090 + udp: + 9001: 30091 + +tcp: + 9000: "default/test:8080" + +udp: + 9001: "default/test:8080" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-extra-modules.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-extra-modules.yaml new file mode 100644 index 0000000..f299dbf --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-extra-modules.yaml @@ -0,0 +1,10 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + service: + type: ClusterIP + extraModules: + - name: opentelemetry + image: busybox diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-headers-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-headers-values.yaml new file mode 100644 index 0000000..ab7d47b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-headers-values.yaml @@ -0,0 +1,14 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + addHeaders: + X-Frame-Options: deny + proxySetHeaders: + X-Forwarded-Proto: https + service: + type: ClusterIP diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-internal-lb-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-internal-lb-values.yaml new file mode 100644 index 0000000..0a200a7 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-internal-lb-values.yaml @@ -0,0 +1,14 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: ClusterIP + internal: + enabled: true + annotations: + service.beta.kubernetes.io/aws-load-balancer-internal: "true" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-nodeport-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-nodeport-values.yaml new file mode 100644 index 0000000..3b7aa2f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-nodeport-values.yaml @@ -0,0 +1,10 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: NodePort diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-podannotations-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-podannotations-values.yaml new file mode 100644 index 0000000..0b55306 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-podannotations-values.yaml @@ -0,0 +1,17 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + metrics: + enabled: true + service: + type: ClusterIP + podAnnotations: + prometheus.io/path: /metrics + prometheus.io/port: "10254" + prometheus.io/scheme: http + prometheus.io/scrape: "true" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-tcp-udp-configMapNamespace-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-tcp-udp-configMapNamespace-values.yaml new file mode 100644 index 0000000..acd86a7 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-tcp-udp-configMapNamespace-values.yaml @@ -0,0 +1,20 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: ClusterIP + tcp: + configMapNamespace: default + udp: + configMapNamespace: default + +tcp: + 9000: "default/test:8080" + +udp: + 9001: "default/test:8080" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-tcp-udp-portNamePrefix-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-tcp-udp-portNamePrefix-values.yaml new file mode 100644 index 0000000..90b0f57 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-tcp-udp-portNamePrefix-values.yaml @@ -0,0 +1,18 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: ClusterIP + +tcp: + 9000: "default/test:8080" + +udp: + 9001: "default/test:8080" + +portNamePrefix: "port" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-tcp-udp-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-tcp-udp-values.yaml new file mode 100644 index 0000000..25ee64d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-tcp-udp-values.yaml @@ -0,0 +1,16 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: ClusterIP + +tcp: + 9000: "default/test:8080" + +udp: + 9001: "default/test:8080" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-tcp-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-tcp-values.yaml new file mode 100644 index 0000000..380c8b4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/daemonset-tcp-values.yaml @@ -0,0 +1,14 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: ClusterIP + +tcp: + 9000: "default/test:8080" + 9001: "default/test:8080" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-default-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-default-values.yaml new file mode 100644 index 0000000..82fa23e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-default-values.yaml @@ -0,0 +1,10 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: ClusterIP diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-metrics-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-metrics-values.yaml new file mode 100644 index 0000000..cb3cb54 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-metrics-values.yaml @@ -0,0 +1,12 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + metrics: + enabled: true + service: + type: ClusterIP diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-psp-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-psp-values.yaml new file mode 100644 index 0000000..8026a63 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-psp-values.yaml @@ -0,0 +1,13 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: ClusterIP + +podSecurityPolicy: + enabled: true diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-webhook-and-psp-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-webhook-and-psp-values.yaml new file mode 100644 index 0000000..fccdb13 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-webhook-and-psp-values.yaml @@ -0,0 +1,13 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: true + service: + type: ClusterIP + +podSecurityPolicy: + enabled: true diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-webhook-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-webhook-values.yaml new file mode 100644 index 0000000..54d364d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deamonset-webhook-values.yaml @@ -0,0 +1,10 @@ +controller: + kind: DaemonSet + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: true + service: + type: ClusterIP diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-autoscaling-behavior-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-autoscaling-behavior-values.yaml new file mode 100644 index 0000000..dca3f35 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-autoscaling-behavior-values.yaml @@ -0,0 +1,14 @@ +controller: + autoscaling: + enabled: true + behavior: + scaleDown: + stabilizationWindowSeconds: 300 + policies: + - type: Pods + value: 1 + periodSeconds: 180 + admissionWebhooks: + enabled: false + service: + type: ClusterIP diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-autoscaling-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-autoscaling-values.yaml new file mode 100644 index 0000000..b8b3ac6 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-autoscaling-values.yaml @@ -0,0 +1,11 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + autoscaling: + enabled: true + admissionWebhooks: + enabled: false + service: + type: ClusterIP diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-customconfig-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-customconfig-values.yaml new file mode 100644 index 0000000..1749418 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-customconfig-values.yaml @@ -0,0 +1,12 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + config: + use-proxy-protocol: "true" + allowSnippetAnnotations: false + admissionWebhooks: + enabled: false + service: + type: ClusterIP diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-customnodeport-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-customnodeport-values.yaml new file mode 100644 index 0000000..a564eaf --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-customnodeport-values.yaml @@ -0,0 +1,20 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: NodePort + nodePorts: + tcp: + 9000: 30090 + udp: + 9001: 30091 + +tcp: + 9000: "default/test:8080" + +udp: + 9001: "default/test:8080" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-default-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-default-values.yaml new file mode 100644 index 0000000..9f46b4e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-default-values.yaml @@ -0,0 +1,8 @@ +# Left blank to test default values +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + service: + type: ClusterIP diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-extra-modules.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-extra-modules.yaml new file mode 100644 index 0000000..ec59235 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-extra-modules.yaml @@ -0,0 +1,10 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + service: + type: ClusterIP + extraModules: + - name: opentelemetry + image: busybox diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-headers-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-headers-values.yaml new file mode 100644 index 0000000..17a11ac --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-headers-values.yaml @@ -0,0 +1,13 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + addHeaders: + X-Frame-Options: deny + proxySetHeaders: + X-Forwarded-Proto: https + service: + type: ClusterIP diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-internal-lb-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-internal-lb-values.yaml new file mode 100644 index 0000000..fd8df8d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-internal-lb-values.yaml @@ -0,0 +1,13 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: ClusterIP + internal: + enabled: true + annotations: + service.beta.kubernetes.io/aws-load-balancer-internal: "true" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-metrics-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-metrics-values.yaml new file mode 100644 index 0000000..9209ad5 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-metrics-values.yaml @@ -0,0 +1,11 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + metrics: + enabled: true + service: + type: ClusterIP diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-nodeport-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-nodeport-values.yaml new file mode 100644 index 0000000..cd9b323 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-nodeport-values.yaml @@ -0,0 +1,9 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: NodePort diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-podannotations-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-podannotations-values.yaml new file mode 100644 index 0000000..b48d93c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-podannotations-values.yaml @@ -0,0 +1,16 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + metrics: + enabled: true + service: + type: ClusterIP + podAnnotations: + prometheus.io/path: /metrics + prometheus.io/port: "10254" + prometheus.io/scheme: http + prometheus.io/scrape: "true" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-psp-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-psp-values.yaml new file mode 100644 index 0000000..2f332a7 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-psp-values.yaml @@ -0,0 +1,10 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + service: + type: ClusterIP + +podSecurityPolicy: + enabled: true diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-tcp-udp-configMapNamespace-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-tcp-udp-configMapNamespace-values.yaml new file mode 100644 index 0000000..c51a4e9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-tcp-udp-configMapNamespace-values.yaml @@ -0,0 +1,19 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: ClusterIP + tcp: + configMapNamespace: default + udp: + configMapNamespace: default + +tcp: + 9000: "default/test:8080" + +udp: + 9001: "default/test:8080" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-tcp-udp-portNamePrefix-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-tcp-udp-portNamePrefix-values.yaml new file mode 100644 index 0000000..56323c5 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-tcp-udp-portNamePrefix-values.yaml @@ -0,0 +1,17 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: ClusterIP + +tcp: + 9000: "default/test:8080" + +udp: + 9001: "default/test:8080" + +portNamePrefix: "port" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-tcp-udp-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-tcp-udp-values.yaml new file mode 100644 index 0000000..5b45b69 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-tcp-udp-values.yaml @@ -0,0 +1,15 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: false + service: + type: ClusterIP + +tcp: + 9000: "default/test:8080" + +udp: + 9001: "default/test:8080" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-tcp-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-tcp-values.yaml new file mode 100644 index 0000000..ac0b6e6 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-tcp-values.yaml @@ -0,0 +1,11 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + service: + type: ClusterIP + +tcp: + 9000: "default/test:8080" + 9001: "default/test:8080" diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-webhook-and-psp-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-webhook-and-psp-values.yaml new file mode 100644 index 0000000..6195bb3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-webhook-and-psp-values.yaml @@ -0,0 +1,12 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: true + service: + type: ClusterIP + +podSecurityPolicy: + enabled: true diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-webhook-resources-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-webhook-resources-values.yaml new file mode 100644 index 0000000..49ebbb0 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-webhook-resources-values.yaml @@ -0,0 +1,23 @@ +controller: + service: + type: ClusterIP + admissionWebhooks: + enabled: true + createSecretJob: + resources: + limits: + cpu: 10m + memory: 20Mi + requests: + cpu: 10m + memory: 20Mi + patchWebhookJob: + resources: + limits: + cpu: 10m + memory: 20Mi + requests: + cpu: 10m + memory: 20Mi + patch: + enabled: true diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-webhook-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-webhook-values.yaml new file mode 100644 index 0000000..76669a5 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/ci/deployment-webhook-values.yaml @@ -0,0 +1,9 @@ +controller: + image: + repository: ingress-controller/controller + tag: 1.0.0-dev + digest: null + admissionWebhooks: + enabled: true + service: + type: ClusterIP diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/NOTES.txt new file mode 100644 index 0000000..8985c56 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/NOTES.txt @@ -0,0 +1,80 @@ +The ingress-nginx controller has been installed. + +{{- if contains "NodePort" .Values.controller.service.type }} +Get the application URL by running these commands: + +{{- if (not (empty .Values.controller.service.nodePorts.http)) }} + export HTTP_NODE_PORT={{ .Values.controller.service.nodePorts.http }} +{{- else }} + export HTTP_NODE_PORT=$(kubectl --namespace {{ .Release.Namespace }} get services -o jsonpath="{.spec.ports[0].nodePort}" {{ include "ingress-nginx.controller.fullname" . }}) +{{- end }} +{{- if (not (empty .Values.controller.service.nodePorts.https)) }} + export HTTPS_NODE_PORT={{ .Values.controller.service.nodePorts.https }} +{{- else }} + export HTTPS_NODE_PORT=$(kubectl --namespace {{ .Release.Namespace }} get services -o jsonpath="{.spec.ports[1].nodePort}" {{ include "ingress-nginx.controller.fullname" . }}) +{{- end }} + export NODE_IP=$(kubectl --namespace {{ .Release.Namespace }} get nodes -o jsonpath="{.items[0].status.addresses[1].address}") + + echo "Visit http://$NODE_IP:$HTTP_NODE_PORT to access your application via HTTP." + echo "Visit https://$NODE_IP:$HTTPS_NODE_PORT to access your application via HTTPS." +{{- else if contains "LoadBalancer" .Values.controller.service.type }} +It may take a few minutes for the LoadBalancer IP to be available. +You can watch the status by running 'kubectl --namespace {{ .Release.Namespace }} get services -o wide -w {{ include "ingress-nginx.controller.fullname" . }}' +{{- else if contains "ClusterIP" .Values.controller.service.type }} +Get the application URL by running these commands: + export POD_NAME=$(kubectl --namespace {{ .Release.Namespace }} get pods -o jsonpath="{.items[0].metadata.name}" -l "app={{ template "ingress-nginx.name" . }},component={{ .Values.controller.name }},release={{ .Release.Name }}") + kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:80 + echo "Visit http://127.0.0.1:8080 to access your application." +{{- end }} + +An example Ingress that makes use of the controller: + +{{- $isV1 := semverCompare ">=1" .Chart.AppVersion}} + apiVersion: networking.k8s.io/v1 + kind: Ingress + metadata: + name: example + namespace: foo + {{- if eq $isV1 false }} + annotations: + kubernetes.io/ingress.class: {{ .Values.controller.ingressClass }} + {{- end }} + spec: + {{- if $isV1 }} + ingressClassName: {{ .Values.controller.ingressClassResource.name }} + {{- end }} + rules: + - host: www.example.com + http: + paths: + - pathType: Prefix + backend: + service: + name: exampleService + port: + number: 80 + path: / + # This section is only required if TLS is to be enabled for the Ingress + tls: + - hosts: + - www.example.com + secretName: example-tls + +If TLS is enabled for the Ingress, a Secret containing the certificate and key must also be provided: + + apiVersion: v1 + kind: Secret + metadata: + name: example-tls + namespace: foo + data: + tls.crt: + tls.key: + type: kubernetes.io/tls + +{{- if .Values.controller.headers }} +################################################################################# +###### WARNING: `controller.headers` has been deprecated! ##### +###### It has been renamed to `controller.proxySetHeaders`. ##### +################################################################################# +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/_helpers.tpl new file mode 100644 index 0000000..e69de0c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/_helpers.tpl @@ -0,0 +1,185 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "ingress-nginx.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "ingress-nginx.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "ingress-nginx.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + + +{{/* +Container SecurityContext. +*/}} +{{- define "controller.containerSecurityContext" -}} +{{- if .Values.controller.containerSecurityContext -}} +{{- toYaml .Values.controller.containerSecurityContext -}} +{{- else -}} +capabilities: + drop: + - ALL + add: + - NET_BIND_SERVICE + {{- if .Values.controller.image.chroot }} + - SYS_CHROOT + {{- end }} +runAsUser: {{ .Values.controller.image.runAsUser }} +allowPrivilegeEscalation: {{ .Values.controller.image.allowPrivilegeEscalation }} +{{- end }} +{{- end -}} + +{{/* +Get specific image +*/}} +{{- define "ingress-nginx.image" -}} +{{- if .chroot -}} +{{- printf "%s-chroot" .image -}} +{{- else -}} +{{- printf "%s" .image -}} +{{- end }} +{{- end -}} + +{{/* +Get specific image digest +*/}} +{{- define "ingress-nginx.imageDigest" -}} +{{- if .chroot -}} +{{- if .digestChroot -}} +{{- printf "@%s" .digestChroot -}} +{{- end }} +{{- else -}} +{{ if .digest -}} +{{- printf "@%s" .digest -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Create a default fully qualified controller name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "ingress-nginx.controller.fullname" -}} +{{- printf "%s-%s" (include "ingress-nginx.fullname" .) .Values.controller.name | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Construct the path for the publish-service. + +By convention this will simply use the / to match the name of the +service generated. + +Users can provide an override for an explicit service they want bound via `.Values.controller.publishService.pathOverride` + +*/}} +{{- define "ingress-nginx.controller.publishServicePath" -}} +{{- $defServiceName := printf "%s/%s" "$(POD_NAMESPACE)" (include "ingress-nginx.controller.fullname" .) -}} +{{- $servicePath := default $defServiceName .Values.controller.publishService.pathOverride }} +{{- print $servicePath | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified default backend name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "ingress-nginx.defaultBackend.fullname" -}} +{{- printf "%s-%s" (include "ingress-nginx.fullname" .) .Values.defaultBackend.name | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Common labels +*/}} +{{- define "ingress-nginx.labels" -}} +helm.sh/chart: {{ include "ingress-nginx.chart" . }} +{{ include "ingress-nginx.selectorLabels" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/part-of: {{ template "ingress-nginx.name" . }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- if .Values.commonLabels}} +{{ toYaml .Values.commonLabels }} +{{- end }} +{{- end -}} + +{{/* +Selector labels +*/}} +{{- define "ingress-nginx.selectorLabels" -}} +app.kubernetes.io/name: {{ include "ingress-nginx.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end -}} + +{{/* +Create the name of the controller service account to use +*/}} +{{- define "ingress-nginx.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "ingress-nginx.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Create the name of the backend service account to use - only used when podsecuritypolicy is also enabled +*/}} +{{- define "ingress-nginx.defaultBackend.serviceAccountName" -}} +{{- if .Values.defaultBackend.serviceAccount.create -}} + {{ default (printf "%s-backend" (include "ingress-nginx.fullname" .)) .Values.defaultBackend.serviceAccount.name }} +{{- else -}} + {{ default "default-backend" .Values.defaultBackend.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiGroup for PodSecurityPolicy. +*/}} +{{- define "podSecurityPolicy.apiGroup" -}} +{{- if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}} +{{- print "policy" -}} +{{- else -}} +{{- print "extensions" -}} +{{- end -}} +{{- end -}} + +{{/* +Check the ingress controller version tag is at most three versions behind the last release +*/}} +{{- define "isControllerTagValid" -}} +{{- if not (semverCompare ">=0.27.0-0" .Values.controller.image.tag) -}} +{{- fail "Controller container image tag should be 0.27.0 or higher" -}} +{{- end -}} +{{- end -}} + +{{/* +IngressClass parameters. +*/}} +{{- define "ingressClass.parameters" -}} + {{- if .Values.controller.ingressClassResource.parameters -}} + parameters: +{{ toYaml .Values.controller.ingressClassResource.parameters | indent 4}} + {{ end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/_params.tpl b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/_params.tpl new file mode 100644 index 0000000..305ce0d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/_params.tpl @@ -0,0 +1,62 @@ +{{- define "ingress-nginx.params" -}} +- /nginx-ingress-controller +{{- if .Values.defaultBackend.enabled }} +- --default-backend-service=$(POD_NAMESPACE)/{{ include "ingress-nginx.defaultBackend.fullname" . }} +{{- end }} +{{- if and .Values.controller.publishService.enabled .Values.controller.service.enabled }} +{{- if .Values.controller.service.external.enabled }} +- --publish-service={{ template "ingress-nginx.controller.publishServicePath" . }} +{{- else if .Values.controller.service.internal.enabled }} +- --publish-service={{ template "ingress-nginx.controller.publishServicePath" . }}-internal +{{- end }} +{{- end }} +- --election-id={{ .Values.controller.electionID }} +- --controller-class={{ .Values.controller.ingressClassResource.controllerValue }} +{{- if .Values.controller.ingressClass }} +- --ingress-class={{ .Values.controller.ingressClass }} +{{- end }} +- --configmap={{ default "$(POD_NAMESPACE)" .Values.controller.configMapNamespace }}/{{ include "ingress-nginx.controller.fullname" . }} +{{- if .Values.tcp }} +- --tcp-services-configmap={{ default "$(POD_NAMESPACE)" .Values.controller.tcp.configMapNamespace }}/{{ include "ingress-nginx.fullname" . }}-tcp +{{- end }} +{{- if .Values.udp }} +- --udp-services-configmap={{ default "$(POD_NAMESPACE)" .Values.controller.udp.configMapNamespace }}/{{ include "ingress-nginx.fullname" . }}-udp +{{- end }} +{{- if .Values.controller.scope.enabled }} +- --watch-namespace={{ default "$(POD_NAMESPACE)" .Values.controller.scope.namespace }} +{{- end }} +{{- if and (not .Values.controller.scope.enabled) .Values.controller.scope.namespaceSelector }} +- --watch-namespace-selector={{ default "" .Values.controller.scope.namespaceSelector }} +{{- end }} +{{- if and .Values.controller.reportNodeInternalIp .Values.controller.hostNetwork }} +- --report-node-internal-ip-address={{ .Values.controller.reportNodeInternalIp }} +{{- end }} +{{- if .Values.controller.admissionWebhooks.enabled }} +- --validating-webhook=:{{ .Values.controller.admissionWebhooks.port }} +- --validating-webhook-certificate={{ .Values.controller.admissionWebhooks.certificate }} +- --validating-webhook-key={{ .Values.controller.admissionWebhooks.key }} +{{- end }} +{{- if .Values.controller.maxmindLicenseKey }} +- --maxmind-license-key={{ .Values.controller.maxmindLicenseKey }} +{{- end }} +{{- if .Values.controller.healthCheckHost }} +- --healthz-host={{ .Values.controller.healthCheckHost }} +{{- end }} +{{- if not (eq .Values.controller.healthCheckPath "/healthz") }} +- --health-check-path={{ .Values.controller.healthCheckPath }} +{{- end }} +{{- if .Values.controller.ingressClassByName }} +- --ingress-class-by-name=true +{{- end }} +{{- if .Values.controller.watchIngressWithoutClass }} +- --watch-ingress-without-class=true +{{- end }} +{{- range $key, $value := .Values.controller.extraArgs }} +{{- /* Accept keys without values or with false as value */}} +{{- if eq ($value | quote | len) 2 }} +- --{{ $key }} +{{- else }} +- --{{ $key }}={{ $value }} +{{- end }} +{{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/clusterrole.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/clusterrole.yaml new file mode 100644 index 0000000..5659a1f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/clusterrole.yaml @@ -0,0 +1,34 @@ +{{- if and .Values.controller.admissionWebhooks.enabled .Values.controller.admissionWebhooks.patch.enabled -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ include "ingress-nginx.fullname" . }}-admission + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook + {{- with .Values.controller.admissionWebhooks.patch.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +rules: + - apiGroups: + - admissionregistration.k8s.io + resources: + - validatingwebhookconfigurations + verbs: + - get + - update +{{- if .Values.podSecurityPolicy.enabled }} + - apiGroups: ['extensions'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + {{- with .Values.controller.admissionWebhooks.existingPsp }} + - {{ . }} + {{- else }} + - {{ include "ingress-nginx.fullname" . }}-admission + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/clusterrolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/clusterrolebinding.yaml new file mode 100644 index 0000000..abf17fb --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/clusterrolebinding.yaml @@ -0,0 +1,23 @@ +{{- if and .Values.controller.admissionWebhooks.enabled .Values.controller.admissionWebhooks.patch.enabled -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "ingress-nginx.fullname" . }}-admission + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook + {{- with .Values.controller.admissionWebhooks.patch.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "ingress-nginx.fullname" . }}-admission +subjects: + - kind: ServiceAccount + name: {{ include "ingress-nginx.fullname" . }}-admission + namespace: {{ .Release.Namespace | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/job-createSecret.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/job-createSecret.yaml new file mode 100644 index 0000000..f20e247 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/job-createSecret.yaml @@ -0,0 +1,76 @@ +{{- if and .Values.controller.admissionWebhooks.enabled .Values.controller.admissionWebhooks.patch.enabled -}} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ include "ingress-nginx.fullname" . }}-admission-create + namespace: {{ .Release.Namespace }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + {{- with .Values.controller.admissionWebhooks.annotations }} + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook + {{- with .Values.controller.admissionWebhooks.patch.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: +{{- if .Capabilities.APIVersions.Has "batch/v1alpha1" }} + # Alpha feature since k8s 1.12 + ttlSecondsAfterFinished: 0 +{{- end }} + template: + metadata: + name: {{ include "ingress-nginx.fullname" . }}-admission-create + {{- if .Values.controller.admissionWebhooks.patch.podAnnotations }} + annotations: {{ toYaml .Values.controller.admissionWebhooks.patch.podAnnotations | nindent 8 }} + {{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 8 }} + app.kubernetes.io/component: admission-webhook + {{- with .Values.controller.admissionWebhooks.patch.labels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if .Values.controller.admissionWebhooks.patch.priorityClassName }} + priorityClassName: {{ .Values.controller.admissionWebhooks.patch.priorityClassName }} + {{- end }} + {{- if .Values.imagePullSecrets }} + imagePullSecrets: {{ toYaml .Values.imagePullSecrets | nindent 8 }} + {{- end }} + containers: + - name: create + {{- with .Values.controller.admissionWebhooks.patch.image }} + image: "{{- if .repository -}}{{ .repository }}{{ else }}{{ .registry }}/{{ .image }}{{- end -}}:{{ .tag }}{{- if (.digest) -}} @{{.digest}} {{- end -}}" + {{- end }} + imagePullPolicy: {{ .Values.controller.admissionWebhooks.patch.image.pullPolicy }} + args: + - create + - --host={{ include "ingress-nginx.controller.fullname" . }}-admission,{{ include "ingress-nginx.controller.fullname" . }}-admission.$(POD_NAMESPACE).svc + - --namespace=$(POD_NAMESPACE) + - --secret-name={{ include "ingress-nginx.fullname" . }}-admission + env: + - name: POD_NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + securityContext: + allowPrivilegeEscalation: false + {{- if .Values.controller.admissionWebhooks.createSecretJob.resources }} + resources: {{ toYaml .Values.controller.admissionWebhooks.createSecretJob.resources | nindent 12 }} + {{- end }} + restartPolicy: OnFailure + serviceAccountName: {{ include "ingress-nginx.fullname" . }}-admission + {{- if .Values.controller.admissionWebhooks.patch.nodeSelector }} + nodeSelector: {{ toYaml .Values.controller.admissionWebhooks.patch.nodeSelector | nindent 8 }} + {{- end }} + {{- if .Values.controller.admissionWebhooks.patch.tolerations }} + tolerations: {{ toYaml .Values.controller.admissionWebhooks.patch.tolerations | nindent 8 }} + {{- end }} + securityContext: + runAsNonRoot: true + runAsUser: {{ .Values.controller.admissionWebhooks.patch.runAsUser }} + fsGroup: {{ .Values.controller.admissionWebhooks.patch.fsGroup }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/job-patchWebhook.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/job-patchWebhook.yaml new file mode 100644 index 0000000..8583685 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/job-patchWebhook.yaml @@ -0,0 +1,78 @@ +{{- if and .Values.controller.admissionWebhooks.enabled .Values.controller.admissionWebhooks.patch.enabled -}} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ include "ingress-nginx.fullname" . }}-admission-patch + namespace: {{ .Release.Namespace }} + annotations: + "helm.sh/hook": post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + {{- with .Values.controller.admissionWebhooks.annotations }} + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook + {{- with .Values.controller.admissionWebhooks.patch.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: +{{- if .Capabilities.APIVersions.Has "batch/v1alpha1" }} + # Alpha feature since k8s 1.12 + ttlSecondsAfterFinished: 0 +{{- end }} + template: + metadata: + name: {{ include "ingress-nginx.fullname" . }}-admission-patch + {{- if .Values.controller.admissionWebhooks.patch.podAnnotations }} + annotations: {{ toYaml .Values.controller.admissionWebhooks.patch.podAnnotations | nindent 8 }} + {{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 8 }} + app.kubernetes.io/component: admission-webhook + {{- with .Values.controller.admissionWebhooks.patch.labels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if .Values.controller.admissionWebhooks.patch.priorityClassName }} + priorityClassName: {{ .Values.controller.admissionWebhooks.patch.priorityClassName }} + {{- end }} + {{- if .Values.imagePullSecrets }} + imagePullSecrets: {{ toYaml .Values.imagePullSecrets | nindent 8 }} + {{- end }} + containers: + - name: patch + {{- with .Values.controller.admissionWebhooks.patch.image }} + image: "{{- if .repository -}}{{ .repository }}{{ else }}{{ .registry }}/{{ .image }}{{- end -}}:{{ .tag }}{{- if (.digest) -}} @{{.digest}} {{- end -}}" + {{- end }} + imagePullPolicy: {{ .Values.controller.admissionWebhooks.patch.image.pullPolicy }} + args: + - patch + - --webhook-name={{ include "ingress-nginx.fullname" . }}-admission + - --namespace=$(POD_NAMESPACE) + - --patch-mutating=false + - --secret-name={{ include "ingress-nginx.fullname" . }}-admission + - --patch-failure-policy={{ .Values.controller.admissionWebhooks.failurePolicy }} + env: + - name: POD_NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + securityContext: + allowPrivilegeEscalation: false + {{- if .Values.controller.admissionWebhooks.patchWebhookJob.resources }} + resources: {{ toYaml .Values.controller.admissionWebhooks.patchWebhookJob.resources | nindent 12 }} + {{- end }} + restartPolicy: OnFailure + serviceAccountName: {{ include "ingress-nginx.fullname" . }}-admission + {{- if .Values.controller.admissionWebhooks.patch.nodeSelector }} + nodeSelector: {{ toYaml .Values.controller.admissionWebhooks.patch.nodeSelector | nindent 8 }} + {{- end }} + {{- if .Values.controller.admissionWebhooks.patch.tolerations }} + tolerations: {{ toYaml .Values.controller.admissionWebhooks.patch.tolerations | nindent 8 }} + {{- end }} + securityContext: + runAsNonRoot: true + runAsUser: {{ .Values.controller.admissionWebhooks.patch.runAsUser }} + fsGroup: {{ .Values.controller.admissionWebhooks.patch.fsGroup }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/psp.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/psp.yaml new file mode 100644 index 0000000..70edde3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/psp.yaml @@ -0,0 +1,39 @@ +{{- if and .Values.controller.admissionWebhooks.enabled .Values.controller.admissionWebhooks.patch.enabled .Values.podSecurityPolicy.enabled (empty .Values.controller.admissionWebhooks.existingPsp) -}} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "ingress-nginx.fullname" . }}-admission + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook + {{- with .Values.controller.admissionWebhooks.patch.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + allowPrivilegeEscalation: false + fsGroup: + ranges: + - max: 65535 + min: 1 + rule: MustRunAs + requiredDropCapabilities: + - ALL + runAsUser: + rule: MustRunAsNonRoot + seLinux: + rule: RunAsAny + supplementalGroups: + ranges: + - max: 65535 + min: 1 + rule: MustRunAs + volumes: + - configMap + - emptyDir + - projected + - secret + - downwardAPI +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/role.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/role.yaml new file mode 100644 index 0000000..795bac6 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/role.yaml @@ -0,0 +1,24 @@ +{{- if and .Values.controller.admissionWebhooks.enabled .Values.controller.admissionWebhooks.patch.enabled -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ include "ingress-nginx.fullname" . }}-admission + namespace: {{ .Release.Namespace }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook + {{- with .Values.controller.admissionWebhooks.patch.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +rules: + - apiGroups: + - "" + resources: + - secrets + verbs: + - get + - create +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/rolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/rolebinding.yaml new file mode 100644 index 0000000..698c5c8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/rolebinding.yaml @@ -0,0 +1,24 @@ +{{- if and .Values.controller.admissionWebhooks.enabled .Values.controller.admissionWebhooks.patch.enabled -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "ingress-nginx.fullname" . }}-admission + namespace: {{ .Release.Namespace }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook + {{- with .Values.controller.admissionWebhooks.patch.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "ingress-nginx.fullname" . }}-admission +subjects: + - kind: ServiceAccount + name: {{ include "ingress-nginx.fullname" . }}-admission + namespace: {{ .Release.Namespace | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/serviceaccount.yaml new file mode 100644 index 0000000..eae4751 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/job-patch/serviceaccount.yaml @@ -0,0 +1,16 @@ +{{- if and .Values.controller.admissionWebhooks.enabled .Values.controller.admissionWebhooks.patch.enabled -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "ingress-nginx.fullname" . }}-admission + namespace: {{ .Release.Namespace }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook + {{- with .Values.controller.admissionWebhooks.patch.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/validating-webhook.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/validating-webhook.yaml new file mode 100644 index 0000000..8caffcb --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/admission-webhooks/validating-webhook.yaml @@ -0,0 +1,48 @@ +{{- if .Values.controller.admissionWebhooks.enabled -}} +# before changing this value, check the required kubernetes version +# https://kubernetes.io/docs/reference/access-authn-authz/extensible-admission-controllers/#prerequisites +apiVersion: admissionregistration.k8s.io/v1 +kind: ValidatingWebhookConfiguration +metadata: + {{- if .Values.controller.admissionWebhooks.annotations }} + annotations: {{ toYaml .Values.controller.admissionWebhooks.annotations | nindent 4 }} + {{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: admission-webhook + {{- with .Values.controller.admissionWebhooks.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.fullname" . }}-admission +webhooks: + - name: validate.nginx.ingress.kubernetes.io + matchPolicy: Equivalent + rules: + - apiGroups: + - networking.k8s.io + apiVersions: + - v1 + operations: + - CREATE + - UPDATE + resources: + - ingresses + failurePolicy: {{ .Values.controller.admissionWebhooks.failurePolicy | default "Fail" }} + sideEffects: None + admissionReviewVersions: + - v1 + clientConfig: + service: + namespace: {{ .Release.Namespace | quote }} + name: {{ include "ingress-nginx.controller.fullname" . }}-admission + path: /networking/v1/ingresses + {{- if .Values.controller.admissionWebhooks.timeoutSeconds }} + timeoutSeconds: {{ .Values.controller.admissionWebhooks.timeoutSeconds }} + {{- end }} + {{- if .Values.controller.admissionWebhooks.namespaceSelector }} + namespaceSelector: {{ toYaml .Values.controller.admissionWebhooks.namespaceSelector | nindent 6 }} + {{- end }} + {{- if .Values.controller.admissionWebhooks.objectSelector }} + objectSelector: {{ toYaml .Values.controller.admissionWebhooks.objectSelector | nindent 6 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/clusterrole.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/clusterrole.yaml new file mode 100644 index 0000000..c093f04 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/clusterrole.yaml @@ -0,0 +1,87 @@ +{{- if .Values.rbac.create }} + +{{- if and .Values.rbac.scope (not .Values.controller.scope.enabled) -}} + {{ required "Invalid configuration: 'rbac.scope' should be equal to 'controller.scope.enabled' (true/false)." (index (dict) ".") }} +{{- end }} + +{{- if not .Values.rbac.scope -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.fullname" . }} +rules: + - apiGroups: + - "" + resources: + - configmaps + - endpoints + - nodes + - pods + - secrets +{{- if not .Values.controller.scope.enabled }} + - namespaces +{{- end}} + verbs: + - list + - watch +{{- if and .Values.controller.scope.enabled .Values.controller.scope.namespace }} + - apiGroups: + - "" + resources: + - namespaces + resourceNames: + - "{{ .Values.controller.scope.namespace }}" + verbs: + - get +{{- end }} + - apiGroups: + - "" + resources: + - nodes + verbs: + - get + - apiGroups: + - "" + resources: + - services + verbs: + - get + - list + - watch + - apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch + - apiGroups: + - "" + resources: + - events + verbs: + - create + - patch + - apiGroups: + - networking.k8s.io + resources: + - ingresses/status + verbs: + - update + - apiGroups: + - networking.k8s.io + resources: + - ingressclasses + verbs: + - get + - list + - watch +{{- end }} + +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/clusterrolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/clusterrolebinding.yaml new file mode 100644 index 0000000..acbbd8b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/clusterrolebinding.yaml @@ -0,0 +1,19 @@ +{{- if and .Values.rbac.create (not .Values.rbac.scope) -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.fullname" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "ingress-nginx.fullname" . }} +subjects: + - kind: ServiceAccount + name: {{ template "ingress-nginx.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap-addheaders.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap-addheaders.yaml new file mode 100644 index 0000000..dfd49a1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap-addheaders.yaml @@ -0,0 +1,14 @@ +{{- if .Values.controller.addHeaders -}} +apiVersion: v1 +kind: ConfigMap +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.fullname" . }}-custom-add-headers + namespace: {{ .Release.Namespace }} +data: {{ toYaml .Values.controller.addHeaders | nindent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap-proxyheaders.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap-proxyheaders.yaml new file mode 100644 index 0000000..f8d15fa --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap-proxyheaders.yaml @@ -0,0 +1,19 @@ +{{- if or .Values.controller.proxySetHeaders .Values.controller.headers -}} +apiVersion: v1 +kind: ConfigMap +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.fullname" . }}-custom-proxy-headers + namespace: {{ .Release.Namespace }} +data: +{{- if .Values.controller.proxySetHeaders }} +{{ toYaml .Values.controller.proxySetHeaders | indent 2 }} +{{ else if and .Values.controller.headers (not .Values.controller.proxySetHeaders) }} +{{ toYaml .Values.controller.headers | indent 2 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap-tcp.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap-tcp.yaml new file mode 100644 index 0000000..0f6088e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap-tcp.yaml @@ -0,0 +1,17 @@ +{{- if .Values.tcp -}} +apiVersion: v1 +kind: ConfigMap +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +{{- if .Values.controller.tcp.annotations }} + annotations: {{ toYaml .Values.controller.tcp.annotations | nindent 4 }} +{{- end }} + name: {{ include "ingress-nginx.fullname" . }}-tcp + namespace: {{ .Release.Namespace }} +data: {{ tpl (toYaml .Values.tcp) . | nindent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap-udp.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap-udp.yaml new file mode 100644 index 0000000..3772ec5 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap-udp.yaml @@ -0,0 +1,17 @@ +{{- if .Values.udp -}} +apiVersion: v1 +kind: ConfigMap +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +{{- if .Values.controller.udp.annotations }} + annotations: {{ toYaml .Values.controller.udp.annotations | nindent 4 }} +{{- end }} + name: {{ include "ingress-nginx.fullname" . }}-udp + namespace: {{ .Release.Namespace }} +data: {{ tpl (toYaml .Values.udp) . | nindent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap.yaml new file mode 100644 index 0000000..f28b26e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-configmap.yaml @@ -0,0 +1,29 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +{{- if .Values.controller.configAnnotations }} + annotations: {{ toYaml .Values.controller.configAnnotations | nindent 4 }} +{{- end }} + name: {{ include "ingress-nginx.controller.fullname" . }} + namespace: {{ .Release.Namespace }} +data: + allow-snippet-annotations: "{{ .Values.controller.allowSnippetAnnotations }}" +{{- if .Values.controller.addHeaders }} + add-headers: {{ .Release.Namespace }}/{{ include "ingress-nginx.fullname" . }}-custom-add-headers +{{- end }} +{{- if or .Values.controller.proxySetHeaders .Values.controller.headers }} + proxy-set-headers: {{ .Release.Namespace }}/{{ include "ingress-nginx.fullname" . }}-custom-proxy-headers +{{- end }} +{{- if .Values.dhParam }} + ssl-dh-param: {{ printf "%s/%s" .Release.Namespace (include "ingress-nginx.controller.fullname" .) }} +{{- end }} +{{- range $key, $value := .Values.controller.config }} + {{- $key | nindent 2 }}: {{ $value | quote }} +{{- end }} + diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-daemonset.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-daemonset.yaml new file mode 100644 index 0000000..2dca8e5 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-daemonset.yaml @@ -0,0 +1,223 @@ +{{- if or (eq .Values.controller.kind "DaemonSet") (eq .Values.controller.kind "Both") -}} +{{- include "isControllerTagValid" . -}} +apiVersion: apps/v1 +kind: DaemonSet +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.controller.fullname" . }} + namespace: {{ .Release.Namespace }} + {{- if .Values.controller.annotations }} + annotations: {{ toYaml .Values.controller.annotations | nindent 4 }} + {{- end }} +spec: + selector: + matchLabels: + {{- include "ingress-nginx.selectorLabels" . | nindent 6 }} + app.kubernetes.io/component: controller + revisionHistoryLimit: {{ .Values.revisionHistoryLimit }} + {{- if .Values.controller.updateStrategy }} + updateStrategy: {{ toYaml .Values.controller.updateStrategy | nindent 4 }} + {{- end }} + minReadySeconds: {{ .Values.controller.minReadySeconds }} + template: + metadata: + {{- if .Values.controller.podAnnotations }} + annotations: + {{- range $key, $value := .Values.controller.podAnnotations }} + {{ $key }}: {{ $value | quote }} + {{- end }} + {{- end }} + labels: + {{- include "ingress-nginx.selectorLabels" . | nindent 8 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.controller.podLabels }} + {{- toYaml .Values.controller.podLabels | nindent 8 }} + {{- end }} + spec: + {{- if .Values.controller.dnsConfig }} + dnsConfig: {{ toYaml .Values.controller.dnsConfig | nindent 8 }} + {{- end }} + {{- if .Values.controller.hostname }} + hostname: {{ toYaml .Values.controller.hostname | nindent 8 }} + {{- end }} + dnsPolicy: {{ .Values.controller.dnsPolicy }} + {{- if .Values.imagePullSecrets }} + imagePullSecrets: {{ toYaml .Values.imagePullSecrets | nindent 8 }} + {{- end }} + {{- if .Values.controller.priorityClassName }} + priorityClassName: {{ .Values.controller.priorityClassName }} + {{- end }} + {{- if or .Values.controller.podSecurityContext .Values.controller.sysctls }} + securityContext: + {{- end }} + {{- if .Values.controller.podSecurityContext }} + {{- toYaml .Values.controller.podSecurityContext | nindent 8 }} + {{- end }} + {{- if .Values.controller.sysctls }} + sysctls: + {{- range $sysctl, $value := .Values.controller.sysctls }} + - name: {{ $sysctl | quote }} + value: {{ $value | quote }} + {{- end }} + {{- end }} + {{- if .Values.controller.shareProcessNamespace }} + shareProcessNamespace: {{ .Values.controller.shareProcessNamespace }} + {{- end }} + containers: + - name: {{ .Values.controller.containerName }} + {{- with .Values.controller.image }} + image: "{{- if .repository -}}{{ .repository }}{{ else }}{{ .registry }}/{{ include "ingress-nginx.image" . }}{{- end -}}:{{ .tag }}{{ include "ingress-nginx.imageDigest" . }}" + {{- end }} + imagePullPolicy: {{ .Values.controller.image.pullPolicy }} + {{- if .Values.controller.lifecycle }} + lifecycle: {{ toYaml .Values.controller.lifecycle | nindent 12 }} + {{- end }} + args: + {{- include "ingress-nginx.params" . | nindent 12 }} + securityContext: {{ include "controller.containerSecurityContext" . | nindent 12 }} + env: + - name: POD_NAME + valueFrom: + fieldRef: + fieldPath: metadata.name + - name: POD_NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + {{- if .Values.controller.enableMimalloc }} + - name: LD_PRELOAD + value: /usr/local/lib/libmimalloc.so + {{- end }} + {{- if .Values.controller.extraEnvs }} + {{- toYaml .Values.controller.extraEnvs | nindent 12 }} + {{- end }} + {{- if .Values.controller.startupProbe }} + startupProbe: {{ toYaml .Values.controller.startupProbe | nindent 12 }} + {{- end }} + livenessProbe: {{ toYaml .Values.controller.livenessProbe | nindent 12 }} + readinessProbe: {{ toYaml .Values.controller.readinessProbe | nindent 12 }} + ports: + {{- range $key, $value := .Values.controller.containerPort }} + - name: {{ $key }} + containerPort: {{ $value }} + protocol: TCP + {{- if $.Values.controller.hostPort.enabled }} + hostPort: {{ index $.Values.controller.hostPort.ports $key | default $value }} + {{- end }} + {{- end }} + {{- if .Values.controller.metrics.enabled }} + - name: metrics + containerPort: {{ .Values.controller.metrics.port }} + protocol: TCP + {{- end }} + {{- if .Values.controller.admissionWebhooks.enabled }} + - name: webhook + containerPort: {{ .Values.controller.admissionWebhooks.port }} + protocol: TCP + {{- end }} + {{- range $key, $value := .Values.tcp }} + - name: {{ if $.Values.portNamePrefix }}{{ $.Values.portNamePrefix }}-{{ end }}{{ $key }}-tcp + containerPort: {{ $key }} + protocol: TCP + {{- if $.Values.controller.hostPort.enabled }} + hostPort: {{ $key }} + {{- end }} + {{- end }} + {{- range $key, $value := .Values.udp }} + - name: {{ if $.Values.portNamePrefix }}{{ $.Values.portNamePrefix }}-{{ end }}{{ $key }}-udp + containerPort: {{ $key }} + protocol: UDP + {{- if $.Values.controller.hostPort.enabled }} + hostPort: {{ $key }} + {{- end }} + {{- end }} + {{- if (or .Values.controller.customTemplate.configMapName .Values.controller.extraVolumeMounts .Values.controller.admissionWebhooks.enabled .Values.controller.extraModules) }} + volumeMounts: + {{- if .Values.controller.extraModules }} + - name: modules + mountPath: /modules_mount + {{- end }} + {{- if .Values.controller.customTemplate.configMapName }} + - mountPath: /etc/nginx/template + name: nginx-template-volume + readOnly: true + {{- end }} + {{- if .Values.controller.admissionWebhooks.enabled }} + - name: webhook-cert + mountPath: /usr/local/certificates/ + readOnly: true + {{- end }} + {{- if .Values.controller.extraVolumeMounts }} + {{- toYaml .Values.controller.extraVolumeMounts | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.controller.resources }} + resources: {{ toYaml .Values.controller.resources | nindent 12 }} + {{- end }} + {{- if .Values.controller.extraContainers }} + {{ toYaml .Values.controller.extraContainers | nindent 8 }} + {{- end }} + + + {{- if (or .Values.controller.extraInitContainers .Values.controller.extraModules) }} + initContainers: + {{- if .Values.controller.extraInitContainers }} + {{ toYaml .Values.controller.extraInitContainers | nindent 8 }} + {{- end }} + {{- if .Values.controller.extraModules }} + {{- range .Values.controller.extraModules }} + - name: {{ .Name }} + image: {{ .Image }} + command: ['sh', '-c', '/usr/local/bin/init_module.sh'] + {{- end }} + {{- end }} + {{- end }} + {{- if .Values.controller.hostNetwork }} + hostNetwork: {{ .Values.controller.hostNetwork }} + {{- end }} + {{- if .Values.controller.nodeSelector }} + nodeSelector: {{ toYaml .Values.controller.nodeSelector | nindent 8 }} + {{- end }} + {{- if .Values.controller.tolerations }} + tolerations: {{ toYaml .Values.controller.tolerations | nindent 8 }} + {{- end }} + {{- if .Values.controller.affinity }} + affinity: {{ toYaml .Values.controller.affinity | nindent 8 }} + {{- end }} + {{- if .Values.controller.topologySpreadConstraints }} + topologySpreadConstraints: {{ toYaml .Values.controller.topologySpreadConstraints | nindent 8 }} + {{- end }} + serviceAccountName: {{ template "ingress-nginx.serviceAccountName" . }} + terminationGracePeriodSeconds: {{ .Values.controller.terminationGracePeriodSeconds }} + {{- if (or .Values.controller.customTemplate.configMapName .Values.controller.extraVolumeMounts .Values.controller.admissionWebhooks.enabled .Values.controller.extraVolumes .Values.controller.extraModules) }} + volumes: + {{- if .Values.controller.extraModules }} + - name: modules + emptyDir: {} + {{- end }} + {{- if .Values.controller.customTemplate.configMapName }} + - name: nginx-template-volume + configMap: + name: {{ .Values.controller.customTemplate.configMapName }} + items: + - key: {{ .Values.controller.customTemplate.configMapKey }} + path: nginx.tmpl + {{- end }} + {{- if .Values.controller.admissionWebhooks.enabled }} + - name: webhook-cert + secret: + secretName: {{ include "ingress-nginx.fullname" . }}-admission + {{- end }} + {{- if .Values.controller.extraVolumes }} + {{ toYaml .Values.controller.extraVolumes | nindent 8 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-deployment.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-deployment.yaml new file mode 100644 index 0000000..5b781f8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-deployment.yaml @@ -0,0 +1,228 @@ +{{- if or (eq .Values.controller.kind "Deployment") (eq .Values.controller.kind "Both") -}} +{{- include "isControllerTagValid" . -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.controller.fullname" . }} + namespace: {{ .Release.Namespace }} + {{- if .Values.controller.annotations }} + annotations: {{ toYaml .Values.controller.annotations | nindent 4 }} + {{- end }} +spec: + selector: + matchLabels: + {{- include "ingress-nginx.selectorLabels" . | nindent 6 }} + app.kubernetes.io/component: controller + {{- if not .Values.controller.autoscaling.enabled }} + replicas: {{ .Values.controller.replicaCount }} + {{- end }} + revisionHistoryLimit: {{ .Values.revisionHistoryLimit }} + {{- if .Values.controller.updateStrategy }} + strategy: + {{ toYaml .Values.controller.updateStrategy | nindent 4 }} + {{- end }} + minReadySeconds: {{ .Values.controller.minReadySeconds }} + template: + metadata: + {{- if .Values.controller.podAnnotations }} + annotations: + {{- range $key, $value := .Values.controller.podAnnotations }} + {{ $key }}: {{ $value | quote }} + {{- end }} + {{- end }} + labels: + {{- include "ingress-nginx.selectorLabels" . | nindent 8 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.controller.podLabels }} + {{- toYaml .Values.controller.podLabels | nindent 8 }} + {{- end }} + spec: + {{- if .Values.controller.dnsConfig }} + dnsConfig: {{ toYaml .Values.controller.dnsConfig | nindent 8 }} + {{- end }} + {{- if .Values.controller.hostname }} + hostname: {{ toYaml .Values.controller.hostname | nindent 8 }} + {{- end }} + dnsPolicy: {{ .Values.controller.dnsPolicy }} + {{- if .Values.imagePullSecrets }} + imagePullSecrets: {{ toYaml .Values.imagePullSecrets | nindent 8 }} + {{- end }} + {{- if .Values.controller.priorityClassName }} + priorityClassName: {{ .Values.controller.priorityClassName | quote }} + {{- end }} + {{- if or .Values.controller.podSecurityContext .Values.controller.sysctls }} + securityContext: + {{- end }} + {{- if .Values.controller.podSecurityContext }} + {{- toYaml .Values.controller.podSecurityContext | nindent 8 }} + {{- end }} + {{- if .Values.controller.sysctls }} + sysctls: + {{- range $sysctl, $value := .Values.controller.sysctls }} + - name: {{ $sysctl | quote }} + value: {{ $value | quote }} + {{- end }} + {{- end }} + {{- if .Values.controller.shareProcessNamespace }} + shareProcessNamespace: {{ .Values.controller.shareProcessNamespace }} + {{- end }} + containers: + - name: {{ .Values.controller.containerName }} + {{- with .Values.controller.image }} + image: "{{- if .repository -}}{{ .repository }}{{ else }}{{ .registry }}/{{ include "ingress-nginx.image" . }}{{- end -}}:{{ .tag }}{{ include "ingress-nginx.imageDigest" . }}" + {{- end }} + imagePullPolicy: {{ .Values.controller.image.pullPolicy }} + {{- if .Values.controller.lifecycle }} + lifecycle: {{ toYaml .Values.controller.lifecycle | nindent 12 }} + {{- end }} + args: + {{- include "ingress-nginx.params" . | nindent 12 }} + securityContext: {{ include "controller.containerSecurityContext" . | nindent 12 }} + env: + - name: POD_NAME + valueFrom: + fieldRef: + fieldPath: metadata.name + - name: POD_NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + {{- if .Values.controller.enableMimalloc }} + - name: LD_PRELOAD + value: /usr/local/lib/libmimalloc.so + {{- end }} + {{- if .Values.controller.extraEnvs }} + {{- toYaml .Values.controller.extraEnvs | nindent 12 }} + {{- end }} + {{- if .Values.controller.startupProbe }} + startupProbe: {{ toYaml .Values.controller.startupProbe | nindent 12 }} + {{- end }} + livenessProbe: {{ toYaml .Values.controller.livenessProbe | nindent 12 }} + readinessProbe: {{ toYaml .Values.controller.readinessProbe | nindent 12 }} + ports: + {{- range $key, $value := .Values.controller.containerPort }} + - name: {{ $key }} + containerPort: {{ $value }} + protocol: TCP + {{- if $.Values.controller.hostPort.enabled }} + hostPort: {{ index $.Values.controller.hostPort.ports $key | default $value }} + {{- end }} + {{- end }} + {{- if .Values.controller.metrics.enabled }} + - name: metrics + containerPort: {{ .Values.controller.metrics.port }} + protocol: TCP + {{- end }} + {{- if .Values.controller.admissionWebhooks.enabled }} + - name: webhook + containerPort: {{ .Values.controller.admissionWebhooks.port }} + protocol: TCP + {{- end }} + {{- range $key, $value := .Values.tcp }} + - name: {{ if $.Values.portNamePrefix }}{{ $.Values.portNamePrefix }}-{{ end }}{{ $key }}-tcp + containerPort: {{ $key }} + protocol: TCP + {{- if $.Values.controller.hostPort.enabled }} + hostPort: {{ $key }} + {{- end }} + {{- end }} + {{- range $key, $value := .Values.udp }} + - name: {{ if $.Values.portNamePrefix }}{{ $.Values.portNamePrefix }}-{{ end }}{{ $key }}-udp + containerPort: {{ $key }} + protocol: UDP + {{- if $.Values.controller.hostPort.enabled }} + hostPort: {{ $key }} + {{- end }} + {{- end }} + {{- if (or .Values.controller.customTemplate.configMapName .Values.controller.extraVolumeMounts .Values.controller.admissionWebhooks.enabled .Values.controller.extraModules) }} + volumeMounts: + {{- if .Values.controller.extraModules }} + - name: modules + mountPath: /modules_mount + {{- end }} + {{- if .Values.controller.customTemplate.configMapName }} + - mountPath: /etc/nginx/template + name: nginx-template-volume + readOnly: true + {{- end }} + {{- if .Values.controller.admissionWebhooks.enabled }} + - name: webhook-cert + mountPath: /usr/local/certificates/ + readOnly: true + {{- end }} + {{- if .Values.controller.extraVolumeMounts }} + {{- toYaml .Values.controller.extraVolumeMounts | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.controller.resources }} + resources: {{ toYaml .Values.controller.resources | nindent 12 }} + {{- end }} + {{- if .Values.controller.extraContainers }} + {{ toYaml .Values.controller.extraContainers | nindent 8 }} + {{- end }} + {{- if (or .Values.controller.extraInitContainers .Values.controller.extraModules) }} + initContainers: + {{- if .Values.controller.extraInitContainers }} + {{ toYaml .Values.controller.extraInitContainers | nindent 8 }} + {{- end }} + {{- if .Values.controller.extraModules }} + {{- range .Values.controller.extraModules }} + - name: {{ .name }} + image: {{ .image }} + command: ['sh', '-c', '/usr/local/bin/init_module.sh'] + volumeMounts: + - name: modules + mountPath: /modules_mount + {{- end }} + {{- end }} + {{- end }} + {{- if .Values.controller.hostNetwork }} + hostNetwork: {{ .Values.controller.hostNetwork }} + {{- end }} + {{- if .Values.controller.nodeSelector }} + nodeSelector: {{ toYaml .Values.controller.nodeSelector | nindent 8 }} + {{- end }} + {{- if .Values.controller.tolerations }} + tolerations: {{ toYaml .Values.controller.tolerations | nindent 8 }} + {{- end }} + {{- if .Values.controller.affinity }} + affinity: {{ toYaml .Values.controller.affinity | nindent 8 }} + {{- end }} + {{- if .Values.controller.topologySpreadConstraints }} + topologySpreadConstraints: {{ toYaml .Values.controller.topologySpreadConstraints | nindent 8 }} + {{- end }} + serviceAccountName: {{ template "ingress-nginx.serviceAccountName" . }} + terminationGracePeriodSeconds: {{ .Values.controller.terminationGracePeriodSeconds }} + {{- if (or .Values.controller.customTemplate.configMapName .Values.controller.extraVolumeMounts .Values.controller.admissionWebhooks.enabled .Values.controller.extraVolumes .Values.controller.extraModules) }} + volumes: + {{- if .Values.controller.extraModules }} + - name: modules + emptyDir: {} + {{- end }} + {{- if .Values.controller.customTemplate.configMapName }} + - name: nginx-template-volume + configMap: + name: {{ .Values.controller.customTemplate.configMapName }} + items: + - key: {{ .Values.controller.customTemplate.configMapKey }} + path: nginx.tmpl + {{- end }} + {{- if .Values.controller.admissionWebhooks.enabled }} + - name: webhook-cert + secret: + secretName: {{ include "ingress-nginx.fullname" . }}-admission + {{- end }} + {{- if .Values.controller.extraVolumes }} + {{ toYaml .Values.controller.extraVolumes | nindent 8 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-hpa.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-hpa.yaml new file mode 100644 index 0000000..e0979f1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-hpa.yaml @@ -0,0 +1,52 @@ +{{- if and .Values.controller.autoscaling.enabled (or (eq .Values.controller.kind "Deployment") (eq .Values.controller.kind "Both")) -}} +{{- if not .Values.controller.keda.enabled }} + +apiVersion: autoscaling/v2beta2 +kind: HorizontalPodAutoscaler +metadata: + annotations: + {{- with .Values.controller.autoscaling.annotations }} + {{- toYaml . | trimSuffix "\n" | nindent 4 }} + {{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.controller.fullname" . }} + namespace: {{ .Release.Namespace }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "ingress-nginx.controller.fullname" . }} + minReplicas: {{ .Values.controller.autoscaling.minReplicas }} + maxReplicas: {{ .Values.controller.autoscaling.maxReplicas }} + metrics: + {{- with .Values.controller.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + target: + type: Utilization + averageUtilization: {{ . }} + {{- end }} + {{- with .Values.controller.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + target: + type: Utilization + averageUtilization: {{ . }} + {{- end }} + {{- with .Values.controller.autoscalingTemplate }} + {{- toYaml . | nindent 2 }} + {{- end }} + {{- with .Values.controller.autoscaling.behavior }} + behavior: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} + diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-ingressclass.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-ingressclass.yaml new file mode 100644 index 0000000..9492784 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-ingressclass.yaml @@ -0,0 +1,21 @@ +{{- if .Values.controller.ingressClassResource.enabled -}} +# We don't support namespaced ingressClass yet +# So a ClusterRole and a ClusterRoleBinding is required +apiVersion: networking.k8s.io/v1 +kind: IngressClass +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ .Values.controller.ingressClassResource.name }} +{{- if .Values.controller.ingressClassResource.default }} + annotations: + ingressclass.kubernetes.io/is-default-class: "true" +{{- end }} +spec: + controller: {{ .Values.controller.ingressClassResource.controllerValue }} + {{ template "ingressClass.parameters" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-keda.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-keda.yaml new file mode 100644 index 0000000..875157e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-keda.yaml @@ -0,0 +1,42 @@ +{{- if and .Values.controller.keda.enabled (or (eq .Values.controller.kind "Deployment") (eq .Values.controller.kind "Both")) -}} +# https://keda.sh/docs/ + +apiVersion: {{ .Values.controller.keda.apiVersion }} +kind: ScaledObject +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.controller.fullname" . }} + {{- if .Values.controller.keda.scaledObject.annotations }} + annotations: {{ toYaml .Values.controller.keda.scaledObject.annotations | nindent 4 }} + {{- end }} +spec: + scaleTargetRef: +{{- if eq .Values.controller.keda.apiVersion "keda.k8s.io/v1alpha1" }} + deploymentName: {{ include "ingress-nginx.controller.fullname" . }} +{{- else if eq .Values.controller.keda.apiVersion "keda.sh/v1alpha1" }} + name: {{ include "ingress-nginx.controller.fullname" . }} +{{- end }} + pollingInterval: {{ .Values.controller.keda.pollingInterval }} + cooldownPeriod: {{ .Values.controller.keda.cooldownPeriod }} + minReplicaCount: {{ .Values.controller.keda.minReplicas }} + maxReplicaCount: {{ .Values.controller.keda.maxReplicas }} + triggers: +{{- with .Values.controller.keda.triggers }} +{{ toYaml . | indent 2 }} +{{ end }} + advanced: + restoreToOriginalReplicaCount: {{ .Values.controller.keda.restoreToOriginalReplicaCount }} +{{- if .Values.controller.keda.behavior }} + horizontalPodAutoscalerConfig: + behavior: +{{ with .Values.controller.keda.behavior -}} +{{ toYaml . | indent 8 }} +{{ end }} + +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-poddisruptionbudget.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-poddisruptionbudget.yaml new file mode 100644 index 0000000..8dfbe98 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-poddisruptionbudget.yaml @@ -0,0 +1,19 @@ +{{- if or (and .Values.controller.autoscaling.enabled (gt (.Values.controller.autoscaling.minReplicas | int) 1)) (and (not .Values.controller.autoscaling.enabled) (gt (.Values.controller.replicaCount | int) 1)) }} +apiVersion: {{ ternary "policy/v1" "policy/v1beta1" (semverCompare ">=1.21.0-0" .Capabilities.KubeVersion.Version) }} +kind: PodDisruptionBudget +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.controller.fullname" . }} + namespace: {{ .Release.Namespace }} +spec: + selector: + matchLabels: + {{- include "ingress-nginx.selectorLabels" . | nindent 6 }} + app.kubernetes.io/component: controller + minAvailable: {{ .Values.controller.minAvailable }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-prometheusrules.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-prometheusrules.yaml new file mode 100644 index 0000000..ca54275 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-prometheusrules.yaml @@ -0,0 +1,21 @@ +{{- if and .Values.controller.metrics.enabled .Values.controller.metrics.prometheusRule.enabled -}} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ include "ingress-nginx.controller.fullname" . }} +{{- if .Values.controller.metrics.prometheusRule.namespace }} + namespace: {{ .Values.controller.metrics.prometheusRule.namespace | quote }} +{{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- if .Values.controller.metrics.prometheusRule.additionalLabels }} + {{- toYaml .Values.controller.metrics.prometheusRule.additionalLabels | nindent 4 }} + {{- end }} +spec: +{{- if .Values.controller.metrics.prometheusRule.rules }} + groups: + - name: {{ template "ingress-nginx.name" . }} + rules: {{- toYaml .Values.controller.metrics.prometheusRule.rules | nindent 4 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-psp.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-psp.yaml new file mode 100644 index 0000000..fe34408 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-psp.yaml @@ -0,0 +1,92 @@ +{{- if and .Values.podSecurityPolicy.enabled (empty .Values.controller.existingPsp) -}} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "ingress-nginx.fullname" . }} + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + allowedCapabilities: + - NET_BIND_SERVICE + {{- if .Values.controller.image.chroot }} + - SYS_CHROOT + {{- end }} +{{- if .Values.controller.sysctls }} + allowedUnsafeSysctls: + {{- range $sysctl, $value := .Values.controller.sysctls }} + - {{ $sysctl }} + {{- end }} +{{- end }} + privileged: false + allowPrivilegeEscalation: true + # Allow core volume types. + volumes: + - 'configMap' + - 'emptyDir' + #- 'projected' + - 'secret' + #- 'downwardAPI' +{{- if .Values.controller.hostNetwork }} + hostNetwork: {{ .Values.controller.hostNetwork }} +{{- end }} +{{- if or .Values.controller.hostNetwork .Values.controller.hostPort.enabled }} + hostPorts: +{{- if .Values.controller.hostNetwork }} +{{- range $key, $value := .Values.controller.containerPort }} + # {{ $key }} + - min: {{ $value }} + max: {{ $value }} +{{- end }} +{{- else if .Values.controller.hostPort.enabled }} +{{- range $key, $value := .Values.controller.hostPort.ports }} + # {{ $key }} + - min: {{ $value }} + max: {{ $value }} +{{- end }} +{{- end }} +{{- if .Values.controller.metrics.enabled }} + # metrics + - min: {{ .Values.controller.metrics.port }} + max: {{ .Values.controller.metrics.port }} +{{- end }} +{{- if .Values.controller.admissionWebhooks.enabled }} + # admission webhooks + - min: {{ .Values.controller.admissionWebhooks.port }} + max: {{ .Values.controller.admissionWebhooks.port }} +{{- end }} +{{- range $key, $value := .Values.tcp }} + # {{ $key }}-tcp + - min: {{ $key }} + max: {{ $key }} +{{- end }} +{{- range $key, $value := .Values.udp }} + # {{ $key }}-udp + - min: {{ $key }} + max: {{ $key }} +{{- end }} +{{- end }} + hostIPC: false + hostPID: false + runAsUser: + # Require the container to run without root privileges. + rule: 'MustRunAsNonRoot' + supplementalGroups: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 1 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 1 + max: 65535 + readOnlyRootFilesystem: false + seLinux: + rule: 'RunAsAny' +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-role.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-role.yaml new file mode 100644 index 0000000..47bbc32 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-role.yaml @@ -0,0 +1,93 @@ +{{- if .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.fullname" . }} + namespace: {{ .Release.Namespace }} +rules: + - apiGroups: + - "" + resources: + - namespaces + verbs: + - get + - apiGroups: + - "" + resources: + - configmaps + - pods + - secrets + - endpoints + verbs: + - get + - list + - watch + - apiGroups: + - "" + resources: + - services + verbs: + - get + - list + - watch + - apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch + - apiGroups: + - networking.k8s.io + resources: + - ingresses/status + verbs: + - update + - apiGroups: + - networking.k8s.io + resources: + - ingressclasses + verbs: + - get + - list + - watch + - apiGroups: + - "" + resources: + - configmaps + resourceNames: + - {{ .Values.controller.electionID }} + verbs: + - get + - update + - apiGroups: + - "" + resources: + - configmaps + verbs: + - create + - apiGroups: + - "" + resources: + - events + verbs: + - create + - patch +{{- if .Values.podSecurityPolicy.enabled }} + - apiGroups: [{{ template "podSecurityPolicy.apiGroup" . }}] + resources: ['podsecuritypolicies'] + verbs: ['use'] + {{- with .Values.controller.existingPsp }} + resourceNames: [{{ . }}] + {{- else }} + resourceNames: [{{ include "ingress-nginx.fullname" . }}] + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-rolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-rolebinding.yaml new file mode 100644 index 0000000..e846a11 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-rolebinding.yaml @@ -0,0 +1,21 @@ +{{- if .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.fullname" . }} + namespace: {{ .Release.Namespace }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "ingress-nginx.fullname" . }} +subjects: + - kind: ServiceAccount + name: {{ template "ingress-nginx.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-service-internal.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-service-internal.yaml new file mode 100644 index 0000000..aae3e15 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-service-internal.yaml @@ -0,0 +1,79 @@ +{{- if and .Values.controller.service.enabled .Values.controller.service.internal.enabled .Values.controller.service.internal.annotations}} +apiVersion: v1 +kind: Service +metadata: + annotations: + {{- range $key, $value := .Values.controller.service.internal.annotations }} + {{ $key }}: {{ $value | quote }} + {{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- if .Values.controller.service.labels }} + {{- toYaml .Values.controller.service.labels | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.controller.fullname" . }}-internal + namespace: {{ .Release.Namespace }} +spec: + type: "{{ .Values.controller.service.type }}" +{{- if .Values.controller.service.internal.loadBalancerIP }} + loadBalancerIP: {{ .Values.controller.service.internal.loadBalancerIP }} +{{- end }} +{{- if .Values.controller.service.internal.loadBalancerSourceRanges }} + loadBalancerSourceRanges: {{ toYaml .Values.controller.service.internal.loadBalancerSourceRanges | nindent 4 }} +{{- end }} +{{- if .Values.controller.service.internal.externalTrafficPolicy }} + externalTrafficPolicy: {{ .Values.controller.service.internal.externalTrafficPolicy }} +{{- end }} + ports: + {{- $setNodePorts := (or (eq .Values.controller.service.type "NodePort") (eq .Values.controller.service.type "LoadBalancer")) }} + {{- if .Values.controller.service.enableHttp }} + - name: http + port: {{ .Values.controller.service.ports.http }} + protocol: TCP + targetPort: {{ .Values.controller.service.targetPorts.http }} + {{- if semverCompare ">=1.20" .Capabilities.KubeVersion.Version }} + appProtocol: http + {{- end }} + {{- if (and $setNodePorts (not (empty .Values.controller.service.nodePorts.http))) }} + nodePort: {{ .Values.controller.service.nodePorts.http }} + {{- end }} + {{- end }} + {{- if .Values.controller.service.enableHttps }} + - name: https + port: {{ .Values.controller.service.ports.https }} + protocol: TCP + targetPort: {{ .Values.controller.service.targetPorts.https }} + {{- if semverCompare ">=1.20" .Capabilities.KubeVersion.Version }} + appProtocol: https + {{- end }} + {{- if (and $setNodePorts (not (empty .Values.controller.service.nodePorts.https))) }} + nodePort: {{ .Values.controller.service.nodePorts.https }} + {{- end }} + {{- end }} + {{- range $key, $value := .Values.tcp }} + - name: {{ if $.Values.portNamePrefix }}{{ $.Values.portNamePrefix }}-{{ end }}{{ $key }}-tcp + port: {{ $key }} + protocol: TCP + targetPort: {{ if $.Values.portNamePrefix }}{{ $.Values.portNamePrefix }}-{{ end }}{{ $key }}-tcp + {{- if $.Values.controller.service.nodePorts.tcp }} + {{- if index $.Values.controller.service.nodePorts.tcp $key }} + nodePort: {{ index $.Values.controller.service.nodePorts.tcp $key }} + {{- end }} + {{- end }} + {{- end }} + {{- range $key, $value := .Values.udp }} + - name: {{ if $.Values.portNamePrefix }}{{ $.Values.portNamePrefix }}-{{ end }}{{ $key }}-udp + port: {{ $key }} + protocol: UDP + targetPort: {{ if $.Values.portNamePrefix }}{{ $.Values.portNamePrefix }}-{{ end }}{{ $key }}-udp + {{- if $.Values.controller.service.nodePorts.udp }} + {{- if index $.Values.controller.service.nodePorts.udp $key }} + nodePort: {{ index $.Values.controller.service.nodePorts.udp $key }} + {{- end }} + {{- end }} + {{- end }} + selector: + {{- include "ingress-nginx.selectorLabels" . | nindent 4 }} + app.kubernetes.io/component: controller +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-service-metrics.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-service-metrics.yaml new file mode 100644 index 0000000..0aaf414 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-service-metrics.yaml @@ -0,0 +1,45 @@ +{{- if .Values.controller.metrics.enabled -}} +apiVersion: v1 +kind: Service +metadata: +{{- if .Values.controller.metrics.service.annotations }} + annotations: {{ toYaml .Values.controller.metrics.service.annotations | nindent 4 }} +{{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- if .Values.controller.metrics.service.labels }} + {{- toYaml .Values.controller.metrics.service.labels | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.controller.fullname" . }}-metrics + namespace: {{ .Release.Namespace }} +spec: + type: {{ .Values.controller.metrics.service.type }} +{{- if .Values.controller.metrics.service.clusterIP }} + clusterIP: {{ .Values.controller.metrics.service.clusterIP }} +{{- end }} +{{- if .Values.controller.metrics.service.externalIPs }} + externalIPs: {{ toYaml .Values.controller.metrics.service.externalIPs | nindent 4 }} +{{- end }} +{{- if .Values.controller.metrics.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.controller.metrics.service.loadBalancerIP }} +{{- end }} +{{- if .Values.controller.metrics.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: {{ toYaml .Values.controller.metrics.service.loadBalancerSourceRanges | nindent 4 }} +{{- end }} +{{- if .Values.controller.metrics.service.externalTrafficPolicy }} + externalTrafficPolicy: {{ .Values.controller.metrics.service.externalTrafficPolicy }} +{{- end }} + ports: + - name: metrics + port: {{ .Values.controller.metrics.service.servicePort }} + protocol: TCP + targetPort: metrics + {{- $setNodePorts := (or (eq .Values.controller.metrics.service.type "NodePort") (eq .Values.controller.metrics.service.type "LoadBalancer")) }} + {{- if (and $setNodePorts (not (empty .Values.controller.metrics.service.nodePort))) }} + nodePort: {{ .Values.controller.metrics.service.nodePort }} + {{- end }} + selector: + {{- include "ingress-nginx.selectorLabels" . | nindent 4 }} + app.kubernetes.io/component: controller +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-service-webhook.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-service-webhook.yaml new file mode 100644 index 0000000..2aae24f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-service-webhook.yaml @@ -0,0 +1,40 @@ +{{- if .Values.controller.admissionWebhooks.enabled -}} +apiVersion: v1 +kind: Service +metadata: +{{- if .Values.controller.admissionWebhooks.service.annotations }} + annotations: {{ toYaml .Values.controller.admissionWebhooks.service.annotations | nindent 4 }} +{{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.controller.fullname" . }}-admission + namespace: {{ .Release.Namespace }} +spec: + type: {{ .Values.controller.admissionWebhooks.service.type }} +{{- if .Values.controller.admissionWebhooks.service.clusterIP }} + clusterIP: {{ .Values.controller.admissionWebhooks.service.clusterIP }} +{{- end }} +{{- if .Values.controller.admissionWebhooks.service.externalIPs }} + externalIPs: {{ toYaml .Values.controller.admissionWebhooks.service.externalIPs | nindent 4 }} +{{- end }} +{{- if .Values.controller.admissionWebhooks.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.controller.admissionWebhooks.service.loadBalancerIP }} +{{- end }} +{{- if .Values.controller.admissionWebhooks.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: {{ toYaml .Values.controller.admissionWebhooks.service.loadBalancerSourceRanges | nindent 4 }} +{{- end }} + ports: + - name: https-webhook + port: 443 + targetPort: webhook + {{- if semverCompare ">=1.20" .Capabilities.KubeVersion.Version }} + appProtocol: https + {{- end }} + selector: + {{- include "ingress-nginx.selectorLabels" . | nindent 4 }} + app.kubernetes.io/component: controller +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-service.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-service.yaml new file mode 100644 index 0000000..2b28196 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-service.yaml @@ -0,0 +1,101 @@ +{{- if and .Values.controller.service.enabled .Values.controller.service.external.enabled -}} +apiVersion: v1 +kind: Service +metadata: + annotations: + {{- range $key, $value := .Values.controller.service.annotations }} + {{ $key }}: {{ $value | quote }} + {{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- if .Values.controller.service.labels }} + {{- toYaml .Values.controller.service.labels | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.controller.fullname" . }} + namespace: {{ .Release.Namespace }} +spec: + type: {{ .Values.controller.service.type }} +{{- if .Values.controller.service.clusterIP }} + clusterIP: {{ .Values.controller.service.clusterIP }} +{{- end }} +{{- if .Values.controller.service.externalIPs }} + externalIPs: {{ toYaml .Values.controller.service.externalIPs | nindent 4 }} +{{- end }} +{{- if .Values.controller.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.controller.service.loadBalancerIP }} +{{- end }} +{{- if .Values.controller.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: {{ toYaml .Values.controller.service.loadBalancerSourceRanges | nindent 4 }} +{{- end }} +{{- if .Values.controller.service.externalTrafficPolicy }} + externalTrafficPolicy: {{ .Values.controller.service.externalTrafficPolicy }} +{{- end }} +{{- if .Values.controller.service.sessionAffinity }} + sessionAffinity: {{ .Values.controller.service.sessionAffinity }} +{{- end }} +{{- if .Values.controller.service.healthCheckNodePort }} + healthCheckNodePort: {{ .Values.controller.service.healthCheckNodePort }} +{{- end }} +{{- if semverCompare ">=1.21.0-0" .Capabilities.KubeVersion.Version -}} +{{- if .Values.controller.service.ipFamilyPolicy }} + ipFamilyPolicy: {{ .Values.controller.service.ipFamilyPolicy }} +{{- end }} +{{- end }} +{{- if semverCompare ">=1.21.0-0" .Capabilities.KubeVersion.Version -}} +{{- if .Values.controller.service.ipFamilies }} + ipFamilies: {{ toYaml .Values.controller.service.ipFamilies | nindent 4 }} +{{- end }} +{{- end }} + ports: + {{- $setNodePorts := (or (eq .Values.controller.service.type "NodePort") (eq .Values.controller.service.type "LoadBalancer")) }} + {{- if .Values.controller.service.enableHttp }} + - name: http + port: {{ .Values.controller.service.ports.http }} + protocol: TCP + targetPort: {{ .Values.controller.service.targetPorts.http }} + {{- if and (semverCompare ">=1.20" .Capabilities.KubeVersion.Version) (.Values.controller.service.appProtocol) }} + appProtocol: http + {{- end }} + {{- if (and $setNodePorts (not (empty .Values.controller.service.nodePorts.http))) }} + nodePort: {{ .Values.controller.service.nodePorts.http }} + {{- end }} + {{- end }} + {{- if .Values.controller.service.enableHttps }} + - name: https + port: {{ .Values.controller.service.ports.https }} + protocol: TCP + targetPort: {{ .Values.controller.service.targetPorts.https }} + {{- if and (semverCompare ">=1.20" .Capabilities.KubeVersion.Version) (.Values.controller.service.appProtocol) }} + appProtocol: https + {{- end }} + {{- if (and $setNodePorts (not (empty .Values.controller.service.nodePorts.https))) }} + nodePort: {{ .Values.controller.service.nodePorts.https }} + {{- end }} + {{- end }} + {{- range $key, $value := .Values.tcp }} + - name: {{ if $.Values.portNamePrefix }}{{ $.Values.portNamePrefix }}-{{ end }}{{ $key }}-tcp + port: {{ $key }} + protocol: TCP + targetPort: {{ if $.Values.portNamePrefix }}{{ $.Values.portNamePrefix }}-{{ end }}{{ $key }}-tcp + {{- if $.Values.controller.service.nodePorts.tcp }} + {{- if index $.Values.controller.service.nodePorts.tcp $key }} + nodePort: {{ index $.Values.controller.service.nodePorts.tcp $key }} + {{- end }} + {{- end }} + {{- end }} + {{- range $key, $value := .Values.udp }} + - name: {{ if $.Values.portNamePrefix }}{{ $.Values.portNamePrefix }}-{{ end }}{{ $key }}-udp + port: {{ $key }} + protocol: UDP + targetPort: {{ if $.Values.portNamePrefix }}{{ $.Values.portNamePrefix }}-{{ end }}{{ $key }}-udp + {{- if $.Values.controller.service.nodePorts.udp }} + {{- if index $.Values.controller.service.nodePorts.udp $key }} + nodePort: {{ index $.Values.controller.service.nodePorts.udp $key }} + {{- end }} + {{- end }} + {{- end }} + selector: + {{- include "ingress-nginx.selectorLabels" . | nindent 4 }} + app.kubernetes.io/component: controller +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-serviceaccount.yaml new file mode 100644 index 0000000..824b2a1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-serviceaccount.yaml @@ -0,0 +1,18 @@ +{{- if or .Values.serviceAccount.create -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- with .Values.controller.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ template "ingress-nginx.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} + {{- if .Values.serviceAccount.annotations }} + annotations: + {{ toYaml .Values.serviceAccount.annotations | indent 4 }} + {{- end }} +automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-servicemonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-servicemonitor.yaml new file mode 100644 index 0000000..4dbc6da --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/controller-servicemonitor.yaml @@ -0,0 +1,48 @@ +{{- if and .Values.controller.metrics.enabled .Values.controller.metrics.serviceMonitor.enabled -}} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "ingress-nginx.controller.fullname" . }} +{{- if .Values.controller.metrics.serviceMonitor.namespace }} + namespace: {{ .Values.controller.metrics.serviceMonitor.namespace | quote }} +{{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: controller + {{- if .Values.controller.metrics.serviceMonitor.additionalLabels }} + {{- toYaml .Values.controller.metrics.serviceMonitor.additionalLabels | nindent 4 }} + {{- end }} +spec: + endpoints: + - port: metrics + interval: {{ .Values.controller.metrics.serviceMonitor.scrapeInterval }} + {{- if .Values.controller.metrics.serviceMonitor.honorLabels }} + honorLabels: true + {{- end }} + {{- if .Values.controller.metrics.serviceMonitor.relabelings }} + relabelings: {{ toYaml .Values.controller.metrics.serviceMonitor.relabelings | nindent 8 }} + {{- end }} + {{- if .Values.controller.metrics.serviceMonitor.metricRelabelings }} + metricRelabelings: {{ toYaml .Values.controller.metrics.serviceMonitor.metricRelabelings | nindent 8 }} + {{- end }} +{{- if .Values.controller.metrics.serviceMonitor.jobLabel }} + jobLabel: {{ .Values.controller.metrics.serviceMonitor.jobLabel | quote }} +{{- end }} +{{- if .Values.controller.metrics.serviceMonitor.namespaceSelector }} + namespaceSelector: {{ toYaml .Values.controller.metrics.serviceMonitor.namespaceSelector | nindent 4 }} +{{- else }} + namespaceSelector: + matchNames: + - {{ .Release.Namespace }} +{{- end }} +{{- if .Values.controller.metrics.serviceMonitor.targetLabels }} + targetLabels: + {{- range .Values.controller.metrics.serviceMonitor.targetLabels }} + - {{ . }} + {{- end }} +{{- end }} + selector: + matchLabels: + {{- include "ingress-nginx.selectorLabels" . | nindent 6 }} + app.kubernetes.io/component: controller +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-deployment.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-deployment.yaml new file mode 100644 index 0000000..fd3e96e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-deployment.yaml @@ -0,0 +1,118 @@ +{{- if .Values.defaultBackend.enabled -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: default-backend + {{- with .Values.defaultBackend.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.defaultBackend.fullname" . }} + namespace: {{ .Release.Namespace }} +spec: + selector: + matchLabels: + {{- include "ingress-nginx.selectorLabels" . | nindent 6 }} + app.kubernetes.io/component: default-backend +{{- if not .Values.defaultBackend.autoscaling.enabled }} + replicas: {{ .Values.defaultBackend.replicaCount }} +{{- end }} + revisionHistoryLimit: {{ .Values.revisionHistoryLimit }} + template: + metadata: + {{- if .Values.defaultBackend.podAnnotations }} + annotations: {{ toYaml .Values.defaultBackend.podAnnotations | nindent 8 }} + {{- end }} + labels: + {{- include "ingress-nginx.selectorLabels" . | nindent 8 }} + app.kubernetes.io/component: default-backend + {{- with .Values.defaultBackend.labels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.defaultBackend.podLabels }} + {{- toYaml .Values.defaultBackend.podLabels | nindent 8 }} + {{- end }} + spec: + {{- if .Values.imagePullSecrets }} + imagePullSecrets: {{ toYaml .Values.imagePullSecrets | nindent 8 }} + {{- end }} + {{- if .Values.defaultBackend.priorityClassName }} + priorityClassName: {{ .Values.defaultBackend.priorityClassName }} + {{- end }} + {{- if .Values.defaultBackend.podSecurityContext }} + securityContext: {{ toYaml .Values.defaultBackend.podSecurityContext | nindent 8 }} + {{- end }} + containers: + - name: {{ template "ingress-nginx.name" . }}-default-backend + {{- with .Values.defaultBackend.image }} + image: "{{- if .repository -}}{{ .repository }}{{ else }}{{ .registry }}/{{ .image }}{{- end -}}:{{ .tag }}{{- if (.digest) -}} @{{.digest}} {{- end -}}" + {{- end }} + imagePullPolicy: {{ .Values.defaultBackend.image.pullPolicy }} + {{- if .Values.defaultBackend.extraArgs }} + args: + {{- range $key, $value := .Values.defaultBackend.extraArgs }} + {{- /* Accept keys without values or with false as value */}} + {{- if eq ($value | quote | len) 2 }} + - --{{ $key }} + {{- else }} + - --{{ $key }}={{ $value }} + {{- end }} + {{- end }} + {{- end }} + securityContext: + capabilities: + drop: + - ALL + runAsUser: {{ .Values.defaultBackend.image.runAsUser }} + runAsNonRoot: {{ .Values.defaultBackend.image.runAsNonRoot }} + allowPrivilegeEscalation: {{ .Values.defaultBackend.image.allowPrivilegeEscalation }} + readOnlyRootFilesystem: {{ .Values.defaultBackend.image.readOnlyRootFilesystem}} + {{- if .Values.defaultBackend.extraEnvs }} + env: {{ toYaml .Values.defaultBackend.extraEnvs | nindent 12 }} + {{- end }} + livenessProbe: + httpGet: + path: /healthz + port: {{ .Values.defaultBackend.port }} + scheme: HTTP + initialDelaySeconds: {{ .Values.defaultBackend.livenessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.defaultBackend.livenessProbe.periodSeconds }} + timeoutSeconds: {{ .Values.defaultBackend.livenessProbe.timeoutSeconds }} + successThreshold: {{ .Values.defaultBackend.livenessProbe.successThreshold }} + failureThreshold: {{ .Values.defaultBackend.livenessProbe.failureThreshold }} + readinessProbe: + httpGet: + path: /healthz + port: {{ .Values.defaultBackend.port }} + scheme: HTTP + initialDelaySeconds: {{ .Values.defaultBackend.readinessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.defaultBackend.readinessProbe.periodSeconds }} + timeoutSeconds: {{ .Values.defaultBackend.readinessProbe.timeoutSeconds }} + successThreshold: {{ .Values.defaultBackend.readinessProbe.successThreshold }} + failureThreshold: {{ .Values.defaultBackend.readinessProbe.failureThreshold }} + ports: + - name: http + containerPort: {{ .Values.defaultBackend.port }} + protocol: TCP + {{- if .Values.defaultBackend.extraVolumeMounts }} + volumeMounts: {{- toYaml .Values.defaultBackend.extraVolumeMounts | nindent 12 }} + {{- end }} + {{- if .Values.defaultBackend.resources }} + resources: {{ toYaml .Values.defaultBackend.resources | nindent 12 }} + {{- end }} + {{- if .Values.defaultBackend.nodeSelector }} + nodeSelector: {{ toYaml .Values.defaultBackend.nodeSelector | nindent 8 }} + {{- end }} + serviceAccountName: {{ template "ingress-nginx.defaultBackend.serviceAccountName" . }} + {{- if .Values.defaultBackend.tolerations }} + tolerations: {{ toYaml .Values.defaultBackend.tolerations | nindent 8 }} + {{- end }} + {{- if .Values.defaultBackend.affinity }} + affinity: {{ toYaml .Values.defaultBackend.affinity | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: 60 + {{- if .Values.defaultBackend.extraVolumes }} + volumes: {{ toYaml .Values.defaultBackend.extraVolumes | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-hpa.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-hpa.yaml new file mode 100644 index 0000000..594d265 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-hpa.yaml @@ -0,0 +1,33 @@ +{{- if and .Values.defaultBackend.enabled .Values.defaultBackend.autoscaling.enabled }} +apiVersion: autoscaling/v2beta1 +kind: HorizontalPodAutoscaler +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: default-backend + {{- with .Values.defaultBackend.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ template "ingress-nginx.defaultBackend.fullname" . }} + namespace: {{ .Release.Namespace }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ template "ingress-nginx.defaultBackend.fullname" . }} + minReplicas: {{ .Values.defaultBackend.autoscaling.minReplicas }} + maxReplicas: {{ .Values.defaultBackend.autoscaling.maxReplicas }} + metrics: +{{- with .Values.defaultBackend.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + targetAverageUtilization: {{ . }} +{{- end }} +{{- with .Values.defaultBackend.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + targetAverageUtilization: {{ . }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-poddisruptionbudget.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-poddisruptionbudget.yaml new file mode 100644 index 0000000..00891ce --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-poddisruptionbudget.yaml @@ -0,0 +1,21 @@ +{{- if .Values.defaultBackend.enabled -}} +{{- if or (gt (.Values.defaultBackend.replicaCount | int) 1) (gt (.Values.defaultBackend.autoscaling.minReplicas | int) 1) }} +apiVersion: {{ ternary "policy/v1" "policy/v1beta1" (semverCompare ">=1.21.0-0" .Capabilities.KubeVersion.Version) }} +kind: PodDisruptionBudget +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: default-backend + {{- with .Values.defaultBackend.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.defaultBackend.fullname" . }} + namespace: {{ .Release.Namespace }} +spec: + selector: + matchLabels: + {{- include "ingress-nginx.selectorLabels" . | nindent 6 }} + app.kubernetes.io/component: default-backend + minAvailable: {{ .Values.defaultBackend.minAvailable }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-psp.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-psp.yaml new file mode 100644 index 0000000..42061c5 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-psp.yaml @@ -0,0 +1,36 @@ +{{- if and .Values.podSecurityPolicy.enabled .Values.defaultBackend.enabled (empty .Values.defaultBackend.existingPsp) -}} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "ingress-nginx.fullname" . }}-backend + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: default-backend + {{- with .Values.defaultBackend.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + allowPrivilegeEscalation: false + fsGroup: + ranges: + - max: 65535 + min: 1 + rule: MustRunAs + requiredDropCapabilities: + - ALL + runAsUser: + rule: MustRunAsNonRoot + seLinux: + rule: RunAsAny + supplementalGroups: + ranges: + - max: 65535 + min: 1 + rule: MustRunAs + volumes: + - configMap + - emptyDir + - projected + - secret + - downwardAPI +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-role.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-role.yaml new file mode 100644 index 0000000..a2b457c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-role.yaml @@ -0,0 +1,22 @@ +{{- if and .Values.rbac.create .Values.podSecurityPolicy.enabled .Values.defaultBackend.enabled -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: default-backend + {{- with .Values.defaultBackend.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.fullname" . }}-backend + namespace: {{ .Release.Namespace }} +rules: + - apiGroups: [{{ template "podSecurityPolicy.apiGroup" . }}] + resources: ['podsecuritypolicies'] + verbs: ['use'] + {{- with .Values.defaultBackend.existingPsp }} + resourceNames: [{{ . }}] + {{- else }} + resourceNames: [{{ include "ingress-nginx.fullname" . }}-backend] + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-rolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-rolebinding.yaml new file mode 100644 index 0000000..dbaa516 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-rolebinding.yaml @@ -0,0 +1,21 @@ +{{- if and .Values.rbac.create .Values.podSecurityPolicy.enabled .Values.defaultBackend.enabled -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: default-backend + {{- with .Values.defaultBackend.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.fullname" . }}-backend + namespace: {{ .Release.Namespace }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "ingress-nginx.fullname" . }}-backend +subjects: + - kind: ServiceAccount + name: {{ template "ingress-nginx.defaultBackend.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-service.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-service.yaml new file mode 100644 index 0000000..5f1d09a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-service.yaml @@ -0,0 +1,41 @@ +{{- if .Values.defaultBackend.enabled -}} +apiVersion: v1 +kind: Service +metadata: +{{- if .Values.defaultBackend.service.annotations }} + annotations: {{ toYaml .Values.defaultBackend.service.annotations | nindent 4 }} +{{- end }} + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: default-backend + {{- with .Values.defaultBackend.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "ingress-nginx.defaultBackend.fullname" . }} + namespace: {{ .Release.Namespace }} +spec: + type: {{ .Values.defaultBackend.service.type }} +{{- if .Values.defaultBackend.service.clusterIP }} + clusterIP: {{ .Values.defaultBackend.service.clusterIP }} +{{- end }} +{{- if .Values.defaultBackend.service.externalIPs }} + externalIPs: {{ toYaml .Values.defaultBackend.service.externalIPs | nindent 4 }} +{{- end }} +{{- if .Values.defaultBackend.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.defaultBackend.service.loadBalancerIP }} +{{- end }} +{{- if .Values.defaultBackend.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: {{ toYaml .Values.defaultBackend.service.loadBalancerSourceRanges | nindent 4 }} +{{- end }} + ports: + - name: http + port: {{ .Values.defaultBackend.service.servicePort }} + protocol: TCP + targetPort: http + {{- if semverCompare ">=1.20" .Capabilities.KubeVersion.Version }} + appProtocol: http + {{- end }} + selector: + {{- include "ingress-nginx.selectorLabels" . | nindent 4 }} + app.kubernetes.io/component: default-backend +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-serviceaccount.yaml new file mode 100644 index 0000000..b45a95a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/default-backend-serviceaccount.yaml @@ -0,0 +1,14 @@ +{{- if and .Values.defaultBackend.enabled .Values.defaultBackend.serviceAccount.create -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + {{- include "ingress-nginx.labels" . | nindent 4 }} + app.kubernetes.io/component: default-backend + {{- with .Values.defaultBackend.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ template "ingress-nginx.defaultBackend.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} +automountServiceAccountToken: {{ .Values.defaultBackend.serviceAccount.automountServiceAccountToken }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/dh-param-secret.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/dh-param-secret.yaml new file mode 100644 index 0000000..12e7a4f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/templates/dh-param-secret.yaml @@ -0,0 +1,10 @@ +{{- with .Values.dhParam -}} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "ingress-nginx.controller.fullname" $ }} + labels: + {{- include "ingress-nginx.labels" $ | nindent 4 }} +data: + dhparam.pem: {{ . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/values.yaml new file mode 100644 index 0000000..695f23b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/ingress-nginx/values.yaml @@ -0,0 +1,931 @@ +## nginx configuration +## Ref: https://github.com/kubernetes/ingress-nginx/blob/main/docs/user-guide/nginx-configuration/index.md +## + +## Overrides for generated resource names +# See templates/_helpers.tpl +# nameOverride: +# fullnameOverride: + +## Labels to apply to all resources +## +commonLabels: {} +# scmhash: abc123 +# myLabel: aakkmd + +controller: + name: controller + image: + ## Keep false as default for now! + chroot: false + registry: registry.k8s.io + image: ingress-nginx/controller + ## for backwards compatibility consider setting the full image url via the repository value below + ## use *either* current default registry/image or repository format or installing chart by providing the values.yaml will fail + ## repository: + tag: "v1.2.1" + digest: sha256:5516d103a9c2ecc4f026efbd4b40662ce22dc1f824fb129ed121460aaa5c47f8 + digestChroot: sha256:d301551cf62bc3fb75c69fa56f7aa1d9e87b5079333adaf38afe84d9b7439355 + pullPolicy: IfNotPresent + # www-data -> uid 101 + runAsUser: 101 + allowPrivilegeEscalation: true + + # -- Use an existing PSP instead of creating one + existingPsp: "" + + # -- Configures the controller container name + containerName: controller + + # -- Configures the ports that the nginx-controller listens on + containerPort: + http: 80 + https: 443 + + # -- Will add custom configuration options to Nginx https://kubernetes.github.io/ingress-nginx/user-guide/nginx-configuration/configmap/ + config: {} + + # -- Annotations to be added to the controller config configuration configmap. + configAnnotations: {} + + # -- Will add custom headers before sending traffic to backends according to https://github.com/kubernetes/ingress-nginx/tree/main/docs/examples/customization/custom-headers + proxySetHeaders: {} + + # -- Will add custom headers before sending response traffic to the client according to: https://kubernetes.github.io/ingress-nginx/user-guide/nginx-configuration/configmap/#add-headers + addHeaders: {} + + # -- Optionally customize the pod dnsConfig. + dnsConfig: {} + + # -- Optionally customize the pod hostname. + hostname: {} + + # -- Optionally change this to ClusterFirstWithHostNet in case you have 'hostNetwork: true'. + # By default, while using host network, name resolution uses the host's DNS. If you wish nginx-controller + # to keep resolving names inside the k8s network, use ClusterFirstWithHostNet. + dnsPolicy: ClusterFirst + + # -- Bare-metal considerations via the host network https://kubernetes.github.io/ingress-nginx/deploy/baremetal/#via-the-host-network + # Ingress status was blank because there is no Service exposing the NGINX Ingress controller in a configuration using the host network, the default --publish-service flag used in standard cloud setups does not apply + reportNodeInternalIp: false + + # -- Process Ingress objects without ingressClass annotation/ingressClassName field + # Overrides value for --watch-ingress-without-class flag of the controller binary + # Defaults to false + watchIngressWithoutClass: false + + # -- Process IngressClass per name (additionally as per spec.controller). + ingressClassByName: false + + # -- This configuration defines if Ingress Controller should allow users to set + # their own *-snippet annotations, otherwise this is forbidden / dropped + # when users add those annotations. + # Global snippets in ConfigMap are still respected + allowSnippetAnnotations: true + + # -- Required for use with CNI based kubernetes installations (such as ones set up by kubeadm), + # since CNI and hostport don't mix yet. Can be deprecated once https://github.com/kubernetes/kubernetes/issues/23920 + # is merged + hostNetwork: false + + ## Use host ports 80 and 443 + ## Disabled by default + hostPort: + # -- Enable 'hostPort' or not + enabled: false + ports: + # -- 'hostPort' http port + http: 80 + # -- 'hostPort' https port + https: 443 + + # -- Election ID to use for status update + electionID: ingress-controller-leader + + ## This section refers to the creation of the IngressClass resource + ## IngressClass resources are supported since k8s >= 1.18 and required since k8s >= 1.19 + ingressClassResource: + # -- Name of the ingressClass + name: nginx + # -- Is this ingressClass enabled or not + enabled: true + # -- Is this the default ingressClass for the cluster + default: false + # -- Controller-value of the controller that is processing this ingressClass + controllerValue: "k8s.io/ingress-nginx" + + # -- Parameters is a link to a custom resource containing additional + # configuration for the controller. This is optional if the controller + # does not require extra parameters. + parameters: {} + + # -- For backwards compatibility with ingress.class annotation, use ingressClass. + # Algorithm is as follows, first ingressClassName is considered, if not present, controller looks for ingress.class annotation + ingressClass: nginx + + # -- Labels to add to the pod container metadata + podLabels: {} + # key: value + + # -- Security Context policies for controller pods + podSecurityContext: {} + + # -- See https://kubernetes.io/docs/tasks/administer-cluster/sysctl-cluster/ for notes on enabling and using sysctls + sysctls: {} + # sysctls: + # "net.core.somaxconn": "8192" + + # -- Allows customization of the source of the IP address or FQDN to report + # in the ingress status field. By default, it reads the information provided + # by the service. If disable, the status field reports the IP address of the + # node or nodes where an ingress controller pod is running. + publishService: + # -- Enable 'publishService' or not + enabled: true + # -- Allows overriding of the publish service to bind to + # Must be / + pathOverride: "" + + # Limit the scope of the controller to a specific namespace + scope: + # -- Enable 'scope' or not + enabled: false + # -- Namespace to limit the controller to; defaults to $(POD_NAMESPACE) + namespace: "" + # -- When scope.enabled == false, instead of watching all namespaces, we watching namespaces whose labels + # only match with namespaceSelector. Format like foo=bar. Defaults to empty, means watching all namespaces. + namespaceSelector: "" + + # -- Allows customization of the configmap / nginx-configmap namespace; defaults to $(POD_NAMESPACE) + configMapNamespace: "" + + tcp: + # -- Allows customization of the tcp-services-configmap; defaults to $(POD_NAMESPACE) + configMapNamespace: "" + # -- Annotations to be added to the tcp config configmap + annotations: {} + + udp: + # -- Allows customization of the udp-services-configmap; defaults to $(POD_NAMESPACE) + configMapNamespace: "" + # -- Annotations to be added to the udp config configmap + annotations: {} + + # -- Maxmind license key to download GeoLite2 Databases. + ## https://blog.maxmind.com/2019/12/18/significant-changes-to-accessing-and-using-geolite2-databases + maxmindLicenseKey: "" + + # -- Additional command line arguments to pass to nginx-ingress-controller + # E.g. to specify the default SSL certificate you can use + extraArgs: {} + ## extraArgs: + ## default-ssl-certificate: "/" + + # -- Additional environment variables to set + extraEnvs: [] + # extraEnvs: + # - name: FOO + # valueFrom: + # secretKeyRef: + # key: FOO + # name: secret-resource + + # -- Use a `DaemonSet` or `Deployment` + kind: Deployment + + # -- Annotations to be added to the controller Deployment or DaemonSet + ## + annotations: {} + # keel.sh/pollSchedule: "@every 60m" + + # -- Labels to be added to the controller Deployment or DaemonSet and other resources that do not have option to specify labels + ## + labels: {} + # keel.sh/policy: patch + # keel.sh/trigger: poll + + + # -- The update strategy to apply to the Deployment or DaemonSet + ## + updateStrategy: {} + # rollingUpdate: + # maxUnavailable: 1 + # type: RollingUpdate + + # -- `minReadySeconds` to avoid killing pods before we are ready + ## + minReadySeconds: 0 + + + # -- Node tolerations for server scheduling to nodes with taints + ## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/ + ## + tolerations: [] + # - key: "key" + # operator: "Equal|Exists" + # value: "value" + # effect: "NoSchedule|PreferNoSchedule|NoExecute(1.6 only)" + + # -- Affinity and anti-affinity rules for server scheduling to nodes + ## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + ## + affinity: {} + # # An example of preferred pod anti-affinity, weight is in the range 1-100 + # podAntiAffinity: + # preferredDuringSchedulingIgnoredDuringExecution: + # - weight: 100 + # podAffinityTerm: + # labelSelector: + # matchExpressions: + # - key: app.kubernetes.io/name + # operator: In + # values: + # - ingress-nginx + # - key: app.kubernetes.io/instance + # operator: In + # values: + # - ingress-nginx + # - key: app.kubernetes.io/component + # operator: In + # values: + # - controller + # topologyKey: kubernetes.io/hostname + + # # An example of required pod anti-affinity + # podAntiAffinity: + # requiredDuringSchedulingIgnoredDuringExecution: + # - labelSelector: + # matchExpressions: + # - key: app.kubernetes.io/name + # operator: In + # values: + # - ingress-nginx + # - key: app.kubernetes.io/instance + # operator: In + # values: + # - ingress-nginx + # - key: app.kubernetes.io/component + # operator: In + # values: + # - controller + # topologyKey: "kubernetes.io/hostname" + + # -- Topology spread constraints rely on node labels to identify the topology domain(s) that each Node is in. + ## Ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ + ## + topologySpreadConstraints: [] + # - maxSkew: 1 + # topologyKey: topology.kubernetes.io/zone + # whenUnsatisfiable: DoNotSchedule + # labelSelector: + # matchLabels: + # app.kubernetes.io/instance: ingress-nginx-internal + + # -- `terminationGracePeriodSeconds` to avoid killing pods before we are ready + ## wait up to five minutes for the drain of connections + ## + terminationGracePeriodSeconds: 300 + + # -- Node labels for controller pod assignment + ## Ref: https://kubernetes.io/docs/user-guide/node-selection/ + ## + nodeSelector: + kubernetes.io/os: linux + + ## Liveness and readiness probe values + ## Ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#container-probes + ## + ## startupProbe: + ## httpGet: + ## # should match container.healthCheckPath + ## path: "/healthz" + ## port: 10254 + ## scheme: HTTP + ## initialDelaySeconds: 5 + ## periodSeconds: 5 + ## timeoutSeconds: 2 + ## successThreshold: 1 + ## failureThreshold: 5 + livenessProbe: + httpGet: + # should match container.healthCheckPath + path: "/healthz" + port: 10254 + scheme: HTTP + initialDelaySeconds: 10 + periodSeconds: 10 + timeoutSeconds: 1 + successThreshold: 1 + failureThreshold: 5 + readinessProbe: + httpGet: + # should match container.healthCheckPath + path: "/healthz" + port: 10254 + scheme: HTTP + initialDelaySeconds: 10 + periodSeconds: 10 + timeoutSeconds: 1 + successThreshold: 1 + failureThreshold: 3 + + + # -- Path of the health check endpoint. All requests received on the port defined by + # the healthz-port parameter are forwarded internally to this path. + healthCheckPath: "/healthz" + + # -- Address to bind the health check endpoint. + # It is better to set this option to the internal node address + # if the ingress nginx controller is running in the `hostNetwork: true` mode. + healthCheckHost: "" + + # -- Annotations to be added to controller pods + ## + podAnnotations: {} + + replicaCount: 1 + + minAvailable: 1 + + ## Define requests resources to avoid probe issues due to CPU utilization in busy nodes + ## ref: https://github.com/kubernetes/ingress-nginx/issues/4735#issuecomment-551204903 + ## Ideally, there should be no limits. + ## https://engineering.indeedblog.com/blog/2019/12/cpu-throttling-regression-fix/ + resources: + ## limits: + ## cpu: 100m + ## memory: 90Mi + requests: + cpu: 100m + memory: 90Mi + + # Mutually exclusive with keda autoscaling + autoscaling: + enabled: false + minReplicas: 1 + maxReplicas: 11 + targetCPUUtilizationPercentage: 50 + targetMemoryUtilizationPercentage: 50 + behavior: {} + # scaleDown: + # stabilizationWindowSeconds: 300 + # policies: + # - type: Pods + # value: 1 + # periodSeconds: 180 + # scaleUp: + # stabilizationWindowSeconds: 300 + # policies: + # - type: Pods + # value: 2 + # periodSeconds: 60 + + autoscalingTemplate: [] + # Custom or additional autoscaling metrics + # ref: https://kubernetes.io/docs/tasks/run-application/horizontal-pod-autoscale/#support-for-custom-metrics + # - type: Pods + # pods: + # metric: + # name: nginx_ingress_controller_nginx_process_requests_total + # target: + # type: AverageValue + # averageValue: 10000m + + # Mutually exclusive with hpa autoscaling + keda: + apiVersion: "keda.sh/v1alpha1" + ## apiVersion changes with keda 1.x vs 2.x + ## 2.x = keda.sh/v1alpha1 + ## 1.x = keda.k8s.io/v1alpha1 + enabled: false + minReplicas: 1 + maxReplicas: 11 + pollingInterval: 30 + cooldownPeriod: 300 + restoreToOriginalReplicaCount: false + scaledObject: + annotations: {} + # Custom annotations for ScaledObject resource + # annotations: + # key: value + triggers: [] + # - type: prometheus + # metadata: + # serverAddress: http://:9090 + # metricName: http_requests_total + # threshold: '100' + # query: sum(rate(http_requests_total{deployment="my-deployment"}[2m])) + + behavior: {} + # scaleDown: + # stabilizationWindowSeconds: 300 + # policies: + # - type: Pods + # value: 1 + # periodSeconds: 180 + # scaleUp: + # stabilizationWindowSeconds: 300 + # policies: + # - type: Pods + # value: 2 + # periodSeconds: 60 + + # -- Enable mimalloc as a drop-in replacement for malloc. + ## ref: https://github.com/microsoft/mimalloc + ## + enableMimalloc: true + + ## Override NGINX template + customTemplate: + configMapName: "" + configMapKey: "" + + service: + enabled: true + + # -- If enabled is adding an appProtocol option for Kubernetes service. An appProtocol field replacing annotations that were + # using for setting a backend protocol. Here is an example for AWS: service.beta.kubernetes.io/aws-load-balancer-backend-protocol: http + # It allows choosing the protocol for each backend specified in the Kubernetes service. + # See the following GitHub issue for more details about the purpose: https://github.com/kubernetes/kubernetes/issues/40244 + # Will be ignored for Kubernetes versions older than 1.20 + ## + appProtocol: true + + annotations: {} + labels: {} + # clusterIP: "" + + # -- List of IP addresses at which the controller services are available + ## Ref: https://kubernetes.io/docs/user-guide/services/#external-ips + ## + externalIPs: [] + + # -- Used by cloud providers to connect the resulting `LoadBalancer` to a pre-existing static IP according to https://kubernetes.io/docs/concepts/services-networking/service/#loadbalancer + loadBalancerIP: "" + loadBalancerSourceRanges: [] + + enableHttp: true + enableHttps: true + + ## Set external traffic policy to: "Local" to preserve source IP on providers supporting it. + ## Ref: https://kubernetes.io/docs/tutorials/services/source-ip/#source-ip-for-services-with-typeloadbalancer + # externalTrafficPolicy: "" + + ## Must be either "None" or "ClientIP" if set. Kubernetes will default to "None". + ## Ref: https://kubernetes.io/docs/concepts/services-networking/service/#virtual-ips-and-service-proxies + # sessionAffinity: "" + + ## Specifies the health check node port (numeric port number) for the service. If healthCheckNodePort isn’t specified, + ## the service controller allocates a port from your cluster’s NodePort range. + ## Ref: https://kubernetes.io/docs/tasks/access-application-cluster/create-external-load-balancer/#preserving-the-client-source-ip + # healthCheckNodePort: 0 + + # -- Represents the dual-stack-ness requested or required by this Service. Possible values are + # SingleStack, PreferDualStack or RequireDualStack. + # The ipFamilies and clusterIPs fields depend on the value of this field. + ## Ref: https://kubernetes.io/docs/concepts/services-networking/dual-stack/ + ipFamilyPolicy: "SingleStack" + + # -- List of IP families (e.g. IPv4, IPv6) assigned to the service. This field is usually assigned automatically + # based on cluster configuration and the ipFamilyPolicy field. + ## Ref: https://kubernetes.io/docs/concepts/services-networking/dual-stack/ + ipFamilies: + - IPv4 + + ports: + http: 80 + https: 443 + + targetPorts: + http: http + https: https + + type: LoadBalancer + + ## type: NodePort + ## nodePorts: + ## http: 32080 + ## https: 32443 + ## tcp: + ## 8080: 32808 + nodePorts: + http: "" + https: "" + tcp: {} + udp: {} + + external: + enabled: true + + internal: + # -- Enables an additional internal load balancer (besides the external one). + enabled: false + # -- Annotations are mandatory for the load balancer to come up. Varies with the cloud service. + annotations: {} + + # loadBalancerIP: "" + + # -- Restrict access For LoadBalancer service. Defaults to 0.0.0.0/0. + loadBalancerSourceRanges: [] + + ## Set external traffic policy to: "Local" to preserve source IP on + ## providers supporting it + ## Ref: https://kubernetes.io/docs/tutorials/services/source-ip/#source-ip-for-services-with-typeloadbalancer + # externalTrafficPolicy: "" + + # shareProcessNamespace enables process namespace sharing within the pod. + # This can be used for example to signal log rotation using `kill -USR1` from a sidecar. + shareProcessNamespace: false + + # -- Additional containers to be added to the controller pod. + # See https://github.com/lemonldap-ng-controller/lemonldap-ng-controller as example. + extraContainers: [] + # - name: my-sidecar + # image: nginx:latest + # - name: lemonldap-ng-controller + # image: lemonldapng/lemonldap-ng-controller:0.2.0 + # args: + # - /lemonldap-ng-controller + # - --alsologtostderr + # - --configmap=$(POD_NAMESPACE)/lemonldap-ng-configuration + # env: + # - name: POD_NAME + # valueFrom: + # fieldRef: + # fieldPath: metadata.name + # - name: POD_NAMESPACE + # valueFrom: + # fieldRef: + # fieldPath: metadata.namespace + # volumeMounts: + # - name: copy-portal-skins + # mountPath: /srv/var/lib/lemonldap-ng/portal/skins + + # -- Additional volumeMounts to the controller main container. + extraVolumeMounts: [] + # - name: copy-portal-skins + # mountPath: /var/lib/lemonldap-ng/portal/skins + + # -- Additional volumes to the controller pod. + extraVolumes: [] + # - name: copy-portal-skins + # emptyDir: {} + + # -- Containers, which are run before the app containers are started. + extraInitContainers: [] + # - name: init-myservice + # image: busybox + # command: ['sh', '-c', 'until nslookup myservice; do echo waiting for myservice; sleep 2; done;'] + + extraModules: [] + ## Modules, which are mounted into the core nginx image + # - name: opentelemetry + # image: registry.k8s.io/ingress-nginx/opentelemetry:v20220415-controller-v1.2.0-beta.0-2-g81c2afd97@sha256:ce61e2cf0b347dffebb2dcbf57c33891d2217c1bad9c0959c878e5be671ef941 + # + # The image must contain a `/usr/local/bin/init_module.sh` executable, which + # will be executed as initContainers, to move its config files within the + # mounted volume. + + admissionWebhooks: + annotations: {} + # ignore-check.kube-linter.io/no-read-only-rootfs: "This deployment needs write access to root filesystem". + + ## Additional annotations to the admission webhooks. + ## These annotations will be added to the ValidatingWebhookConfiguration and + ## the Jobs Spec of the admission webhooks. + enabled: true + failurePolicy: Fail + # timeoutSeconds: 10 + port: 8443 + certificate: "/usr/local/certificates/cert" + key: "/usr/local/certificates/key" + namespaceSelector: {} + objectSelector: {} + # -- Labels to be added to admission webhooks + labels: {} + + # -- Use an existing PSP instead of creating one + existingPsp: "" + + service: + annotations: {} + # clusterIP: "" + externalIPs: [] + # loadBalancerIP: "" + loadBalancerSourceRanges: [] + servicePort: 443 + type: ClusterIP + + createSecretJob: + resources: {} + # limits: + # cpu: 10m + # memory: 20Mi + # requests: + # cpu: 10m + # memory: 20Mi + + patchWebhookJob: + resources: {} + + patch: + enabled: true + image: + registry: registry.k8s.io + image: ingress-nginx/kube-webhook-certgen + ## for backwards compatibility consider setting the full image url via the repository value below + ## use *either* current default registry/image or repository format or installing chart by providing the values.yaml will fail + ## repository: + tag: v1.1.1 + digest: sha256:64d8c73dca984af206adf9d6d7e46aa550362b1d7a01f3a0a91b20cc67868660 + pullPolicy: IfNotPresent + # -- Provide a priority class name to the webhook patching job + ## + priorityClassName: "" + podAnnotations: {} + nodeSelector: + kubernetes.io/os: linux + tolerations: [] + # -- Labels to be added to patch job resources + labels: {} + runAsUser: 2000 + fsGroup: 2000 + + metrics: + port: 10254 + # if this port is changed, change healthz-port: in extraArgs: accordingly + enabled: false + + service: + annotations: {} + # prometheus.io/scrape: "true" + # prometheus.io/port: "10254" + + # clusterIP: "" + + # -- List of IP addresses at which the stats-exporter service is available + ## Ref: https://kubernetes.io/docs/user-guide/services/#external-ips + ## + externalIPs: [] + + # loadBalancerIP: "" + loadBalancerSourceRanges: [] + servicePort: 10254 + type: ClusterIP + # externalTrafficPolicy: "" + # nodePort: "" + + serviceMonitor: + enabled: false + additionalLabels: {} + ## The label to use to retrieve the job name from. + ## jobLabel: "app.kubernetes.io/name" + namespace: "" + namespaceSelector: {} + ## Default: scrape .Release.Namespace only + ## To scrape all, use the following: + ## namespaceSelector: + ## any: true + scrapeInterval: 30s + # honorLabels: true + targetLabels: [] + relabelings: [] + metricRelabelings: [] + + prometheusRule: + enabled: false + additionalLabels: {} + # namespace: "" + rules: [] + # # These are just examples rules, please adapt them to your needs + # - alert: NGINXConfigFailed + # expr: count(nginx_ingress_controller_config_last_reload_successful == 0) > 0 + # for: 1s + # labels: + # severity: critical + # annotations: + # description: bad ingress config - nginx config test failed + # summary: uninstall the latest ingress changes to allow config reloads to resume + # - alert: NGINXCertificateExpiry + # expr: (avg(nginx_ingress_controller_ssl_expire_time_seconds) by (host) - time()) < 604800 + # for: 1s + # labels: + # severity: critical + # annotations: + # description: ssl certificate(s) will expire in less then a week + # summary: renew expiring certificates to avoid downtime + # - alert: NGINXTooMany500s + # expr: 100 * ( sum( nginx_ingress_controller_requests{status=~"5.+"} ) / sum(nginx_ingress_controller_requests) ) > 5 + # for: 1m + # labels: + # severity: warning + # annotations: + # description: Too many 5XXs + # summary: More than 5% of all requests returned 5XX, this requires your attention + # - alert: NGINXTooMany400s + # expr: 100 * ( sum( nginx_ingress_controller_requests{status=~"4.+"} ) / sum(nginx_ingress_controller_requests) ) > 5 + # for: 1m + # labels: + # severity: warning + # annotations: + # description: Too many 4XXs + # summary: More than 5% of all requests returned 4XX, this requires your attention + + # -- Improve connection draining when ingress controller pod is deleted using a lifecycle hook: + # With this new hook, we increased the default terminationGracePeriodSeconds from 30 seconds + # to 300, allowing the draining of connections up to five minutes. + # If the active connections end before that, the pod will terminate gracefully at that time. + # To effectively take advantage of this feature, the Configmap feature + # worker-shutdown-timeout new value is 240s instead of 10s. + ## + lifecycle: + preStop: + exec: + command: + - /wait-shutdown + + priorityClassName: "" + +# -- Rollback limit +## +revisionHistoryLimit: 10 + +## Default 404 backend +## +defaultBackend: + ## + enabled: false + + name: defaultbackend + image: + registry: registry.k8s.io + image: defaultbackend-amd64 + ## for backwards compatibility consider setting the full image url via the repository value below + ## use *either* current default registry/image or repository format or installing chart by providing the values.yaml will fail + ## repository: + tag: "1.5" + pullPolicy: IfNotPresent + # nobody user -> uid 65534 + runAsUser: 65534 + runAsNonRoot: true + readOnlyRootFilesystem: true + allowPrivilegeEscalation: false + + # -- Use an existing PSP instead of creating one + existingPsp: "" + + extraArgs: {} + + serviceAccount: + create: true + name: "" + automountServiceAccountToken: true + # -- Additional environment variables to set for defaultBackend pods + extraEnvs: [] + + port: 8080 + + ## Readiness and liveness probes for default backend + ## Ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/ + ## + livenessProbe: + failureThreshold: 3 + initialDelaySeconds: 30 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 5 + readinessProbe: + failureThreshold: 6 + initialDelaySeconds: 0 + periodSeconds: 5 + successThreshold: 1 + timeoutSeconds: 5 + + # -- Node tolerations for server scheduling to nodes with taints + ## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/ + ## + tolerations: [] + # - key: "key" + # operator: "Equal|Exists" + # value: "value" + # effect: "NoSchedule|PreferNoSchedule|NoExecute(1.6 only)" + + affinity: {} + + # -- Security Context policies for controller pods + # See https://kubernetes.io/docs/tasks/administer-cluster/sysctl-cluster/ for + # notes on enabling and using sysctls + ## + podSecurityContext: {} + + # -- Security Context policies for controller main container. + # See https://kubernetes.io/docs/tasks/administer-cluster/sysctl-cluster/ for + # notes on enabling and using sysctls + ## + containerSecurityContext: {} + + # -- Labels to add to the pod container metadata + podLabels: {} + # key: value + + # -- Node labels for default backend pod assignment + ## Ref: https://kubernetes.io/docs/user-guide/node-selection/ + ## + nodeSelector: + kubernetes.io/os: linux + + # -- Annotations to be added to default backend pods + ## + podAnnotations: {} + + replicaCount: 1 + + minAvailable: 1 + + resources: {} + # limits: + # cpu: 10m + # memory: 20Mi + # requests: + # cpu: 10m + # memory: 20Mi + + extraVolumeMounts: [] + ## Additional volumeMounts to the default backend container. + # - name: copy-portal-skins + # mountPath: /var/lib/lemonldap-ng/portal/skins + + extraVolumes: [] + ## Additional volumes to the default backend pod. + # - name: copy-portal-skins + # emptyDir: {} + + autoscaling: + annotations: {} + enabled: false + minReplicas: 1 + maxReplicas: 2 + targetCPUUtilizationPercentage: 50 + targetMemoryUtilizationPercentage: 50 + + service: + annotations: {} + + # clusterIP: "" + + # -- List of IP addresses at which the default backend service is available + ## Ref: https://kubernetes.io/docs/user-guide/services/#external-ips + ## + externalIPs: [] + + # loadBalancerIP: "" + loadBalancerSourceRanges: [] + servicePort: 80 + type: ClusterIP + + priorityClassName: "" + # -- Labels to be added to the default backend resources + labels: {} + +## Enable RBAC as per https://github.com/kubernetes/ingress-nginx/blob/main/docs/deploy/rbac.md and https://github.com/kubernetes/ingress-nginx/issues/266 +rbac: + create: true + scope: false + +## If true, create & use Pod Security Policy resources +## https://kubernetes.io/docs/concepts/policy/pod-security-policy/ +podSecurityPolicy: + enabled: false + +serviceAccount: + create: true + name: "" + automountServiceAccountToken: true + # -- Annotations for the controller service account + annotations: {} + +# -- Optional array of imagePullSecrets containing private registry credentials +## Ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ +imagePullSecrets: [] +# - name: secretName + +# -- TCP service key-value pairs +## Ref: https://github.com/kubernetes/ingress-nginx/blob/main/docs/user-guide/exposing-tcp-udp-services.md +## +tcp: {} +# 8080: "default/example-tcp-svc:9000" + +# -- UDP service key-value pairs +## Ref: https://github.com/kubernetes/ingress-nginx/blob/main/docs/user-guide/exposing-tcp-udp-services.md +## +udp: {} +# 53: "kube-system/kube-dns:53" + +# -- Prefix for TCP and UDP ports names in ingress controller service +## Some cloud providers, like Yandex Cloud may have a requirements for a port name regex to support cloud load balancer integration +portNamePrefix: "" + +# -- (string) A base64-encoded Diffie-Hellman parameter. +# This can be generated with: `openssl dhparam 4096 2> /dev/null | base64` +## Ref: https://github.com/kubernetes/ingress-nginx/tree/main/docs/examples/customization/ssl-dh-param +dhParam: diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/mariadb/.helmignore new file mode 100644 index 0000000..f0c1319 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/.helmignore @@ -0,0 +1,21 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/Chart.lock b/observability/lgtm-distributed/charts/oncall/charts/mariadb/Chart.lock new file mode 100644 index 0000000..cc6e4f1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/Chart.lock @@ -0,0 +1,6 @@ +dependencies: +- name: common + repository: oci://registry-1.docker.io/bitnamicharts + version: 2.4.0 +digest: sha256:8c1a5dc923412d11d4d841420494b499cb707305c8b9f87f45ea1a8bf3172cb3 +generated: "2023-05-21T18:46:17.326179513Z" diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/Chart.yaml new file mode 100644 index 0000000..aa7b2b9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/Chart.yaml @@ -0,0 +1,29 @@ +annotations: + category: Database + licenses: Apache-2.0 +apiVersion: v2 +appVersion: 10.11.4 +dependencies: +- name: common + repository: oci://registry-1.docker.io/bitnamicharts + tags: + - bitnami-common + version: 2.x.x +description: MariaDB is an open source, community-developed SQL database server that + is widely in use around the world due to its enterprise features, flexibility, and + collaboration with leading tech firms. +home: https://bitnami.com +icon: https://bitnami.com/assets/stacks/mariadb/img/mariadb-stack-220x234.png +keywords: +- mariadb +- mysql +- database +- sql +- prometheus +maintainers: +- name: VMware, Inc. + url: https://github.com/bitnami/charts +name: mariadb +sources: +- https://github.com/bitnami/charts/tree/main/bitnami/mariadb +version: 12.2.5 diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/README.md b/observability/lgtm-distributed/charts/oncall/charts/mariadb/README.md new file mode 100644 index 0000000..8fc6bd9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/README.md @@ -0,0 +1,558 @@ + + +# MariaDB packaged by Bitnami + +MariaDB is an open source, community-developed SQL database server that is widely in use around the world due to its enterprise features, flexibility, and collaboration with leading tech firms. + +[Overview of MariaDB](https://mariadb.org/) + +Trademarks: This software listing is packaged by Bitnami. The respective trademarks mentioned in the offering are owned by the respective companies, and use of them does not imply any affiliation or endorsement. + +## TL;DR + +```console +helm install my-release oci://registry-1.docker.io/bitnamicharts/mariadb +``` + +## Introduction + +This chart bootstraps a [MariaDB](https://github.com/bitnami/containers/tree/main/bitnami/mariadb) replication cluster deployment on a [Kubernetes](https://kubernetes.io) cluster using the [Helm](https://helm.sh) package manager. + +MariaDB is developed as open source software and as a relational database it provides an SQL interface for accessing data. The latest versions of MariaDB also include GIS and JSON features. + +Bitnami charts can be used with [Kubeapps](https://kubeapps.dev/) for deployment and management of Helm Charts in clusters. + +## Prerequisites + +- Kubernetes 1.19+ +- Helm 3.2.0+ +- PV provisioner support in the underlying infrastructure + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```console +helm install my-release oci://registry-1.docker.io/bitnamicharts/mariadb +``` + +The command deploys MariaDB on the Kubernetes cluster in the default configuration. The [Parameters](#parameters) section lists the parameters that can be configured during installation. + +> **Tip**: List all releases using `helm list` + +## Uninstalling the Chart + +To uninstall/delete the `my-release` deployment: + +```console +helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + +## Parameters + +### Global parameters + +| Name | Description | Value | +| ------------------------- | ----------------------------------------------- | ----- | +| `global.imageRegistry` | Global Docker Image registry | `""` | +| `global.imagePullSecrets` | Global Docker registry secret names as an array | `[]` | +| `global.storageClass` | Global storage class for dynamic provisioning | `""` | + +### Common parameters + +| Name | Description | Value | +| ------------------------- | --------------------------------------------------------------------------------------- | --------------- | +| `kubeVersion` | Force target Kubernetes version (using Helm capabilities if not set) | `""` | +| `nameOverride` | String to partially override mariadb.fullname | `""` | +| `fullnameOverride` | String to fully override mariadb.fullname | `""` | +| `clusterDomain` | Default Kubernetes cluster domain | `cluster.local` | +| `commonAnnotations` | Common annotations to add to all MariaDB resources (sub-charts are not considered) | `{}` | +| `commonLabels` | Common labels to add to all MariaDB resources (sub-charts are not considered) | `{}` | +| `schedulerName` | Name of the scheduler (other than default) to dispatch pods | `""` | +| `runtimeClassName` | Name of the Runtime Class for all MariaDB pods | `""` | +| `extraDeploy` | Array of extra objects to deploy with the release (evaluated as a template) | `[]` | +| `diagnosticMode.enabled` | Enable diagnostic mode (all probes will be disabled and the command will be overridden) | `false` | +| `diagnosticMode.command` | Command to override all containers in the deployment | `["sleep"]` | +| `diagnosticMode.args` | Args to override all containers in the deployment | `["infinity"]` | +| `serviceBindings.enabled` | Create secret for service binding (Experimental) | `false` | + +### MariaDB common parameters + +| Name | Description | Value | +| -------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------- | +| `image.registry` | MariaDB image registry | `docker.io` | +| `image.repository` | MariaDB image repository | `bitnami/mariadb` | +| `image.tag` | MariaDB image tag (immutable tags are recommended) | `10.11.4-debian-11-r0` | +| `image.digest` | MariaDB image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag | `""` | +| `image.pullPolicy` | MariaDB image pull policy | `IfNotPresent` | +| `image.pullSecrets` | Specify docker-registry secret names as an array | `[]` | +| `image.debug` | Specify if debug logs should be enabled | `false` | +| `architecture` | MariaDB architecture (`standalone` or `replication`) | `standalone` | +| `auth.rootPassword` | Password for the `root` user. Ignored if existing secret is provided. | `""` | +| `auth.database` | Name for a custom database to create | `my_database` | +| `auth.username` | Name for a custom user to create | `""` | +| `auth.password` | Password for the new user. Ignored if existing secret is provided | `""` | +| `auth.replicationUser` | MariaDB replication user | `replicator` | +| `auth.replicationPassword` | MariaDB replication user password. Ignored if existing secret is provided | `""` | +| `auth.existingSecret` | Use existing secret for password details (`auth.rootPassword`, `auth.password`, `auth.replicationPassword` will be ignored and picked up from this secret). The secret has to contain the keys `mariadb-root-password`, `mariadb-replication-password` and `mariadb-password` | `""` | +| `auth.forcePassword` | Force users to specify required passwords | `false` | +| `auth.usePasswordFiles` | Mount credentials as files instead of using environment variables | `false` | +| `auth.customPasswordFiles` | Use custom password files when `auth.usePasswordFiles` is set to `true`. Define path for keys `root` and `user`, also define `replicator` if `architecture` is set to `replication` | `{}` | +| `initdbScripts` | Dictionary of initdb scripts | `{}` | +| `initdbScriptsConfigMap` | ConfigMap with the initdb scripts (Note: Overrides `initdbScripts`) | `""` | + +### MariaDB Primary parameters + +| Name | Description | Value | +| ----------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------- | ------------------- | +| `primary.name` | Name of the primary database (eg primary, master, leader, ...) | `primary` | +| `primary.command` | Override default container command on MariaDB Primary container(s) (useful when using custom images) | `[]` | +| `primary.args` | Override default container args on MariaDB Primary container(s) (useful when using custom images) | `[]` | +| `primary.lifecycleHooks` | for the MariaDB Primary container(s) to automate configuration before or after startup | `{}` | +| `primary.hostAliases` | Add deployment host aliases | `[]` | +| `primary.configuration` | MariaDB Primary configuration to be injected as ConfigMap | `""` | +| `primary.existingConfigmap` | Name of existing ConfigMap with MariaDB Primary configuration. | `""` | +| `primary.updateStrategy.type` | MariaDB primary statefulset strategy type | `RollingUpdate` | +| `primary.rollingUpdatePartition` | Partition update strategy for Mariadb Primary statefulset | `""` | +| `primary.podAnnotations` | Additional pod annotations for MariaDB primary pods | `{}` | +| `primary.podLabels` | Extra labels for MariaDB primary pods | `{}` | +| `primary.podAffinityPreset` | MariaDB primary pod affinity preset. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `primary.podAntiAffinityPreset` | MariaDB primary pod anti-affinity preset. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` | `soft` | +| `primary.nodeAffinityPreset.type` | MariaDB primary node affinity preset type. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `primary.nodeAffinityPreset.key` | MariaDB primary node label key to match Ignored if `primary.affinity` is set. | `""` | +| `primary.nodeAffinityPreset.values` | MariaDB primary node label values to match. Ignored if `primary.affinity` is set. | `[]` | +| `primary.affinity` | Affinity for MariaDB primary pods assignment | `{}` | +| `primary.nodeSelector` | Node labels for MariaDB primary pods assignment | `{}` | +| `primary.tolerations` | Tolerations for MariaDB primary pods assignment | `[]` | +| `primary.schedulerName` | Name of the k8s scheduler (other than default) | `""` | +| `primary.podManagementPolicy` | podManagementPolicy to manage scaling operation of MariaDB primary pods | `""` | +| `primary.topologySpreadConstraints` | Topology Spread Constraints for MariaDB primary pods assignment | `[]` | +| `primary.priorityClassName` | Priority class for MariaDB primary pods assignment | `""` | +| `primary.runtimeClassName` | Runtime Class for MariaDB primary pods | `""` | +| `primary.podSecurityContext.enabled` | Enable security context for MariaDB primary pods | `true` | +| `primary.podSecurityContext.fsGroup` | Group ID for the mounted volumes' filesystem | `1001` | +| `primary.containerSecurityContext.enabled` | MariaDB primary container securityContext | `true` | +| `primary.containerSecurityContext.runAsUser` | User ID for the MariaDB primary container | `1001` | +| `primary.containerSecurityContext.runAsNonRoot` | Set primary container's Security Context runAsNonRoot | `true` | +| `primary.containerSecurityContext.privileged` | Set primary container's Security Context privileged | `false` | +| `primary.containerSecurityContext.allowPrivilegeEscalation` | Set primary container's Security Context allowPrivilegeEscalation | `false` | +| `primary.resources.limits` | The resources limits for MariaDB primary containers | `{}` | +| `primary.resources.requests` | The requested resources for MariaDB primary containers | `{}` | +| `primary.startupProbe.enabled` | Enable startupProbe | `false` | +| `primary.startupProbe.initialDelaySeconds` | Initial delay seconds for startupProbe | `120` | +| `primary.startupProbe.periodSeconds` | Period seconds for startupProbe | `15` | +| `primary.startupProbe.timeoutSeconds` | Timeout seconds for startupProbe | `5` | +| `primary.startupProbe.failureThreshold` | Failure threshold for startupProbe | `10` | +| `primary.startupProbe.successThreshold` | Success threshold for startupProbe | `1` | +| `primary.livenessProbe.enabled` | Enable livenessProbe | `true` | +| `primary.livenessProbe.initialDelaySeconds` | Initial delay seconds for livenessProbe | `120` | +| `primary.livenessProbe.periodSeconds` | Period seconds for livenessProbe | `10` | +| `primary.livenessProbe.timeoutSeconds` | Timeout seconds for livenessProbe | `1` | +| `primary.livenessProbe.failureThreshold` | Failure threshold for livenessProbe | `3` | +| `primary.livenessProbe.successThreshold` | Success threshold for livenessProbe | `1` | +| `primary.readinessProbe.enabled` | Enable readinessProbe | `true` | +| `primary.readinessProbe.initialDelaySeconds` | Initial delay seconds for readinessProbe | `30` | +| `primary.readinessProbe.periodSeconds` | Period seconds for readinessProbe | `10` | +| `primary.readinessProbe.timeoutSeconds` | Timeout seconds for readinessProbe | `1` | +| `primary.readinessProbe.failureThreshold` | Failure threshold for readinessProbe | `3` | +| `primary.readinessProbe.successThreshold` | Success threshold for readinessProbe | `1` | +| `primary.customStartupProbe` | Override default startup probe for MariaDB primary containers | `{}` | +| `primary.customLivenessProbe` | Override default liveness probe for MariaDB primary containers | `{}` | +| `primary.customReadinessProbe` | Override default readiness probe for MariaDB primary containers | `{}` | +| `primary.startupWaitOptions` | Override default builtin startup wait check options for MariaDB primary containers | `{}` | +| `primary.extraFlags` | MariaDB primary additional command line flags | `""` | +| `primary.extraEnvVars` | Extra environment variables to be set on MariaDB primary containers | `[]` | +| `primary.extraEnvVarsCM` | Name of existing ConfigMap containing extra env vars for MariaDB primary containers | `""` | +| `primary.extraEnvVarsSecret` | Name of existing Secret containing extra env vars for MariaDB primary containers | `""` | +| `primary.persistence.enabled` | Enable persistence on MariaDB primary replicas using a `PersistentVolumeClaim`. If false, use emptyDir | `true` | +| `primary.persistence.existingClaim` | Name of an existing `PersistentVolumeClaim` for MariaDB primary replicas | `""` | +| `primary.persistence.subPath` | Subdirectory of the volume to mount at | `""` | +| `primary.persistence.storageClass` | MariaDB primary persistent volume storage Class | `""` | +| `primary.persistence.labels` | Labels for the PVC | `{}` | +| `primary.persistence.annotations` | MariaDB primary persistent volume claim annotations | `{}` | +| `primary.persistence.accessModes` | MariaDB primary persistent volume access Modes | `["ReadWriteOnce"]` | +| `primary.persistence.size` | MariaDB primary persistent volume size | `8Gi` | +| `primary.persistence.selector` | Selector to match an existing Persistent Volume | `{}` | +| `primary.extraVolumes` | Optionally specify extra list of additional volumes to the MariaDB Primary pod(s) | `[]` | +| `primary.extraVolumeMounts` | Optionally specify extra list of additional volumeMounts for the MariaDB Primary container(s) | `[]` | +| `primary.initContainers` | Add additional init containers for the MariaDB Primary pod(s) | `[]` | +| `primary.sidecars` | Add additional sidecar containers for the MariaDB Primary pod(s) | `[]` | +| `primary.service.type` | MariaDB Primary Kubernetes service type | `ClusterIP` | +| `primary.service.ports.mysql` | MariaDB Primary Kubernetes service port for MariaDB | `3306` | +| `primary.service.ports.metrics` | MariaDB Primary Kubernetes service port for metrics | `9104` | +| `primary.service.nodePorts.mysql` | MariaDB Primary Kubernetes service node port | `""` | +| `primary.service.clusterIP` | MariaDB Primary Kubernetes service clusterIP IP | `""` | +| `primary.service.loadBalancerIP` | MariaDB Primary loadBalancerIP if service type is `LoadBalancer` | `""` | +| `primary.service.externalTrafficPolicy` | Enable client source IP preservation | `Cluster` | +| `primary.service.loadBalancerSourceRanges` | Address that are allowed when MariaDB Primary service is LoadBalancer | `[]` | +| `primary.service.extraPorts` | Extra ports to expose (normally used with the `sidecar` value) | `[]` | +| `primary.service.annotations` | Provide any additional annotations which may be required | `{}` | +| `primary.service.sessionAffinity` | Session Affinity for Kubernetes service, can be "None" or "ClientIP" | `None` | +| `primary.service.sessionAffinityConfig` | Additional settings for the sessionAffinity | `{}` | +| `primary.pdb.create` | Enable/disable a Pod Disruption Budget creation for MariaDB primary pods | `false` | +| `primary.pdb.minAvailable` | Minimum number/percentage of MariaDB primary pods that must still be available after the eviction | `1` | +| `primary.pdb.maxUnavailable` | Maximum number/percentage of MariaDB primary pods that can be unavailable after the eviction | `""` | +| `primary.revisionHistoryLimit` | Maximum number of revisions that will be maintained in the StatefulSet | `10` | + +### MariaDB Secondary parameters + +| Name | Description | Value | +| ------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- | ------------------- | +| `secondary.name` | Name of the secondary database (eg secondary, slave, ...) | `secondary` | +| `secondary.replicaCount` | Number of MariaDB secondary replicas | `1` | +| `secondary.command` | Override default container command on MariaDB Secondary container(s) (useful when using custom images) | `[]` | +| `secondary.args` | Override default container args on MariaDB Secondary container(s) (useful when using custom images) | `[]` | +| `secondary.lifecycleHooks` | for the MariaDB Secondary container(s) to automate configuration before or after startup | `{}` | +| `secondary.hostAliases` | Add deployment host aliases | `[]` | +| `secondary.configuration` | MariaDB Secondary configuration to be injected as ConfigMap | `""` | +| `secondary.existingConfigmap` | Name of existing ConfigMap with MariaDB Secondary configuration. | `""` | +| `secondary.updateStrategy.type` | MariaDB secondary statefulset strategy type | `RollingUpdate` | +| `secondary.rollingUpdatePartition` | Partition update strategy for Mariadb Secondary statefulset | `""` | +| `secondary.podAnnotations` | Additional pod annotations for MariaDB secondary pods | `{}` | +| `secondary.podLabels` | Extra labels for MariaDB secondary pods | `{}` | +| `secondary.podAffinityPreset` | MariaDB secondary pod affinity preset. Ignored if `secondary.affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `secondary.podAntiAffinityPreset` | MariaDB secondary pod anti-affinity preset. Ignored if `secondary.affinity` is set. Allowed values: `soft` or `hard` | `soft` | +| `secondary.nodeAffinityPreset.type` | MariaDB secondary node affinity preset type. Ignored if `secondary.affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `secondary.nodeAffinityPreset.key` | MariaDB secondary node label key to match Ignored if `secondary.affinity` is set. | `""` | +| `secondary.nodeAffinityPreset.values` | MariaDB secondary node label values to match. Ignored if `secondary.affinity` is set. | `[]` | +| `secondary.affinity` | Affinity for MariaDB secondary pods assignment | `{}` | +| `secondary.nodeSelector` | Node labels for MariaDB secondary pods assignment | `{}` | +| `secondary.tolerations` | Tolerations for MariaDB secondary pods assignment | `[]` | +| `secondary.topologySpreadConstraints` | Topology Spread Constraints for MariaDB secondary pods assignment | `[]` | +| `secondary.priorityClassName` | Priority class for MariaDB secondary pods assignment | `""` | +| `secondary.runtimeClassName` | Runtime Class for MariaDB secondary pods | `""` | +| `secondary.schedulerName` | Name of the k8s scheduler (other than default) | `""` | +| `secondary.podManagementPolicy` | podManagementPolicy to manage scaling operation of MariaDB secondary pods | `""` | +| `secondary.podSecurityContext.enabled` | Enable security context for MariaDB secondary pods | `true` | +| `secondary.podSecurityContext.fsGroup` | Group ID for the mounted volumes' filesystem | `1001` | +| `secondary.containerSecurityContext.enabled` | MariaDB secondary container securityContext | `true` | +| `secondary.containerSecurityContext.runAsUser` | User ID for the MariaDB secondary container | `1001` | +| `secondary.containerSecurityContext.runAsNonRoot` | Set secondary container's Security Context runAsNonRoot | `true` | +| `secondary.containerSecurityContext.privileged` | Set secondary container's Security Context privileged | `false` | +| `secondary.containerSecurityContext.allowPrivilegeEscalation` | Set secondary container's Security Context allowPrivilegeEscalation | `false` | +| `secondary.resources.limits` | The resources limits for MariaDB secondary containers | `{}` | +| `secondary.resources.requests` | The requested resources for MariaDB secondary containers | `{}` | +| `secondary.startupProbe.enabled` | Enable startupProbe | `false` | +| `secondary.startupProbe.initialDelaySeconds` | Initial delay seconds for startupProbe | `120` | +| `secondary.startupProbe.periodSeconds` | Period seconds for startupProbe | `15` | +| `secondary.startupProbe.timeoutSeconds` | Timeout seconds for startupProbe | `5` | +| `secondary.startupProbe.failureThreshold` | Failure threshold for startupProbe | `10` | +| `secondary.startupProbe.successThreshold` | Success threshold for startupProbe | `1` | +| `secondary.livenessProbe.enabled` | Enable livenessProbe | `true` | +| `secondary.livenessProbe.initialDelaySeconds` | Initial delay seconds for livenessProbe | `120` | +| `secondary.livenessProbe.periodSeconds` | Period seconds for livenessProbe | `10` | +| `secondary.livenessProbe.timeoutSeconds` | Timeout seconds for livenessProbe | `1` | +| `secondary.livenessProbe.failureThreshold` | Failure threshold for livenessProbe | `3` | +| `secondary.livenessProbe.successThreshold` | Success threshold for livenessProbe | `1` | +| `secondary.readinessProbe.enabled` | Enable readinessProbe | `true` | +| `secondary.readinessProbe.initialDelaySeconds` | Initial delay seconds for readinessProbe | `30` | +| `secondary.readinessProbe.periodSeconds` | Period seconds for readinessProbe | `10` | +| `secondary.readinessProbe.timeoutSeconds` | Timeout seconds for readinessProbe | `1` | +| `secondary.readinessProbe.failureThreshold` | Failure threshold for readinessProbe | `3` | +| `secondary.readinessProbe.successThreshold` | Success threshold for readinessProbe | `1` | +| `secondary.customStartupProbe` | Override default startup probe for MariaDB secondary containers | `{}` | +| `secondary.customLivenessProbe` | Override default liveness probe for MariaDB secondary containers | `{}` | +| `secondary.customReadinessProbe` | Override default readiness probe for MariaDB secondary containers | `{}` | +| `secondary.startupWaitOptions` | Override default builtin startup wait check options for MariaDB secondary containers | `{}` | +| `secondary.extraFlags` | MariaDB secondary additional command line flags | `""` | +| `secondary.extraEnvVars` | Extra environment variables to be set on MariaDB secondary containers | `[]` | +| `secondary.extraEnvVarsCM` | Name of existing ConfigMap containing extra env vars for MariaDB secondary containers | `""` | +| `secondary.extraEnvVarsSecret` | Name of existing Secret containing extra env vars for MariaDB secondary containers | `""` | +| `secondary.persistence.enabled` | Enable persistence on MariaDB secondary replicas using a `PersistentVolumeClaim` | `true` | +| `secondary.persistence.subPath` | Subdirectory of the volume to mount at | `""` | +| `secondary.persistence.storageClass` | MariaDB secondary persistent volume storage Class | `""` | +| `secondary.persistence.labels` | Labels for the PVC | `{}` | +| `secondary.persistence.annotations` | MariaDB secondary persistent volume claim annotations | `{}` | +| `secondary.persistence.accessModes` | MariaDB secondary persistent volume access Modes | `["ReadWriteOnce"]` | +| `secondary.persistence.size` | MariaDB secondary persistent volume size | `8Gi` | +| `secondary.persistence.selector` | Selector to match an existing Persistent Volume | `{}` | +| `secondary.extraVolumes` | Optionally specify extra list of additional volumes to the MariaDB secondary pod(s) | `[]` | +| `secondary.extraVolumeMounts` | Optionally specify extra list of additional volumeMounts for the MariaDB secondary container(s) | `[]` | +| `secondary.initContainers` | Add additional init containers for the MariaDB secondary pod(s) | `[]` | +| `secondary.sidecars` | Add additional sidecar containers for the MariaDB secondary pod(s) | `[]` | +| `secondary.service.type` | MariaDB secondary Kubernetes service type | `ClusterIP` | +| `secondary.service.ports.mysql` | MariaDB secondary Kubernetes service port for MariaDB | `3306` | +| `secondary.service.ports.metrics` | MariaDB secondary Kubernetes service port for metrics | `9104` | +| `secondary.service.nodePorts.mysql` | MariaDB secondary Kubernetes service node port | `""` | +| `secondary.service.clusterIP` | MariaDB secondary Kubernetes service clusterIP IP | `""` | +| `secondary.service.loadBalancerIP` | MariaDB secondary loadBalancerIP if service type is `LoadBalancer` | `""` | +| `secondary.service.externalTrafficPolicy` | Enable client source IP preservation | `Cluster` | +| `secondary.service.loadBalancerSourceRanges` | Address that are allowed when MariaDB secondary service is LoadBalancer | `[]` | +| `secondary.service.extraPorts` | Extra ports to expose (normally used with the `sidecar` value) | `[]` | +| `secondary.service.annotations` | Provide any additional annotations which may be required | `{}` | +| `secondary.service.sessionAffinity` | Session Affinity for Kubernetes service, can be "None" or "ClientIP" | `None` | +| `secondary.service.sessionAffinityConfig` | Additional settings for the sessionAffinity | `{}` | +| `secondary.pdb.create` | Enable/disable a Pod Disruption Budget creation for MariaDB secondary pods | `false` | +| `secondary.pdb.minAvailable` | Minimum number/percentage of MariaDB secondary pods that should remain scheduled | `1` | +| `secondary.pdb.maxUnavailable` | Maximum number/percentage of MariaDB secondary pods that may be made unavailable | `""` | +| `secondary.revisionHistoryLimit` | Maximum number of revisions that will be maintained in the StatefulSet | `10` | + +### RBAC parameters + +| Name | Description | Value | +| --------------------------------------------- | -------------------------------------------------------------- | ------- | +| `serviceAccount.create` | Enable the creation of a ServiceAccount for MariaDB pods | `true` | +| `serviceAccount.name` | Name of the created ServiceAccount | `""` | +| `serviceAccount.annotations` | Annotations for MariaDB Service Account | `{}` | +| `serviceAccount.automountServiceAccountToken` | Automount service account token for the server service account | `false` | +| `rbac.create` | Whether to create and use RBAC resources or not | `false` | + +### Volume Permissions parameters + +| Name | Description | Value | +| -------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | ----------------------- | +| `volumePermissions.enabled` | Enable init container that changes the owner and group of the persistent volume(s) mountpoint to `runAsUser:fsGroup` | `false` | +| `volumePermissions.image.registry` | Init container volume-permissions image registry | `docker.io` | +| `volumePermissions.image.repository` | Init container volume-permissions image repository | `bitnami/bitnami-shell` | +| `volumePermissions.image.tag` | Init container volume-permissions image tag (immutable tags are recommended) | `11-debian-11-r123` | +| `volumePermissions.image.digest` | Init container volume-permissions image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag | `""` | +| `volumePermissions.image.pullPolicy` | Init container volume-permissions image pull policy | `IfNotPresent` | +| `volumePermissions.image.pullSecrets` | Specify docker-registry secret names as an array | `[]` | +| `volumePermissions.resources.limits` | Init container volume-permissions resource limits | `{}` | +| `volumePermissions.resources.requests` | Init container volume-permissions resource requests | `{}` | + +### Metrics parameters + +| Name | Description | Value | +| ----------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ------------------------- | +| `metrics.enabled` | Start a side-car prometheus exporter | `false` | +| `metrics.image.registry` | Exporter image registry | `docker.io` | +| `metrics.image.repository` | Exporter image repository | `bitnami/mysqld-exporter` | +| `metrics.image.tag` | Exporter image tag (immutable tags are recommended) | `0.14.0-debian-11-r125` | +| `metrics.image.digest` | Exporter image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag | `""` | +| `metrics.image.pullPolicy` | Exporter image pull policy | `IfNotPresent` | +| `metrics.image.pullSecrets` | Specify docker-registry secret names as an array | `[]` | +| `metrics.annotations` | Annotations for the Exporter pod | `{}` | +| `metrics.extraArgs` | Extra args to be passed to mysqld_exporter | `{}` | +| `metrics.extraVolumeMounts` | Optionally specify extra list of additional volumeMounts for the MariaDB metrics container(s) | `{}` | +| `metrics.containerSecurityContext.enabled` | Enable security context for MariaDB metrics container | `false` | +| `metrics.containerSecurityContext.privileged` | Set metrics container's Security Context privileged | `false` | +| `metrics.containerSecurityContext.allowPrivilegeEscalation` | Set metrics container's Security Context allowPrivilegeEscalation | `false` | +| `metrics.resources.limits` | The resources limits for MariaDB prometheus exporter containers | `{}` | +| `metrics.resources.requests` | The requested resources for MariaDB prometheus exporter containers | `{}` | +| `metrics.livenessProbe.enabled` | Enable livenessProbe | `true` | +| `metrics.livenessProbe.initialDelaySeconds` | Initial delay seconds for livenessProbe | `120` | +| `metrics.livenessProbe.periodSeconds` | Period seconds for livenessProbe | `10` | +| `metrics.livenessProbe.timeoutSeconds` | Timeout seconds for livenessProbe | `1` | +| `metrics.livenessProbe.failureThreshold` | Failure threshold for livenessProbe | `3` | +| `metrics.livenessProbe.successThreshold` | Success threshold for livenessProbe | `1` | +| `metrics.readinessProbe.enabled` | Enable readinessProbe | `true` | +| `metrics.readinessProbe.initialDelaySeconds` | Initial delay seconds for readinessProbe | `30` | +| `metrics.readinessProbe.periodSeconds` | Period seconds for readinessProbe | `10` | +| `metrics.readinessProbe.timeoutSeconds` | Timeout seconds for readinessProbe | `1` | +| `metrics.readinessProbe.failureThreshold` | Failure threshold for readinessProbe | `3` | +| `metrics.readinessProbe.successThreshold` | Success threshold for readinessProbe | `1` | +| `metrics.serviceMonitor.enabled` | Create ServiceMonitor Resource for scraping metrics using PrometheusOperator | `false` | +| `metrics.serviceMonitor.namespace` | Namespace which Prometheus is running in | `""` | +| `metrics.serviceMonitor.jobLabel` | The name of the label on the target service to use as the job name in prometheus. | `""` | +| `metrics.serviceMonitor.interval` | Interval at which metrics should be scraped | `30s` | +| `metrics.serviceMonitor.scrapeTimeout` | Specify the timeout after which the scrape is ended | `""` | +| `metrics.serviceMonitor.relabelings` | RelabelConfigs to apply to samples before scraping | `[]` | +| `metrics.serviceMonitor.metricRelabelings` | MetricRelabelConfigs to apply to samples before ingestion | `[]` | +| `metrics.serviceMonitor.honorLabels` | honorLabels chooses the metric's labels on collisions with target labels | `false` | +| `metrics.serviceMonitor.selector` | ServiceMonitor selector labels | `{}` | +| `metrics.serviceMonitor.labels` | Extra labels for the ServiceMonitor | `{}` | +| `metrics.prometheusRule.enabled` | if `true`, creates a Prometheus Operator PrometheusRule (also requires `metrics.enabled` to be `true` and `metrics.prometheusRule.rules`) | `false` | +| `metrics.prometheusRule.namespace` | Namespace for the PrometheusRule Resource (defaults to the Release Namespace) | `""` | +| `metrics.prometheusRule.additionalLabels` | Additional labels that can be used so PrometheusRule will be discovered by Prometheus | `{}` | +| `metrics.prometheusRule.rules` | Prometheus Rule definitions | `[]` | + +### NetworkPolicy parameters + +| Name | Description | Value | +| ---------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ------- | +| `networkPolicy.enabled` | Enable network policies | `false` | +| `networkPolicy.metrics.enabled` | Enable network policy for metrics (prometheus) | `false` | +| `networkPolicy.metrics.namespaceSelector` | Monitoring namespace selector labels. These labels will be used to identify the prometheus' namespace. | `{}` | +| `networkPolicy.metrics.podSelector` | Monitoring pod selector labels. These labels will be used to identify the Prometheus pods. | `{}` | +| `networkPolicy.ingressRules.primaryAccessOnlyFrom.enabled` | Enable ingress rule that makes primary mariadb nodes only accessible from a particular origin. | `false` | +| `networkPolicy.ingressRules.primaryAccessOnlyFrom.namespaceSelector` | Namespace selector label that is allowed to access the primary node. This label will be used to identified the allowed namespace(s). | `{}` | +| `networkPolicy.ingressRules.primaryAccessOnlyFrom.podSelector` | Pods selector label that is allowed to access the primary node. This label will be used to identified the allowed pod(s). | `{}` | +| `networkPolicy.ingressRules.primaryAccessOnlyFrom.customRules` | Custom network policy for the primary node. | `[]` | +| `networkPolicy.ingressRules.secondaryAccessOnlyFrom.enabled` | Enable ingress rule that makes primary mariadb nodes only accessible from a particular origin. | `false` | +| `networkPolicy.ingressRules.secondaryAccessOnlyFrom.namespaceSelector` | Namespace selector label that is allowed to acces the secondary nodes. This label will be used to identified the allowed namespace(s). | `{}` | +| `networkPolicy.ingressRules.secondaryAccessOnlyFrom.podSelector` | Pods selector label that is allowed to access the secondary nodes. This label will be used to identified the allowed pod(s). | `{}` | +| `networkPolicy.ingressRules.secondaryAccessOnlyFrom.customRules` | Custom network policy for the secondary nodes. | `[]` | +| `networkPolicy.egressRules.denyConnectionsToExternal` | Enable egress rule that denies outgoing traffic outside the cluster, except for DNS (port 53). | `false` | +| `networkPolicy.egressRules.customRules` | Custom network policy rule | `{}` | + +The above parameters map to the env variables defined in [bitnami/mariadb](https://github.com/bitnami/containers/tree/main/bitnami/mariadb). For more information please refer to the [bitnami/mariadb](https://github.com/bitnami/containers/tree/main/bitnami/mariadb) image documentation. + +Specify each parameter using the `--set key=value[,key=value]` argument to `helm install`. For example, + +```console +helm install my-release \ + --set auth.rootPassword=secretpassword,auth.database=app_database \ + oci://registry-1.docker.io/bitnamicharts/mariadb +``` + +The above command sets the MariaDB `root` account password to `secretpassword`. Additionally it creates a database named `my_database`. + +> NOTE: Once this chart is deployed, it is not possible to change the application's access credentials, such as usernames or passwords, using Helm. To change these application credentials after deployment, delete any persistent volumes (PVs) used by the chart and re-deploy it, or use the application's built-in administrative tools if available. + +Alternatively, a YAML file that specifies the values for the parameters can be provided while installing the chart. For example, + +```console +helm install my-release -f values.yaml oci://registry-1.docker.io/bitnamicharts/mariadb +``` + +> **Tip**: You can use the default [values.yaml](values.yaml) + +## Configuration and installation details + +### [Rolling VS Immutable tags](https://docs.bitnami.com/containers/how-to/understand-rolling-tags-containers/) + +It is strongly recommended to use immutable tags in a production environment. This ensures your deployment does not change automatically if the same tag is updated with a different image. + +Bitnami will release a new chart updating its containers if a new version of the main container, significant changes, or critical vulnerabilities exist. + +### Change MariaDB version + +To modify the MariaDB version used in this chart you can specify a [valid image tag](https://hub.docker.com/r/bitnami/mariadb/tags/) using the `image.tag` parameter. For example, `image.tag=X.Y.Z`. This approach is also applicable to other images like exporters. + +### Initialize a fresh instance + +The [Bitnami MariaDB](https://github.com/bitnami/containers/tree/main/bitnami/mariadb) image allows you to use your custom scripts to initialize a fresh instance. Custom scripts may be specified using the `initdbScripts` parameter. Alternatively, an external ConfigMap may be created with all the initialization scripts and the ConfigMap passed to the chart via the `initdbScriptsConfigMap` parameter. Note that this will override the `initdbScripts` parameter. + +The allowed extensions are `.sh`, `.sql` and `.sql.gz`. + +These scripts are treated differently depending on their extension. While `.sh` scripts are executed on all the nodes, `.sql` and `.sql.gz` scripts are only executed on the primary nodes. This is because `.sh` scripts support conditional tests to identify the type of node they are running on, while such tests are not supported in `.sql` or `.sql.gz` files. + +[Refer to the chart documentation for more information and a usage example](https://docs.bitnami.com/kubernetes/infrastructure/mariadb/configuration/customize-new-instance/). + +### Sidecars and Init Containers + +If additional containers are needed in the same pod as MariaDB (such as additional metrics or logging exporters), they can be defined using the sidecars parameter. + +The Helm chart already includes sidecar containers for the Prometheus exporters. These can be activated by adding the `--set enable-metrics=true` parameter at deployment time. The `sidecars` parameter should therefore only be used for any extra sidecar containers. [See an example of configuring and using sidecar containers](https://docs.bitnami.com/kubernetes/infrastructure/mariadb/configuration/configure-sidecar-init-containers/). + +Similarly, additional containers can be added to MariaDB pods using the `initContainers` parameter. [See an example of configuring and using init containers](https://docs.bitnami.com/kubernetes/infrastructure/mariadb/configuration/configure-sidecar-init-containers/). + +## Persistence + +The [Bitnami MariaDB](https://github.com/bitnami/containers/tree/main/bitnami/mariadb) image stores the MariaDB data and configurations at the `/bitnami/mariadb` path of the container. + +The chart mounts a [Persistent Volume](https://kubernetes.io/docs/concepts/storage/persistent-volumes/) volume at this location. The volume is created using dynamic volume provisioning, by default. An existing PersistentVolumeClaim can also be defined. + +If you encounter errors when working with persistent volumes, refer to our [troubleshooting guide for persistent volumes](https://docs.bitnami.com/kubernetes/faq/troubleshooting/troubleshooting-persistence-volumes/). + +### Adjust permissions of persistent volume mountpoint + +As the image run as non-root by default, it is necessary to adjust the ownership of the persistent volume so that the container can write data into it. + +By default, the chart is configured to use Kubernetes Security Context to automatically change the ownership of the volume. However, this feature does not work in all Kubernetes distributions. + +As an alternative, this chart supports using an initContainer to change the ownership of the volume before mounting it in the final destination. You can enable this initContainer by setting `volumePermissions.enabled` to `true`. + +## Troubleshooting + +Find more information about how to deal with common errors related to Bitnami's Helm charts in [this troubleshooting guide](https://docs.bitnami.com/general/how-to/troubleshoot-helm-chart-issues). + +## Upgrading + +It's necessary to set the `auth.rootPassword` parameter when upgrading for readiness/liveness probes to work properly. When you install this chart for the first time, some notes will be displayed providing the credentials you must use under the 'Administrator credentials' section. Please note down the password and run the command below to upgrade your chart: + +```console +helm upgrade my-release oci://registry-1.docker.io/bitnamicharts/mariadb --set auth.rootPassword=[ROOT_PASSWORD] +``` + +| Note: you need to substitute the placeholder _[ROOT_PASSWORD]_ with the value obtained in the installation notes. + +### To 11.0.0 + +This major release bumps default MariaDB branch to 10.6. Follow the [official instructions](https://mariadb.com/kb/en/upgrading-from-mariadb-105-to-mariadb-106/) from upgrading between 10.5 and 10.6. + +No major issues are expected during the upgrade. + +### To 10.0.0 + +This major release renames several values in this chart and adds missing features, in order to be inline with the rest of assets in the Bitnami charts repository. + +Affected values: + +- `primary.service.port` was deprecated, we recommend using `primary.service.ports.mysql` instead. +- `primary.service.nodePort` was deprecated, we recommend using `primary.service.nodePorts.mysql` instead. +- `secondary.service.port` was deprecated, we recommend using `secondary.service.ports.mysql` instead. +- `secondary.service.nodePort` was deprecated, we recommend using `secondary.service.nodePorts.mysql` instead. +- `metrics.serviceMonitor.additionalLabels` was deprecated, we recommend using `metrics.serviceMonitor.selector` instead. +- `primary.pdb.enabled` renamed as `primary.pdb.create`. +- `secondary.pdb.enabled` renamed as `secondary.pdb.create`. +- `primary.updateStrategy` changed from String type (previously default to 'rollingUpdate') to Object type, allowing users to configure other updateStrategy parameters, similar to other charts. +- Removed value `primary.rollingUpdatePartition`, now configured using `primary.updateStrategy` setting `primary.updateStrategy.rollingUpdate.partition`. +- `secondary.updateStrategy` changed from String type (previously default to 'rollingUpdate') to Object type, allowing users to configure other updateStrategy parameters, similar to other charts. +- Removed value `secondary.rollingUpdatePartition`, now configured using `secondary.updateStrategy` setting `secondary.updateStrategy.rollingUpdate.partition`. +- `metrics.serviceMonitor.relabellings`, previously used to configure ServiceMonitor metricRelabelings, has been replaced with the value `metrics.serviceMonitor.metricRelabelings`, and new value `metrics.serviceMonitor.relabelings` can be used to set ServiceMonitor relabelings parameter + +### To 9.0.0 + +[On November 13, 2020, Helm v2 support was formally finished](https://github.com/helm/charts#status-of-the-project), this major version is the result of the required changes applied to the Helm Chart to be able to incorporate the different features added in Helm v3 and to be consistent with the Helm project itself regarding the Helm v2 EOL. + +[Learn more about this change and related upgrade considerations](https://docs.bitnami.com/kubernetes/infrastructure/mariadb/administration/upgrade-helm3/). + +### To 8.0.0 + +- Several parameters were renamed or disappeared in favor of new ones on this major version: + - The terms _master_ and _slave_ have been replaced by the terms _primary_ and _secondary_. Therefore, parameters prefixed with `master` or `slave` are now prefixed with `primary` or `secondary`, respectively. + - `securityContext.*` is deprecated in favor of `primary.podSecurityContext`, `primary.containerSecurityContext`, `secondary.podSecurityContext`, and `secondary.containerSecurityContext`. + - Credentials parameter are reorganized under the `auth` parameter. + - `replication.enabled` parameter is deprecated in favor of `architecture` parameter that accepts two values: `standalone` and `replication`. +- The default MariaDB version was updated from 10.3 to 10.5. According to the official documentation, upgrading from 10.3 should be painless. However, there are some things that have changed which could affect an upgrade: + - [Incompatible changes upgrading from MariaDB 10.3 to MariaDB 10.4](https://mariadb.com/kb/en/upgrading-from-mariadb-103-to-mariadb-104/#incompatible-changes-between-103-and-104). + - [Incompatible changes upgrading from MariaDB 10.4 to MariaDB 10.5](https://mariadb.com/kb/en/upgrading-from-mariadb-104-to-mariadb-105/#incompatible-changes-between-104-and-105). +- Chart labels were adapted to follow the [Helm charts standard labels](https://helm.sh/docs/chart_best_practices/labels/#standard-labels). +- This version also introduces `bitnami/common`, a [library chart](https://helm.sh/docs/topics/library_charts/#helm) as a dependency. More documentation about this new utility could be found [here](https://github.com/bitnami/charts/tree/main/bitnami/common#bitnami-common-library-chart). Please, make sure that you have updated the chart dependencies before executing any upgrade. + +Consequences: + +Backwards compatibility is not guaranteed. To upgrade to `8.0.0`, install a new release of the MariaDB chart, and migrate the data from your previous release. You have 2 alternatives to do so: + +- Create a backup of the database, and restore it on the new release using tools such as [mysqldump](https://mariadb.com/kb/en/mysqldump/). +- Reuse the PVC used to hold the master data on your previous release. To do so, use the `primary.persistence.existingClaim` parameter. The following example assumes that the release name is `mariadb`: + +```console +helm install mariadb oci://registry-1.docker.io/bitnamicharts/mariadb --set auth.rootPassword=[ROOT_PASSWORD] --set primary.persistence.existingClaim=[EXISTING_PVC] +``` + +| Note: you need to substitute the placeholder _[EXISTING_PVC]_ with the name of the PVC used on your previous release, and _[ROOT_PASSWORD]_ with the root password used in your previous release. + +### To 7.0.0 + +Helm performs a lookup for the object based on its group (apps), version (v1), and kind (Deployment). Also known as its GroupVersionKind, or GVK. Changing the GVK is considered a compatibility breaker from Kubernetes' point of view, so you cannot "upgrade" those objects to the new GVK in-place. Earlier versions of Helm 3 did not perform the lookup correctly which has since been fixed to match the spec. + +In the `apiVersion` of the statefulset resources was updated to `apps/v1` in tune with the api's deprecated, resulting in compatibility breakage. + +This major version bump signifies this change. + +### To 6.0.0 + +MariaDB version was updated from 10.1 to 10.3, there are no changes in the chart itself. According to the official documentation, upgrading from 10.1 should be painless. However, there are some things that have changed which could affect an upgrade: + +- [Incompatible changes upgrading from MariaDB 10.1 to MariaDB 10.2](https://mariadb.com/kb/en/library/upgrading-from-mariadb-101-to-mariadb-102//#incompatible-changes-between-101-and-102) +- [Incompatible changes upgrading from MariaDB 10.2 to MariaDB 10.3](https://mariadb.com/kb/en/library/upgrading-from-mariadb-102-to-mariadb-103/#incompatible-changes-between-102-and-103) + +### To 5.0.0 + +Backwards compatibility is not guaranteed unless you modify the labels used on the chart's deployments. +Use the workaround below to upgrade from versions previous to 5.0.0. The following example assumes that the release name is mariadb: + +```console +kubectl delete statefulset opencart-mariadb --cascade=false +``` + +## License + +Copyright © 2023 VMware, Inc. + +Licensed under the Apache License, Version 2.0 (the "License"); +you may not use this file except in compliance with the License. +You may obtain a copy of the License at + + + +Unless required by applicable law or agreed to in writing, software +distributed under the License is distributed on an "AS IS" BASIS, +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +See the License for the specific language governing permissions and +limitations under the License. \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/.helmignore new file mode 100644 index 0000000..50af031 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/.helmignore @@ -0,0 +1,22 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/Chart.yaml new file mode 100644 index 0000000..4fc56bb --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/Chart.yaml @@ -0,0 +1,23 @@ +annotations: + category: Infrastructure + licenses: Apache-2.0 +apiVersion: v2 +appVersion: 2.4.0 +description: A Library Helm Chart for grouping common logic between bitnami charts. + This chart is not deployable by itself. +home: https://bitnami.com +icon: https://bitnami.com/downloads/logos/bitnami-mark.png +keywords: +- common +- helper +- template +- function +- bitnami +maintainers: +- name: VMware, Inc. + url: https://github.com/bitnami/charts +name: common +sources: +- https://github.com/bitnami/charts +type: library +version: 2.4.0 diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/README.md b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/README.md new file mode 100644 index 0000000..72fca33 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/README.md @@ -0,0 +1,235 @@ +# Bitnami Common Library Chart + +A [Helm Library Chart](https://helm.sh/docs/topics/library_charts/#helm) for grouping common logic between Bitnami charts. + +Looking to use our applications in production? Try [VMware Application Catalog](https://bitnami.com/enterprise), the enterprise edition of Bitnami Application Catalog. + +## TL;DR + +```yaml +dependencies: + - name: common + version: 1.x.x + repository: oci://registry-1.docker.io/bitnamicharts +``` + +```console +helm dependency update +``` + +```yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "common.names.fullname" . }} +data: + myvalue: "Hello World" +``` + +## Introduction + +This chart provides a common template helpers which can be used to develop new charts using [Helm](https://helm.sh) package manager. + +Bitnami charts can be used with [Kubeapps](https://kubeapps.dev/) for deployment and management of Helm Charts in clusters. + +## Prerequisites + +- Kubernetes 1.19+ +- Helm 3.2.0+ + +## Parameters + +## Special input schemas + +### ImageRoot + +```yaml +registry: + type: string + description: Docker registry where the image is located + example: docker.io + +repository: + type: string + description: Repository and image name + example: bitnami/nginx + +tag: + type: string + description: image tag + example: 1.16.1-debian-10-r63 + +pullPolicy: + type: string + description: Specify a imagePullPolicy. Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + +pullSecrets: + type: array + items: + type: string + description: Optionally specify an array of imagePullSecrets (evaluated as templates). + +debug: + type: boolean + description: Set to true if you would like to see extra information on logs + example: false + +## An instance would be: +# registry: docker.io +# repository: bitnami/nginx +# tag: 1.16.1-debian-10-r63 +# pullPolicy: IfNotPresent +# debug: false +``` + +### Persistence + +```yaml +enabled: + type: boolean + description: Whether enable persistence. + example: true + +storageClass: + type: string + description: Ghost data Persistent Volume Storage Class, If set to "-", storageClassName: "" which disables dynamic provisioning. + example: "-" + +accessMode: + type: string + description: Access mode for the Persistent Volume Storage. + example: ReadWriteOnce + +size: + type: string + description: Size the Persistent Volume Storage. + example: 8Gi + +path: + type: string + description: Path to be persisted. + example: /bitnami + +## An instance would be: +# enabled: true +# storageClass: "-" +# accessMode: ReadWriteOnce +# size: 8Gi +# path: /bitnami +``` + +### ExistingSecret + +```yaml +name: + type: string + description: Name of the existing secret. + example: mySecret +keyMapping: + description: Mapping between the expected key name and the name of the key in the existing secret. + type: object + +## An instance would be: +# name: mySecret +# keyMapping: +# password: myPasswordKey +``` + +#### Example of use + +When we store sensitive data for a deployment in a secret, some times we want to give to users the possibility of using theirs existing secrets. + +```yaml +# templates/secret.yaml +--- +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "common.names.fullname" . }} + labels: + app: {{ include "common.names.fullname" . }} +type: Opaque +data: + password: {{ .Values.password | b64enc | quote }} + +# templates/dpl.yaml +--- +... + env: + - name: PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "common.secrets.name" (dict "existingSecret" .Values.existingSecret "context" $) }} + key: {{ include "common.secrets.key" (dict "existingSecret" .Values.existingSecret "key" "password") }} +... + +# values.yaml +--- +name: mySecret +keyMapping: + password: myPasswordKey +``` + +### ValidateValue + +#### NOTES.txt + +```console +{{- $validateValueConf00 := (dict "valueKey" "path.to.value00" "secret" "secretName" "field" "password-00") -}} +{{- $validateValueConf01 := (dict "valueKey" "path.to.value01" "secret" "secretName" "field" "password-01") -}} + +{{ include "common.validations.values.multiple.empty" (dict "required" (list $validateValueConf00 $validateValueConf01) "context" $) }} +``` + +If we force those values to be empty we will see some alerts + +```console +helm install test mychart --set path.to.value00="",path.to.value01="" + 'path.to.value00' must not be empty, please add '--set path.to.value00=$PASSWORD_00' to the command. To get the current value: + + export PASSWORD_00=$(kubectl get secret --namespace default secretName -o jsonpath="{.data.password-00}" | base64 -d) + + 'path.to.value01' must not be empty, please add '--set path.to.value01=$PASSWORD_01' to the command. To get the current value: + + export PASSWORD_01=$(kubectl get secret --namespace default secretName -o jsonpath="{.data.password-01}" | base64 -d) +``` + +## Upgrading + +### To 1.0.0 + +[On November 13, 2020, Helm v2 support was formally finished](https://github.com/helm/charts#status-of-the-project), this major version is the result of the required changes applied to the Helm Chart to be able to incorporate the different features added in Helm v3 and to be consistent with the Helm project itself regarding the Helm v2 EOL. + +#### What changes were introduced in this major version? + +- Previous versions of this Helm Chart use `apiVersion: v1` (installable by both Helm 2 and 3), this Helm Chart was updated to `apiVersion: v2` (installable by Helm 3 only). [Here](https://helm.sh/docs/topics/charts/#the-apiversion-field) you can find more information about the `apiVersion` field. +- Use `type: library`. [Here](https://v3.helm.sh/docs/faq/#library-chart-support) you can find more information. +- The different fields present in the *Chart.yaml* file has been ordered alphabetically in a homogeneous way for all the Bitnami Helm Charts + +#### Considerations when upgrading to this version + +- If you want to upgrade to this version from a previous one installed with Helm v3, you shouldn't face any issues +- If you want to upgrade to this version using Helm v2, this scenario is not supported as this version doesn't support Helm v2 anymore +- If you installed the previous version with Helm v2 and wants to upgrade to this version with Helm v3, please refer to the [official Helm documentation](https://helm.sh/docs/topics/v2_v3_migration/#migration-use-cases) about migrating from Helm v2 to v3 + +#### Useful links + +- +- +- + +## License + +Copyright © 2023 Bitnami + +Licensed under the Apache License, Version 2.0 (the "License"); +you may not use this file except in compliance with the License. +You may obtain a copy of the License at + + + +Unless required by applicable law or agreed to in writing, software +distributed under the License is distributed on an "AS IS" BASIS, +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +See the License for the specific language governing permissions and +limitations under the License. diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_affinities.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_affinities.tpl new file mode 100644 index 0000000..81902a6 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_affinities.tpl @@ -0,0 +1,106 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Return a soft nodeAffinity definition +{{ include "common.affinities.nodes.soft" (dict "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.nodes.soft" -}} +preferredDuringSchedulingIgnoredDuringExecution: + - preference: + matchExpressions: + - key: {{ .key }} + operator: In + values: + {{- range .values }} + - {{ . | quote }} + {{- end }} + weight: 1 +{{- end -}} + +{{/* +Return a hard nodeAffinity definition +{{ include "common.affinities.nodes.hard" (dict "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.nodes.hard" -}} +requiredDuringSchedulingIgnoredDuringExecution: + nodeSelectorTerms: + - matchExpressions: + - key: {{ .key }} + operator: In + values: + {{- range .values }} + - {{ . | quote }} + {{- end }} +{{- end -}} + +{{/* +Return a nodeAffinity definition +{{ include "common.affinities.nodes" (dict "type" "soft" "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.nodes" -}} + {{- if eq .type "soft" }} + {{- include "common.affinities.nodes.soft" . -}} + {{- else if eq .type "hard" }} + {{- include "common.affinities.nodes.hard" . -}} + {{- end -}} +{{- end -}} + +{{/* +Return a topologyKey definition +{{ include "common.affinities.topologyKey" (dict "topologyKey" "BAR") -}} +*/}} +{{- define "common.affinities.topologyKey" -}} +{{ .topologyKey | default "kubernetes.io/hostname" -}} +{{- end -}} + +{{/* +Return a soft podAffinity/podAntiAffinity definition +{{ include "common.affinities.pods.soft" (dict "component" "FOO" "extraMatchLabels" .Values.extraMatchLabels "topologyKey" "BAR" "context" $) -}} +*/}} +{{- define "common.affinities.pods.soft" -}} +{{- $component := default "" .component -}} +{{- $extraMatchLabels := default (dict) .extraMatchLabels -}} +preferredDuringSchedulingIgnoredDuringExecution: + - podAffinityTerm: + labelSelector: + matchLabels: {{- (include "common.labels.matchLabels" .context) | nindent 10 }} + {{- if not (empty $component) }} + {{ printf "app.kubernetes.io/component: %s" $component }} + {{- end }} + {{- range $key, $value := $extraMatchLabels }} + {{ $key }}: {{ $value | quote }} + {{- end }} + topologyKey: {{ include "common.affinities.topologyKey" (dict "topologyKey" .topologyKey) }} + weight: 1 +{{- end -}} + +{{/* +Return a hard podAffinity/podAntiAffinity definition +{{ include "common.affinities.pods.hard" (dict "component" "FOO" "extraMatchLabels" .Values.extraMatchLabels "topologyKey" "BAR" "context" $) -}} +*/}} +{{- define "common.affinities.pods.hard" -}} +{{- $component := default "" .component -}} +{{- $extraMatchLabels := default (dict) .extraMatchLabels -}} +requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: {{- (include "common.labels.matchLabels" .context) | nindent 8 }} + {{- if not (empty $component) }} + {{ printf "app.kubernetes.io/component: %s" $component }} + {{- end }} + {{- range $key, $value := $extraMatchLabels }} + {{ $key }}: {{ $value | quote }} + {{- end }} + topologyKey: {{ include "common.affinities.topologyKey" (dict "topologyKey" .topologyKey) }} +{{- end -}} + +{{/* +Return a podAffinity/podAntiAffinity definition +{{ include "common.affinities.pods" (dict "type" "soft" "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.pods" -}} + {{- if eq .type "soft" }} + {{- include "common.affinities.pods.soft" . -}} + {{- else if eq .type "hard" }} + {{- include "common.affinities.pods.hard" . -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_capabilities.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_capabilities.tpl new file mode 100644 index 0000000..697486a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_capabilities.tpl @@ -0,0 +1,180 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Return the target Kubernetes version +*/}} +{{- define "common.capabilities.kubeVersion" -}} +{{- if .Values.global }} + {{- if .Values.global.kubeVersion }} + {{- .Values.global.kubeVersion -}} + {{- else }} + {{- default .Capabilities.KubeVersion.Version .Values.kubeVersion -}} + {{- end -}} +{{- else }} +{{- default .Capabilities.KubeVersion.Version .Values.kubeVersion -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for poddisruptionbudget. +*/}} +{{- define "common.capabilities.policy.apiVersion" -}} +{{- if semverCompare "<1.21-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "policy/v1beta1" -}} +{{- else -}} +{{- print "policy/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for networkpolicy. +*/}} +{{- define "common.capabilities.networkPolicy.apiVersion" -}} +{{- if semverCompare "<1.7-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for cronjob. +*/}} +{{- define "common.capabilities.cronjob.apiVersion" -}} +{{- if semverCompare "<1.21-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "batch/v1beta1" -}} +{{- else -}} +{{- print "batch/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for daemonset. +*/}} +{{- define "common.capabilities.daemonset.apiVersion" -}} +{{- if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else -}} +{{- print "apps/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for deployment. +*/}} +{{- define "common.capabilities.deployment.apiVersion" -}} +{{- if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else -}} +{{- print "apps/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for statefulset. +*/}} +{{- define "common.capabilities.statefulset.apiVersion" -}} +{{- if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "apps/v1beta1" -}} +{{- else -}} +{{- print "apps/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "common.capabilities.ingress.apiVersion" -}} +{{- if .Values.ingress -}} +{{- if .Values.ingress.apiVersion -}} +{{- .Values.ingress.apiVersion -}} +{{- else if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else if semverCompare "<1.19-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "networking.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end }} +{{- else if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else if semverCompare "<1.19-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "networking.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for RBAC resources. +*/}} +{{- define "common.capabilities.rbac.apiVersion" -}} +{{- if semverCompare "<1.17-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "rbac.authorization.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "rbac.authorization.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for CRDs. +*/}} +{{- define "common.capabilities.crd.apiVersion" -}} +{{- if semverCompare "<1.19-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "apiextensions.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "apiextensions.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for APIService. +*/}} +{{- define "common.capabilities.apiService.apiVersion" -}} +{{- if semverCompare "<1.10-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "apiregistration.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "apiregistration.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for Horizontal Pod Autoscaler. +*/}} +{{- define "common.capabilities.hpa.apiVersion" -}} +{{- if semverCompare "<1.23-0" (include "common.capabilities.kubeVersion" .context) -}} +{{- if .beta2 -}} +{{- print "autoscaling/v2beta2" -}} +{{- else -}} +{{- print "autoscaling/v2beta1" -}} +{{- end -}} +{{- else -}} +{{- print "autoscaling/v2" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for Vertical Pod Autoscaler. +*/}} +{{- define "common.capabilities.vpa.apiVersion" -}} +{{- if semverCompare "<1.23-0" (include "common.capabilities.kubeVersion" .context) -}} +{{- if .beta2 -}} +{{- print "autoscaling/v2beta2" -}} +{{- else -}} +{{- print "autoscaling/v2beta1" -}} +{{- end -}} +{{- else -}} +{{- print "autoscaling/v2" -}} +{{- end -}} +{{- end -}} + +{{/* +Returns true if the used Helm version is 3.3+. +A way to check the used Helm version was not introduced until version 3.3.0 with .Capabilities.HelmVersion, which contains an additional "{}}" structure. +This check is introduced as a regexMatch instead of {{ if .Capabilities.HelmVersion }} because checking for the key HelmVersion in <3.3 results in a "interface not found" error. +**To be removed when the catalog's minimun Helm version is 3.3** +*/}} +{{- define "common.capabilities.supportsHelmVersion" -}} +{{- if regexMatch "{(v[0-9])*[^}]*}}$" (.Capabilities | toString ) }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_errors.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_errors.tpl new file mode 100644 index 0000000..a79cc2e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_errors.tpl @@ -0,0 +1,23 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Through error when upgrading using empty passwords values that must not be empty. + +Usage: +{{- $validationError00 := include "common.validations.values.single.empty" (dict "valueKey" "path.to.password00" "secret" "secretName" "field" "password-00") -}} +{{- $validationError01 := include "common.validations.values.single.empty" (dict "valueKey" "path.to.password01" "secret" "secretName" "field" "password-01") -}} +{{ include "common.errors.upgrade.passwords.empty" (dict "validationErrors" (list $validationError00 $validationError01) "context" $) }} + +Required password params: + - validationErrors - String - Required. List of validation strings to be return, if it is empty it won't throw error. + - context - Context - Required. Parent context. +*/}} +{{- define "common.errors.upgrade.passwords.empty" -}} + {{- $validationErrors := join "" .validationErrors -}} + {{- if and $validationErrors .context.Release.IsUpgrade -}} + {{- $errorString := "\nPASSWORDS ERROR: You must provide your current passwords when upgrading the release." -}} + {{- $errorString = print $errorString "\n Note that even after reinstallation, old credentials may be needed as they may be kept in persistent volume claims." -}} + {{- $errorString = print $errorString "\n Further information can be obtained at https://docs.bitnami.com/general/how-to/troubleshoot-helm-chart-issues/#credential-errors-while-upgrading-chart-releases" -}} + {{- $errorString = print $errorString "\n%s" -}} + {{- printf $errorString $validationErrors | fail -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_images.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_images.tpl new file mode 100644 index 0000000..d60c22e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_images.tpl @@ -0,0 +1,80 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Return the proper image name +{{ include "common.images.image" ( dict "imageRoot" .Values.path.to.the.image "global" .Values.global ) }} +*/}} +{{- define "common.images.image" -}} +{{- $registryName := .imageRoot.registry -}} +{{- $repositoryName := .imageRoot.repository -}} +{{- $separator := ":" -}} +{{- $termination := .imageRoot.tag | toString -}} +{{- if .global }} + {{- if .global.imageRegistry }} + {{- $registryName = .global.imageRegistry -}} + {{- end -}} +{{- end -}} +{{- if .imageRoot.digest }} + {{- $separator = "@" -}} + {{- $termination = .imageRoot.digest | toString -}} +{{- end -}} +{{- if $registryName }} + {{- printf "%s/%s%s%s" $registryName $repositoryName $separator $termination -}} +{{- else -}} + {{- printf "%s%s%s" $repositoryName $separator $termination -}} +{{- end -}} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names (deprecated: use common.images.renderPullSecrets instead) +{{ include "common.images.pullSecrets" ( dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "global" .Values.global) }} +*/}} +{{- define "common.images.pullSecrets" -}} + {{- $pullSecrets := list }} + + {{- if .global }} + {{- range .global.imagePullSecrets -}} + {{- $pullSecrets = append $pullSecrets . -}} + {{- end -}} + {{- end -}} + + {{- range .images -}} + {{- range .pullSecrets -}} + {{- $pullSecrets = append $pullSecrets . -}} + {{- end -}} + {{- end -}} + + {{- if (not (empty $pullSecrets)) }} +imagePullSecrets: + {{- range $pullSecrets | uniq }} + - name: {{ . }} + {{- end }} + {{- end }} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names evaluating values as templates +{{ include "common.images.renderPullSecrets" ( dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "context" $) }} +*/}} +{{- define "common.images.renderPullSecrets" -}} + {{- $pullSecrets := list }} + {{- $context := .context }} + + {{- if $context.Values.global }} + {{- range $context.Values.global.imagePullSecrets -}} + {{- $pullSecrets = append $pullSecrets (include "common.tplvalues.render" (dict "value" . "context" $context)) -}} + {{- end -}} + {{- end -}} + + {{- range .images -}} + {{- range .pullSecrets -}} + {{- $pullSecrets = append $pullSecrets (include "common.tplvalues.render" (dict "value" . "context" $context)) -}} + {{- end -}} + {{- end -}} + + {{- if (not (empty $pullSecrets)) }} +imagePullSecrets: + {{- range $pullSecrets | uniq }} + - name: {{ . }} + {{- end }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_ingress.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_ingress.tpl new file mode 100644 index 0000000..831da9c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_ingress.tpl @@ -0,0 +1,68 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Generate backend entry that is compatible with all Kubernetes API versions. + +Usage: +{{ include "common.ingress.backend" (dict "serviceName" "backendName" "servicePort" "backendPort" "context" $) }} + +Params: + - serviceName - String. Name of an existing service backend + - servicePort - String/Int. Port name (or number) of the service. It will be translated to different yaml depending if it is a string or an integer. + - context - Dict - Required. The context for the template evaluation. +*/}} +{{- define "common.ingress.backend" -}} +{{- $apiVersion := (include "common.capabilities.ingress.apiVersion" .context) -}} +{{- if or (eq $apiVersion "extensions/v1beta1") (eq $apiVersion "networking.k8s.io/v1beta1") -}} +serviceName: {{ .serviceName }} +servicePort: {{ .servicePort }} +{{- else -}} +service: + name: {{ .serviceName }} + port: + {{- if typeIs "string" .servicePort }} + name: {{ .servicePort }} + {{- else if or (typeIs "int" .servicePort) (typeIs "float64" .servicePort) }} + number: {{ .servicePort | int }} + {{- end }} +{{- end -}} +{{- end -}} + +{{/* +Print "true" if the API pathType field is supported +Usage: +{{ include "common.ingress.supportsPathType" . }} +*/}} +{{- define "common.ingress.supportsPathType" -}} +{{- if (semverCompare "<1.18-0" (include "common.capabilities.kubeVersion" .)) -}} +{{- print "false" -}} +{{- else -}} +{{- print "true" -}} +{{- end -}} +{{- end -}} + +{{/* +Returns true if the ingressClassname field is supported +Usage: +{{ include "common.ingress.supportsIngressClassname" . }} +*/}} +{{- define "common.ingress.supportsIngressClassname" -}} +{{- if semverCompare "<1.18-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "false" -}} +{{- else -}} +{{- print "true" -}} +{{- end -}} +{{- end -}} + +{{/* +Return true if cert-manager required annotations for TLS signed +certificates are set in the Ingress annotations +Ref: https://cert-manager.io/docs/usage/ingress/#supported-annotations +Usage: +{{ include "common.ingress.certManagerRequest" ( dict "annotations" .Values.path.to.the.ingress.annotations ) }} +*/}} +{{- define "common.ingress.certManagerRequest" -}} +{{ if or (hasKey .annotations "cert-manager.io/cluster-issuer") (hasKey .annotations "cert-manager.io/issuer") (hasKey .annotations "kubernetes.io/tls-acme") }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_labels.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_labels.tpl new file mode 100644 index 0000000..252066c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_labels.tpl @@ -0,0 +1,18 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Kubernetes standard labels +*/}} +{{- define "common.labels.standard" -}} +app.kubernetes.io/name: {{ include "common.names.name" . }} +helm.sh/chart: {{ include "common.names.chart" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end -}} + +{{/* +Labels to use on deploy.spec.selector.matchLabels and svc.spec.selector +*/}} +{{- define "common.labels.matchLabels" -}} +app.kubernetes.io/name: {{ include "common.names.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_names.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_names.tpl new file mode 100644 index 0000000..617a234 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_names.tpl @@ -0,0 +1,66 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "common.names.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "common.names.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "common.names.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Create a default fully qualified dependency name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +Usage: +{{ include "common.names.dependency.fullname" (dict "chartName" "dependency-chart-name" "chartValues" .Values.dependency-chart "context" $) }} +*/}} +{{- define "common.names.dependency.fullname" -}} +{{- if .chartValues.fullnameOverride -}} +{{- .chartValues.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .chartName .chartValues.nameOverride -}} +{{- if contains $name .context.Release.Name -}} +{{- .context.Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .context.Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts. +*/}} +{{- define "common.names.namespace" -}} +{{- default .Release.Namespace .Values.namespaceOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a fully qualified app name adding the installation's namespace. +*/}} +{{- define "common.names.fullname.namespace" -}} +{{- printf "%s-%s" (include "common.names.fullname" .) (include "common.names.namespace" .) | trunc 63 | trimSuffix "-" -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_secrets.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_secrets.tpl new file mode 100644 index 0000000..a1708b2 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_secrets.tpl @@ -0,0 +1,165 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Generate secret name. + +Usage: +{{ include "common.secrets.name" (dict "existingSecret" .Values.path.to.the.existingSecret "defaultNameSuffix" "mySuffix" "context" $) }} + +Params: + - existingSecret - ExistingSecret/String - Optional. The path to the existing secrets in the values.yaml given by the user + to be used instead of the default one. Allows for it to be of type String (just the secret name) for backwards compatibility. + +info: https://github.com/bitnami/charts/tree/main/bitnami/common#existingsecret + - defaultNameSuffix - String - Optional. It is used only if we have several secrets in the same deployment. + - context - Dict - Required. The context for the template evaluation. +*/}} +{{- define "common.secrets.name" -}} +{{- $name := (include "common.names.fullname" .context) -}} + +{{- if .defaultNameSuffix -}} +{{- $name = printf "%s-%s" $name .defaultNameSuffix | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{- with .existingSecret -}} +{{- if not (typeIs "string" .) -}} +{{- with .name -}} +{{- $name = . -}} +{{- end -}} +{{- else -}} +{{- $name = . -}} +{{- end -}} +{{- end -}} + +{{- printf "%s" $name -}} +{{- end -}} + +{{/* +Generate secret key. + +Usage: +{{ include "common.secrets.key" (dict "existingSecret" .Values.path.to.the.existingSecret "key" "keyName") }} + +Params: + - existingSecret - ExistingSecret/String - Optional. The path to the existing secrets in the values.yaml given by the user + to be used instead of the default one. Allows for it to be of type String (just the secret name) for backwards compatibility. + +info: https://github.com/bitnami/charts/tree/main/bitnami/common#existingsecret + - key - String - Required. Name of the key in the secret. +*/}} +{{- define "common.secrets.key" -}} +{{- $key := .key -}} + +{{- if .existingSecret -}} + {{- if not (typeIs "string" .existingSecret) -}} + {{- if .existingSecret.keyMapping -}} + {{- $key = index .existingSecret.keyMapping $.key -}} + {{- end -}} + {{- end }} +{{- end -}} + +{{- printf "%s" $key -}} +{{- end -}} + +{{/* +Generate secret password or retrieve one if already created. + +Usage: +{{ include "common.secrets.passwords.manage" (dict "secret" "secret-name" "key" "keyName" "providedValues" (list "path.to.password1" "path.to.password2") "length" 10 "strong" false "chartName" "chartName" "context" $) }} + +Params: + - secret - String - Required - Name of the 'Secret' resource where the password is stored. + - key - String - Required - Name of the key in the secret. + - providedValues - List - Required - The path to the validating value in the values.yaml, e.g: "mysql.password". Will pick first parameter with a defined value. + - length - int - Optional - Length of the generated random password. + - strong - Boolean - Optional - Whether to add symbols to the generated random password. + - chartName - String - Optional - Name of the chart used when said chart is deployed as a subchart. + - context - Context - Required - Parent context. + +The order in which this function returns a secret password: + 1. Already existing 'Secret' resource + (If a 'Secret' resource is found under the name provided to the 'secret' parameter to this function and that 'Secret' resource contains a key with the name passed as the 'key' parameter to this function then the value of this existing secret password will be returned) + 2. Password provided via the values.yaml + (If one of the keys passed to the 'providedValues' parameter to this function is a valid path to a key in the values.yaml and has a value, the value of the first key with a value will be returned) + 3. Randomly generated secret password + (A new random secret password with the length specified in the 'length' parameter will be generated and returned) + +*/}} +{{- define "common.secrets.passwords.manage" -}} + +{{- $password := "" }} +{{- $subchart := "" }} +{{- $chartName := default "" .chartName }} +{{- $passwordLength := default 10 .length }} +{{- $providedPasswordKey := include "common.utils.getKeyFromList" (dict "keys" .providedValues "context" $.context) }} +{{- $providedPasswordValue := include "common.utils.getValueFromKey" (dict "key" $providedPasswordKey "context" $.context) }} +{{- $secretData := (lookup "v1" "Secret" (include "common.names.namespace" .context) .secret).data }} +{{- if $secretData }} + {{- if hasKey $secretData .key }} + {{- $password = index $secretData .key | quote }} + {{- else }} + {{- printf "\nPASSWORDS ERROR: The secret \"%s\" does not contain the key \"%s\"\n" .secret .key | fail -}} + {{- end -}} +{{- else if $providedPasswordValue }} + {{- $password = $providedPasswordValue | toString | b64enc | quote }} +{{- else }} + + {{- if .context.Values.enabled }} + {{- $subchart = $chartName }} + {{- end -}} + + {{- $requiredPassword := dict "valueKey" $providedPasswordKey "secret" .secret "field" .key "subchart" $subchart "context" $.context -}} + {{- $requiredPasswordError := include "common.validations.values.single.empty" $requiredPassword -}} + {{- $passwordValidationErrors := list $requiredPasswordError -}} + {{- include "common.errors.upgrade.passwords.empty" (dict "validationErrors" $passwordValidationErrors "context" $.context) -}} + + {{- if .strong }} + {{- $subStr := list (lower (randAlpha 1)) (randNumeric 1) (upper (randAlpha 1)) | join "_" }} + {{- $password = randAscii $passwordLength }} + {{- $password = regexReplaceAllLiteral "\\W" $password "@" | substr 5 $passwordLength }} + {{- $password = printf "%s%s" $subStr $password | toString | shuffle | b64enc | quote }} + {{- else }} + {{- $password = randAlphaNum $passwordLength | b64enc | quote }} + {{- end }} +{{- end -}} +{{- printf "%s" $password -}} +{{- end -}} + +{{/* +Reuses the value from an existing secret, otherwise sets its value to a default value. + +Usage: +{{ include "common.secrets.lookup" (dict "secret" "secret-name" "key" "keyName" "defaultValue" .Values.myValue "context" $) }} + +Params: + - secret - String - Required - Name of the 'Secret' resource where the password is stored. + - key - String - Required - Name of the key in the secret. + - defaultValue - String - Required - The path to the validating value in the values.yaml, e.g: "mysql.password". Will pick first parameter with a defined value. + - context - Context - Required - Parent context. + +*/}} +{{- define "common.secrets.lookup" -}} +{{- $value := "" -}} +{{- $defaultValue := required "\n'common.secrets.lookup': Argument 'defaultValue' missing or empty" .defaultValue -}} +{{- $secretData := (lookup "v1" "Secret" (include "common.names.namespace" .context) .secret).data -}} +{{- if and $secretData (hasKey $secretData .key) -}} + {{- $value = index $secretData .key -}} +{{- else -}} + {{- $value = $defaultValue | toString | b64enc -}} +{{- end -}} +{{- printf "%s" $value -}} +{{- end -}} + +{{/* +Returns whether a previous generated secret already exists + +Usage: +{{ include "common.secrets.exists" (dict "secret" "secret-name" "context" $) }} + +Params: + - secret - String - Required - Name of the 'Secret' resource where the password is stored. + - context - Context - Required - Parent context. +*/}} +{{- define "common.secrets.exists" -}} +{{- $secret := (lookup "v1" "Secret" (include "common.names.namespace" .context) .secret) }} +{{- if $secret }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_storage.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_storage.tpl new file mode 100644 index 0000000..60e2a84 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_storage.tpl @@ -0,0 +1,23 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Return the proper Storage Class +{{ include "common.storage.class" ( dict "persistence" .Values.path.to.the.persistence "global" $) }} +*/}} +{{- define "common.storage.class" -}} + +{{- $storageClass := .persistence.storageClass -}} +{{- if .global -}} + {{- if .global.storageClass -}} + {{- $storageClass = .global.storageClass -}} + {{- end -}} +{{- end -}} + +{{- if $storageClass -}} + {{- if (eq "-" $storageClass) -}} + {{- printf "storageClassName: \"\"" -}} + {{- else }} + {{- printf "storageClassName: %s" $storageClass -}} + {{- end -}} +{{- end -}} + +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_tplvalues.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_tplvalues.tpl new file mode 100644 index 0000000..2db1668 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_tplvalues.tpl @@ -0,0 +1,13 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Renders a value that contains template. +Usage: +{{ include "common.tplvalues.render" ( dict "value" .Values.path.to.the.Value "context" $) }} +*/}} +{{- define "common.tplvalues.render" -}} + {{- if typeIs "string" .value }} + {{- tpl .value .context }} + {{- else }} + {{- tpl (.value | toYaml) .context }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_utils.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_utils.tpl new file mode 100644 index 0000000..b1ead50 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_utils.tpl @@ -0,0 +1,62 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Print instructions to get a secret value. +Usage: +{{ include "common.utils.secret.getvalue" (dict "secret" "secret-name" "field" "secret-value-field" "context" $) }} +*/}} +{{- define "common.utils.secret.getvalue" -}} +{{- $varname := include "common.utils.fieldToEnvVar" . -}} +export {{ $varname }}=$(kubectl get secret --namespace {{ include "common.names.namespace" .context | quote }} {{ .secret }} -o jsonpath="{.data.{{ .field }}}" | base64 -d) +{{- end -}} + +{{/* +Build env var name given a field +Usage: +{{ include "common.utils.fieldToEnvVar" dict "field" "my-password" }} +*/}} +{{- define "common.utils.fieldToEnvVar" -}} + {{- $fieldNameSplit := splitList "-" .field -}} + {{- $upperCaseFieldNameSplit := list -}} + + {{- range $fieldNameSplit -}} + {{- $upperCaseFieldNameSplit = append $upperCaseFieldNameSplit ( upper . ) -}} + {{- end -}} + + {{ join "_" $upperCaseFieldNameSplit }} +{{- end -}} + +{{/* +Gets a value from .Values given +Usage: +{{ include "common.utils.getValueFromKey" (dict "key" "path.to.key" "context" $) }} +*/}} +{{- define "common.utils.getValueFromKey" -}} +{{- $splitKey := splitList "." .key -}} +{{- $value := "" -}} +{{- $latestObj := $.context.Values -}} +{{- range $splitKey -}} + {{- if not $latestObj -}} + {{- printf "please review the entire path of '%s' exists in values" $.key | fail -}} + {{- end -}} + {{- $value = ( index $latestObj . ) -}} + {{- $latestObj = $value -}} +{{- end -}} +{{- printf "%v" (default "" $value) -}} +{{- end -}} + +{{/* +Returns first .Values key with a defined value or first of the list if all non-defined +Usage: +{{ include "common.utils.getKeyFromList" (dict "keys" (list "path.to.key1" "path.to.key2") "context" $) }} +*/}} +{{- define "common.utils.getKeyFromList" -}} +{{- $key := first .keys -}} +{{- $reverseKeys := reverse .keys }} +{{- range $reverseKeys }} + {{- $value := include "common.utils.getValueFromKey" (dict "key" . "context" $.context ) }} + {{- if $value -}} + {{- $key = . }} + {{- end -}} +{{- end -}} +{{- printf "%s" $key -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_warnings.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_warnings.tpl new file mode 100644 index 0000000..ae10fa4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/_warnings.tpl @@ -0,0 +1,14 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Warning about using rolling tag. +Usage: +{{ include "common.warnings.rollingTag" .Values.path.to.the.imageRoot }} +*/}} +{{- define "common.warnings.rollingTag" -}} + +{{- if and (contains "bitnami/" .repository) (not (.tag | toString | regexFind "-r\\d+$|sha256:")) }} +WARNING: Rolling tag detected ({{ .repository }}:{{ .tag }}), please note that it is strongly recommended to avoid using rolling tags in a production environment. ++info https://docs.bitnami.com/containers/how-to/understand-rolling-tags-containers/ +{{- end }} + +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_cassandra.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_cassandra.tpl new file mode 100644 index 0000000..ded1ae3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_cassandra.tpl @@ -0,0 +1,72 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate Cassandra required passwords are not empty. + +Usage: +{{ include "common.validations.values.cassandra.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where Cassandra values are stored, e.g: "cassandra-passwords-secret" + - subchart - Boolean - Optional. Whether Cassandra is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.cassandra.passwords" -}} + {{- $existingSecret := include "common.cassandra.values.existingSecret" . -}} + {{- $enabled := include "common.cassandra.values.enabled" . -}} + {{- $dbUserPrefix := include "common.cassandra.values.key.dbUser" . -}} + {{- $valueKeyPassword := printf "%s.password" $dbUserPrefix -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "cassandra-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.cassandra.values.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether Cassandra is used as subchart or not. Default: false +*/}} +{{- define "common.cassandra.values.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.cassandra.dbUser.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.dbUser.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled cassandra. + +Usage: +{{ include "common.cassandra.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.cassandra.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.cassandra.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key dbUser + +Usage: +{{ include "common.cassandra.values.key.dbUser" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether Cassandra is used as subchart or not. Default: false +*/}} +{{- define "common.cassandra.values.key.dbUser" -}} + {{- if .subchart -}} + cassandra.dbUser + {{- else -}} + dbUser + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_mariadb.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_mariadb.tpl new file mode 100644 index 0000000..b6906ff --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_mariadb.tpl @@ -0,0 +1,103 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate MariaDB required passwords are not empty. + +Usage: +{{ include "common.validations.values.mariadb.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where MariaDB values are stored, e.g: "mysql-passwords-secret" + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.mariadb.passwords" -}} + {{- $existingSecret := include "common.mariadb.values.auth.existingSecret" . -}} + {{- $enabled := include "common.mariadb.values.enabled" . -}} + {{- $architecture := include "common.mariadb.values.architecture" . -}} + {{- $authPrefix := include "common.mariadb.values.key.auth" . -}} + {{- $valueKeyRootPassword := printf "%s.rootPassword" $authPrefix -}} + {{- $valueKeyUsername := printf "%s.username" $authPrefix -}} + {{- $valueKeyPassword := printf "%s.password" $authPrefix -}} + {{- $valueKeyReplicationPassword := printf "%s.replicationPassword" $authPrefix -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredRootPassword := dict "valueKey" $valueKeyRootPassword "secret" .secret "field" "mariadb-root-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRootPassword -}} + + {{- $valueUsername := include "common.utils.getValueFromKey" (dict "key" $valueKeyUsername "context" .context) }} + {{- if not (empty $valueUsername) -}} + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "mariadb-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + {{- end -}} + + {{- if (eq $architecture "replication") -}} + {{- $requiredReplicationPassword := dict "valueKey" $valueKeyReplicationPassword "secret" .secret "field" "mariadb-replication-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredReplicationPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.mariadb.values.auth.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.mariadb.values.auth.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.mariadb.auth.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.auth.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled mariadb. + +Usage: +{{ include "common.mariadb.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.mariadb.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.mariadb.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for architecture + +Usage: +{{ include "common.mariadb.values.architecture" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.mariadb.values.architecture" -}} + {{- if .subchart -}} + {{- .context.Values.mariadb.architecture -}} + {{- else -}} + {{- .context.Values.architecture -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key auth + +Usage: +{{ include "common.mariadb.values.key.auth" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.mariadb.values.key.auth" -}} + {{- if .subchart -}} + mariadb.auth + {{- else -}} + auth + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_mongodb.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_mongodb.tpl new file mode 100644 index 0000000..f820ec1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_mongodb.tpl @@ -0,0 +1,108 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate MongoDB® required passwords are not empty. + +Usage: +{{ include "common.validations.values.mongodb.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where MongoDB® values are stored, e.g: "mongodb-passwords-secret" + - subchart - Boolean - Optional. Whether MongoDB® is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.mongodb.passwords" -}} + {{- $existingSecret := include "common.mongodb.values.auth.existingSecret" . -}} + {{- $enabled := include "common.mongodb.values.enabled" . -}} + {{- $authPrefix := include "common.mongodb.values.key.auth" . -}} + {{- $architecture := include "common.mongodb.values.architecture" . -}} + {{- $valueKeyRootPassword := printf "%s.rootPassword" $authPrefix -}} + {{- $valueKeyUsername := printf "%s.username" $authPrefix -}} + {{- $valueKeyDatabase := printf "%s.database" $authPrefix -}} + {{- $valueKeyPassword := printf "%s.password" $authPrefix -}} + {{- $valueKeyReplicaSetKey := printf "%s.replicaSetKey" $authPrefix -}} + {{- $valueKeyAuthEnabled := printf "%s.enabled" $authPrefix -}} + + {{- $authEnabled := include "common.utils.getValueFromKey" (dict "key" $valueKeyAuthEnabled "context" .context) -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") (eq $authEnabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredRootPassword := dict "valueKey" $valueKeyRootPassword "secret" .secret "field" "mongodb-root-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRootPassword -}} + + {{- $valueUsername := include "common.utils.getValueFromKey" (dict "key" $valueKeyUsername "context" .context) }} + {{- $valueDatabase := include "common.utils.getValueFromKey" (dict "key" $valueKeyDatabase "context" .context) }} + {{- if and $valueUsername $valueDatabase -}} + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "mongodb-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + {{- end -}} + + {{- if (eq $architecture "replicaset") -}} + {{- $requiredReplicaSetKey := dict "valueKey" $valueKeyReplicaSetKey "secret" .secret "field" "mongodb-replica-set-key" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredReplicaSetKey -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.mongodb.values.auth.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MongoDb is used as subchart or not. Default: false +*/}} +{{- define "common.mongodb.values.auth.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.mongodb.auth.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.auth.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled mongodb. + +Usage: +{{ include "common.mongodb.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.mongodb.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.mongodb.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key auth + +Usage: +{{ include "common.mongodb.values.key.auth" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MongoDB® is used as subchart or not. Default: false +*/}} +{{- define "common.mongodb.values.key.auth" -}} + {{- if .subchart -}} + mongodb.auth + {{- else -}} + auth + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for architecture + +Usage: +{{ include "common.mongodb.values.architecture" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MongoDB® is used as subchart or not. Default: false +*/}} +{{- define "common.mongodb.values.architecture" -}} + {{- if .subchart -}} + {{- .context.Values.mongodb.architecture -}} + {{- else -}} + {{- .context.Values.architecture -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_mysql.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_mysql.tpl new file mode 100644 index 0000000..74472a0 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_mysql.tpl @@ -0,0 +1,103 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate MySQL required passwords are not empty. + +Usage: +{{ include "common.validations.values.mysql.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where MySQL values are stored, e.g: "mysql-passwords-secret" + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.mysql.passwords" -}} + {{- $existingSecret := include "common.mysql.values.auth.existingSecret" . -}} + {{- $enabled := include "common.mysql.values.enabled" . -}} + {{- $architecture := include "common.mysql.values.architecture" . -}} + {{- $authPrefix := include "common.mysql.values.key.auth" . -}} + {{- $valueKeyRootPassword := printf "%s.rootPassword" $authPrefix -}} + {{- $valueKeyUsername := printf "%s.username" $authPrefix -}} + {{- $valueKeyPassword := printf "%s.password" $authPrefix -}} + {{- $valueKeyReplicationPassword := printf "%s.replicationPassword" $authPrefix -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredRootPassword := dict "valueKey" $valueKeyRootPassword "secret" .secret "field" "mysql-root-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRootPassword -}} + + {{- $valueUsername := include "common.utils.getValueFromKey" (dict "key" $valueKeyUsername "context" .context) }} + {{- if not (empty $valueUsername) -}} + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "mysql-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + {{- end -}} + + {{- if (eq $architecture "replication") -}} + {{- $requiredReplicationPassword := dict "valueKey" $valueKeyReplicationPassword "secret" .secret "field" "mysql-replication-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredReplicationPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.mysql.values.auth.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.mysql.values.auth.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.mysql.auth.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.auth.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled mysql. + +Usage: +{{ include "common.mysql.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.mysql.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.mysql.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for architecture + +Usage: +{{ include "common.mysql.values.architecture" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.mysql.values.architecture" -}} + {{- if .subchart -}} + {{- .context.Values.mysql.architecture -}} + {{- else -}} + {{- .context.Values.architecture -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key auth + +Usage: +{{ include "common.mysql.values.key.auth" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.mysql.values.key.auth" -}} + {{- if .subchart -}} + mysql.auth + {{- else -}} + auth + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_postgresql.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_postgresql.tpl new file mode 100644 index 0000000..164ec0d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_postgresql.tpl @@ -0,0 +1,129 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate PostgreSQL required passwords are not empty. + +Usage: +{{ include "common.validations.values.postgresql.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where postgresql values are stored, e.g: "postgresql-passwords-secret" + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.postgresql.passwords" -}} + {{- $existingSecret := include "common.postgresql.values.existingSecret" . -}} + {{- $enabled := include "common.postgresql.values.enabled" . -}} + {{- $valueKeyPostgresqlPassword := include "common.postgresql.values.key.postgressPassword" . -}} + {{- $valueKeyPostgresqlReplicationEnabled := include "common.postgresql.values.key.replicationPassword" . -}} + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + {{- $requiredPostgresqlPassword := dict "valueKey" $valueKeyPostgresqlPassword "secret" .secret "field" "postgresql-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPostgresqlPassword -}} + + {{- $enabledReplication := include "common.postgresql.values.enabled.replication" . -}} + {{- if (eq $enabledReplication "true") -}} + {{- $requiredPostgresqlReplicationPassword := dict "valueKey" $valueKeyPostgresqlReplicationEnabled "secret" .secret "field" "postgresql-replication-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPostgresqlReplicationPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to decide whether evaluate global values. + +Usage: +{{ include "common.postgresql.values.use.global" (dict "key" "key-of-global" "context" $) }} +Params: + - key - String - Required. Field to be evaluated within global, e.g: "existingSecret" +*/}} +{{- define "common.postgresql.values.use.global" -}} + {{- if .context.Values.global -}} + {{- if .context.Values.global.postgresql -}} + {{- index .context.Values.global.postgresql .key | quote -}} + {{- end -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.postgresql.values.existingSecret" (dict "context" $) }} +*/}} +{{- define "common.postgresql.values.existingSecret" -}} + {{- $globalValue := include "common.postgresql.values.use.global" (dict "key" "existingSecret" "context" .context) -}} + + {{- if .subchart -}} + {{- default (.context.Values.postgresql.existingSecret | quote) $globalValue -}} + {{- else -}} + {{- default (.context.Values.existingSecret | quote) $globalValue -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled postgresql. + +Usage: +{{ include "common.postgresql.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.postgresql.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.postgresql.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key postgressPassword. + +Usage: +{{ include "common.postgresql.values.key.postgressPassword" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.postgresql.values.key.postgressPassword" -}} + {{- $globalValue := include "common.postgresql.values.use.global" (dict "key" "postgresqlUsername" "context" .context) -}} + + {{- if not $globalValue -}} + {{- if .subchart -}} + postgresql.postgresqlPassword + {{- else -}} + postgresqlPassword + {{- end -}} + {{- else -}} + global.postgresql.postgresqlPassword + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled.replication. + +Usage: +{{ include "common.postgresql.values.enabled.replication" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.postgresql.values.enabled.replication" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.postgresql.replication.enabled -}} + {{- else -}} + {{- printf "%v" .context.Values.replication.enabled -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key replication.password. + +Usage: +{{ include "common.postgresql.values.key.replicationPassword" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.postgresql.values.key.replicationPassword" -}} + {{- if .subchart -}} + postgresql.replication.password + {{- else -}} + replication.password + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_redis.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_redis.tpl new file mode 100644 index 0000000..dcccfc1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_redis.tpl @@ -0,0 +1,76 @@ + +{{/* vim: set filetype=mustache: */}} +{{/* +Validate Redis® required passwords are not empty. + +Usage: +{{ include "common.validations.values.redis.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where redis values are stored, e.g: "redis-passwords-secret" + - subchart - Boolean - Optional. Whether redis is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.redis.passwords" -}} + {{- $enabled := include "common.redis.values.enabled" . -}} + {{- $valueKeyPrefix := include "common.redis.values.keys.prefix" . -}} + {{- $standarizedVersion := include "common.redis.values.standarized.version" . }} + + {{- $existingSecret := ternary (printf "%s%s" $valueKeyPrefix "auth.existingSecret") (printf "%s%s" $valueKeyPrefix "existingSecret") (eq $standarizedVersion "true") }} + {{- $existingSecretValue := include "common.utils.getValueFromKey" (dict "key" $existingSecret "context" .context) }} + + {{- $valueKeyRedisPassword := ternary (printf "%s%s" $valueKeyPrefix "auth.password") (printf "%s%s" $valueKeyPrefix "password") (eq $standarizedVersion "true") }} + {{- $valueKeyRedisUseAuth := ternary (printf "%s%s" $valueKeyPrefix "auth.enabled") (printf "%s%s" $valueKeyPrefix "usePassword") (eq $standarizedVersion "true") }} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $useAuth := include "common.utils.getValueFromKey" (dict "key" $valueKeyRedisUseAuth "context" .context) -}} + {{- if eq $useAuth "true" -}} + {{- $requiredRedisPassword := dict "valueKey" $valueKeyRedisPassword "secret" .secret "field" "redis-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRedisPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled redis. + +Usage: +{{ include "common.redis.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.redis.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.redis.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right prefix path for the values + +Usage: +{{ include "common.redis.values.key.prefix" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether redis is used as subchart or not. Default: false +*/}} +{{- define "common.redis.values.keys.prefix" -}} + {{- if .subchart -}}redis.{{- else -}}{{- end -}} +{{- end -}} + +{{/* +Checks whether the redis chart's includes the standarizations (version >= 14) + +Usage: +{{ include "common.redis.values.standarized.version" (dict "context" $) }} +*/}} +{{- define "common.redis.values.standarized.version" -}} + + {{- $standarizedAuth := printf "%s%s" (include "common.redis.values.keys.prefix" .) "auth" -}} + {{- $standarizedAuthValues := include "common.utils.getValueFromKey" (dict "key" $standarizedAuth "context" .context) }} + + {{- if $standarizedAuthValues -}} + {{- true -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_validations.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_validations.tpl new file mode 100644 index 0000000..9a814cf --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/templates/validations/_validations.tpl @@ -0,0 +1,46 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate values must not be empty. + +Usage: +{{- $validateValueConf00 := (dict "valueKey" "path.to.value" "secret" "secretName" "field" "password-00") -}} +{{- $validateValueConf01 := (dict "valueKey" "path.to.value" "secret" "secretName" "field" "password-01") -}} +{{ include "common.validations.values.empty" (dict "required" (list $validateValueConf00 $validateValueConf01) "context" $) }} + +Validate value params: + - valueKey - String - Required. The path to the validating value in the values.yaml, e.g: "mysql.password" + - secret - String - Optional. Name of the secret where the validating value is generated/stored, e.g: "mysql-passwords-secret" + - field - String - Optional. Name of the field in the secret data, e.g: "mysql-password" +*/}} +{{- define "common.validations.values.multiple.empty" -}} + {{- range .required -}} + {{- include "common.validations.values.single.empty" (dict "valueKey" .valueKey "secret" .secret "field" .field "context" $.context) -}} + {{- end -}} +{{- end -}} + +{{/* +Validate a value must not be empty. + +Usage: +{{ include "common.validations.value.empty" (dict "valueKey" "mariadb.password" "secret" "secretName" "field" "my-password" "subchart" "subchart" "context" $) }} + +Validate value params: + - valueKey - String - Required. The path to the validating value in the values.yaml, e.g: "mysql.password" + - secret - String - Optional. Name of the secret where the validating value is generated/stored, e.g: "mysql-passwords-secret" + - field - String - Optional. Name of the field in the secret data, e.g: "mysql-password" + - subchart - String - Optional - Name of the subchart that the validated password is part of. +*/}} +{{- define "common.validations.values.single.empty" -}} + {{- $value := include "common.utils.getValueFromKey" (dict "key" .valueKey "context" .context) }} + {{- $subchart := ternary "" (printf "%s." .subchart) (empty .subchart) }} + + {{- if not $value -}} + {{- $varname := "my-value" -}} + {{- $getCurrentValue := "" -}} + {{- if and .secret .field -}} + {{- $varname = include "common.utils.fieldToEnvVar" . -}} + {{- $getCurrentValue = printf " To get the current value:\n\n %s\n" (include "common.utils.secret.getvalue" .) -}} + {{- end -}} + {{- printf "\n '%s' must not be empty, please add '--set %s%s=$%s' to the command.%s" .valueKey $subchart .valueKey $varname $getCurrentValue -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/values.yaml new file mode 100644 index 0000000..f2df68e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/charts/common/values.yaml @@ -0,0 +1,5 @@ +## bitnami/common +## It is required by CI/CD tools and processes. +## @skip exampleValue +## +exampleValue: common-chart diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/NOTES.txt new file mode 100644 index 0000000..ba55fd8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/NOTES.txt @@ -0,0 +1,75 @@ +CHART NAME: {{ .Chart.Name }} +CHART VERSION: {{ .Chart.Version }} +APP VERSION: {{ .Chart.AppVersion }} + +** Please be patient while the chart is being deployed ** + +{{- if .Values.diagnosticMode.enabled }} +The chart has been deployed in diagnostic mode. All probes have been disabled and the command has been overwritten with: + + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 4 }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 4 }} + +Get the list of pods by executing: + + kubectl get pods --namespace {{ .Release.Namespace }} -l app.kubernetes.io/instance={{ .Release.Name }} + +Access the pod you want to debug by executing + + kubectl exec --namespace {{ .Release.Namespace }} -ti -- bash + +In order to replicate the container startup scripts execute this command: + + /opt/bitnami/scripts/mariadb/entrypoint.sh /opt/bitnami/scripts/mariadb/run.sh + +{{- else }} + +Tip: + + Watch the deployment status using the command: kubectl get pods -w --namespace {{ .Release.Namespace }} -l app.kubernetes.io/instance={{ .Release.Name }} + +Services: + + echo Primary: {{ include "mariadb.primary.fullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }}:{{ coalesce .Values.primary.service.ports.mysql .Values.primary.service.port }} +{{- if eq .Values.architecture "replication" }} + echo Secondary: {{ include "mariadb.secondary.fullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }}:{{ coalesce .Values.secondary.service.ports.mysql .Values.secondary.service.port }} +{{- end }} + +Administrator credentials: + + Username: root + Password : $(kubectl get secret --namespace {{ .Release.Namespace }} {{ template "mariadb.secretName" . }} -o jsonpath="{.data.mariadb-root-password}" | base64 -d) + +To connect to your database: + + 1. Run a pod that you can use as a client: + + kubectl run {{ include "common.names.fullname" . }}-client --rm --tty -i --restart='Never' --image {{ template "mariadb.image" . }} --namespace {{ .Release.Namespace }} --command -- bash + + 2. To connect to primary service (read/write): + + mysql -h {{ include "mariadb.primary.fullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }} -uroot -p {{ .Values.auth.database }} + +{{- if eq .Values.architecture "replication" }} + + 3. To connect to secondary service (read-only): + + mysql -h {{ include "mariadb.secondary.fullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }} -uroot -p {{ .Values.auth.database }} +{{- end }} + +To upgrade this helm chart: + + 1. Obtain the password as described on the 'Administrator credentials' section and set the 'auth.rootPassword' parameter as shown below: + + ROOT_PASSWORD=$(kubectl get secret --namespace {{ .Release.Namespace }} {{ template "mariadb.secretName" . }} -o jsonpath="{.data.mariadb-root-password}" | base64 -d) + helm upgrade --namespace {{ .Release.Namespace }} {{ .Release.Name }} oci://registry-1.docker.io/bitnamicharts/mariadb --set auth.rootPassword=$ROOT_PASSWORD + +{{- include "common.warnings.rollingTag" .Values.image }} +{{- include "common.warnings.rollingTag" .Values.metrics.image }} +{{- include "common.warnings.rollingTag" .Values.volumePermissions.image }} +{{- include "mariadb.validateValues" . }} +{{- if not .Values.auth.customPasswordFiles -}} + {{- $passwordValidationErrors := include "common.validations.values.mariadb.passwords" (dict "secret" (include "common.names.fullname" .) "context" $) -}} + {{- include "common.errors.upgrade.passwords.empty" (dict "validationErrors" (list $passwordValidationErrors) "context" $) -}} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/_helpers.tpl new file mode 100644 index 0000000..d940b5a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/_helpers.tpl @@ -0,0 +1,159 @@ +{{/* vim: set filetype=mustache: */}} + +{{- define "mariadb.primary.fullname" -}} +{{- if eq .Values.architecture "replication" }} +{{- printf "%s-%s" (include "common.names.fullname" .) .Values.primary.name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- include "common.names.fullname" . -}} +{{- end -}} +{{- end -}} + +{{- define "mariadb.secondary.fullname" -}} +{{- printf "%s-%s" (include "common.names.fullname" .) .Values.secondary.name | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Return the proper MariaDB image name +*/}} +{{- define "mariadb.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return the proper metrics image name +*/}} +{{- define "mariadb.metrics.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.metrics.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return the proper image name (for the init container volume-permissions image) +*/}} +{{- define "mariadb.volumePermissions.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.volumePermissions.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names +*/}} +{{- define "mariadb.imagePullSecrets" -}} +{{ include "common.images.pullSecrets" (dict "images" (list .Values.image .Values.metrics.image .Values.volumePermissions.image) "global" .Values.global) }} +{{- end -}} + +{{ template "mariadb.initdbScriptsCM" . }} +{{/* +Get the initialization scripts ConfigMap name. +*/}} +{{- define "mariadb.initdbScriptsCM" -}} +{{- if .Values.initdbScriptsConfigMap -}} +{{- printf "%s" (tpl .Values.initdbScriptsConfigMap $) -}} +{{- else -}} +{{- printf "%s-init-scripts" (include "mariadb.primary.fullname" .) -}} +{{- end -}} +{{- end -}} + +{{/* +Create the name of the service account to use +*/}} +{{- define "mariadb.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "common.names.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Return the configmap with the MariaDB Primary configuration +*/}} +{{- define "mariadb.primary.configmapName" -}} +{{- if .Values.primary.existingConfigmap -}} + {{- printf "%s" (tpl .Values.primary.existingConfigmap $) -}} +{{- else -}} + {{- printf "%s" (include "mariadb.primary.fullname" .) -}} +{{- end -}} +{{- end -}} + +{{/* +Return true if a configmap object should be created for MariaDB Secondary +*/}} +{{- define "mariadb.primary.createConfigmap" -}} +{{- if and .Values.primary.configuration (not .Values.primary.existingConfigmap) }} + {{- true -}} +{{- else -}} +{{- end -}} +{{- end -}} + +{{/* +Return the configmap with the MariaDB Primary configuration +*/}} +{{- define "mariadb.secondary.configmapName" -}} +{{- if .Values.secondary.existingConfigmap -}} + {{- printf "%s" (tpl .Values.secondary.existingConfigmap $) -}} +{{- else -}} + {{- printf "%s" (include "mariadb.secondary.fullname" .) -}} +{{- end -}} +{{- end -}} + +{{/* +Return true if a configmap object should be created for MariaDB Secondary +*/}} +{{- define "mariadb.secondary.createConfigmap" -}} +{{- if and (eq .Values.architecture "replication") .Values.secondary.configuration (not .Values.secondary.existingConfigmap) }} + {{- true -}} +{{- else -}} +{{- end -}} +{{- end -}} + +{{/* +Return the secret with MariaDB credentials +*/}} +{{- define "mariadb.secretName" -}} + {{- if .Values.auth.existingSecret -}} + {{- printf "%s" (tpl .Values.auth.existingSecret $) -}} + {{- else -}} + {{- printf "%s" (include "common.names.fullname" .) -}} + {{- end -}} +{{- end -}} + +{{/* +Return true if a secret object should be created for MariaDB +*/}} +{{- define "mariadb.createSecret" -}} +{{- if not (or .Values.auth.existingSecret .Values.auth.customPasswordFiles) }} + {{- true -}} +{{- end -}} +{{- end -}} + +{{/* +Compile all warnings into a single message, and call fail. +*/}} +{{- define "mariadb.validateValues" -}} +{{- $messages := list -}} +{{- $messages := append $messages (include "mariadb.validateValues.architecture" .) -}} +{{- $messages := without $messages "" -}} +{{- $message := join "\n" $messages -}} + +{{- if $message -}} +{{- printf "\nVALUES VALIDATION:\n%s" $message | fail -}} +{{- end -}} +{{- end -}} + +{{/* Validate values of MariaDB - must provide a valid architecture */}} +{{- define "mariadb.validateValues.architecture" -}} +{{- if and (ne .Values.architecture "standalone") (ne .Values.architecture "replication") -}} +mariadb: architecture + Invalid architecture selected. Valid values are "standalone" and + "replication". Please set a valid architecture (--set architecture="xxxx") +{{- end -}} +{{- end -}} + +{{/* +Get existing password to access MariaDB +*/}} +{{- define "mariadb.secret.existPassword" -}} +{{- $secret := (lookup "v1" "Secret" .Release.Namespace (include "mariadb.secretName" .)).data -}} +{{- if hasKey $secret "mariadb-password" }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/extra-list.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/extra-list.yaml new file mode 100644 index 0000000..9ac65f9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/extra-list.yaml @@ -0,0 +1,4 @@ +{{- range .Values.extraDeploy }} +--- +{{ include "common.tplvalues.render" (dict "value" . "context" $) }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/networkpolicy-egress.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/networkpolicy-egress.yaml new file mode 100644 index 0000000..84f5d83 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/networkpolicy-egress.yaml @@ -0,0 +1,33 @@ +{{- if and .Values.networkPolicy.enabled (or .Values.networkPolicy.egressRules.denyConnectionsToExternal .Values.networkPolicy.egressRules.customRules) }} +apiVersion: {{ include "common.capabilities.networkPolicy.apiVersion" . }} +kind: NetworkPolicy +metadata: + name: {{ printf "%s-egress" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + podSelector: + matchLabels: + {{- include "common.labels.standard" . | nindent 6 }} + policyTypes: + - Egress + egress: + {{- if .Values.networkPolicy.egressRules.denyConnectionsToExternal }} + - ports: + - port: 53 + protocol: UDP + - port: 53 + protocol: TCP + - to: + - namespaceSelector: {} + {{- end }} + {{- if .Values.networkPolicy.egressRules.customRules }} + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.egressRules.customRules "context" $) | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/configmap.yaml new file mode 100644 index 0000000..ae4d5b1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/configmap.yaml @@ -0,0 +1,18 @@ +{{- if (include "mariadb.primary.createConfigmap" .) }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "mariadb.primary.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: primary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: + my.cnf: |- +{{ .Values.primary.configuration | indent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/initialization-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/initialization-configmap.yaml new file mode 100644 index 0000000..f85903c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/initialization-configmap.yaml @@ -0,0 +1,11 @@ +{{- if and .Values.initdbScripts (not .Values.initdbScriptsConfigMap) }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ printf "%s-init-scripts" (include "mariadb.primary.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: primary +data: +{{- include "common.tplvalues.render" (dict "value" .Values.initdbScripts "context" .) | nindent 2 }} +{{ end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/networkpolicy-ingress.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/networkpolicy-ingress.yaml new file mode 100644 index 0000000..125d0dd --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/networkpolicy-ingress.yaml @@ -0,0 +1,56 @@ +{{- if and .Values.networkPolicy.enabled (or .Values.networkPolicy.metrics.enabled .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.enabled) }} +apiVersion: {{ include "common.capabilities.networkPolicy.apiVersion" . }} +kind: NetworkPolicy +metadata: + name: {{ printf "%s-ingress" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + podSelector: + matchLabels: + app.kubernetes.io/component: primary + {{- include "common.labels.standard" . | nindent 6 }} + ingress: + {{- if and .Values.metrics.enabled .Values.networkPolicy.metrics.enabled (or .Values.networkPolicy.metrics.namespaceSelector .Values.networkPolicy.metrics.podSelector) }} + - from: + {{- if .Values.networkPolicy.metrics.namespaceSelector }} + - namespaceSelector: + matchLabels: + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.metrics.namespaceSelector "context" $) | nindent 14 }} + {{- end }} + {{- if .Values.networkPolicy.metrics.podSelector }} + - podSelector: + matchLabels: + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.metrics.podSelector "context" $) | nindent 14 }} + {{- end }} + {{- end }} + {{- if and .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.enabled (or .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.namespaceSelector .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.podSelector) }} + - from: + {{- if .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.namespaceSelector }} + - namespaceSelector: + matchLabels: + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.namespaceSelector "context" $) | nindent 14 }} + {{- end }} + {{- if .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.podSelector }} + - podSelector: + matchLabels: + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.podSelector "context" $) | nindent 14 }} + {{- end }} + {{- end }} + {{- if and .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.enabled (eq .Values.architecture "replication") }} + - from: + - podSelector: + matchLabels: + app.kubernetes.io/component: secondary + {{- include "common.labels.standard" . | nindent 14 }} + {{- end }} + {{- if .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.customRules }} + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.customRules "context" $) | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/pdb.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/pdb.yaml new file mode 100644 index 0000000..d923058 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/pdb.yaml @@ -0,0 +1,25 @@ +{{- if .Values.primary.pdb.create }} +apiVersion: {{ include "common.capabilities.policy.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "mariadb.primary.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: primary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + {{- if .Values.primary.pdb.minAvailable }} + minAvailable: {{ .Values.primary.pdb.minAvailable }} + {{- end }} + {{- if .Values.primary.pdb.maxUnavailable }} + maxUnavailable: {{ .Values.primary.pdb.maxUnavailable }} + {{- end }} + selector: + matchLabels: {{ include "common.labels.matchLabels" . | nindent 6 }} + app.kubernetes.io/component: primary +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/statefulset.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/statefulset.yaml new file mode 100644 index 0000000..b1605df --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/statefulset.yaml @@ -0,0 +1,397 @@ +apiVersion: {{ include "common.capabilities.statefulset.apiVersion" . }} +kind: StatefulSet +metadata: + name: {{ include "mariadb.primary.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: primary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + replicas: 1 + revisionHistoryLimit: {{ .Values.primary.revisionHistoryLimit }} + selector: + matchLabels: {{ include "common.labels.matchLabels" . | nindent 6 }} + app.kubernetes.io/component: primary + serviceName: {{ include "mariadb.primary.fullname" . }} + {{- if .Values.primary.updateStrategy }} + updateStrategy: {{- toYaml .Values.primary.updateStrategy | nindent 4 }} + {{- end }} + template: + metadata: + annotations: + {{- if (include "mariadb.primary.createConfigmap" .) }} + checksum/configuration: {{ include (print $.Template.BasePath "/primary/configmap.yaml") . | sha256sum }} + {{- end }} + {{- if .Values.primary.podAnnotations }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.podAnnotations "context" $) | nindent 8 }} + {{- end }} + labels: {{- include "common.labels.standard" . | nindent 8 }} + app.kubernetes.io/component: primary + {{- if .Values.primary.podLabels }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.podLabels "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 8 }} + {{- end }} + spec: + {{- include "mariadb.imagePullSecrets" . | nindent 6 }} + {{- if .Values.primary.hostAliases }} + hostAliases: {{- include "common.tplvalues.render" (dict "value" .Values.primary.hostAliases "context" $) | nindent 8 }} + {{- end }} + {{- if or .Values.primary.schedulerName .Values.schedulerName }} + schedulerName: {{ (coalesce .Values.primary.schedulerName .Values.schedulerName) | quote }} + {{- end }} + serviceAccountName: {{ template "mariadb.serviceAccountName" . }} + {{- if .Values.primary.affinity }} + affinity: {{- include "common.tplvalues.render" (dict "value" .Values.primary.affinity "context" $) | nindent 8 }} + {{- else }} + affinity: + podAffinity: {{- include "common.affinities.pods" (dict "type" .Values.primary.podAffinityPreset "component" "primary" "context" $) | nindent 10 }} + podAntiAffinity: {{- include "common.affinities.pods" (dict "type" .Values.primary.podAntiAffinityPreset "component" "primary" "context" $) | nindent 10 }} + nodeAffinity: {{- include "common.affinities.nodes" (dict "type" .Values.primary.nodeAffinityPreset.type "key" .Values.primary.nodeAffinityPreset.key "values" .Values.primary.nodeAffinityPreset.values) | nindent 10 }} + {{- end }} + {{- if .Values.primary.nodeSelector }} + nodeSelector: {{- include "common.tplvalues.render" (dict "value" .Values.primary.nodeSelector "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.primary.tolerations }} + tolerations: {{- include "common.tplvalues.render" (dict "value" .Values.primary.tolerations "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.primary.schedulerName }} + schedulerName: {{ .Values.primary.schedulerName }} + {{- end }} + {{- if .Values.primary.topologySpreadConstraints }} + topologySpreadConstraints: {{- include "common.tplvalues.render" (dict "value" .Values.primary.topologySpreadConstraints "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.primary.priorityClassName }} + priorityClassName: {{ .Values.primary.priorityClassName | quote }} + {{- else if .Values.priorityClassName }} + priorityClassName: {{ .Values.priorityClassName | quote }} + {{- end }} + {{- if .Values.primary.runtimeClassName }} + runtimeClassName: {{ .Values.primary.runtimeClassName | quote }} + {{- else if .Values.runtimeClassName }} + runtimeClassName: {{ .Values.runtimeClassName | quote }} + {{- end }} + {{- if .Values.primary.podSecurityContext.enabled }} + securityContext: {{- omit .Values.primary.podSecurityContext "enabled" | toYaml | nindent 8 }} + {{- end }} + {{- if or .Values.primary.initContainers (and .Values.primary.podSecurityContext.enabled .Values.volumePermissions.enabled .Values.primary.persistence.enabled) }} + initContainers: + {{- if .Values.primary.initContainers }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.initContainers "context" $) | nindent 8 }} + {{- end }} + {{- if and .Values.primary.podSecurityContext.enabled .Values.volumePermissions.enabled .Values.primary.persistence.enabled }} + - name: volume-permissions + image: {{ include "mariadb.volumePermissions.image" . }} + imagePullPolicy: {{ .Values.volumePermissions.image.pullPolicy | quote }} + command: + - /bin/bash + - -ec + - | + chown -R {{ .Values.primary.containerSecurityContext.runAsUser }}:{{ .Values.primary.podSecurityContext.fsGroup }} /bitnami/mariadb + securityContext: + runAsUser: 0 + {{- if .Values.volumePermissions.resources }} + resources: {{- toYaml .Values.volumePermissions.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: data + mountPath: /bitnami/mariadb + {{- if .Values.primary.persistence.subPath }} + subPath: {{ .Values.primary.persistence.subPath }} + {{- end }} + {{- end }} + {{- end }} + containers: + - name: mariadb + image: {{ include "mariadb.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy | quote }} + {{- if .Values.primary.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.primary.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + {{- else if .Values.primary.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.primary.command "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else if .Values.primary.args }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.primary.args "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.primary.lifecycleHooks }} + lifecycle: {{- include "common.tplvalues.render" (dict "value" .Values.primary.lifecycleHooks "context" $) | nindent 12 }} + {{- end }} + env: + - name: BITNAMI_DEBUG + value: {{ ternary "true" "false" (or .Values.image.debug .Values.diagnosticMode.enabled) | quote }} + {{- if .Values.auth.usePasswordFiles }} + - name: MARIADB_ROOT_PASSWORD_FILE + value: {{ default "/opt/bitnami/mariadb/secrets/mariadb-root-password" .Values.auth.customPasswordFiles.root }} + {{- else }} + - name: MARIADB_ROOT_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "mariadb.secretName" . }} + key: mariadb-root-password + {{- end }} + {{- if not (empty .Values.auth.username) }} + - name: MARIADB_USER + value: {{ .Values.auth.username | quote }} + {{- if .Values.auth.usePasswordFiles }} + - name: MARIADB_PASSWORD_FILE + value: {{ default "/opt/bitnami/mariadb/secrets/mariadb-password" .Values.auth.customPasswordFiles.user }} + {{- else }} + - name: MARIADB_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "mariadb.secretName" . }} + key: mariadb-password + {{- end }} + {{- end }} + - name: MARIADB_DATABASE + value: {{ .Values.auth.database | quote }} + {{- if eq .Values.architecture "replication" }} + - name: MARIADB_REPLICATION_MODE + value: "master" + - name: MARIADB_REPLICATION_USER + value: {{ .Values.auth.replicationUser | quote }} + {{- if .Values.auth.usePasswordFiles }} + - name: MARIADB_REPLICATION_PASSWORD_FILE + value: {{ default "/opt/bitnami/mariadb/secrets/mariadb-replication-password" .Values.auth.customPasswordFiles.replicator }} + {{- else }} + - name: MARIADB_REPLICATION_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "mariadb.secretName" . }} + key: mariadb-replication-password + {{- end }} + {{- end }} + {{- if .Values.primary.extraFlags }} + - name: MARIADB_EXTRA_FLAGS + value: "{{ .Values.primary.extraFlags }}" + {{- end }} + {{- if .Values.primary.startupWaitOptions }} + - name: MARIADB_STARTUP_WAIT_RETRIES + value: "{{ .Values.primary.startupWaitOptions.retries | default 300 }}" + - name: MARIADB_STARTUP_WAIT_SLEEP_TIME + value: "{{ .Values.primary.startupWaitOptions.sleepTime | default 2 }}" + {{- end }} + {{- if .Values.primary.extraEnvVars }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.extraEnvVars "context" $) | nindent 12 }} + {{- end }} + {{- if or .Values.primary.extraEnvVarsCM .Values.primary.extraEnvVarsSecret }} + envFrom: + {{- if .Values.primary.extraEnvVarsCM }} + - configMapRef: + name: {{ .Values.primary.extraEnvVarsCM }} + {{- end }} + {{- if .Values.primary.extraEnvVarsSecret }} + - secretRef: + name: {{ .Values.primary.extraEnvVarsSecret }} + {{- end }} + {{- end }} + ports: + - name: mysql + containerPort: 3306 + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.primary.customStartupProbe }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.primary.customStartupProbe "context" $) | nindent 12 }} + {{- else if .Values.primary.startupProbe.enabled }} + startupProbe: {{- omit .Values.primary.startupProbe "enabled" | toYaml | nindent 12 }} + exec: + command: + - /bin/bash + - -ec + - | + password_aux="${MARIADB_ROOT_PASSWORD:-}" + if [[ -f "${MARIADB_ROOT_PASSWORD_FILE:-}" ]]; then + password_aux=$(cat "$MARIADB_ROOT_PASSWORD_FILE") + fi + mysqladmin status -uroot -p"${password_aux}" + {{- end }} + {{- if .Values.primary.customLivenessProbe }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.primary.customLivenessProbe "context" $) | nindent 12 }} + {{- else if .Values.primary.livenessProbe.enabled }} + livenessProbe: {{- omit .Values.primary.livenessProbe "enabled" | toYaml | nindent 12 }} + exec: + command: + - /bin/bash + - -ec + - | + password_aux="${MARIADB_ROOT_PASSWORD:-}" + if [[ -f "${MARIADB_ROOT_PASSWORD_FILE:-}" ]]; then + password_aux=$(cat "$MARIADB_ROOT_PASSWORD_FILE") + fi + mysqladmin status -uroot -p"${password_aux}" + {{- end }} + {{- if .Values.primary.customReadinessProbe }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.primary.customReadinessProbe "context" $) | nindent 12 }} + {{- else if .Values.primary.readinessProbe.enabled }} + readinessProbe: {{- omit .Values.primary.readinessProbe "enabled" | toYaml | nindent 12 }} + exec: + command: + - /bin/bash + - -ec + - | + password_aux="${MARIADB_ROOT_PASSWORD:-}" + if [[ -f "${MARIADB_ROOT_PASSWORD_FILE:-}" ]]; then + password_aux=$(cat "$MARIADB_ROOT_PASSWORD_FILE") + fi + mysqladmin status -uroot -p"${password_aux}" + {{- end }} + {{- end }} + {{- if .Values.primary.resources }} + resources: {{ toYaml .Values.primary.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: data + mountPath: /bitnami/mariadb + {{- if .Values.primary.persistence.subPath }} + subPath: {{ .Values.primary.persistence.subPath }} + {{- end }} + {{- if or .Values.initdbScriptsConfigMap .Values.initdbScripts }} + - name: custom-init-scripts + mountPath: /docker-entrypoint-initdb.d + {{- end }} + {{- if or .Values.primary.configuration .Values.primary.existingConfigmap }} + - name: config + mountPath: /opt/bitnami/mariadb/conf/my.cnf + subPath: my.cnf + {{- end }} + {{- if and .Values.auth.usePasswordFiles (not .Values.auth.customPasswordFiles) }} + - name: mariadb-credentials + mountPath: /opt/bitnami/mariadb/secrets/ + {{- end }} + {{- if .Values.primary.extraVolumeMounts }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.extraVolumeMounts "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.metrics.enabled }} + - name: metrics + image: {{ include "mariadb.metrics.image" . }} + imagePullPolicy: {{ .Values.metrics.image.pullPolicy | quote }} + {{- if .Values.metrics.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.metrics.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + env: + {{- if .Values.auth.usePasswordFiles }} + - name: MARIADB_ROOT_PASSWORD_FILE + value: {{ default "/opt/bitnami/mysqld-exporter/secrets/mariadb-root-password" .Values.auth.customPasswordFiles.root }} + {{- else }} + - name: MARIADB_ROOT_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "mariadb.secretName" . }} + key: mariadb-root-password + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else }} + command: + - /bin/bash + - -ec + - | + password_aux="${MARIADB_ROOT_PASSWORD:-}" + if [[ -f "${MARIADB_ROOT_PASSWORD_FILE:-}" ]]; then + password_aux=$(cat "$MARIADB_ROOT_PASSWORD_FILE") + fi + DATA_SOURCE_NAME="root:${password_aux}@(localhost:3306)/" /bin/mysqld_exporter {{- range .Values.metrics.extraArgs.primary }} {{ . }} {{- end }} + {{- end }} + ports: + - name: metrics + containerPort: 9104 + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.metrics.livenessProbe.enabled }} + livenessProbe: {{- omit .Values.metrics.livenessProbe "enabled" | toYaml | nindent 12 }} + httpGet: + path: /metrics + port: metrics + {{- end }} + {{- if .Values.metrics.readinessProbe.enabled }} + readinessProbe: {{- omit .Values.metrics.readinessProbe "enabled" | toYaml | nindent 12 }} + httpGet: + path: /metrics + port: metrics + {{- end }} + {{- end }} + {{- if .Values.metrics.resources }} + resources: {{- toYaml .Values.metrics.resources | nindent 12 }} + {{- end }} + volumeMounts: + {{- if and .Values.auth.usePasswordFiles (not .Values.auth.customPasswordFiles) }} + - name: mariadb-credentials + mountPath: /opt/bitnami/mysqld-exporter/secrets/ + {{- end }} + {{- if .Values.metrics.extraVolumeMounts.primary }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.extraVolumeMounts.primary "context" $) | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.primary.sidecars }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.sidecars "context" $) | nindent 8 }} + {{- end }} + volumes: + {{- if or .Values.primary.configuration .Values.primary.existingConfigmap }} + - name: config + configMap: + name: {{ include "mariadb.primary.configmapName" . }} + {{- end }} + {{- if or .Values.initdbScriptsConfigMap .Values.initdbScripts }} + - name: custom-init-scripts + configMap: + name: {{ template "mariadb.initdbScriptsCM" . }} + {{- end }} + {{- if and .Values.auth.usePasswordFiles (not .Values.auth.customPasswordFiles) }} + - name: mariadb-credentials + secret: + secretName: {{ template "mariadb.secretName" . }} + items: + - key: mariadb-root-password + path: mariadb-root-password + - key: mariadb-password + path: mariadb-password + {{- if eq .Values.architecture "replication" }} + - key: mariadb-replication-password + path: mariadb-replication-password + {{- end }} + {{- end }} + {{- if .Values.primary.extraVolumes }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.extraVolumes "context" $) | nindent 8 }} + {{- end }} + {{- if and .Values.primary.persistence.enabled .Values.primary.persistence.existingClaim }} + - name: data + persistentVolumeClaim: + claimName: {{ tpl .Values.primary.persistence.existingClaim . }} + {{- else if not .Values.primary.persistence.enabled }} + - name: data + emptyDir: {} + {{- else if and .Values.primary.persistence.enabled (not .Values.primary.persistence.existingClaim) }} + volumeClaimTemplates: + - metadata: + name: data + labels: {{ include "common.labels.matchLabels" . | nindent 10 }} + app.kubernetes.io/component: primary + {{- if .Values.primary.persistence.annotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.primary.persistence.annotations "context" $ ) | nindent 10 }} + {{- end }} + {{- if .Values.primary.persistence.labels }} + labels: {{- include "common.tplvalues.render" (dict "value" .Values.primary.persistence.labels "context" $) | nindent 10 }} + {{- end }} + spec: + accessModes: + {{- range .Values.primary.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + resources: + requests: + storage: {{ .Values.primary.persistence.size | quote }} + {{ include "common.storage.class" (dict "persistence" .Values.primary.persistence "global" .Values.global) }} + {{- if .Values.primary.persistence.selector }} + selector: {{- include "common.tplvalues.render" (dict "value" .Values.primary.persistence.selector "context" $) | nindent 10 }} + {{- end -}} + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/svc.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/svc.yaml new file mode 100644 index 0000000..85d3156 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/primary/svc.yaml @@ -0,0 +1,61 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mariadb.primary.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: primary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.primary.service.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.primary.service.annotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if and .Values.metrics.enabled .Values.metrics.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.annotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.primary.service.type }} + {{- if and .Values.primary.service.clusterIP (eq .Values.primary.service.type "ClusterIP") }} + clusterIP: {{ .Values.primary.service.clusterIP }} + {{- end }} + {{- if and .Values.primary.service.externalTrafficPolicy (or (eq .Values.primary.service.type "LoadBalancer") (eq .Values.primary.service.type "NodePort")) }} + externalTrafficPolicy: {{ .Values.primary.service.externalTrafficPolicy | quote }} + {{- end }} + {{- if and (eq .Values.primary.service.type "LoadBalancer") .Values.primary.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: {{ .Values.primary.service.loadBalancerSourceRanges }} + {{ end }} + {{- if (and (eq .Values.primary.service.type "LoadBalancer") (not (empty .Values.primary.service.loadBalancerIP))) }} + loadBalancerIP: {{ .Values.primary.service.loadBalancerIP }} + {{- end }} + {{- if .Values.primary.service.sessionAffinity }} + sessionAffinity: {{ .Values.primary.service.sessionAffinity }} + {{- end }} + {{- if .Values.primary.service.sessionAffinityConfig }} + sessionAffinityConfig: {{- include "common.tplvalues.render" (dict "value" .Values.primary.service.sessionAffinityConfig "context" $) | nindent 4 }} + {{- end }} + ports: + - name: mysql + port: {{ coalesce .Values.primary.service.ports.mysql .Values.primary.service.port }} + protocol: TCP + targetPort: mysql + {{- if (and (or (eq .Values.primary.service.type "NodePort") (eq .Values.primary.service.type "LoadBalancer")) (coalesce .Values.primary.service.nodePorts.mysql .Values.primary.service.nodePort)) }} + nodePort: {{ coalesce .Values.primary.service.nodePorts.mysql .Values.primary.service.nodePort }} + {{- else if eq .Values.primary.service.type "ClusterIP" }} + nodePort: null + {{- end }} + {{- if and .Values.metrics.enabled (gt (.Values.primary.service.ports.metrics | int) 0) }} + - name: metrics + port: {{ .Values.primary.service.ports.metrics }} + protocol: TCP + targetPort: metrics + {{- end }} + {{- if .Values.primary.service.extraPorts }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.service.extraPorts "context" $) | nindent 4 }} + {{- end }} + selector: {{ include "common.labels.matchLabels" . | nindent 4 }} + app.kubernetes.io/component: primary diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/prometheusrules.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/prometheusrules.yaml new file mode 100644 index 0000000..523e533 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/prometheusrules.yaml @@ -0,0 +1,26 @@ +{{- if and .Values.metrics.enabled .Values.metrics.prometheusRule.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ include "common.names.fullname" . }} + {{- if .Values.metrics.prometheusRule.namespace }} + namespace: {{ .Values.metrics.prometheusRule.namespace }} + {{- else }} + namespace: {{ .Release.Namespace | quote }} + {{- end }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: metrics + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.metrics.prometheusRule.additionalLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.prometheusRule.additionalLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + groups: + - name: {{ include "common.names.fullname" . }} + rules: {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.prometheusRule.rules "context" $ ) | nindent 6 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/role.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/role.yaml new file mode 100644 index 0000000..a561f51 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/role.yaml @@ -0,0 +1,21 @@ +{{- if and .Values.serviceAccount.create .Values.rbac.create }} +apiVersion: {{ include "common.capabilities.rbac.apiVersion" . }} +kind: Role +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +rules: + - apiGroups: + - "" + resources: + - endpoints + verbs: + - get +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/rolebinding.yaml new file mode 100644 index 0000000..671aa6e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/rolebinding.yaml @@ -0,0 +1,21 @@ +{{- if and .Values.serviceAccount.create .Values.rbac.create }} +kind: RoleBinding +apiVersion: {{ include "common.capabilities.rbac.apiVersion" . }} +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +subjects: + - kind: ServiceAccount + name: {{ include "mariadb.serviceAccountName" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "common.names.fullname" . -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/configmap.yaml new file mode 100644 index 0000000..4cfec64 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/configmap.yaml @@ -0,0 +1,18 @@ +{{- if (include "mariadb.secondary.createConfigmap" .) }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "mariadb.secondary.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: secondary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: + my.cnf: |- +{{ .Values.secondary.configuration | indent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/networkpolicy-ingress.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/networkpolicy-ingress.yaml new file mode 100644 index 0000000..51a8885 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/networkpolicy-ingress.yaml @@ -0,0 +1,49 @@ +{{- if and .Values.networkPolicy.enabled (eq .Values.architecture "replication") (or .Values.networkPolicy.metrics.enabled .Values.networkPolicy.ingressRules.secondaryAccessOnlyFrom.enabled) }} +apiVersion: {{ include "common.capabilities.networkPolicy.apiVersion" . }} +kind: NetworkPolicy +metadata: + name: {{ printf "%s-ingress-secondary" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + podSelector: + matchLabels: + app.kubernetes.io/component: secondary + {{- include "common.labels.standard" . | nindent 6 }} + ingress: + {{- if and .Values.metrics.enabled .Values.networkPolicy.metrics.enabled (or .Values.networkPolicy.metrics.namespaceSelector .Values.networkPolicy.metrics.podSelector) }} + - from: + {{- if .Values.networkPolicy.metrics.namespaceSelector }} + - namespaceSelector: + matchLabels: + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.metrics.namespaceSelector "context" $) | nindent 14 }} + {{- end }} + {{- if .Values.networkPolicy.metrics.podSelector }} + - podSelector: + matchLabels: + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.metrics.podSelector "context" $) | nindent 14 }} + {{- end }} + {{- end }} + {{- if and .Values.networkPolicy.ingressRules.secondaryAccessOnlyFrom.enabled (or .Values.networkPolicy.ingressRules.secondaryAccessOnlyFrom.namespaceSelector .Values.networkPolicy.ingressRules.secondaryAccessOnlyFrom.podSelector) }} + - from: + {{- if .Values.networkPolicy.ingressRules.secondaryAccessOnlyFrom.namespaceSelector }} + - namespaceSelector: + matchLabels: + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.ingressRules.secondaryAccessOnlyFrom.namespaceSelector "context" $) | nindent 14 }} + {{- end }} + {{- if .Values.networkPolicy.ingressRules.secondaryAccessOnlyFrom.podSelector }} + - podSelector: + matchLabels: + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.ingressRules.secondaryAccessOnlyFrom.podSelector "context" $) | nindent 14 }} + {{- end }} + {{- end }} + {{- if .Values.networkPolicy.ingressRules.secondaryAccessOnlyFrom.customRules }} + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.ingressRules.secondaryAccessOnlyFrom.customRules "context" $) | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/pdb.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/pdb.yaml new file mode 100644 index 0000000..cae28ff --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/pdb.yaml @@ -0,0 +1,25 @@ +{{- if and (eq .Values.architecture "replication") .Values.secondary.pdb.create }} +apiVersion: {{ include "common.capabilities.policy.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "mariadb.secondary.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: secondary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + {{- if .Values.secondary.pdb.minAvailable }} + minAvailable: {{ .Values.secondary.pdb.minAvailable }} + {{- end }} + {{- if .Values.secondary.pdb.maxUnavailable }} + maxUnavailable: {{ .Values.secondary.pdb.maxUnavailable }} + {{- end }} + selector: + matchLabels: {{ include "common.labels.matchLabels" . | nindent 6 }} + app.kubernetes.io/component: secondary +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/statefulset.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/statefulset.yaml new file mode 100644 index 0000000..568bf7f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/statefulset.yaml @@ -0,0 +1,368 @@ +{{- if eq .Values.architecture "replication" }} +apiVersion: {{ include "common.capabilities.statefulset.apiVersion" . }} +kind: StatefulSet +metadata: + name: {{ include "mariadb.secondary.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: secondary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.secondary.replicaCount }} + revisionHistoryLimit: {{ .Values.secondary.revisionHistoryLimit }} + selector: + matchLabels: {{ include "common.labels.matchLabels" . | nindent 6 }} + app.kubernetes.io/component: secondary + serviceName: {{ include "mariadb.secondary.fullname" . }} + podManagementPolicy: {{ .Values.secondary.podManagementPolicy }} + {{- if .Values.secondary.updateStrategy }} + updateStrategy: {{- toYaml .Values.secondary.updateStrategy | nindent 4 }} + {{- end }} + template: + metadata: + annotations: + {{- if (include "mariadb.secondary.createConfigmap" .) }} + checksum/configuration: {{ include (print $.Template.BasePath "/secondary/configmap.yaml") . | sha256sum }} + {{- end }} + {{- if .Values.secondary.podAnnotations }} + {{- include "common.tplvalues.render" (dict "value" .Values.secondary.podAnnotations "context" $) | nindent 8 }} + {{- end }} + labels: {{- include "common.labels.standard" . | nindent 8 }} + app.kubernetes.io/component: secondary + {{- if .Values.secondary.podLabels }} + {{- include "common.tplvalues.render" (dict "value" .Values.secondary.podLabels "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 8 }} + {{- end }} + spec: + {{- include "mariadb.imagePullSecrets" . | nindent 6 }} + {{- if or .Values.secondary.schedulerName .Values.schedulerName }} + schedulerName: {{ (coalesce .Values.secondary.schedulerName .Values.schedulerName) | quote }} + {{- end }} + serviceAccountName: {{ template "mariadb.serviceAccountName" . }} + {{- if .Values.secondary.hostAliases }} + hostAliases: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.hostAliases "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.secondary.affinity }} + affinity: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.affinity "context" $) | nindent 8 }} + {{- else }} + affinity: + podAffinity: {{- include "common.affinities.pods" (dict "type" .Values.secondary.podAffinityPreset "component" "secondary" "context" $) | nindent 10 }} + podAntiAffinity: {{- include "common.affinities.pods" (dict "type" .Values.secondary.podAntiAffinityPreset "component" "secondary" "context" $) | nindent 10 }} + nodeAffinity: {{- include "common.affinities.nodes" (dict "type" .Values.secondary.nodeAffinityPreset.type "key" .Values.secondary.nodeAffinityPreset.key "values" .Values.secondary.nodeAffinityPreset.values) | nindent 10 }} + {{- end }} + {{- if .Values.secondary.nodeSelector }} + nodeSelector: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.nodeSelector "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.secondary.tolerations }} + tolerations: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.tolerations "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.secondary.topologySpreadConstraints }} + topologySpreadConstraints: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.topologySpreadConstraints "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.secondary.priorityClassName }} + priorityClassName: {{ .Values.secondary.priorityClassName | quote }} + {{- else if .Values.priorityClassName }} + priorityClassName: {{ .Values.priorityClassName | quote }} + {{- end }} + {{- if .Values.secondary.runtimeClassName }} + runtimeClassName: {{ .Values.secondary.runtimeClassName | quote }} + {{- else if .Values.runtimeClassName }} + runtimeClassName: {{ .Values.runtimeClassName | quote }} + {{- end }} + {{- if .Values.secondary.podSecurityContext.enabled }} + securityContext: {{- omit .Values.secondary.podSecurityContext "enabled" | toYaml | nindent 8 }} + {{- end }} + {{- if or .Values.secondary.initContainers (and .Values.secondary.podSecurityContext.enabled .Values.volumePermissions.enabled .Values.secondary.persistence.enabled) }} + initContainers: + {{- if .Values.secondary.initContainers }} + {{- include "common.tplvalues.render" (dict "value" .Values.secondary.initContainers "context" $) | nindent 8 }} + {{- end }} + {{- if and .Values.secondary.podSecurityContext.enabled .Values.volumePermissions.enabled .Values.secondary.persistence.enabled }} + - name: volume-permissions + image: {{ include "mariadb.volumePermissions.image" . }} + imagePullPolicy: {{ .Values.volumePermissions.image.pullPolicy | quote }} + command: + - /bin/bash + - -ec + - | + chown -R {{ .Values.secondary.containerSecurityContext.runAsUser }}:{{ .Values.secondary.podSecurityContext.fsGroup }} /bitnami/mariadb + securityContext: + runAsUser: 0 + {{- if .Values.volumePermissions.resources }} + resources: {{- toYaml .Values.volumePermissions.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: data + mountPath: /bitnami/mariadb + {{- if .Values.secondary.persistence.subPath }} + subPath: {{ .Values.secondary.persistence.subPath }} + {{- end }} + {{- end }} + {{- end }} + containers: + - name: mariadb + image: {{ include "mariadb.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy | quote }} + {{- if .Values.secondary.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.secondary.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + {{- else if .Values.secondary.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.command "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else if .Values.secondary.args }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.args "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.secondary.lifecycleHooks }} + lifecycle: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.lifecycleHooks "context" $) | nindent 12 }} + {{- end }} + env: + - name: BITNAMI_DEBUG + value: {{ ternary "true" "false" (or .Values.image.debug .Values.diagnosticMode.enabled) | quote }} + - name: MARIADB_REPLICATION_MODE + value: "slave" + - name: MARIADB_MASTER_HOST + value: {{ include "mariadb.primary.fullname" . }} + - name: MARIADB_MASTER_PORT_NUMBER + value: {{ coalesce .Values.primary.service.ports.mysql .Values.primary.service.port | quote }} + - name: MARIADB_MASTER_ROOT_USER + value: "root" + {{- if .Values.auth.usePasswordFiles }} + - name: MARIADB_MASTER_ROOT_PASSWORD_FILE + value: {{ default "/opt/bitnami/mariadb/secrets/mariadb-root-password" .Values.auth.customPasswordFiles.root }} + {{- else }} + - name: MARIADB_MASTER_ROOT_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "mariadb.secretName" . }} + key: mariadb-root-password + {{- end }} + - name: MARIADB_REPLICATION_USER + value: {{ .Values.auth.replicationUser | quote }} + {{- if .Values.auth.usePasswordFiles }} + - name: MARIADB_REPLICATION_PASSWORD_FILE + value: {{ default "/opt/bitnami/mariadb/secrets/mariadb-replication-password" .Values.auth.customPasswordFiles.replicator }} + {{- else }} + - name: MARIADB_REPLICATION_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "mariadb.secretName" . }} + key: mariadb-replication-password + {{- end }} + {{- if .Values.secondary.extraFlags }} + - name: MARIADB_EXTRA_FLAGS + value: "{{ .Values.secondary.extraFlags }}" + {{- end }} + {{- if .Values.secondary.startupWaitOptions }} + - name: MARIADB_STARTUP_WAIT_RETRIES + value: "{{ .Values.secondary.startupWaitOptions.retries | default 300 }}" + - name: MARIADB_STARTUP_WAIT_SLEEP_TIME + value: "{{ .Values.secondary.startupWaitOptions.sleepTime | default 2 }}" + {{- end }} + {{- if .Values.secondary.extraEnvVars }} + {{- include "common.tplvalues.render" (dict "value" .Values.secondary.extraEnvVars "context" $) | nindent 12 }} + {{- end }} + {{- if or .Values.secondary.extraEnvVarsCM .Values.secondary.extraEnvVarsSecret }} + envFrom: + {{- if .Values.secondary.extraEnvVarsCM }} + - configMapRef: + name: {{ .Values.secondary.extraEnvVarsCM }} + {{- end }} + {{- if .Values.secondary.extraEnvVarsSecret }} + - secretRef: + name: {{ .Values.secondary.extraEnvVarsSecret }} + {{- end }} + {{- end }} + ports: + - name: mysql + containerPort: 3306 + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.secondary.customStartupProbe }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.customStartupProbe "context" $) | nindent 12 }} + {{- else if .Values.secondary.startupProbe.enabled }} + startupProbe: {{- omit .Values.secondary.startupProbe "enabled" | toYaml | nindent 12 }} + exec: + command: + - /bin/bash + - -ec + - | + password_aux="${MARIADB_MASTER_ROOT_PASSWORD:-}" + if [[ -f "${MARIADB_MASTER_ROOT_PASSWORD_FILE:-}" ]]; then + password_aux=$(cat "$MARIADB_MASTER_ROOT_PASSWORD_FILE") + fi + mysqladmin status -uroot -p"${password_aux}" + {{- end }} + {{- if .Values.secondary.customLivenessProbe }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.customLivenessProbe "context" $) | nindent 12 }} + {{- else if .Values.secondary.livenessProbe.enabled }} + livenessProbe: {{- omit .Values.secondary.livenessProbe "enabled" | toYaml | nindent 12 }} + exec: + command: + - /bin/bash + - -ec + - | + password_aux="${MARIADB_MASTER_ROOT_PASSWORD:-}" + if [[ -f "${MARIADB_MASTER_ROOT_PASSWORD_FILE:-}" ]]; then + password_aux=$(cat "$MARIADB_MASTER_ROOT_PASSWORD_FILE") + fi + mysqladmin status -uroot -p"${password_aux}" + {{- end }} + {{- if .Values.secondary.customReadinessProbe }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.customReadinessProbe "context" $) | nindent 12 }} + {{- else if .Values.secondary.readinessProbe.enabled }} + readinessProbe: {{- omit .Values.secondary.readinessProbe "enabled" | toYaml | nindent 12 }} + exec: + command: + - /bin/bash + - -ec + - | + password_aux="${MARIADB_MASTER_ROOT_PASSWORD:-}" + if [[ -f "${MARIADB_MASTER_ROOT_PASSWORD_FILE:-}" ]]; then + password_aux=$(cat "$MARIADB_MASTER_ROOT_PASSWORD_FILE") + fi + mysqladmin status -uroot -p"${password_aux}" + {{- end }} + {{- end }} + {{- if .Values.secondary.resources }} + resources: {{ toYaml .Values.secondary.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: data + mountPath: /bitnami/mariadb + {{- if .Values.secondary.persistence.subPath }} + subPath: {{ .Values.secondary.persistence.subPath }} + {{- end }} + {{- if or .Values.secondary.configuration .Values.secondary.existingConfigmap }} + - name: config + mountPath: /opt/bitnami/mariadb/conf/my.cnf + subPath: my.cnf + {{- end }} + {{- if and .Values.auth.usePasswordFiles (not .Values.auth.customPasswordFiles) }} + - name: mariadb-credentials + mountPath: /opt/bitnami/mariadb/secrets/ + {{- end }} + {{- if .Values.secondary.extraVolumeMounts }} + {{- include "common.tplvalues.render" (dict "value" .Values.secondary.extraVolumeMounts "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.metrics.enabled }} + - name: metrics + image: {{ include "mariadb.metrics.image" . }} + imagePullPolicy: {{ .Values.metrics.image.pullPolicy | quote }} + {{- if .Values.metrics.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.metrics.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + env: + {{- if .Values.auth.usePasswordFiles }} + - name: MARIADB_ROOT_PASSWORD_FILE + value: {{ default "/opt/bitnami/mysqld-exporter/secrets/mariadb-root-password" .Values.auth.customPasswordFiles.root }} + {{- else }} + - name: MARIADB_ROOT_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "mariadb.secretName" . }} + key: mariadb-root-password + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else }} + command: + - /bin/bash + - -ec + - | + password_aux="${MARIADB_ROOT_PASSWORD:-}" + if [[ -f "${MARIADB_ROOT_PASSWORD_FILE:-}" ]]; then + password_aux=$(cat "$MARIADB_ROOT_PASSWORD_FILE") + fi + DATA_SOURCE_NAME="root:${password_aux}@(localhost:3306)/" /bin/mysqld_exporter {{- range .Values.metrics.extraArgs.secondary }} {{ . }} {{- end }} + {{- end }} + ports: + - name: metrics + containerPort: 9104 + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.metrics.livenessProbe.enabled }} + livenessProbe: {{- omit .Values.metrics.livenessProbe "enabled" | toYaml | nindent 12 }} + httpGet: + path: /metrics + port: metrics + {{- end }} + {{- if .Values.metrics.readinessProbe.enabled }} + readinessProbe: {{- omit .Values.metrics.readinessProbe "enabled" | toYaml | nindent 12 }} + httpGet: + path: /metrics + port: metrics + {{- end }} + {{- end }} + {{- if .Values.metrics.resources }} + resources: {{- toYaml .Values.metrics.resources | nindent 12 }} + {{- end }} + volumeMounts: + {{- if and .Values.auth.usePasswordFiles (not .Values.auth.customPasswordFiles) }} + - name: mariadb-credentials + mountPath: /opt/bitnami/mysqld-exporter/secrets/ + {{- end }} + {{- if .Values.metrics.extraVolumeMounts.secondary }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.extraVolumeMounts.secondary "context" $) | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.secondary.sidecars }} + {{- include "common.tplvalues.render" (dict "value" .Values.secondary.sidecars "context" $) | nindent 8 }} + {{- end }} + volumes: + {{- if or .Values.secondary.configuration .Values.secondary.existingConfigmap }} + - name: config + configMap: + name: {{ include "mariadb.secondary.configmapName" . }} + {{- end }} + {{- if and .Values.auth.usePasswordFiles (not .Values.auth.customPasswordFiles) }} + - name: mariadb-credentials + secret: + secretName: {{ template "mariadb.secretName" . }} + items: + - key: mariadb-root-password + path: mariadb-root-password + - key: mariadb-replication-password + path: mariadb-replication-password + {{- end }} + {{- if .Values.secondary.extraVolumes }} + {{- include "common.tplvalues.render" (dict "value" .Values.secondary.extraVolumes "context" $) | nindent 8 }} + {{- end }} + {{- if not .Values.secondary.persistence.enabled }} + - name: data + emptyDir: {} + {{- else }} + volumeClaimTemplates: + - metadata: + name: data + labels: {{ include "common.labels.matchLabels" . | nindent 10 }} + app.kubernetes.io/component: secondary + {{- if .Values.secondary.persistence.annotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.secondary.persistence.annotations "context" $ ) | nindent 10 }} + {{- end }} + {{- if .Values.primary.persistence.labels }} + labels: {{- include "common.tplvalues.render" (dict "value" .Values.primary.persistence.labels "context" $) | nindent 10 }} + {{- end }} + spec: + accessModes: + {{- range .Values.secondary.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + resources: + requests: + storage: {{ .Values.secondary.persistence.size | quote }} + {{ include "common.storage.class" (dict "persistence" .Values.secondary.persistence "global" .Values.global) }} + {{- if .Values.secondary.persistence.selector }} + selector: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.persistence.selector "context" $) | nindent 10 }} + {{- end -}} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/svc.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/svc.yaml new file mode 100644 index 0000000..3d72171 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secondary/svc.yaml @@ -0,0 +1,63 @@ +{{- if eq .Values.architecture "replication" }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "mariadb.secondary.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: secondary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.secondary.service.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.secondary.service.annotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if and .Values.metrics.enabled .Values.metrics.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.annotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.secondary.service.type }} + {{- if and .Values.secondary.service.clusterIP (eq .Values.secondary.service.type "ClusterIP") }} + clusterIP: {{ .Values.secondary.service.clusterIP }} + {{- end }} + {{- if and .Values.secondary.service.externalTrafficPolicy (or (eq .Values.secondary.service.type "LoadBalancer") (eq .Values.secondary.service.type "NodePort")) }} + externalTrafficPolicy: {{ .Values.secondary.service.externalTrafficPolicy | quote }} + {{- end }} + {{- if and (eq .Values.secondary.service.type "LoadBalancer") .Values.secondary.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: {{ .Values.secondary.service.loadBalancerSourceRanges }} + {{ end }} + {{- if and (eq .Values.secondary.service.type "LoadBalancer") (not (empty .Values.secondary.service.loadBalancerIP)) }} + loadBalancerIP: {{ .Values.secondary.service.loadBalancerIP }} + {{- end }} + {{- if .Values.secondary.service.sessionAffinity }} + sessionAffinity: {{ .Values.secondary.service.sessionAffinity }} + {{- end }} + {{- if .Values.secondary.service.sessionAffinityConfig }} + sessionAffinityConfig: {{- include "common.tplvalues.render" (dict "value" .Values.secondary.service.sessionAffinityConfig "context" $) | nindent 4 }} + {{- end }} + ports: + - name: mysql + port: {{ coalesce .Values.secondary.service.ports.mysql .Values.secondary.service.port }} + protocol: TCP + targetPort: mysql + {{- if (and (or (eq .Values.secondary.service.type "NodePort") (eq .Values.secondary.service.type "LoadBalancer")) (coalesce .Values.secondary.service.nodePorts.mysql .Values.secondary.service.nodePort)) }} + nodePort: {{ coalesce .Values.secondary.service.nodePorts.mysql .Values.secondary.service.nodePort }} + {{- else if eq .Values.secondary.service.type "ClusterIP" }} + nodePort: null + {{- end }} + {{- if and .Values.metrics.enabled (gt (.Values.secondary.service.ports.metrics | int) 0) }} + - name: metrics + port: {{ .Values.secondary.service.ports.metrics }} + protocol: TCP + targetPort: metrics + {{- end }} + {{- if .Values.secondary.service.extraPorts }} + {{- include "common.tplvalues.render" (dict "value" .Values.secondary.service.extraPorts "context" $) | nindent 4 }} + {{- end }} + selector: {{ include "common.labels.matchLabels" . | nindent 4 }} + app.kubernetes.io/component: secondary +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secrets.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secrets.yaml new file mode 100644 index 0000000..c2fca12 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/secrets.yaml @@ -0,0 +1,102 @@ +{{- $host := include "mariadb.primary.fullname" . }} +{{- $port := print .Values.primary.service.ports.mysql }} +{{- $rootPassword := include "common.secrets.passwords.manage" ( dict "secret" ( include "mariadb.secretName" . ) "key" "mariadb-root-password" "providedValues" ( list "auth.rootPassword" ) "context" $ ) | trimAll "\"" | b64dec }} +{{- $password := .Values.auth.password }} +{{- if and .Values.auth.username ( include "mariadb.secret.existPassword" . ) }} +{{- $password = include "common.secrets.passwords.manage" ( dict "secret" ( include "mariadb.secretName" . ) "key" "mariadb-password" "providedValues" ( list "auth.password" ) "context" $ ) | trimAll "\"" | b64dec }} +{{- else if ( and .Values.auth.username ( not .Values.auth.forcePassword ) ( empty .Values.auth.password ) ) }} +{{- $password = randAlphaNum 10 }} +{{- end }} +{{- if eq ( include "mariadb.createSecret" . ) "true" }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: Opaque +data: + {{- if ( not .Values.auth.forcePassword ) }} + mariadb-root-password: {{ print $rootPassword | b64enc | quote }} + {{- else }} + mariadb-root-password: {{ required "A MariaDB Root Password is required!" .Values.auth.rootPassword | b64enc | quote }} + {{- end }} + {{- if .Values.auth.username }} + {{- if ( not .Values.auth.forcePassword ) }} + mariadb-password: {{ print $password | b64enc | quote }} + {{- else }} + mariadb-password: {{ required "A MariaDB Database Password is required!" $password | b64enc | quote }} + {{- end }} + {{- end }} + {{- if eq .Values.architecture "replication" }} + {{- if ( not .Values.auth.forcePassword ) }} + mariadb-replication-password: {{ include "common.secrets.passwords.manage" ( dict "secret" ( include "common.names.fullname" . ) "key" "mariadb-replication-password" "providedValues" ( list "auth.replicationPassword" ) "context" $ ) }} + {{- else }} + mariadb-replication-password: {{ required "A MariaDB Replication Password is required!" .Values.auth.replicationPassword | b64enc | quote }} + {{- end }} + {{- end }} +{{- end }} + +{{- if .Values.serviceBindings.enabled }} +--- +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "common.names.fullname" . }}-svcbind-root + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: servicebinding.io/mysql +data: + provider: {{ print "bitnami" | b64enc | quote }} + type: {{ print "mysql" | b64enc | quote }} + host: {{ print $host | b64enc | quote }} + port: {{ print $port | b64enc | quote }} + username: {{ print "root" | b64enc | quote }} + password: {{ print $rootPassword | b64enc | quote }} + uri: {{ printf "mysql://root:%s@%s:%s" $rootPassword $host $port | b64enc | quote }} + +{{- if .Values.auth.username }} +{{- $database := .Values.auth.database }} +--- +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "common.names.fullname" . }}-svcbind-custom-user + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: servicebinding.io/mysql +data: + provider: {{ print "bitnami" | b64enc | quote }} + type: {{ print "mysql" | b64enc | quote }} + host: {{ print $host | b64enc | quote }} + port: {{ print $port | b64enc | quote }} + username: {{ print .Values.auth.username | b64enc | quote }} + {{- if $database }} + database: {{ print $database | b64enc | quote }} + {{- end }} + {{- if and .Values.auth.forcePassword ( empty $password ) }} + password: {{ required "A MariaDB Database Password is required!" $password | b64enc | quote }} + {{- else }} + password: {{ print $password | b64enc | quote }} + {{- end }} + uri: {{ printf "mysql://%s:%s@%s:%s/%s" .Values.auth.username $password $host $port $database | b64enc | quote }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/serviceaccount.yaml new file mode 100644 index 0000000..03a6b4e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/serviceaccount.yaml @@ -0,0 +1,19 @@ +{{- if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "mariadb.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + annotations: + {{- if .Values.serviceAccount.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.serviceAccount.annotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/servicemonitor.yaml new file mode 100644 index 0000000..ca5bf7c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/templates/servicemonitor.yaml @@ -0,0 +1,48 @@ +{{- if and .Values.metrics.enabled .Values.metrics.serviceMonitor.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "common.names.fullname" . }} + {{- if .Values.metrics.serviceMonitor.namespace }} + namespace: {{ .Values.metrics.serviceMonitor.namespace }} + {{- else }} + namespace: {{ .Release.Namespace | quote }} + {{- end }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.labels }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.serviceMonitor.labels "context" $) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + jobLabel: {{ .Values.metrics.serviceMonitor.jobLabel | quote }} + endpoints: + - port: metrics + {{- if .Values.metrics.serviceMonitor.interval }} + interval: {{ .Values.metrics.serviceMonitor.interval }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.metrics.serviceMonitor.scrapeTimeout }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.honorLabels }} + honorLabels: {{ .Values.metrics.serviceMonitor.honorLabels }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.metricRelabelings }} + metricRelabelings: {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.metricRelabelings "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.relabelings }} + relabelings: {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.relabelings "context" $) | nindent 8 }} + {{- end }} + namespaceSelector: + matchNames: + - {{ .Release.Namespace | quote }} + selector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + {{- if .Values.metrics.serviceMonitor.selector }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.serviceMonitor.selector "context" $) | nindent 6 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/values.schema.json b/observability/lgtm-distributed/charts/oncall/charts/mariadb/values.schema.json new file mode 100644 index 0000000..500c4eb --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/values.schema.json @@ -0,0 +1,176 @@ +{ + "$schema": "http://json-schema.org/schema#", + "type": "object", + "properties": { + "architecture": { + "type": "string", + "title": "MariaDB architecture", + "form": true, + "description": "Allowed values: `standalone` or `replication`" + }, + "auth": { + "type": "object", + "title": "Authentication configuration", + "form": true, + "properties": { + "rootPassword": { + "type": "string", + "title": "MariaDB root password", + "form": true, + "description": "Defaults to a random 10-character alphanumeric string if not set" + }, + "database": { + "type": "string", + "title": "MariaDB custom database", + "description": "Name of the custom database to be created during the 1st initialization of MariaDB", + "form": true + }, + "username": { + "type": "string", + "title": "MariaDB custom user", + "description": "Name of the custom user to be created during the 1st initialization of MariaDB. This user only has permissions on the MariaDB custom database", + "form": true + }, + "password": { + "type": "string", + "title": "Password for MariaDB custom user", + "description": "Defaults to a random 10-character alphanumeric string if not set", + "form": true, + "hidden": { + "value": false, + "path": "usePassword" + } + }, + "replicationUser": { + "type": "string", + "title": "MariaDB replication user", + "description": "Name of user used to manage replication.", + "form": true, + "hidden": { + "value": "standalone", + "path": "architecture" + } + }, + "replicationPassword": { + "type": "string", + "title": "Password for MariaDB replication user", + "description": "Defaults to a random 10-character alphanumeric string if not set", + "form": true, + "hidden": { + "value": "standalone", + "path": "architecture" + } + } + } + }, + "primary": { + "type": "object", + "title": "Primary replicas settings", + "form": true, + "properties": { + "persistence": { + "type": "object", + "title": "Persistence for primary replicas", + "form": true, + "properties": { + "enabled": { + "type": "boolean", + "form": true, + "title": "Enable persistence", + "description": "Enable persistence using Persistent Volume Claims" + }, + "size": { + "type": "string", + "title": "Persistent Volume Size", + "form": true, + "render": "slider", + "sliderMin": 1, + "sliderMax": 100, + "sliderUnit": "Gi", + "hidden": { + "value": false, + "path": "persistence/enabled" + } + } + } + } + } + }, + "secondary": { + "type": "object", + "title": "Secondary replicas settings", + "form": true, + "hidden": { + "value": false, + "path": "replication/enabled" + }, + "properties": { + "persistence": { + "type": "object", + "title": "Persistence for secondary replicas", + "form": true, + "properties": { + "enabled": { + "type": "boolean", + "form": true, + "title": "Enable persistence", + "description": "Enable persistence using Persistent Volume Claims" + }, + "size": { + "type": "string", + "title": "Persistent Volume Size", + "form": true, + "render": "slider", + "sliderMin": 1, + "sliderMax": 100, + "sliderUnit": "Gi", + "hidden": { + "value": false, + "path": "persistence/enabled" + } + } + } + } + } + }, + "volumePermissions": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean", + "form": true, + "title": "Enable Init Containers", + "description": "Use an init container to set required folder permissions on the data volume before mounting it in the final destination" + } + } + }, + "metrics": { + "type": "object", + "form": true, + "title": "Prometheus metrics details", + "properties": { + "enabled": { + "type": "boolean", + "title": "Create Prometheus metrics exporter", + "description": "Create a side-car container to expose Prometheus metrics", + "form": true + }, + "serviceMonitor": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean", + "title": "Create Prometheus Operator ServiceMonitor", + "description": "Create a ServiceMonitor to track metrics using Prometheus Operator", + "form": true, + "hidden": { + "value": false, + "path": "metrics/enabled" + } + } + } + } + } + } + } +} diff --git a/observability/lgtm-distributed/charts/oncall/charts/mariadb/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/mariadb/values.yaml new file mode 100644 index 0000000..5f19aec --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/mariadb/values.yaml @@ -0,0 +1,1335 @@ +## @section Global parameters +## Global Docker image parameters +## Please, note that this will override the image parameters, including dependencies, configured to use the global value +## Current available global Docker image parameters: imageRegistry, imagePullSecrets and storageClass +## + +## @param global.imageRegistry Global Docker Image registry +## @param global.imagePullSecrets Global Docker registry secret names as an array +## @param global.storageClass Global storage class for dynamic provisioning +## +global: + imageRegistry: "" + ## E.g. + ## imagePullSecrets: + ## - myRegistryKeySecretName + ## + imagePullSecrets: [] + storageClass: "" + +## @section Common parameters +## + +## @param kubeVersion Force target Kubernetes version (using Helm capabilities if not set) +## +kubeVersion: "" +## @param nameOverride String to partially override mariadb.fullname +## +nameOverride: "" +## @param fullnameOverride String to fully override mariadb.fullname +## +fullnameOverride: "" +## @param clusterDomain Default Kubernetes cluster domain +## +clusterDomain: cluster.local +## @param commonAnnotations Common annotations to add to all MariaDB resources (sub-charts are not considered) +## +commonAnnotations: {} +## @param commonLabels Common labels to add to all MariaDB resources (sub-charts are not considered) +## +commonLabels: {} +## @param schedulerName Name of the scheduler (other than default) to dispatch pods +## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ +## +schedulerName: "" +## @param runtimeClassName Name of the Runtime Class for all MariaDB pods +## ref: https://kubernetes.io/docs/concepts/containers/runtime-class/ +## +runtimeClassName: "" +## @param extraDeploy Array of extra objects to deploy with the release (evaluated as a template) +## +extraDeploy: [] + +## Enable diagnostic mode in the deployment +## +diagnosticMode: + ## @param diagnosticMode.enabled Enable diagnostic mode (all probes will be disabled and the command will be overridden) + ## + enabled: false + ## @param diagnosticMode.command Command to override all containers in the deployment + ## + command: + - sleep + ## @param diagnosticMode.args Args to override all containers in the deployment + ## + args: + - infinity + +## @param serviceBindings.enabled Create secret for service binding (Experimental) +## Ref: https://servicebinding.io/service-provider/ +## +serviceBindings: + enabled: false + +## @section MariaDB common parameters +## + +## Bitnami MariaDB image +## ref: https://hub.docker.com/r/bitnami/mariadb/tags/ +## @param image.registry MariaDB image registry +## @param image.repository MariaDB image repository +## @param image.tag MariaDB image tag (immutable tags are recommended) +## @param image.digest MariaDB image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag +## @param image.pullPolicy MariaDB image pull policy +## @param image.pullSecrets Specify docker-registry secret names as an array +## @param image.debug Specify if debug logs should be enabled +## +image: + registry: docker.io + repository: bitnami/mariadb + tag: 10.11.4-debian-11-r0 + digest: "" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets (secrets must be manually created in the namespace) + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## Set to true if you would like to see extra information on logs + ## It turns BASH and/or NAMI debugging in the image + ## + debug: false +## @param architecture MariaDB architecture (`standalone` or `replication`) +## +architecture: standalone +## MariaDB Authentication parameters +## +auth: + ## @param auth.rootPassword Password for the `root` user. Ignored if existing secret is provided. + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/mariadb#setting-the-root-password-on-first-run + ## + rootPassword: "" + ## @param auth.database Name for a custom database to create + ## ref: https://github.com/bitnami/containers/blob/main/bitnami/mariadb/README.md#creating-a-database-on-first-run + ## + database: my_database + ## @param auth.username Name for a custom user to create + ## ref: https://github.com/bitnami/containers/blob/main/bitnami/mariadb/README.md#creating-a-database-user-on-first-run + ## + username: "" + ## @param auth.password Password for the new user. Ignored if existing secret is provided + ## + password: "" + ## @param auth.replicationUser MariaDB replication user + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/mariadb#setting-up-a-replication-cluster + ## + replicationUser: replicator + ## @param auth.replicationPassword MariaDB replication user password. Ignored if existing secret is provided + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/mariadb#setting-up-a-replication-cluster + ## + replicationPassword: "" + ## @param auth.existingSecret Use existing secret for password details (`auth.rootPassword`, `auth.password`, `auth.replicationPassword` will be ignored and picked up from this secret). The secret has to contain the keys `mariadb-root-password`, `mariadb-replication-password` and `mariadb-password` + ## + existingSecret: "" + ## @param auth.forcePassword Force users to specify required passwords + ## + forcePassword: false + ## @param auth.usePasswordFiles Mount credentials as files instead of using environment variables + ## + usePasswordFiles: false + ## @param auth.customPasswordFiles Use custom password files when `auth.usePasswordFiles` is set to `true`. Define path for keys `root` and `user`, also define `replicator` if `architecture` is set to `replication` + ## Example: + ## customPasswordFiles: + ## root: /vault/secrets/mariadb-root + ## user: /vault/secrets/mariadb-user + ## replicator: /vault/secrets/mariadb-replicator + ## + customPasswordFiles: {} +## @param initdbScripts Dictionary of initdb scripts +## Specify dictionary of scripts to be run at first boot +## Example: +## initdbScripts: +## my_init_script.sh: | +## #!/bin/bash +## echo "Do something." +## +initdbScripts: {} +## @param initdbScriptsConfigMap ConfigMap with the initdb scripts (Note: Overrides `initdbScripts`) +## +initdbScriptsConfigMap: "" + +## @section MariaDB Primary parameters +## + +## Mariadb Primary parameters +## +primary: + ## @param primary.name Name of the primary database (eg primary, master, leader, ...) + ## + name: primary + ## @param primary.command Override default container command on MariaDB Primary container(s) (useful when using custom images) + ## + command: [] + ## @param primary.args Override default container args on MariaDB Primary container(s) (useful when using custom images) + ## + args: [] + ## @param primary.lifecycleHooks for the MariaDB Primary container(s) to automate configuration before or after startup + ## + lifecycleHooks: {} + ## @param primary.hostAliases Add deployment host aliases + ## https://kubernetes.io/docs/concepts/services-networking/add-entries-to-pod-etc-hosts-with-host-aliases/ + ## + hostAliases: [] + ## @param primary.configuration [string] MariaDB Primary configuration to be injected as ConfigMap + ## ref: https://mysql.com/kb/en/mysql/configuring-mysql-with-mycnf/#example-of-configuration-file + ## + configuration: |- + [mysqld] + skip-name-resolve + explicit_defaults_for_timestamp + basedir=/opt/bitnami/mariadb + plugin_dir=/opt/bitnami/mariadb/plugin + port=3306 + socket=/opt/bitnami/mariadb/tmp/mysql.sock + tmpdir=/opt/bitnami/mariadb/tmp + max_allowed_packet=16M + bind-address=* + pid-file=/opt/bitnami/mariadb/tmp/mysqld.pid + log-error=/opt/bitnami/mariadb/logs/mysqld.log + character-set-server=UTF8 + collation-server=utf8_general_ci + slow_query_log=0 + slow_query_log_file=/opt/bitnami/mariadb/logs/mysqld.log + long_query_time=10.0 + + [client] + port=3306 + socket=/opt/bitnami/mariadb/tmp/mysql.sock + default-character-set=UTF8 + plugin_dir=/opt/bitnami/mariadb/plugin + + [manager] + port=3306 + socket=/opt/bitnami/mariadb/tmp/mysql.sock + pid-file=/opt/bitnami/mariadb/tmp/mysqld.pid + ## @param primary.existingConfigmap Name of existing ConfigMap with MariaDB Primary configuration. + ## NOTE: When it's set the 'configuration' parameter is ignored + ## + existingConfigmap: "" + ## @param primary.updateStrategy.type MariaDB primary statefulset strategy type + ## ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#update-strategies + ## + updateStrategy: + ## StrategyType + ## Can be set to RollingUpdate or OnDelete + ## + type: RollingUpdate + ## @param primary.rollingUpdatePartition Partition update strategy for Mariadb Primary statefulset + ## https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#partitions + ## + rollingUpdatePartition: "" + ## @param primary.podAnnotations Additional pod annotations for MariaDB primary pods + ## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/ + ## + podAnnotations: {} + ## @param primary.podLabels Extra labels for MariaDB primary pods + ## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + ## + podLabels: {} + ## @param primary.podAffinityPreset MariaDB primary pod affinity preset. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity + ## + podAffinityPreset: "" + ## @param primary.podAntiAffinityPreset MariaDB primary pod anti-affinity preset. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` + ## Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity + ## + podAntiAffinityPreset: soft + ## Mariadb Primary node affinity preset + ## Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#node-affinity + ## + nodeAffinityPreset: + ## @param primary.nodeAffinityPreset.type MariaDB primary node affinity preset type. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` + ## + type: "" + ## @param primary.nodeAffinityPreset.key MariaDB primary node label key to match Ignored if `primary.affinity` is set. + ## E.g. + ## key: "kubernetes.io/e2e-az-name" + ## + key: "" + ## @param primary.nodeAffinityPreset.values MariaDB primary node label values to match. Ignored if `primary.affinity` is set. + ## E.g. + ## values: + ## - e2e-az1 + ## - e2e-az2 + ## + values: [] + ## @param primary.affinity Affinity for MariaDB primary pods assignment + ## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + ## Note: podAffinityPreset, podAntiAffinityPreset, and nodeAffinityPreset will be ignored when it's set + ## + affinity: {} + ## @param primary.nodeSelector Node labels for MariaDB primary pods assignment + ## Ref: https://kubernetes.io/docs/user-guide/node-selection/ + ## + nodeSelector: {} + ## @param primary.tolerations Tolerations for MariaDB primary pods assignment + ## Ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + ## + tolerations: [] + ## @param primary.schedulerName Name of the k8s scheduler (other than default) + ## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ + ## + schedulerName: "" + ## @param primary.podManagementPolicy podManagementPolicy to manage scaling operation of MariaDB primary pods + ## ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#pod-management-policies + ## + podManagementPolicy: "" + ## @param primary.topologySpreadConstraints Topology Spread Constraints for MariaDB primary pods assignment + ## ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ + ## E.g. + ## topologySpreadConstraints: + ## - maxSkew: 1 + ## topologyKey: topology.kubernetes.io/zone + ## whenUnsatisfiable: DoNotSchedule + ## + topologySpreadConstraints: [] + ## @param primary.priorityClassName Priority class for MariaDB primary pods assignment + ## Ref: https://kubernetes.io/docs/concepts/configuration/pod-priority-preemption/ + ## + priorityClassName: "" + ## @param primary.runtimeClassName Runtime Class for MariaDB primary pods + ## Ref: https://kubernetes.io/docs/concepts/containers/runtime-class/ + ## + runtimeClassName: "" + ## MariaDB primary Pod security context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-pod + ## @param primary.podSecurityContext.enabled Enable security context for MariaDB primary pods + ## @param primary.podSecurityContext.fsGroup Group ID for the mounted volumes' filesystem + ## + podSecurityContext: + enabled: true + fsGroup: 1001 + ## MariaDB primary container security context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-container + ## @param primary.containerSecurityContext.enabled MariaDB primary container securityContext + ## @param primary.containerSecurityContext.runAsUser User ID for the MariaDB primary container + ## @param primary.containerSecurityContext.runAsNonRoot Set primary container's Security Context runAsNonRoot + ## @param primary.containerSecurityContext.privileged Set primary container's Security Context privileged + ## @param primary.containerSecurityContext.allowPrivilegeEscalation Set primary container's Security Context allowPrivilegeEscalation + ## + containerSecurityContext: + enabled: true + runAsUser: 1001 + runAsNonRoot: true + privileged: false + allowPrivilegeEscalation: false + ## MariaDB primary container's resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## We usually recommend not to specify default resources and to leave this as a conscious + ## choice for the user. This also increases chances charts run on environments with little + ## resources, such as Minikube. If you do want to specify resources, uncomment the following + ## lines, adjust them as necessary, and remove the curly braces after 'resources:'. + ## @param primary.resources.limits The resources limits for MariaDB primary containers + ## @param primary.resources.requests The requested resources for MariaDB primary containers + ## + resources: + ## Example: + ## limits: + ## cpu: 100m + ## memory: 256Mi + ## + limits: {} + ## Examples: + ## requests: + ## cpu: 100m + ## memory: 256Mi + ## + requests: {} + ## Configure extra options for MariaDB primary containers' liveness, readiness and startup probes + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes) + ## @param primary.startupProbe.enabled Enable startupProbe + ## @param primary.startupProbe.initialDelaySeconds Initial delay seconds for startupProbe + ## @param primary.startupProbe.periodSeconds Period seconds for startupProbe + ## @param primary.startupProbe.timeoutSeconds Timeout seconds for startupProbe + ## @param primary.startupProbe.failureThreshold Failure threshold for startupProbe + ## @param primary.startupProbe.successThreshold Success threshold for startupProbe + ## + startupProbe: + enabled: false + initialDelaySeconds: 120 + periodSeconds: 15 + timeoutSeconds: 5 + failureThreshold: 10 + successThreshold: 1 + ## Configure extra options for liveness probe + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes + ## @param primary.livenessProbe.enabled Enable livenessProbe + ## @param primary.livenessProbe.initialDelaySeconds Initial delay seconds for livenessProbe + ## @param primary.livenessProbe.periodSeconds Period seconds for livenessProbe + ## @param primary.livenessProbe.timeoutSeconds Timeout seconds for livenessProbe + ## @param primary.livenessProbe.failureThreshold Failure threshold for livenessProbe + ## @param primary.livenessProbe.successThreshold Success threshold for livenessProbe + ## + livenessProbe: + enabled: true + initialDelaySeconds: 120 + periodSeconds: 10 + timeoutSeconds: 1 + failureThreshold: 3 + successThreshold: 1 + ## @param primary.readinessProbe.enabled Enable readinessProbe + ## @param primary.readinessProbe.initialDelaySeconds Initial delay seconds for readinessProbe + ## @param primary.readinessProbe.periodSeconds Period seconds for readinessProbe + ## @param primary.readinessProbe.timeoutSeconds Timeout seconds for readinessProbe + ## @param primary.readinessProbe.failureThreshold Failure threshold for readinessProbe + ## @param primary.readinessProbe.successThreshold Success threshold for readinessProbe + ## + readinessProbe: + enabled: true + initialDelaySeconds: 30 + periodSeconds: 10 + timeoutSeconds: 1 + failureThreshold: 3 + successThreshold: 1 + ## @param primary.customStartupProbe Override default startup probe for MariaDB primary containers + ## + customStartupProbe: {} + ## @param primary.customLivenessProbe Override default liveness probe for MariaDB primary containers + ## + customLivenessProbe: {} + ## @param primary.customReadinessProbe Override default readiness probe for MariaDB primary containers + ## + customReadinessProbe: {} + ## @param primary.startupWaitOptions Override default builtin startup wait check options for MariaDB primary containers + ## `bitnami/mariadb` Docker image has built-in startup check mechanism, + ## which periodically checks if MariaDB service has started up and stops it + ## if all checks have failed after X tries. Use these to control these checks. + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/mariadb/pull/240 + ## Example (with default options): + ## startupWaitOptions: + ## retries: 300 + ## waitTime: 2 + ## + startupWaitOptions: {} + ## @param primary.extraFlags MariaDB primary additional command line flags + ## Can be used to specify command line flags, for example: + ## E.g. + ## extraFlags: "--max-connect-errors=1000 --max_connections=155" + ## + extraFlags: "" + ## @param primary.extraEnvVars Extra environment variables to be set on MariaDB primary containers + ## E.g. + ## extraEnvVars: + ## - name: TZ + ## value: "Europe/Paris" + ## + extraEnvVars: [] + ## @param primary.extraEnvVarsCM Name of existing ConfigMap containing extra env vars for MariaDB primary containers + ## + extraEnvVarsCM: "" + ## @param primary.extraEnvVarsSecret Name of existing Secret containing extra env vars for MariaDB primary containers + ## + extraEnvVarsSecret: "" + ## Enable persistence using Persistent Volume Claims + ## ref: https://kubernetes.io/docs/user-guide/persistent-volumes/ + ## + persistence: + ## @param primary.persistence.enabled Enable persistence on MariaDB primary replicas using a `PersistentVolumeClaim`. If false, use emptyDir + ## + enabled: true + ## @param primary.persistence.existingClaim Name of an existing `PersistentVolumeClaim` for MariaDB primary replicas + ## NOTE: When it's set the rest of persistence parameters are ignored + ## + existingClaim: "" + ## @param primary.persistence.subPath Subdirectory of the volume to mount at + ## + subPath: "" + ## @param primary.persistence.storageClass MariaDB primary persistent volume storage Class + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is + ## set, choosing the default provisioner. (gp2 on AWS, standard on + ## GKE, AWS & OpenStack) + ## + storageClass: "" + ## @param primary.persistence.labels Labels for the PVC + ## + labels: {} + ## @param primary.persistence.annotations MariaDB primary persistent volume claim annotations + ## + annotations: {} + ## @param primary.persistence.accessModes MariaDB primary persistent volume access Modes + ## + accessModes: + - ReadWriteOnce + ## @param primary.persistence.size MariaDB primary persistent volume size + ## + size: 8Gi + ## @param primary.persistence.selector Selector to match an existing Persistent Volume + ## selector: + ## matchLabels: + ## app: my-app + ## + selector: {} + ## @param primary.extraVolumes Optionally specify extra list of additional volumes to the MariaDB Primary pod(s) + ## + extraVolumes: [] + ## @param primary.extraVolumeMounts Optionally specify extra list of additional volumeMounts for the MariaDB Primary container(s) + ## + extraVolumeMounts: [] + ## @param primary.initContainers Add additional init containers for the MariaDB Primary pod(s) + ## + initContainers: [] + ## @param primary.sidecars Add additional sidecar containers for the MariaDB Primary pod(s) + ## + sidecars: [] + ## MariaDB Primary Service parameters + ## + service: + ## @param primary.service.type MariaDB Primary Kubernetes service type + ## + type: ClusterIP + ports: + ## @param primary.service.ports.mysql MariaDB Primary Kubernetes service port for MariaDB + ## + mysql: 3306 + ## @param primary.service.ports.metrics MariaDB Primary Kubernetes service port for metrics + ## + metrics: 9104 + ## @param primary.service.nodePorts.mysql MariaDB Primary Kubernetes service node port + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#type-nodeport + ## + nodePorts: + mysql: "" + ## @param primary.service.clusterIP MariaDB Primary Kubernetes service clusterIP IP + ## + clusterIP: "" + ## @param primary.service.loadBalancerIP MariaDB Primary loadBalancerIP if service type is `LoadBalancer` + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#internal-load-balancer + ## + loadBalancerIP: "" + ## @param primary.service.externalTrafficPolicy Enable client source IP preservation + ## ref https://kubernetes.io/docs/tasks/access-application-cluster/create-external-load-balancer/#preserving-the-client-source-ip + ## + externalTrafficPolicy: Cluster + ## @param primary.service.loadBalancerSourceRanges Address that are allowed when MariaDB Primary service is LoadBalancer + ## https://kubernetes.io/docs/tasks/access-application-cluster/configure-cloud-provider-firewall/#restrict-access-for-loadbalancer-service + ## E.g. + ## loadBalancerSourceRanges: + ## - 10.10.10.0/24 + ## + loadBalancerSourceRanges: [] + ## @param primary.service.extraPorts Extra ports to expose (normally used with the `sidecar` value) + ## + extraPorts: [] + ## @param primary.service.annotations Provide any additional annotations which may be required + ## + annotations: {} + ## @param primary.service.sessionAffinity Session Affinity for Kubernetes service, can be "None" or "ClientIP" + ## If "ClientIP", consecutive client requests will be directed to the same Pod + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#virtual-ips-and-service-proxies + ## + sessionAffinity: None + ## @param primary.service.sessionAffinityConfig Additional settings for the sessionAffinity + ## sessionAffinityConfig: + ## clientIP: + ## timeoutSeconds: 300 + ## + sessionAffinityConfig: {} + ## MariaDB primary Pod Disruption Budget configuration + ## ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/ + ## + pdb: + ## @param primary.pdb.create Enable/disable a Pod Disruption Budget creation for MariaDB primary pods + ## + create: false + ## @param primary.pdb.minAvailable Minimum number/percentage of MariaDB primary pods that must still be available after the eviction + ## + minAvailable: 1 + ## @param primary.pdb.maxUnavailable Maximum number/percentage of MariaDB primary pods that can be unavailable after the eviction + ## + maxUnavailable: "" + ## @param primary.revisionHistoryLimit Maximum number of revisions that will be maintained in the StatefulSet + ## + revisionHistoryLimit: 10 + +## @section MariaDB Secondary parameters +## + +## Mariadb Secondary parameters +## +secondary: + ## @param secondary.name Name of the secondary database (eg secondary, slave, ...) + ## + name: secondary + ## @param secondary.replicaCount Number of MariaDB secondary replicas + ## + replicaCount: 1 + ## @param secondary.command Override default container command on MariaDB Secondary container(s) (useful when using custom images) + ## + command: [] + ## @param secondary.args Override default container args on MariaDB Secondary container(s) (useful when using custom images) + ## + args: [] + ## @param secondary.lifecycleHooks for the MariaDB Secondary container(s) to automate configuration before or after startup + ## + lifecycleHooks: {} + ## @param secondary.hostAliases Add deployment host aliases + ## https://kubernetes.io/docs/concepts/services-networking/add-entries-to-pod-etc-hosts-with-host-aliases/ + ## + hostAliases: [] + ## @param secondary.configuration [string] MariaDB Secondary configuration to be injected as ConfigMap + ## ref: https://mysql.com/kb/en/mysql/configuring-mysql-with-mycnf/#example-of-configuration-file + ## + configuration: |- + [mysqld] + skip-name-resolve + explicit_defaults_for_timestamp + basedir=/opt/bitnami/mariadb + port=3306 + socket=/opt/bitnami/mariadb/tmp/mysql.sock + tmpdir=/opt/bitnami/mariadb/tmp + max_allowed_packet=16M + bind-address=0.0.0.0 + pid-file=/opt/bitnami/mariadb/tmp/mysqld.pid + log-error=/opt/bitnami/mariadb/logs/mysqld.log + character-set-server=UTF8 + collation-server=utf8_general_ci + slow_query_log=0 + slow_query_log_file=/opt/bitnami/mariadb/logs/mysqld.log + long_query_time=10.0 + + [client] + port=3306 + socket=/opt/bitnami/mariadb/tmp/mysql.sock + default-character-set=UTF8 + + [manager] + port=3306 + socket=/opt/bitnami/mariadb/tmp/mysql.sock + pid-file=/opt/bitnami/mariadb/tmp/mysqld.pid + ## @param secondary.existingConfigmap Name of existing ConfigMap with MariaDB Secondary configuration. + ## NOTE: When it's set the 'configuration' parameter is ignored + ## + existingConfigmap: "" + ## @param secondary.updateStrategy.type MariaDB secondary statefulset strategy type + ## ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#update-strategies + ## + updateStrategy: + ## StrategyType + ## Can be set to RollingUpdate or OnDelete + ## + type: RollingUpdate + ## @param secondary.rollingUpdatePartition Partition update strategy for Mariadb Secondary statefulset + ## https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#partitions + ## + rollingUpdatePartition: "" + ## @param secondary.podAnnotations Additional pod annotations for MariaDB secondary pods + ## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/ + ## + podAnnotations: {} + ## @param secondary.podLabels Extra labels for MariaDB secondary pods + ## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + ## + podLabels: {} + ## @param secondary.podAffinityPreset MariaDB secondary pod affinity preset. Ignored if `secondary.affinity` is set. Allowed values: `soft` or `hard` + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity + ## + podAffinityPreset: "" + ## @param secondary.podAntiAffinityPreset MariaDB secondary pod anti-affinity preset. Ignored if `secondary.affinity` is set. Allowed values: `soft` or `hard` + ## Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity + ## + podAntiAffinityPreset: soft + ## Mariadb Secondary node affinity preset + ## Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#node-affinity + ## + nodeAffinityPreset: + ## @param secondary.nodeAffinityPreset.type MariaDB secondary node affinity preset type. Ignored if `secondary.affinity` is set. Allowed values: `soft` or `hard` + ## + type: "" + ## @param secondary.nodeAffinityPreset.key MariaDB secondary node label key to match Ignored if `secondary.affinity` is set. + ## E.g. + ## key: "kubernetes.io/e2e-az-name" + ## + key: "" + ## @param secondary.nodeAffinityPreset.values MariaDB secondary node label values to match. Ignored if `secondary.affinity` is set. + ## E.g. + ## values: + ## - e2e-az1 + ## - e2e-az2 + ## + values: [] + ## @param secondary.affinity Affinity for MariaDB secondary pods assignment + ## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + ## Note: podAffinityPreset, podAntiAffinityPreset, and nodeAffinityPreset will be ignored when it's set + ## + affinity: {} + ## @param secondary.nodeSelector Node labels for MariaDB secondary pods assignment + ## Ref: https://kubernetes.io/docs/user-guide/node-selection/ + ## + nodeSelector: {} + ## @param secondary.tolerations Tolerations for MariaDB secondary pods assignment + ## Ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + ## + tolerations: [] + ## @param secondary.topologySpreadConstraints Topology Spread Constraints for MariaDB secondary pods assignment + ## ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ + ## E.g. + ## topologySpreadConstraints: + ## - maxSkew: 1 + ## topologyKey: topology.kubernetes.io/zone + ## whenUnsatisfiable: DoNotSchedule + ## + topologySpreadConstraints: [] + ## @param secondary.priorityClassName Priority class for MariaDB secondary pods assignment + ## Ref: https://kubernetes.io/docs/concepts/configuration/pod-priority-preemption/ + ## + priorityClassName: "" + ## @param secondary.runtimeClassName Runtime Class for MariaDB secondary pods + ## Ref: https://kubernetes.io/docs/concepts/containers/runtime-class/ + ## + runtimeClassName: "" + ## @param secondary.schedulerName Name of the k8s scheduler (other than default) + ## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ + ## + schedulerName: "" + ## @param secondary.podManagementPolicy podManagementPolicy to manage scaling operation of MariaDB secondary pods + ## ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#pod-management-policies + ## + podManagementPolicy: "" + ## MariaDB secondary Pod security context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-pod + ## @param secondary.podSecurityContext.enabled Enable security context for MariaDB secondary pods + ## @param secondary.podSecurityContext.fsGroup Group ID for the mounted volumes' filesystem + ## + podSecurityContext: + enabled: true + fsGroup: 1001 + ## MariaDB secondary container security context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-container + ## @param secondary.containerSecurityContext.enabled MariaDB secondary container securityContext + ## @param secondary.containerSecurityContext.runAsUser User ID for the MariaDB secondary container + ## @param secondary.containerSecurityContext.runAsNonRoot Set secondary container's Security Context runAsNonRoot + ## @param secondary.containerSecurityContext.privileged Set secondary container's Security Context privileged + ## @param secondary.containerSecurityContext.allowPrivilegeEscalation Set secondary container's Security Context allowPrivilegeEscalation + ## + containerSecurityContext: + enabled: true + runAsUser: 1001 + runAsNonRoot: true + privileged: false + allowPrivilegeEscalation: false + ## MariaDB secondary container's resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## We usually recommend not to specify default resources and to leave this as a conscious + ## choice for the user. This also increases chances charts run on environments with little + ## resources, such as Minikube. If you do want to specify resources, uncomment the following + ## lines, adjust them as necessary, and remove the curly braces after 'resources:'. + ## @param secondary.resources.limits The resources limits for MariaDB secondary containers + ## @param secondary.resources.requests The requested resources for MariaDB secondary containers + ## + resources: + ## Example: + ## limits: + ## cpu: 100m + ## memory: 256Mi + ## + limits: {} + ## Examples: + ## requests: + ## cpu: 100m + ## memory: 256Mi + ## + requests: {} + ## Configure extra options for MariaDB Secondary containers' liveness, readiness and startup probes + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes) + ## @param secondary.startupProbe.enabled Enable startupProbe + ## @param secondary.startupProbe.initialDelaySeconds Initial delay seconds for startupProbe + ## @param secondary.startupProbe.periodSeconds Period seconds for startupProbe + ## @param secondary.startupProbe.timeoutSeconds Timeout seconds for startupProbe + ## @param secondary.startupProbe.failureThreshold Failure threshold for startupProbe + ## @param secondary.startupProbe.successThreshold Success threshold for startupProbe + ## + startupProbe: + enabled: false + initialDelaySeconds: 120 + periodSeconds: 15 + timeoutSeconds: 5 + failureThreshold: 10 + successThreshold: 1 + ## Configure extra options for liveness probe + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes + ## @param secondary.livenessProbe.enabled Enable livenessProbe + ## @param secondary.livenessProbe.initialDelaySeconds Initial delay seconds for livenessProbe + ## @param secondary.livenessProbe.periodSeconds Period seconds for livenessProbe + ## @param secondary.livenessProbe.timeoutSeconds Timeout seconds for livenessProbe + ## @param secondary.livenessProbe.failureThreshold Failure threshold for livenessProbe + ## @param secondary.livenessProbe.successThreshold Success threshold for livenessProbe + ## + livenessProbe: + enabled: true + initialDelaySeconds: 120 + periodSeconds: 10 + timeoutSeconds: 1 + failureThreshold: 3 + successThreshold: 1 + ## @param secondary.readinessProbe.enabled Enable readinessProbe + ## @param secondary.readinessProbe.initialDelaySeconds Initial delay seconds for readinessProbe + ## @param secondary.readinessProbe.periodSeconds Period seconds for readinessProbe + ## @param secondary.readinessProbe.timeoutSeconds Timeout seconds for readinessProbe + ## @param secondary.readinessProbe.failureThreshold Failure threshold for readinessProbe + ## @param secondary.readinessProbe.successThreshold Success threshold for readinessProbe + ## + readinessProbe: + enabled: true + initialDelaySeconds: 30 + periodSeconds: 10 + timeoutSeconds: 1 + failureThreshold: 3 + successThreshold: 1 + ## @param secondary.customStartupProbe Override default startup probe for MariaDB secondary containers + ## + customStartupProbe: {} + ## @param secondary.customLivenessProbe Override default liveness probe for MariaDB secondary containers + ## + customLivenessProbe: {} + ## @param secondary.customReadinessProbe Override default readiness probe for MariaDB secondary containers + ## + customReadinessProbe: {} + ## @param secondary.startupWaitOptions Override default builtin startup wait check options for MariaDB secondary containers + ## `bitnami/mariadb` Docker image has built-in startup check mechanism, + ## which periodically checks if MariaDB service has started up and stops it + ## if all checks have failed after X tries. Use these to control these checks. + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/mariadb/pull/240 + ## Example (with default options): + ## startupWaitOptions: + ## retries: 300 + ## waitTime: 2 + ## + startupWaitOptions: {} + ## @param secondary.extraFlags MariaDB secondary additional command line flags + ## Can be used to specify command line flags, for example: + ## E.g. + ## extraFlags: "--max-connect-errors=1000 --max_connections=155" + ## + extraFlags: "" + ## @param secondary.extraEnvVars Extra environment variables to be set on MariaDB secondary containers + ## E.g. + ## extraEnvVars: + ## - name: TZ + ## value: "Europe/Paris" + ## + extraEnvVars: [] + ## @param secondary.extraEnvVarsCM Name of existing ConfigMap containing extra env vars for MariaDB secondary containers + ## + extraEnvVarsCM: "" + ## @param secondary.extraEnvVarsSecret Name of existing Secret containing extra env vars for MariaDB secondary containers + ## + extraEnvVarsSecret: "" + ## Enable persistence using Persistent Volume Claims + ## ref: https://kubernetes.io/docs/user-guide/persistent-volumes/ + ## + persistence: + ## @param secondary.persistence.enabled Enable persistence on MariaDB secondary replicas using a `PersistentVolumeClaim` + ## + enabled: true + ## @param secondary.persistence.subPath Subdirectory of the volume to mount at + ## + subPath: "" + ## @param secondary.persistence.storageClass MariaDB secondary persistent volume storage Class + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is + ## set, choosing the default provisioner. (gp2 on AWS, standard on + ## GKE, AWS & OpenStack) + ## + storageClass: "" + ## @param secondary.persistence.labels Labels for the PVC + ## + labels: {} + ## @param secondary.persistence.annotations MariaDB secondary persistent volume claim annotations + ## + annotations: {} + ## @param secondary.persistence.accessModes MariaDB secondary persistent volume access Modes + ## + accessModes: + - ReadWriteOnce + ## @param secondary.persistence.size MariaDB secondary persistent volume size + ## + size: 8Gi + ## @param secondary.persistence.selector Selector to match an existing Persistent Volume + ## selector: + ## matchLabels: + ## app: my-app + ## + selector: {} + ## @param secondary.extraVolumes Optionally specify extra list of additional volumes to the MariaDB secondary pod(s) + ## + extraVolumes: [] + ## @param secondary.extraVolumeMounts Optionally specify extra list of additional volumeMounts for the MariaDB secondary container(s) + ## + extraVolumeMounts: [] + ## @param secondary.initContainers Add additional init containers for the MariaDB secondary pod(s) + ## + initContainers: [] + ## @param secondary.sidecars Add additional sidecar containers for the MariaDB secondary pod(s) + ## + sidecars: [] + ## MariaDB Secondary Service parameters + ## + service: + ## @param secondary.service.type MariaDB secondary Kubernetes service type + ## + type: ClusterIP + ports: + ## @param secondary.service.ports.mysql MariaDB secondary Kubernetes service port for MariaDB + ## + mysql: 3306 + ## @param secondary.service.ports.metrics MariaDB secondary Kubernetes service port for metrics + ## + metrics: 9104 + ## @param secondary.service.nodePorts.mysql MariaDB secondary Kubernetes service node port + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#type-nodeport + ## + nodePorts: + mysql: "" + ## @param secondary.service.clusterIP MariaDB secondary Kubernetes service clusterIP IP + ## e.g: + ## clusterIP: None + ## + clusterIP: "" + ## @param secondary.service.loadBalancerIP MariaDB secondary loadBalancerIP if service type is `LoadBalancer` + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#internal-load-balancer + ## + loadBalancerIP: "" + ## @param secondary.service.externalTrafficPolicy Enable client source IP preservation + ## ref https://kubernetes.io/docs/tasks/access-application-cluster/create-external-load-balancer/#preserving-the-client-source-ip + ## + externalTrafficPolicy: Cluster + ## @param secondary.service.loadBalancerSourceRanges Address that are allowed when MariaDB secondary service is LoadBalancer + ## https://kubernetes.io/docs/tasks/access-application-cluster/configure-cloud-provider-firewall/#restrict-access-for-loadbalancer-service + ## E.g. + ## loadBalancerSourceRanges: + ## - 10.10.10.0/24 + ## + loadBalancerSourceRanges: [] + ## @param secondary.service.extraPorts Extra ports to expose (normally used with the `sidecar` value) + ## + extraPorts: [] + ## @param secondary.service.annotations Provide any additional annotations which may be required + ## + annotations: {} + ## @param secondary.service.sessionAffinity Session Affinity for Kubernetes service, can be "None" or "ClientIP" + ## If "ClientIP", consecutive client requests will be directed to the same Pod + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#virtual-ips-and-service-proxies + ## + sessionAffinity: None + ## @param secondary.service.sessionAffinityConfig Additional settings for the sessionAffinity + ## sessionAffinityConfig: + ## clientIP: + ## timeoutSeconds: 300 + ## + sessionAffinityConfig: {} + ## MariaDB secondary Pod Disruption Budget configuration + ## ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/ + ## + pdb: + ## @param secondary.pdb.create Enable/disable a Pod Disruption Budget creation for MariaDB secondary pods + ## + create: false + ## @param secondary.pdb.minAvailable Minimum number/percentage of MariaDB secondary pods that should remain scheduled + ## + minAvailable: 1 + ## @param secondary.pdb.maxUnavailable Maximum number/percentage of MariaDB secondary pods that may be made unavailable + ## + maxUnavailable: "" + ## @param secondary.revisionHistoryLimit Maximum number of revisions that will be maintained in the StatefulSet + ## + revisionHistoryLimit: 10 + +## @section RBAC parameters +## + +## MariaDB pods ServiceAccount +## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/ +## +serviceAccount: + ## @param serviceAccount.create Enable the creation of a ServiceAccount for MariaDB pods + ## + create: true + ## @param serviceAccount.name Name of the created ServiceAccount + ## If not set and create is true, a name is generated using the mariadb.fullname template + ## + name: "" + ## @param serviceAccount.annotations Annotations for MariaDB Service Account + ## + annotations: {} + ## @param serviceAccount.automountServiceAccountToken Automount service account token for the server service account + ## + automountServiceAccountToken: false +## Role Based Access +## ref: https://kubernetes.io/docs/admin/authorization/rbac/ +## +rbac: + ## @param rbac.create Whether to create and use RBAC resources or not + ## + create: false + +## @section Volume Permissions parameters +## + +## Init containers parameters: +## volumePermissions: Change the owner and group of the persistent volume mountpoint to runAsUser:fsGroup values from the securityContext section. +## +volumePermissions: + ## @param volumePermissions.enabled Enable init container that changes the owner and group of the persistent volume(s) mountpoint to `runAsUser:fsGroup` + ## + enabled: false + ## @param volumePermissions.image.registry Init container volume-permissions image registry + ## @param volumePermissions.image.repository Init container volume-permissions image repository + ## @param volumePermissions.image.tag Init container volume-permissions image tag (immutable tags are recommended) + ## @param volumePermissions.image.digest Init container volume-permissions image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag + ## @param volumePermissions.image.pullPolicy Init container volume-permissions image pull policy + ## @param volumePermissions.image.pullSecrets Specify docker-registry secret names as an array + ## + image: + registry: docker.io + repository: bitnami/bitnami-shell + tag: 11-debian-11-r123 + digest: "" + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets (secrets must be manually created in the namespace) + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## @param volumePermissions.resources.limits Init container volume-permissions resource limits + ## @param volumePermissions.resources.requests Init container volume-permissions resource requests + ## + resources: + limits: {} + requests: {} + +## @section Metrics parameters +## + +## Mysqld Prometheus exporter parameters +## +metrics: + ## @param metrics.enabled Start a side-car prometheus exporter + ## + enabled: false + ## @param metrics.image.registry Exporter image registry + ## @param metrics.image.repository Exporter image repository + ## @param metrics.image.tag Exporter image tag (immutable tags are recommended) + ## @param metrics.image.digest Exporter image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag + ## @param metrics.image.pullPolicy Exporter image pull policy + ## @param metrics.image.pullSecrets Specify docker-registry secret names as an array + ## + image: + registry: docker.io + repository: bitnami/mysqld-exporter + tag: 0.14.0-debian-11-r125 + digest: "" + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets (secrets must be manually created in the namespace) + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## @param metrics.annotations [object] Annotations for the Exporter pod + ## + annotations: + prometheus.io/scrape: "true" + prometheus.io/port: "9104" + ## @param metrics.extraArgs [object] Extra args to be passed to mysqld_exporter + ## ref: https://github.com/prometheus/mysqld_exporter/ + ## E.g. + ## - --collect.auto_increment.columns + ## - --collect.binlog_size + ## - --collect.engine_innodb_status + ## - --collect.engine_tokudb_status + ## - --collect.global_status + ## - --collect.global_variables + ## - --collect.info_schema.clientstats + ## - --collect.info_schema.innodb_metrics + ## - --collect.info_schema.innodb_tablespaces + ## - --collect.info_schema.innodb_cmp + ## - --collect.info_schema.innodb_cmpmem + ## - --collect.info_schema.processlist + ## - --collect.info_schema.processlist.min_time + ## - --collect.info_schema.query_response_time + ## - --collect.info_schema.tables + ## - --collect.info_schema.tables.databases + ## - --collect.info_schema.tablestats + ## - --collect.info_schema.userstats + ## - --collect.perf_schema.eventsstatements + ## - --collect.perf_schema.eventsstatements.digest_text_limit + ## - --collect.perf_schema.eventsstatements.limit + ## - --collect.perf_schema.eventsstatements.timelimit + ## - --collect.perf_schema.eventswaits + ## - --collect.perf_schema.file_events + ## - --collect.perf_schema.file_instances + ## - --collect.perf_schema.indexiowaits + ## - --collect.perf_schema.tableiowaits + ## - --collect.perf_schema.tablelocks + ## - --collect.perf_schema.replication_group_member_stats + ## - --collect.slave_status + ## - --collect.slave_hosts + ## - --collect.heartbeat + ## - --collect.heartbeat.database + ## - --collect.heartbeat.table + ## + extraArgs: + primary: [] + secondary: [] + ## @param metrics.extraVolumeMounts [object] Optionally specify extra list of additional volumeMounts for the MariaDB metrics container(s) + ## + extraVolumeMounts: + primary: [] + secondary: [] + ## MariaDB metrics container Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-container + ## @param metrics.containerSecurityContext.enabled Enable security context for MariaDB metrics container + ## @param metrics.containerSecurityContext.privileged Set metrics container's Security Context privileged + ## @param metrics.containerSecurityContext.allowPrivilegeEscalation Set metrics container's Security Context allowPrivilegeEscalation + ## Example: + ## containerSecurityContext: + ## enabled: true + ## capabilities: + ## drop: ["NET_RAW"] + ## readOnlyRootFilesystem: true + ## + containerSecurityContext: + enabled: false + privileged: false + allowPrivilegeEscalation: false + ## Mysqld Prometheus exporter resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## We usually recommend not to specify default resources and to leave this as a conscious + ## choice for the user. This also increases chances charts run on environments with little + ## resources, such as Minikube. If you do want to specify resources, uncomment the following + ## lines, adjust them as necessary, and remove the curly braces after 'resources:'. + ## @param metrics.resources.limits The resources limits for MariaDB prometheus exporter containers + ## @param metrics.resources.requests The requested resources for MariaDB prometheus exporter containers + ## + resources: + ## Example: + ## limits: + ## cpu: 100m + ## memory: 256Mi + ## + limits: {} + ## Examples: + ## requests: + ## cpu: 100m + ## memory: 256Mi + ## + requests: {} + ## Configure extra options for liveness probe + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes + ## @param metrics.livenessProbe.enabled Enable livenessProbe + ## @param metrics.livenessProbe.initialDelaySeconds Initial delay seconds for livenessProbe + ## @param metrics.livenessProbe.periodSeconds Period seconds for livenessProbe + ## @param metrics.livenessProbe.timeoutSeconds Timeout seconds for livenessProbe + ## @param metrics.livenessProbe.failureThreshold Failure threshold for livenessProbe + ## @param metrics.livenessProbe.successThreshold Success threshold for livenessProbe + ## + livenessProbe: + enabled: true + initialDelaySeconds: 120 + periodSeconds: 10 + timeoutSeconds: 1 + successThreshold: 1 + failureThreshold: 3 + ## Configure extra options for readiness probe + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes + ## @param metrics.readinessProbe.enabled Enable readinessProbe + ## @param metrics.readinessProbe.initialDelaySeconds Initial delay seconds for readinessProbe + ## @param metrics.readinessProbe.periodSeconds Period seconds for readinessProbe + ## @param metrics.readinessProbe.timeoutSeconds Timeout seconds for readinessProbe + ## @param metrics.readinessProbe.failureThreshold Failure threshold for readinessProbe + ## @param metrics.readinessProbe.successThreshold Success threshold for readinessProbe + ## + readinessProbe: + enabled: true + initialDelaySeconds: 30 + periodSeconds: 10 + timeoutSeconds: 1 + successThreshold: 1 + failureThreshold: 3 + ## Prometheus Service Monitor + ## ref: https://github.com/coreos/prometheus-operator + ## + serviceMonitor: + ## @param metrics.serviceMonitor.enabled Create ServiceMonitor Resource for scraping metrics using PrometheusOperator + ## + enabled: false + ## @param metrics.serviceMonitor.namespace Namespace which Prometheus is running in + ## + namespace: "" + ## @param metrics.serviceMonitor.jobLabel The name of the label on the target service to use as the job name in prometheus. + ## + jobLabel: "" + ## @param metrics.serviceMonitor.interval Interval at which metrics should be scraped + ## + interval: 30s + ## @param metrics.serviceMonitor.scrapeTimeout Specify the timeout after which the scrape is ended + ## e.g: + ## scrapeTimeout: 30s + ## + scrapeTimeout: "" + ## @param metrics.serviceMonitor.relabelings RelabelConfigs to apply to samples before scraping + ## ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#relabelconfig + ## + relabelings: [] + ## @param metrics.serviceMonitor.metricRelabelings MetricRelabelConfigs to apply to samples before ingestion + ## ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#relabelconfig + ## + metricRelabelings: [] + ## @param metrics.serviceMonitor.honorLabels honorLabels chooses the metric's labels on collisions with target labels + ## + honorLabels: false + ## @param metrics.serviceMonitor.selector ServiceMonitor selector labels + ## ref: https://github.com/bitnami/charts/tree/main/bitnami/prometheus-operator#prometheus-configuration + ## + ## selector: + ## prometheus: my-prometheus + ## + selector: {} + ## @param metrics.serviceMonitor.labels Extra labels for the ServiceMonitor + ## + labels: {} + ## Prometheus Operator PrometheusRule configuration + ## + prometheusRule: + ## @param metrics.prometheusRule.enabled if `true`, creates a Prometheus Operator PrometheusRule (also requires `metrics.enabled` to be `true` and `metrics.prometheusRule.rules`) + ## + enabled: false + ## @param metrics.prometheusRule.namespace Namespace for the PrometheusRule Resource (defaults to the Release Namespace) + ## + namespace: "" + ## @param metrics.prometheusRule.additionalLabels Additional labels that can be used so PrometheusRule will be discovered by Prometheus + ## + additionalLabels: {} + ## @param metrics.prometheusRule.rules Prometheus Rule definitions + ## - alert: MariaDB-Down + ## expr: absent(up{job="mariadb"} == 1) + ## for: 5m + ## labels: + ## severity: warning + ## service: mariadb + ## annotations: + ## message: 'MariaDB instance {{ `{{` }} $labels.instance {{ `}}` }} is down' + ## summary: MariaDB instance is down + ## + rules: [] + +## @section NetworkPolicy parameters +## + +## Add networkpolicies +## +networkPolicy: + ## @param networkPolicy.enabled Enable network policies + ## + enabled: false + ## @param networkPolicy.metrics.enabled Enable network policy for metrics (prometheus) + ## @param networkPolicy.metrics.namespaceSelector [object] Monitoring namespace selector labels. These labels will be used to identify the prometheus' namespace. + ## @param networkPolicy.metrics.podSelector [object] Monitoring pod selector labels. These labels will be used to identify the Prometheus pods. + ## + metrics: + enabled: false + ## e.g: + ## podSelector: + ## label: monitoring + ## + podSelector: {} + ## e.g: + ## namespaceSelector: + ## label: monitoring + ## + namespaceSelector: {} + ## @param networkPolicy.ingressRules.primaryAccessOnlyFrom.enabled Enable ingress rule that makes primary mariadb nodes only accessible from a particular origin. + ## @param networkPolicy.ingressRules.primaryAccessOnlyFrom.namespaceSelector [object] Namespace selector label that is allowed to access the primary node. This label will be used to identified the allowed namespace(s). + ## @param networkPolicy.ingressRules.primaryAccessOnlyFrom.podSelector [object] Pods selector label that is allowed to access the primary node. This label will be used to identified the allowed pod(s). + ## @param networkPolicy.ingressRules.primaryAccessOnlyFrom.customRules Custom network policy for the primary node. + ## @param networkPolicy.ingressRules.secondaryAccessOnlyFrom.enabled Enable ingress rule that makes primary mariadb nodes only accessible from a particular origin. + ## @param networkPolicy.ingressRules.secondaryAccessOnlyFrom.namespaceSelector [object] Namespace selector label that is allowed to acces the secondary nodes. This label will be used to identified the allowed namespace(s). + ## @param networkPolicy.ingressRules.secondaryAccessOnlyFrom.podSelector [object] Pods selector label that is allowed to access the secondary nodes. This label will be used to identified the allowed pod(s). + ## @param networkPolicy.ingressRules.secondaryAccessOnlyFrom.customRules Custom network policy for the secondary nodes. + ## + ingressRules: + ## Allow access to the primary node only from the indicated: + ## + primaryAccessOnlyFrom: + enabled: false + ## e.g: + ## namespaceSelector: + ## label: ingress + ## + namespaceSelector: {} + ## e.g: + ## podSelector: + ## label: access + ## + podSelector: {} + ## custom ingress rules + ## e.g: + ## customRules: + ## - from: + ## - namespaceSelector: + ## matchLabels: + ## label: example + ## + customRules: [] + + ## Allow access to the secondary node only from the indicated: + ## + secondaryAccessOnlyFrom: + enabled: false + ## e.g: + ## namespaceSelector: + ## label: ingress + ## + namespaceSelector: {} + ## e.g: + ## podSelector: + ## label: access + ## + podSelector: {} + ## custom ingress rules + ## e.g: + ## CustomRules: + ## - from: + ## - namespaceSelector: + ## matchLabels: + ## label: example + ## + customRules: [] + + ## @param networkPolicy.egressRules.denyConnectionsToExternal Enable egress rule that denies outgoing traffic outside the cluster, except for DNS (port 53). + ## @param networkPolicy.egressRules.customRules Custom network policy rule + ## + egressRules: + # Deny connections to external. This is not compatible with an external database. + denyConnectionsToExternal: false + ## Additional custom egress rules + ## e.g: + ## customRules: + ## - to: + ## - namespaceSelector: + ## matchLabels: + ## label: example + ## + customRules: {} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/postgresql/.helmignore new file mode 100644 index 0000000..f0c1319 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/.helmignore @@ -0,0 +1,21 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/Chart.lock b/observability/lgtm-distributed/charts/oncall/charts/postgresql/Chart.lock new file mode 100644 index 0000000..c4e0f64 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/Chart.lock @@ -0,0 +1,6 @@ +dependencies: +- name: common + repository: https://charts.bitnami.com/bitnami + version: 2.0.3 +digest: sha256:7d4a98a9fabc3be62a3898cc530d0979b6a0a4d29c87ed2d128821f21c89ba40 +generated: "2022-09-13T03:02:17.497632542Z" diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/Chart.yaml new file mode 100644 index 0000000..a139c7c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/Chart.yaml @@ -0,0 +1,30 @@ +annotations: + category: Database +apiVersion: v2 +appVersion: 14.5.0 +dependencies: +- name: common + repository: https://charts.bitnami.com/bitnami + tags: + - bitnami-common + version: 2.x.x +description: PostgreSQL (Postgres) is an open source object-relational database known + for reliability and data integrity. ACID-compliant, it supports foreign keys, joins, + views, triggers and stored procedures. +home: https://github.com/bitnami/charts/tree/main/bitnami/postgresql +icon: https://bitnami.com/assets/stacks/postgresql/img/postgresql-stack-220x234.png +keywords: +- postgresql +- postgres +- database +- sql +- replication +- cluster +maintainers: +- name: Bitnami + url: https://github.com/bitnami/charts +name: postgresql +sources: +- https://github.com/bitnami/containers/tree/main/bitnami/postgresql +- https://www.postgresql.org/ +version: 11.9.10 diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/README.md b/observability/lgtm-distributed/charts/oncall/charts/postgresql/README.md new file mode 100644 index 0000000..6136506 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/README.md @@ -0,0 +1,683 @@ + + +# PostgreSQL packaged by Bitnami + +PostgreSQL (Postgres) is an open source object-relational database known for reliability and data integrity. ACID-compliant, it supports foreign keys, joins, views, triggers and stored procedures. + +[Overview of PostgreSQL](http://www.postgresql.org) + +Trademarks: This software listing is packaged by Bitnami. The respective trademarks mentioned in the offering are owned by the respective companies, and use of them does not imply any affiliation or endorsement. + +## TL;DR + +```bash +helm repo add my-repo https://charts.bitnami.com/bitnami +helm install my-release my-repo/postgresql +``` + +## Introduction + +This chart bootstraps a [PostgreSQL](https://github.com/bitnami/containers/tree/main/bitnami/postgresql) deployment on a [Kubernetes](https://kubernetes.io) cluster using the [Helm](https://helm.sh) package manager. + +For HA, please see [this repo](https://github.com/bitnami/charts/tree/main/bitnami/postgresql-ha) + +Bitnami charts can be used with [Kubeapps](https://kubeapps.dev/) for deployment and management of Helm Charts in clusters. + +## Prerequisites + +- Kubernetes 1.19+ +- Helm 3.2.0+ +- PV provisioner support in the underlying infrastructure + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```bash +helm install my-release my-repo/postgresql +``` + +The command deploys PostgreSQL on the Kubernetes cluster in the default configuration. The [Parameters](#parameters) section lists the parameters that can be configured during installation. + +> **Tip**: List all releases using `helm list` + +## Uninstalling the Chart + +To uninstall/delete the `my-release` deployment: + +```console +helm delete my-release +``` + +The command removes all the Kubernetes components but PVC's associated with the chart and deletes the release. + +To delete the PVC's associated with `my-release`: + +```bash +kubectl delete pvc -l release=my-release +``` + +> **Note**: Deleting the PVC's will delete postgresql data as well. Please be cautious before doing it. + +## Parameters + +### Global parameters + +| Name | Description | Value | +| ---------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- | +| `global.imageRegistry` | Global Docker image registry | `""` | +| `global.imagePullSecrets` | Global Docker registry secret names as an array | `[]` | +| `global.storageClass` | Global StorageClass for Persistent Volume(s) | `""` | +| `global.postgresql.auth.postgresPassword` | Password for the "postgres" admin user (overrides `auth.postgresPassword`) | `""` | +| `global.postgresql.auth.username` | Name for a custom user to create (overrides `auth.username`) | `""` | +| `global.postgresql.auth.password` | Password for the custom user to create (overrides `auth.password`) | `""` | +| `global.postgresql.auth.database` | Name for a custom database to create (overrides `auth.database`) | `""` | +| `global.postgresql.auth.existingSecret` | Name of existing secret to use for PostgreSQL credentials (overrides `auth.existingSecret`). | `""` | +| `global.postgresql.auth.secretKeys.adminPasswordKey` | Name of key in existing secret to use for PostgreSQL credentials (overrides `auth.secretKeys.adminPasswordKey`). Only used when `global.postgresql.auth.existingSecret` is set. | `""` | +| `global.postgresql.auth.secretKeys.userPasswordKey` | Name of key in existing secret to use for PostgreSQL credentials (overrides `auth.secretKeys.userPasswordKey`). Only used when `global.postgresql.auth.existingSecret` is set. | `""` | +| `global.postgresql.auth.secretKeys.replicationPasswordKey` | Name of key in existing secret to use for PostgreSQL credentials (overrides `auth.secretKeys.replicationPasswordKey`). Only used when `global.postgresql.auth.existingSecret` is set. | `""` | +| `global.postgresql.service.ports.postgresql` | PostgreSQL service port (overrides `service.ports.postgresql`) | `""` | + + +### Common parameters + +| Name | Description | Value | +| ------------------------ | -------------------------------------------------------------------------------------------- | --------------- | +| `kubeVersion` | Override Kubernetes version | `""` | +| `nameOverride` | String to partially override common.names.fullname template (will maintain the release name) | `""` | +| `fullnameOverride` | String to fully override common.names.fullname template | `""` | +| `clusterDomain` | Kubernetes Cluster Domain | `cluster.local` | +| `extraDeploy` | Array of extra objects to deploy with the release (evaluated as a template) | `[]` | +| `commonLabels` | Add labels to all the deployed resources | `{}` | +| `commonAnnotations` | Add annotations to all the deployed resources | `{}` | +| `diagnosticMode.enabled` | Enable diagnostic mode (all probes will be disabled and the command will be overridden) | `false` | +| `diagnosticMode.command` | Command to override all containers in the statefulset | `["sleep"]` | +| `diagnosticMode.args` | Args to override all containers in the statefulset | `["infinity"]` | + + +### PostgreSQL common parameters + +| Name | Description | Value | +| ---------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------- | +| `image.registry` | PostgreSQL image registry | `docker.io` | +| `image.repository` | PostgreSQL image repository | `bitnami/postgresql` | +| `image.tag` | PostgreSQL image tag (immutable tags are recommended) | `14.5.0-debian-11-r30` | +| `image.digest` | PostgreSQL image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag | `""` | +| `image.pullPolicy` | PostgreSQL image pull policy | `IfNotPresent` | +| `image.pullSecrets` | Specify image pull secrets | `[]` | +| `image.debug` | Specify if debug values should be set | `false` | +| `auth.enablePostgresUser` | Assign a password to the "postgres" admin user. Otherwise, remote access will be blocked for this user | `true` | +| `auth.postgresPassword` | Password for the "postgres" admin user. Ignored if `auth.existingSecret` with key `postgres-password` is provided | `""` | +| `auth.username` | Name for a custom user to create | `""` | +| `auth.password` | Password for the custom user to create. Ignored if `auth.existingSecret` with key `password` is provided | `""` | +| `auth.database` | Name for a custom database to create | `""` | +| `auth.replicationUsername` | Name of the replication user | `repl_user` | +| `auth.replicationPassword` | Password for the replication user. Ignored if `auth.existingSecret` with key `replication-password` is provided | `""` | +| `auth.existingSecret` | Name of existing secret to use for PostgreSQL credentials. `auth.postgresPassword`, `auth.password`, and `auth.replicationPassword` will be ignored and picked up from this secret. The secret might also contains the key `ldap-password` if LDAP is enabled. `ldap.bind_password` will be ignored and picked from this secret in this case. | `""` | +| `auth.secretKeys.adminPasswordKey` | Name of key in existing secret to use for PostgreSQL credentials. Only used when `auth.existingSecret` is set. | `postgres-password` | +| `auth.secretKeys.userPasswordKey` | Name of key in existing secret to use for PostgreSQL credentials. Only used when `auth.existingSecret` is set. | `password` | +| `auth.secretKeys.replicationPasswordKey` | Name of key in existing secret to use for PostgreSQL credentials. Only used when `auth.existingSecret` is set. | `replication-password` | +| `auth.usePasswordFiles` | Mount credentials as a files instead of using an environment variable | `false` | +| `architecture` | PostgreSQL architecture (`standalone` or `replication`) | `standalone` | +| `replication.synchronousCommit` | Set synchronous commit mode. Allowed values: `on`, `remote_apply`, `remote_write`, `local` and `off` | `off` | +| `replication.numSynchronousReplicas` | Number of replicas that will have synchronous replication. Note: Cannot be greater than `readReplicas.replicaCount`. | `0` | +| `replication.applicationName` | Cluster application name. Useful for advanced replication settings | `my_application` | +| `containerPorts.postgresql` | PostgreSQL container port | `5432` | +| `audit.logHostname` | Log client hostnames | `false` | +| `audit.logConnections` | Add client log-in operations to the log file | `false` | +| `audit.logDisconnections` | Add client log-outs operations to the log file | `false` | +| `audit.pgAuditLog` | Add operations to log using the pgAudit extension | `""` | +| `audit.pgAuditLogCatalog` | Log catalog using pgAudit | `off` | +| `audit.clientMinMessages` | Message log level to share with the user | `error` | +| `audit.logLinePrefix` | Template for log line prefix (default if not set) | `""` | +| `audit.logTimezone` | Timezone for the log timestamps | `""` | +| `ldap.enabled` | Enable LDAP support | `false` | +| `ldap.server` | IP address or name of the LDAP server. | `""` | +| `ldap.port` | Port number on the LDAP server to connect to | `""` | +| `ldap.prefix` | String to prepend to the user name when forming the DN to bind | `""` | +| `ldap.suffix` | String to append to the user name when forming the DN to bind | `""` | +| `ldap.basedn` | Root DN to begin the search for the user in | `""` | +| `ldap.binddn` | DN of user to bind to LDAP | `""` | +| `ldap.bindpw` | Password for the user to bind to LDAP | `""` | +| `ldap.searchAttribute` | Attribute to match against the user name in the search | `""` | +| `ldap.searchFilter` | The search filter to use when doing search+bind authentication | `""` | +| `ldap.scheme` | Set to `ldaps` to use LDAPS | `""` | +| `ldap.tls.enabled` | Se to true to enable TLS encryption | `false` | +| `ldap.uri` | LDAP URL beginning in the form `ldap[s]://host[:port]/basedn`. If provided, all the other LDAP parameters will be ignored. | `""` | +| `postgresqlDataDir` | PostgreSQL data dir folder | `/bitnami/postgresql/data` | +| `postgresqlSharedPreloadLibraries` | Shared preload libraries (comma-separated list) | `pgaudit` | +| `shmVolume.enabled` | Enable emptyDir volume for /dev/shm for PostgreSQL pod(s) | `true` | +| `shmVolume.sizeLimit` | Set this to enable a size limit on the shm tmpfs | `""` | +| `tls.enabled` | Enable TLS traffic support | `false` | +| `tls.autoGenerated` | Generate automatically self-signed TLS certificates | `false` | +| `tls.preferServerCiphers` | Whether to use the server's TLS cipher preferences rather than the client's | `true` | +| `tls.certificatesSecret` | Name of an existing secret that contains the certificates | `""` | +| `tls.certFilename` | Certificate filename | `""` | +| `tls.certKeyFilename` | Certificate key filename | `""` | +| `tls.certCAFilename` | CA Certificate filename | `""` | +| `tls.crlFilename` | File containing a Certificate Revocation List | `""` | + + +### PostgreSQL Primary parameters + +| Name | Description | Value | +| -------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ | --------------------- | +| `primary.name` | Name of the primary database (eg primary, master, leader, ...) | `primary` | +| `primary.configuration` | PostgreSQL Primary main configuration to be injected as ConfigMap | `""` | +| `primary.pgHbaConfiguration` | PostgreSQL Primary client authentication configuration | `""` | +| `primary.existingConfigmap` | Name of an existing ConfigMap with PostgreSQL Primary configuration | `""` | +| `primary.extendedConfiguration` | Extended PostgreSQL Primary configuration (appended to main or default configuration) | `""` | +| `primary.existingExtendedConfigmap` | Name of an existing ConfigMap with PostgreSQL Primary extended configuration | `""` | +| `primary.initdb.args` | PostgreSQL initdb extra arguments | `""` | +| `primary.initdb.postgresqlWalDir` | Specify a custom location for the PostgreSQL transaction log | `""` | +| `primary.initdb.scripts` | Dictionary of initdb scripts | `{}` | +| `primary.initdb.scriptsConfigMap` | ConfigMap with scripts to be run at first boot | `""` | +| `primary.initdb.scriptsSecret` | Secret with scripts to be run at first boot (in case it contains sensitive information) | `""` | +| `primary.initdb.user` | Specify the PostgreSQL username to execute the initdb scripts | `""` | +| `primary.initdb.password` | Specify the PostgreSQL password to execute the initdb scripts | `""` | +| `primary.standby.enabled` | Whether to enable current cluster's primary as standby server of another cluster or not | `false` | +| `primary.standby.primaryHost` | The Host of replication primary in the other cluster | `""` | +| `primary.standby.primaryPort` | The Port of replication primary in the other cluster | `""` | +| `primary.extraEnvVars` | Array with extra environment variables to add to PostgreSQL Primary nodes | `[]` | +| `primary.extraEnvVarsCM` | Name of existing ConfigMap containing extra env vars for PostgreSQL Primary nodes | `""` | +| `primary.extraEnvVarsSecret` | Name of existing Secret containing extra env vars for PostgreSQL Primary nodes | `""` | +| `primary.command` | Override default container command (useful when using custom images) | `[]` | +| `primary.args` | Override default container args (useful when using custom images) | `[]` | +| `primary.livenessProbe.enabled` | Enable livenessProbe on PostgreSQL Primary containers | `true` | +| `primary.livenessProbe.initialDelaySeconds` | Initial delay seconds for livenessProbe | `30` | +| `primary.livenessProbe.periodSeconds` | Period seconds for livenessProbe | `10` | +| `primary.livenessProbe.timeoutSeconds` | Timeout seconds for livenessProbe | `5` | +| `primary.livenessProbe.failureThreshold` | Failure threshold for livenessProbe | `6` | +| `primary.livenessProbe.successThreshold` | Success threshold for livenessProbe | `1` | +| `primary.readinessProbe.enabled` | Enable readinessProbe on PostgreSQL Primary containers | `true` | +| `primary.readinessProbe.initialDelaySeconds` | Initial delay seconds for readinessProbe | `5` | +| `primary.readinessProbe.periodSeconds` | Period seconds for readinessProbe | `10` | +| `primary.readinessProbe.timeoutSeconds` | Timeout seconds for readinessProbe | `5` | +| `primary.readinessProbe.failureThreshold` | Failure threshold for readinessProbe | `6` | +| `primary.readinessProbe.successThreshold` | Success threshold for readinessProbe | `1` | +| `primary.startupProbe.enabled` | Enable startupProbe on PostgreSQL Primary containers | `false` | +| `primary.startupProbe.initialDelaySeconds` | Initial delay seconds for startupProbe | `30` | +| `primary.startupProbe.periodSeconds` | Period seconds for startupProbe | `10` | +| `primary.startupProbe.timeoutSeconds` | Timeout seconds for startupProbe | `1` | +| `primary.startupProbe.failureThreshold` | Failure threshold for startupProbe | `15` | +| `primary.startupProbe.successThreshold` | Success threshold for startupProbe | `1` | +| `primary.customLivenessProbe` | Custom livenessProbe that overrides the default one | `{}` | +| `primary.customReadinessProbe` | Custom readinessProbe that overrides the default one | `{}` | +| `primary.customStartupProbe` | Custom startupProbe that overrides the default one | `{}` | +| `primary.lifecycleHooks` | for the PostgreSQL Primary container to automate configuration before or after startup | `{}` | +| `primary.resources.limits` | The resources limits for the PostgreSQL Primary containers | `{}` | +| `primary.resources.requests.memory` | The requested memory for the PostgreSQL Primary containers | `256Mi` | +| `primary.resources.requests.cpu` | The requested cpu for the PostgreSQL Primary containers | `250m` | +| `primary.podSecurityContext.enabled` | Enable security context | `true` | +| `primary.podSecurityContext.fsGroup` | Group ID for the pod | `1001` | +| `primary.containerSecurityContext.enabled` | Enable container security context | `true` | +| `primary.containerSecurityContext.runAsUser` | User ID for the container | `1001` | +| `primary.hostAliases` | PostgreSQL primary pods host aliases | `[]` | +| `primary.hostNetwork` | Specify if host network should be enabled for PostgreSQL pod (postgresql primary) | `false` | +| `primary.hostIPC` | Specify if host IPC should be enabled for PostgreSQL pod (postgresql primary) | `false` | +| `primary.labels` | Map of labels to add to the statefulset (postgresql primary) | `{}` | +| `primary.annotations` | Annotations for PostgreSQL primary pods | `{}` | +| `primary.podLabels` | Map of labels to add to the pods (postgresql primary) | `{}` | +| `primary.podAnnotations` | Map of annotations to add to the pods (postgresql primary) | `{}` | +| `primary.podAffinityPreset` | PostgreSQL primary pod affinity preset. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `primary.podAntiAffinityPreset` | PostgreSQL primary pod anti-affinity preset. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` | `soft` | +| `primary.nodeAffinityPreset.type` | PostgreSQL primary node affinity preset type. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `primary.nodeAffinityPreset.key` | PostgreSQL primary node label key to match Ignored if `primary.affinity` is set. | `""` | +| `primary.nodeAffinityPreset.values` | PostgreSQL primary node label values to match. Ignored if `primary.affinity` is set. | `[]` | +| `primary.affinity` | Affinity for PostgreSQL primary pods assignment | `{}` | +| `primary.nodeSelector` | Node labels for PostgreSQL primary pods assignment | `{}` | +| `primary.tolerations` | Tolerations for PostgreSQL primary pods assignment | `[]` | +| `primary.topologySpreadConstraints` | Topology Spread Constraints for pod assignment spread across your cluster among failure-domains. Evaluated as a template | `[]` | +| `primary.priorityClassName` | Priority Class to use for each pod (postgresql primary) | `""` | +| `primary.schedulerName` | Use an alternate scheduler, e.g. "stork". | `""` | +| `primary.terminationGracePeriodSeconds` | Seconds PostgreSQL primary pod needs to terminate gracefully | `""` | +| `primary.updateStrategy.type` | PostgreSQL Primary statefulset strategy type | `RollingUpdate` | +| `primary.updateStrategy.rollingUpdate` | PostgreSQL Primary statefulset rolling update configuration parameters | `{}` | +| `primary.extraVolumeMounts` | Optionally specify extra list of additional volumeMounts for the PostgreSQL Primary container(s) | `[]` | +| `primary.extraVolumes` | Optionally specify extra list of additional volumes for the PostgreSQL Primary pod(s) | `[]` | +| `primary.sidecars` | Add additional sidecar containers to the PostgreSQL Primary pod(s) | `[]` | +| `primary.initContainers` | Add additional init containers to the PostgreSQL Primary pod(s) | `[]` | +| `primary.extraPodSpec` | Optionally specify extra PodSpec for the PostgreSQL Primary pod(s) | `{}` | +| `primary.service.type` | Kubernetes Service type | `ClusterIP` | +| `primary.service.ports.postgresql` | PostgreSQL service port | `5432` | +| `primary.service.nodePorts.postgresql` | Node port for PostgreSQL | `""` | +| `primary.service.clusterIP` | Static clusterIP or None for headless services | `""` | +| `primary.service.annotations` | Annotations for PostgreSQL primary service | `{}` | +| `primary.service.loadBalancerIP` | Load balancer IP if service type is `LoadBalancer` | `""` | +| `primary.service.externalTrafficPolicy` | Enable client source IP preservation | `Cluster` | +| `primary.service.loadBalancerSourceRanges` | Addresses that are allowed when service is LoadBalancer | `[]` | +| `primary.service.extraPorts` | Extra ports to expose in the PostgreSQL primary service | `[]` | +| `primary.service.sessionAffinity` | Session Affinity for Kubernetes service, can be "None" or "ClientIP" | `None` | +| `primary.service.sessionAffinityConfig` | Additional settings for the sessionAffinity | `{}` | +| `primary.persistence.enabled` | Enable PostgreSQL Primary data persistence using PVC | `true` | +| `primary.persistence.existingClaim` | Name of an existing PVC to use | `""` | +| `primary.persistence.mountPath` | The path the volume will be mounted at | `/bitnami/postgresql` | +| `primary.persistence.subPath` | The subdirectory of the volume to mount to | `""` | +| `primary.persistence.storageClass` | PVC Storage Class for PostgreSQL Primary data volume | `""` | +| `primary.persistence.accessModes` | PVC Access Mode for PostgreSQL volume | `["ReadWriteOnce"]` | +| `primary.persistence.size` | PVC Storage Request for PostgreSQL volume | `8Gi` | +| `primary.persistence.annotations` | Annotations for the PVC | `{}` | +| `primary.persistence.labels` | Labels for the PVC | `{}` | +| `primary.persistence.selector` | Selector to match an existing Persistent Volume (this value is evaluated as a template) | `{}` | +| `primary.persistence.dataSource` | Custom PVC data source | `{}` | + + +### PostgreSQL read only replica parameters (only used when `architecture` is set to `replication`) + +| Name | Description | Value | +| ------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ | --------------------- | +| `readReplicas.name` | Name of the read replicas database (eg secondary, slave, ...) | `read` | +| `readReplicas.replicaCount` | Number of PostgreSQL read only replicas | `1` | +| `readReplicas.extendedConfiguration` | Extended PostgreSQL read only replicas configuration (appended to main or default configuration) | `""` | +| `readReplicas.extraEnvVars` | Array with extra environment variables to add to PostgreSQL read only nodes | `[]` | +| `readReplicas.extraEnvVarsCM` | Name of existing ConfigMap containing extra env vars for PostgreSQL read only nodes | `""` | +| `readReplicas.extraEnvVarsSecret` | Name of existing Secret containing extra env vars for PostgreSQL read only nodes | `""` | +| `readReplicas.command` | Override default container command (useful when using custom images) | `[]` | +| `readReplicas.args` | Override default container args (useful when using custom images) | `[]` | +| `readReplicas.livenessProbe.enabled` | Enable livenessProbe on PostgreSQL read only containers | `true` | +| `readReplicas.livenessProbe.initialDelaySeconds` | Initial delay seconds for livenessProbe | `30` | +| `readReplicas.livenessProbe.periodSeconds` | Period seconds for livenessProbe | `10` | +| `readReplicas.livenessProbe.timeoutSeconds` | Timeout seconds for livenessProbe | `5` | +| `readReplicas.livenessProbe.failureThreshold` | Failure threshold for livenessProbe | `6` | +| `readReplicas.livenessProbe.successThreshold` | Success threshold for livenessProbe | `1` | +| `readReplicas.readinessProbe.enabled` | Enable readinessProbe on PostgreSQL read only containers | `true` | +| `readReplicas.readinessProbe.initialDelaySeconds` | Initial delay seconds for readinessProbe | `5` | +| `readReplicas.readinessProbe.periodSeconds` | Period seconds for readinessProbe | `10` | +| `readReplicas.readinessProbe.timeoutSeconds` | Timeout seconds for readinessProbe | `5` | +| `readReplicas.readinessProbe.failureThreshold` | Failure threshold for readinessProbe | `6` | +| `readReplicas.readinessProbe.successThreshold` | Success threshold for readinessProbe | `1` | +| `readReplicas.startupProbe.enabled` | Enable startupProbe on PostgreSQL read only containers | `false` | +| `readReplicas.startupProbe.initialDelaySeconds` | Initial delay seconds for startupProbe | `30` | +| `readReplicas.startupProbe.periodSeconds` | Period seconds for startupProbe | `10` | +| `readReplicas.startupProbe.timeoutSeconds` | Timeout seconds for startupProbe | `1` | +| `readReplicas.startupProbe.failureThreshold` | Failure threshold for startupProbe | `15` | +| `readReplicas.startupProbe.successThreshold` | Success threshold for startupProbe | `1` | +| `readReplicas.customLivenessProbe` | Custom livenessProbe that overrides the default one | `{}` | +| `readReplicas.customReadinessProbe` | Custom readinessProbe that overrides the default one | `{}` | +| `readReplicas.customStartupProbe` | Custom startupProbe that overrides the default one | `{}` | +| `readReplicas.lifecycleHooks` | for the PostgreSQL read only container to automate configuration before or after startup | `{}` | +| `readReplicas.resources.limits` | The resources limits for the PostgreSQL read only containers | `{}` | +| `readReplicas.resources.requests.memory` | The requested memory for the PostgreSQL read only containers | `256Mi` | +| `readReplicas.resources.requests.cpu` | The requested cpu for the PostgreSQL read only containers | `250m` | +| `readReplicas.podSecurityContext.enabled` | Enable security context | `true` | +| `readReplicas.podSecurityContext.fsGroup` | Group ID for the pod | `1001` | +| `readReplicas.containerSecurityContext.enabled` | Enable container security context | `true` | +| `readReplicas.containerSecurityContext.runAsUser` | User ID for the container | `1001` | +| `readReplicas.hostAliases` | PostgreSQL read only pods host aliases | `[]` | +| `readReplicas.hostNetwork` | Specify if host network should be enabled for PostgreSQL pod (PostgreSQL read only) | `false` | +| `readReplicas.hostIPC` | Specify if host IPC should be enabled for PostgreSQL pod (postgresql primary) | `false` | +| `readReplicas.labels` | Map of labels to add to the statefulset (PostgreSQL read only) | `{}` | +| `readReplicas.annotations` | Annotations for PostgreSQL read only pods | `{}` | +| `readReplicas.podLabels` | Map of labels to add to the pods (PostgreSQL read only) | `{}` | +| `readReplicas.podAnnotations` | Map of annotations to add to the pods (PostgreSQL read only) | `{}` | +| `readReplicas.podAffinityPreset` | PostgreSQL read only pod affinity preset. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `readReplicas.podAntiAffinityPreset` | PostgreSQL read only pod anti-affinity preset. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` | `soft` | +| `readReplicas.nodeAffinityPreset.type` | PostgreSQL read only node affinity preset type. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `readReplicas.nodeAffinityPreset.key` | PostgreSQL read only node label key to match Ignored if `primary.affinity` is set. | `""` | +| `readReplicas.nodeAffinityPreset.values` | PostgreSQL read only node label values to match. Ignored if `primary.affinity` is set. | `[]` | +| `readReplicas.affinity` | Affinity for PostgreSQL read only pods assignment | `{}` | +| `readReplicas.nodeSelector` | Node labels for PostgreSQL read only pods assignment | `{}` | +| `readReplicas.tolerations` | Tolerations for PostgreSQL read only pods assignment | `[]` | +| `readReplicas.topologySpreadConstraints` | Topology Spread Constraints for pod assignment spread across your cluster among failure-domains. Evaluated as a template | `[]` | +| `readReplicas.priorityClassName` | Priority Class to use for each pod (PostgreSQL read only) | `""` | +| `readReplicas.schedulerName` | Use an alternate scheduler, e.g. "stork". | `""` | +| `readReplicas.terminationGracePeriodSeconds` | Seconds PostgreSQL read only pod needs to terminate gracefully | `""` | +| `readReplicas.updateStrategy.type` | PostgreSQL read only statefulset strategy type | `RollingUpdate` | +| `readReplicas.updateStrategy.rollingUpdate` | PostgreSQL read only statefulset rolling update configuration parameters | `{}` | +| `readReplicas.extraVolumeMounts` | Optionally specify extra list of additional volumeMounts for the PostgreSQL read only container(s) | `[]` | +| `readReplicas.extraVolumes` | Optionally specify extra list of additional volumes for the PostgreSQL read only pod(s) | `[]` | +| `readReplicas.sidecars` | Add additional sidecar containers to the PostgreSQL read only pod(s) | `[]` | +| `readReplicas.initContainers` | Add additional init containers to the PostgreSQL read only pod(s) | `[]` | +| `readReplicas.extraPodSpec` | Optionally specify extra PodSpec for the PostgreSQL read only pod(s) | `{}` | +| `readReplicas.service.type` | Kubernetes Service type | `ClusterIP` | +| `readReplicas.service.ports.postgresql` | PostgreSQL service port | `5432` | +| `readReplicas.service.nodePorts.postgresql` | Node port for PostgreSQL | `""` | +| `readReplicas.service.clusterIP` | Static clusterIP or None for headless services | `""` | +| `readReplicas.service.annotations` | Annotations for PostgreSQL read only service | `{}` | +| `readReplicas.service.loadBalancerIP` | Load balancer IP if service type is `LoadBalancer` | `""` | +| `readReplicas.service.externalTrafficPolicy` | Enable client source IP preservation | `Cluster` | +| `readReplicas.service.loadBalancerSourceRanges` | Addresses that are allowed when service is LoadBalancer | `[]` | +| `readReplicas.service.extraPorts` | Extra ports to expose in the PostgreSQL read only service | `[]` | +| `readReplicas.service.sessionAffinity` | Session Affinity for Kubernetes service, can be "None" or "ClientIP" | `None` | +| `readReplicas.service.sessionAffinityConfig` | Additional settings for the sessionAffinity | `{}` | +| `readReplicas.persistence.enabled` | Enable PostgreSQL read only data persistence using PVC | `true` | +| `readReplicas.persistence.existingClaim` | Name of an existing PVC to use | `""` | +| `readReplicas.persistence.mountPath` | The path the volume will be mounted at | `/bitnami/postgresql` | +| `readReplicas.persistence.subPath` | The subdirectory of the volume to mount to | `""` | +| `readReplicas.persistence.storageClass` | PVC Storage Class for PostgreSQL read only data volume | `""` | +| `readReplicas.persistence.accessModes` | PVC Access Mode for PostgreSQL volume | `["ReadWriteOnce"]` | +| `readReplicas.persistence.size` | PVC Storage Request for PostgreSQL volume | `8Gi` | +| `readReplicas.persistence.annotations` | Annotations for the PVC | `{}` | +| `readReplicas.persistence.labels` | Labels for the PVC | `{}` | +| `readReplicas.persistence.selector` | Selector to match an existing Persistent Volume (this value is evaluated as a template) | `{}` | +| `readReplicas.persistence.dataSource` | Custom PVC data source | `{}` | + + +### NetworkPolicy parameters + +| Name | Description | Value | +| ------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | ------- | +| `networkPolicy.enabled` | Enable network policies | `false` | +| `networkPolicy.metrics.enabled` | Enable network policies for metrics (prometheus) | `false` | +| `networkPolicy.metrics.namespaceSelector` | Monitoring namespace selector labels. These labels will be used to identify the prometheus' namespace. | `{}` | +| `networkPolicy.metrics.podSelector` | Monitoring pod selector labels. These labels will be used to identify the Prometheus pods. | `{}` | +| `networkPolicy.ingressRules.primaryAccessOnlyFrom.enabled` | Enable ingress rule that makes PostgreSQL primary node only accessible from a particular origin. | `false` | +| `networkPolicy.ingressRules.primaryAccessOnlyFrom.namespaceSelector` | Namespace selector label that is allowed to access the PostgreSQL primary node. This label will be used to identified the allowed namespace(s). | `{}` | +| `networkPolicy.ingressRules.primaryAccessOnlyFrom.podSelector` | Pods selector label that is allowed to access the PostgreSQL primary node. This label will be used to identified the allowed pod(s). | `{}` | +| `networkPolicy.ingressRules.primaryAccessOnlyFrom.customRules` | Custom network policy for the PostgreSQL primary node. | `{}` | +| `networkPolicy.ingressRules.readReplicasAccessOnlyFrom.enabled` | Enable ingress rule that makes PostgreSQL read-only nodes only accessible from a particular origin. | `false` | +| `networkPolicy.ingressRules.readReplicasAccessOnlyFrom.namespaceSelector` | Namespace selector label that is allowed to access the PostgreSQL read-only nodes. This label will be used to identified the allowed namespace(s). | `{}` | +| `networkPolicy.ingressRules.readReplicasAccessOnlyFrom.podSelector` | Pods selector label that is allowed to access the PostgreSQL read-only nodes. This label will be used to identified the allowed pod(s). | `{}` | +| `networkPolicy.ingressRules.readReplicasAccessOnlyFrom.customRules` | Custom network policy for the PostgreSQL read-only nodes. | `{}` | +| `networkPolicy.egressRules.denyConnectionsToExternal` | Enable egress rule that denies outgoing traffic outside the cluster, except for DNS (port 53). | `false` | +| `networkPolicy.egressRules.customRules` | Custom network policy rule | `{}` | + + +### Volume Permissions parameters + +| Name | Description | Value | +| ------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------- | ----------------------- | +| `volumePermissions.enabled` | Enable init container that changes the owner and group of the persistent volume | `false` | +| `volumePermissions.image.registry` | Init container volume-permissions image registry | `docker.io` | +| `volumePermissions.image.repository` | Init container volume-permissions image repository | `bitnami/bitnami-shell` | +| `volumePermissions.image.tag` | Init container volume-permissions image tag (immutable tags are recommended) | `11-debian-11-r42` | +| `volumePermissions.image.digest` | Init container volume-permissions image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag | `""` | +| `volumePermissions.image.pullPolicy` | Init container volume-permissions image pull policy | `IfNotPresent` | +| `volumePermissions.image.pullSecrets` | Init container volume-permissions image pull secrets | `[]` | +| `volumePermissions.resources.limits` | Init container volume-permissions resource limits | `{}` | +| `volumePermissions.resources.requests` | Init container volume-permissions resource requests | `{}` | +| `volumePermissions.containerSecurityContext.runAsUser` | User ID for the init container | `0` | + + +### Other Parameters + +| Name | Description | Value | +| --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- | ------- | +| `serviceAccount.create` | Enable creation of ServiceAccount for PostgreSQL pod | `false` | +| `serviceAccount.name` | The name of the ServiceAccount to use. | `""` | +| `serviceAccount.automountServiceAccountToken` | Allows auto mount of ServiceAccountToken on the serviceAccount created | `true` | +| `serviceAccount.annotations` | Additional custom annotations for the ServiceAccount | `{}` | +| `rbac.create` | Create Role and RoleBinding (required for PSP to work) | `false` | +| `rbac.rules` | Custom RBAC rules to set | `[]` | +| `psp.create` | Whether to create a PodSecurityPolicy. WARNING: PodSecurityPolicy is deprecated in Kubernetes v1.21 or later, unavailable in v1.25 or later | `false` | + + +### Metrics Parameters + +| Name | Description | Value | +| ----------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | --------------------------- | +| `metrics.enabled` | Start a prometheus exporter | `false` | +| `metrics.image.registry` | PostgreSQL Prometheus Exporter image registry | `docker.io` | +| `metrics.image.repository` | PostgreSQL Prometheus Exporter image repository | `bitnami/postgres-exporter` | +| `metrics.image.tag` | PostgreSQL Prometheus Exporter image tag (immutable tags are recommended) | `0.11.1-debian-11-r19` | +| `metrics.image.digest` | PostgreSQL image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag | `""` | +| `metrics.image.pullPolicy` | PostgreSQL Prometheus Exporter image pull policy | `IfNotPresent` | +| `metrics.image.pullSecrets` | Specify image pull secrets | `[]` | +| `metrics.customMetrics` | Define additional custom metrics | `{}` | +| `metrics.extraEnvVars` | Extra environment variables to add to PostgreSQL Prometheus exporter | `[]` | +| `metrics.containerSecurityContext.enabled` | Enable PostgreSQL Prometheus exporter containers' Security Context | `true` | +| `metrics.containerSecurityContext.runAsUser` | Set PostgreSQL Prometheus exporter containers' Security Context runAsUser | `1001` | +| `metrics.containerSecurityContext.runAsNonRoot` | Set PostgreSQL Prometheus exporter containers' Security Context runAsNonRoot | `true` | +| `metrics.livenessProbe.enabled` | Enable livenessProbe on PostgreSQL Prometheus exporter containers | `true` | +| `metrics.livenessProbe.initialDelaySeconds` | Initial delay seconds for livenessProbe | `5` | +| `metrics.livenessProbe.periodSeconds` | Period seconds for livenessProbe | `10` | +| `metrics.livenessProbe.timeoutSeconds` | Timeout seconds for livenessProbe | `5` | +| `metrics.livenessProbe.failureThreshold` | Failure threshold for livenessProbe | `6` | +| `metrics.livenessProbe.successThreshold` | Success threshold for livenessProbe | `1` | +| `metrics.readinessProbe.enabled` | Enable readinessProbe on PostgreSQL Prometheus exporter containers | `true` | +| `metrics.readinessProbe.initialDelaySeconds` | Initial delay seconds for readinessProbe | `5` | +| `metrics.readinessProbe.periodSeconds` | Period seconds for readinessProbe | `10` | +| `metrics.readinessProbe.timeoutSeconds` | Timeout seconds for readinessProbe | `5` | +| `metrics.readinessProbe.failureThreshold` | Failure threshold for readinessProbe | `6` | +| `metrics.readinessProbe.successThreshold` | Success threshold for readinessProbe | `1` | +| `metrics.startupProbe.enabled` | Enable startupProbe on PostgreSQL Prometheus exporter containers | `false` | +| `metrics.startupProbe.initialDelaySeconds` | Initial delay seconds for startupProbe | `10` | +| `metrics.startupProbe.periodSeconds` | Period seconds for startupProbe | `10` | +| `metrics.startupProbe.timeoutSeconds` | Timeout seconds for startupProbe | `1` | +| `metrics.startupProbe.failureThreshold` | Failure threshold for startupProbe | `15` | +| `metrics.startupProbe.successThreshold` | Success threshold for startupProbe | `1` | +| `metrics.customLivenessProbe` | Custom livenessProbe that overrides the default one | `{}` | +| `metrics.customReadinessProbe` | Custom readinessProbe that overrides the default one | `{}` | +| `metrics.customStartupProbe` | Custom startupProbe that overrides the default one | `{}` | +| `metrics.containerPorts.metrics` | PostgreSQL Prometheus exporter metrics container port | `9187` | +| `metrics.resources.limits` | The resources limits for the PostgreSQL Prometheus exporter container | `{}` | +| `metrics.resources.requests` | The requested resources for the PostgreSQL Prometheus exporter container | `{}` | +| `metrics.service.ports.metrics` | PostgreSQL Prometheus Exporter service port | `9187` | +| `metrics.service.clusterIP` | Static clusterIP or None for headless services | `""` | +| `metrics.service.sessionAffinity` | Control where client requests go, to the same pod or round-robin | `None` | +| `metrics.service.annotations` | Annotations for Prometheus to auto-discover the metrics endpoint | `{}` | +| `metrics.serviceMonitor.enabled` | Create ServiceMonitor Resource for scraping metrics using Prometheus Operator | `false` | +| `metrics.serviceMonitor.namespace` | Namespace for the ServiceMonitor Resource (defaults to the Release Namespace) | `""` | +| `metrics.serviceMonitor.interval` | Interval at which metrics should be scraped. | `""` | +| `metrics.serviceMonitor.scrapeTimeout` | Timeout after which the scrape is ended | `""` | +| `metrics.serviceMonitor.labels` | Additional labels that can be used so ServiceMonitor will be discovered by Prometheus | `{}` | +| `metrics.serviceMonitor.selector` | Prometheus instance selector labels | `{}` | +| `metrics.serviceMonitor.relabelings` | RelabelConfigs to apply to samples before scraping | `[]` | +| `metrics.serviceMonitor.metricRelabelings` | MetricRelabelConfigs to apply to samples before ingestion | `[]` | +| `metrics.serviceMonitor.honorLabels` | Specify honorLabels parameter to add the scrape endpoint | `false` | +| `metrics.serviceMonitor.jobLabel` | The name of the label on the target service to use as the job name in prometheus. | `""` | +| `metrics.prometheusRule.enabled` | Create a PrometheusRule for Prometheus Operator | `false` | +| `metrics.prometheusRule.namespace` | Namespace for the PrometheusRule Resource (defaults to the Release Namespace) | `""` | +| `metrics.prometheusRule.labels` | Additional labels that can be used so PrometheusRule will be discovered by Prometheus | `{}` | +| `metrics.prometheusRule.rules` | PrometheusRule definitions | `[]` | + + +Specify each parameter using the `--set key=value[,key=value]` argument to `helm install`. For example, + +```bash +$ helm install my-release \ + --set auth.postgresPassword=secretpassword + my-repo/postgresql +``` + +The above command sets the PostgreSQL `postgres` account password to `secretpassword`. + +> NOTE: Once this chart is deployed, it is not possible to change the application's access credentials, such as usernames or passwords, using Helm. To change these application credentials after deployment, delete any persistent volumes (PVs) used by the chart and re-deploy it, or use the application's built-in administrative tools if available. + +> **Warning** Setting a password will be ignored on new installation in case when previous Posgresql release was deleted through the helm command. In that case, old PVC will have an old password, and setting it through helm won't take effect. Deleting persistent volumes (PVs) will solve the issue. Refer to [issue 2061](https://github.com/bitnami/charts/issues/2061) for more details + +Alternatively, a YAML file that specifies the values for the parameters can be provided while installing the chart. For example, + +```bash +helm install my-release -f values.yaml my-repo/postgresql +``` + +> **Tip**: You can use the default [values.yaml](values.yaml) + +## Configuration and installation details + +### [Rolling VS Immutable tags](https://docs.bitnami.com/containers/how-to/understand-rolling-tags-containers/) + +It is strongly recommended to use immutable tags in a production environment. This ensures your deployment does not change automatically if the same tag is updated with a different image. + +Bitnami will release a new chart updating its containers if a new version of the main container, significant changes, or critical vulnerabilities exist. + +### Customizing primary and read replica services in a replicated configuration + +At the top level, there is a service object which defines the services for both primary and readReplicas. For deeper customization, there are service objects for both the primary and read types individually. This allows you to override the values in the top level service object so that the primary and read can be of different service types and with different clusterIPs / nodePorts. Also in the case you want the primary and read to be of type nodePort, you will need to set the nodePorts to different values to prevent a collision. The values that are deeper in the primary.service or readReplicas.service objects will take precedence over the top level service object. + +### Use a different PostgreSQL version + +To modify the application version used in this chart, specify a different version of the image using the `image.tag` parameter and/or a different repository using the `image.repository` parameter. Refer to the [chart documentation for more information on these parameters and how to use them with images from a private registry](https://docs.bitnami.com/kubernetes/infrastructure/postgresql/configuration/change-image-version/). + +### postgresql.conf / pg_hba.conf files as configMap + +This helm chart also supports to customize the PostgreSQL configuration file. You can add additional PostgreSQL configuration parameters using the `primary.extendedConfiguration`/`readReplicas.extendedConfiguration` parameters as a string. Alternatively, to replace the entire default configuration use `primary.configuration`. + +You can also add a custom pg_hba.conf using the `primary.pgHbaConfiguration` parameter. + +In addition to these options, you can also set an external ConfigMap with all the configuration files. This is done by setting the `primary.existingConfigmap` parameter. Note that this will override the two previous options. + +### Initialize a fresh instance + +The [Bitnami PostgreSQL](https://github.com/bitnami/containers/tree/main/bitnami/postgresql) image allows you to use your custom scripts to initialize a fresh instance. In order to execute the scripts, you can specify custom scripts using the `primary.initdb.scripts` parameter as a string. + +In addition, you can also set an external ConfigMap with all the initialization scripts. This is done by setting the `primary.initdb.scriptsConfigMap` parameter. Note that this will override the two previous options. If your initialization scripts contain sensitive information such as credentials or passwords, you can use the `primary.initdb.scriptsSecret` parameter. + +The allowed extensions are `.sh`, `.sql` and `.sql.gz`. + +### Securing traffic using TLS + +TLS support can be enabled in the chart by specifying the `tls.` parameters while creating a release. The following parameters should be configured to properly enable the TLS support in the chart: + +- `tls.enabled`: Enable TLS support. Defaults to `false` +- `tls.certificatesSecret`: Name of an existing secret that contains the certificates. No defaults. +- `tls.certFilename`: Certificate filename. No defaults. +- `tls.certKeyFilename`: Certificate key filename. No defaults. + +For example: + +- First, create the secret with the cetificates files: + + ```console + kubectl create secret generic certificates-tls-secret --from-file=./cert.crt --from-file=./cert.key --from-file=./ca.crt + ``` + +- Then, use the following parameters: + + ```console + volumePermissions.enabled=true + tls.enabled=true + tls.certificatesSecret="certificates-tls-secret" + tls.certFilename="cert.crt" + tls.certKeyFilename="cert.key" + ``` + + > Note TLS and VolumePermissions: PostgreSQL requires certain permissions on sensitive files (such as certificate keys) to start up. Due to an on-going [issue](https://github.com/kubernetes/kubernetes/issues/57923) regarding kubernetes permissions and the use of `containerSecurityContext.runAsUser`, you must enable `volumePermissions` to ensure everything works as expected. + +### Sidecars + +If you need additional containers to run within the same pod as PostgreSQL (e.g. an additional metrics or logging exporter), you can do so via the `sidecars` config parameter. Simply define your container according to the Kubernetes container spec. + +```yaml +# For the PostgreSQL primary +primary: + sidecars: + - name: your-image-name + image: your-image + imagePullPolicy: Always + ports: + - name: portname + containerPort: 1234 +# For the PostgreSQL replicas +readReplicas: + sidecars: + - name: your-image-name + image: your-image + imagePullPolicy: Always + ports: + - name: portname + containerPort: 1234 +``` + +### Metrics + +The chart optionally can start a metrics exporter for [prometheus](https://prometheus.io). The metrics endpoint (port 9187) is not exposed and it is expected that the metrics are collected from inside the k8s cluster using something similar as the described in the [example Prometheus scrape configuration](https://github.com/prometheus/prometheus/blob/master/documentation/examples/prometheus-kubernetes.yml). + +The exporter allows to create custom metrics from additional SQL queries. See the Chart's `values.yaml` for an example and consult the [exporters documentation](https://github.com/wrouesnel/postgres_exporter#adding-new-metrics-via-a-config-file) for more details. + +### Use of global variables + +In more complex scenarios, we may have the following tree of dependencies + +``` + +--------------+ + | | + +------------+ Chart 1 +-----------+ + | | | | + | --------+------+ | + | | | + | | | + | | | + | | | + v v v ++-------+------+ +--------+------+ +--------+------+ +| | | | | | +| PostgreSQL | | Sub-chart 1 | | Sub-chart 2 | +| | | | | | ++--------------+ +---------------+ +---------------+ +``` + +The three charts below depend on the parent chart Chart 1. However, subcharts 1 and 2 may need to connect to PostgreSQL as well. In order to do so, subcharts 1 and 2 need to know the PostgreSQL credentials, so one option for deploying could be deploy Chart 1 with the following parameters: + +``` +postgresql.auth.username=testuser +subchart1.postgresql.auth.username=testuser +subchart2.postgresql.auth.username=testuser +postgresql.auth.password=testpass +subchart1.postgresql.auth.password=testpass +subchart2.postgresql.auth.password=testpass +postgresql.auth.database=testdb +subchart1.postgresql.auth.database=testdb +subchart2.postgresql.auth.database=testdb +``` + +If the number of dependent sub-charts increases, installing the chart with parameters can become increasingly difficult. An alternative would be to set the credentials using global variables as follows: + +``` +global.postgresql.auth.username=testuser +global.postgresql.auth.password=testpass +global.postgresql.auth.database=testdb +``` + +This way, the credentials will be available in all of the subcharts. + +## Persistence + +The [Bitnami PostgreSQL](https://github.com/bitnami/containers/tree/main/bitnami/postgresql) image stores the PostgreSQL data and configurations at the `/bitnami/postgresql` path of the container. + +Persistent Volume Claims are used to keep the data across deployments. This is known to work in GCE, AWS, and minikube. +See the [Parameters](#parameters) section to configure the PVC or to disable persistence. + +If you already have data in it, you will fail to sync to standby nodes for all commits, details can refer to the [code present in the container repository](https://github.com/bitnami/containers/tree/main/bitnami/postgresql). If you need to use those data, please covert them to sql and import after `helm install` finished. + +## NetworkPolicy + +To enable network policy for PostgreSQL, install [a networking plugin that implements the Kubernetes NetworkPolicy spec](https://kubernetes.io/docs/tasks/administer-cluster/declare-network-policy#before-you-begin), and set `networkPolicy.enabled` to `true`. + +For Kubernetes v1.5 & v1.6, you must also turn on NetworkPolicy by setting the DefaultDeny namespace annotation. Note: this will enforce policy for _all_ pods in the namespace: + +```bash +kubectl annotate namespace default "net.beta.kubernetes.io/network-policy={\"ingress\":{\"isolation\":\"DefaultDeny\"}}" +``` + +With NetworkPolicy enabled, traffic will be limited to just port 5432. + +For more precise policy, set `networkPolicy.allowExternal=false`. This will only allow pods with the generated client label to connect to PostgreSQL. +This label will be displayed in the output of a successful install. + +## Differences between Bitnami PostgreSQL image and [Docker Official](https://hub.docker.com/_/postgres) image + +- The Docker Official PostgreSQL image does not support replication. If you pass any replication environment variable, this would be ignored. The only environment variables supported by the Docker Official image are POSTGRES_USER, POSTGRES_DB, POSTGRES_PASSWORD, POSTGRES_INITDB_ARGS, POSTGRES_INITDB_WALDIR and PGDATA. All the remaining environment variables are specific to the Bitnami PostgreSQL image. +- The Bitnami PostgreSQL image is non-root by default. This requires that you run the pod with `securityContext` and updates the permissions of the volume with an `initContainer`. A key benefit of this configuration is that the pod follows security best practices and is prepared to run on Kubernetes distributions with hard security constraints like OpenShift. +- For OpenShift, one may either define the runAsUser and fsGroup accordingly, or try this more dynamic option: volumePermissions.securityContext.runAsUser="auto",securityContext.enabled=false,containerSecurityContext.enabled=false,shmVolume.chmod.enabled=false + +### Setting Pod's affinity + +This chart allows you to set your custom affinity using the `XXX.affinity` parameter(s). Find more information about Pod's affinity in the [kubernetes documentation](https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity). + +As an alternative, you can use of the preset configurations for pod affinity, pod anti-affinity, and node affinity available at the [bitnami/common](https://github.com/bitnami/charts/tree/main/bitnami/common#affinities) chart. To do so, set the `XXX.podAffinityPreset`, `XXX.podAntiAffinityPreset`, or `XXX.nodeAffinityPreset` parameters. + +## Troubleshooting + +Find more information about how to deal with common errors related to Bitnami's Helm charts in [this troubleshooting guide](https://docs.bitnami.com/general/how-to/troubleshoot-helm-chart-issues). + +## Upgrading + +Refer to the [chart documentation for more information about how to upgrade from previous releases](https://docs.bitnami.com/kubernetes/infrastructure/postgresql/administration/upgrade/). + +## License + +Copyright © 2022 Bitnami + +Licensed under the Apache License, Version 2.0 (the "License"); +you may not use this file except in compliance with the License. +You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + +Unless required by applicable law or agreed to in writing, software +distributed under the License is distributed on an "AS IS" BASIS, +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +See the License for the specific language governing permissions and +limitations under the License. \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/.helmignore new file mode 100644 index 0000000..50af031 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/.helmignore @@ -0,0 +1,22 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/Chart.yaml new file mode 100644 index 0000000..7d27a79 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/Chart.yaml @@ -0,0 +1,23 @@ +annotations: + category: Infrastructure +apiVersion: v2 +appVersion: 2.0.3 +description: A Library Helm Chart for grouping common logic between bitnami charts. + This chart is not deployable by itself. +home: https://github.com/bitnami/charts/tree/master/bitnami/common +icon: https://bitnami.com/downloads/logos/bitnami-mark.png +keywords: +- common +- helper +- template +- function +- bitnami +maintainers: +- name: Bitnami + url: https://github.com/bitnami/charts +name: common +sources: +- https://github.com/bitnami/charts +- https://www.bitnami.com/ +type: library +version: 2.0.3 diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/README.md b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/README.md new file mode 100644 index 0000000..a2ecd60 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/README.md @@ -0,0 +1,350 @@ +# Bitnami Common Library Chart + +A [Helm Library Chart](https://helm.sh/docs/topics/library_charts/#helm) for grouping common logic between bitnami charts. + +## TL;DR + +```yaml +dependencies: + - name: common + version: 1.x.x + repository: https://charts.bitnami.com/bitnami +``` + +```bash +$ helm dependency update +``` + +```yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "common.names.fullname" . }} +data: + myvalue: "Hello World" +``` + +## Introduction + +This chart provides a common template helpers which can be used to develop new charts using [Helm](https://helm.sh) package manager. + +Bitnami charts can be used with [Kubeapps](https://kubeapps.dev/) for deployment and management of Helm Charts in clusters. + +## Prerequisites + +- Kubernetes 1.19+ +- Helm 3.2.0+ + +## Parameters + +The following table lists the helpers available in the library which are scoped in different sections. + +### Affinities + +| Helper identifier | Description | Expected Input | +|-------------------------------|------------------------------------------------------|------------------------------------------------| +| `common.affinities.nodes.soft` | Return a soft nodeAffinity definition | `dict "key" "FOO" "values" (list "BAR" "BAZ")` | +| `common.affinities.nodes.hard` | Return a hard nodeAffinity definition | `dict "key" "FOO" "values" (list "BAR" "BAZ")` | +| `common.affinities.pods.soft` | Return a soft podAffinity/podAntiAffinity definition | `dict "component" "FOO" "context" $` | +| `common.affinities.pods.hard` | Return a hard podAffinity/podAntiAffinity definition | `dict "component" "FOO" "context" $` | + +### Capabilities + +| Helper identifier | Description | Expected Input | +|------------------------------------------------|------------------------------------------------------------------------------------------------|-------------------| +| `common.capabilities.kubeVersion` | Return the target Kubernetes version (using client default if .Values.kubeVersion is not set). | `.` Chart context | +| `common.capabilities.cronjob.apiVersion` | Return the appropriate apiVersion for cronjob. | `.` Chart context | +| `common.capabilities.deployment.apiVersion` | Return the appropriate apiVersion for deployment. | `.` Chart context | +| `common.capabilities.statefulset.apiVersion` | Return the appropriate apiVersion for statefulset. | `.` Chart context | +| `common.capabilities.ingress.apiVersion` | Return the appropriate apiVersion for ingress. | `.` Chart context | +| `common.capabilities.rbac.apiVersion` | Return the appropriate apiVersion for RBAC resources. | `.` Chart context | +| `common.capabilities.crd.apiVersion` | Return the appropriate apiVersion for CRDs. | `.` Chart context | +| `common.capabilities.policy.apiVersion` | Return the appropriate apiVersion for podsecuritypolicy. | `.` Chart context | +| `common.capabilities.networkPolicy.apiVersion` | Return the appropriate apiVersion for networkpolicy. | `.` Chart context | +| `common.capabilities.apiService.apiVersion` | Return the appropriate apiVersion for APIService. | `.` Chart context | +| `common.capabilities.hpa.apiVersion` | Return the appropriate apiVersion for Horizontal Pod Autoscaler | `.` Chart context | +| `common.capabilities.supportsHelmVersion` | Returns true if the used Helm version is 3.3+ | `.` Chart context | + +### Errors + +| Helper identifier | Description | Expected Input | +|-----------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------| +| `common.errors.upgrade.passwords.empty` | It will ensure required passwords are given when we are upgrading a chart. If `validationErrors` is not empty it will throw an error and will stop the upgrade action. | `dict "validationErrors" (list $validationError00 $validationError01) "context" $` | + +### Images + +| Helper identifier | Description | Expected Input | +|-----------------------------|------------------------------------------------------|---------------------------------------------------------------------------------------------------------| +| `common.images.image` | Return the proper and full image name | `dict "imageRoot" .Values.path.to.the.image "global" $`, see [ImageRoot](#imageroot) for the structure. | +| `common.images.pullSecrets` | Return the proper Docker Image Registry Secret Names (deprecated: use common.images.renderPullSecrets instead) | `dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "global" .Values.global` | +| `common.images.renderPullSecrets` | Return the proper Docker Image Registry Secret Names (evaluates values as templates) | `dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "context" $` | + +### Ingress + +| Helper identifier | Description | Expected Input | +|-------------------------------------------|-------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| `common.ingress.backend` | Generate a proper Ingress backend entry depending on the API version | `dict "serviceName" "foo" "servicePort" "bar"`, see the [Ingress deprecation notice](https://kubernetes.io/blog/2019/07/18/api-deprecations-in-1-16/) for the syntax differences | +| `common.ingress.supportsPathType` | Prints "true" if the pathType field is supported | `.` Chart context | +| `common.ingress.supportsIngressClassname` | Prints "true" if the ingressClassname field is supported | `.` Chart context | +| `common.ingress.certManagerRequest` | Prints "true" if required cert-manager annotations for TLS signed certificates are set in the Ingress annotations | `dict "annotations" .Values.path.to.the.ingress.annotations` | + +### Labels + +| Helper identifier | Description | Expected Input | +|-----------------------------|-----------------------------------------------------------------------------|-------------------| +| `common.labels.standard` | Return Kubernetes standard labels | `.` Chart context | +| `common.labels.matchLabels` | Labels to use on `deploy.spec.selector.matchLabels` and `svc.spec.selector` | `.` Chart context | + +### Names + +| Helper identifier | Description | Expected Input | +|-----------------------------------|-----------------------------------------------------------------------|-------------------| +| `common.names.name` | Expand the name of the chart or use `.Values.nameOverride` | `.` Chart context | +| `common.names.fullname` | Create a default fully qualified app name. | `.` Chart context | +| `common.names.namespace` | Allow the release namespace to be overridden | `.` Chart context | +| `common.names.fullname.namespace` | Create a fully qualified app name adding the installation's namespace | `.` Chart context | +| `common.names.chart` | Chart name plus version | `.` Chart context | + +### Secrets + +| Helper identifier | Description | Expected Input | +|---------------------------|--------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| `common.secrets.name` | Generate the name of the secret. | `dict "existingSecret" .Values.path.to.the.existingSecret "defaultNameSuffix" "mySuffix" "context" $` see [ExistingSecret](#existingsecret) for the structure. | +| `common.secrets.key` | Generate secret key. | `dict "existingSecret" .Values.path.to.the.existingSecret "key" "keyName"` see [ExistingSecret](#existingsecret) for the structure. | +| `common.passwords.manage` | Generate secret password or retrieve one if already created. | `dict "secret" "secret-name" "key" "keyName" "providedValues" (list "path.to.password1" "path.to.password2") "length" 10 "strong" false "chartName" "chartName" "context" $`, length, strong and chartNAme fields are optional. | +| `common.secrets.exists` | Returns whether a previous generated secret already exists. | `dict "secret" "secret-name" "context" $` | + +### Storage + +| Helper identifier | Description | Expected Input | +|-------------------------------|---------------------------------------|---------------------------------------------------------------------------------------------------------------------| +| `common.storage.class` | Return the proper Storage Class | `dict "persistence" .Values.path.to.the.persistence "global" $`, see [Persistence](#persistence) for the structure. | + +### TplValues + +| Helper identifier | Description | Expected Input | +|---------------------------|----------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------| +| `common.tplvalues.render` | Renders a value that contains template | `dict "value" .Values.path.to.the.Value "context" $`, value is the value should rendered as template, context frequently is the chart context `$` or `.` | + +### Utils + +| Helper identifier | Description | Expected Input | +|--------------------------------|------------------------------------------------------------------------------------------|------------------------------------------------------------------------| +| `common.utils.fieldToEnvVar` | Build environment variable name given a field. | `dict "field" "my-password"` | +| `common.utils.secret.getvalue` | Print instructions to get a secret value. | `dict "secret" "secret-name" "field" "secret-value-field" "context" $` | +| `common.utils.getValueFromKey` | Gets a value from `.Values` object given its key path | `dict "key" "path.to.key" "context" $` | +| `common.utils.getKeyFromList` | Returns first `.Values` key with a defined value or first of the list if all non-defined | `dict "keys" (list "path.to.key1" "path.to.key2") "context" $` | + +### Validations + +| Helper identifier | Description | Expected Input | +|--------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| `common.validations.values.single.empty` | Validate a value must not be empty. | `dict "valueKey" "path.to.value" "secret" "secret.name" "field" "my-password" "subchart" "subchart" "context" $` secret, field and subchart are optional. In case they are given, the helper will generate a how to get instruction. See [ValidateValue](#validatevalue) | +| `common.validations.values.multiple.empty` | Validate a multiple values must not be empty. It returns a shared error for all the values. | `dict "required" (list $validateValueConf00 $validateValueConf01) "context" $`. See [ValidateValue](#validatevalue) | +| `common.validations.values.mariadb.passwords` | This helper will ensure required password for MariaDB are not empty. It returns a shared error for all the values. | `dict "secret" "mariadb-secret" "subchart" "true" "context" $` subchart field is optional and could be true or false it depends on where you will use mariadb chart and the helper. | +| `common.validations.values.mysql.passwords` | This helper will ensure required password for MySQL are not empty. It returns a shared error for all the values. | `dict "secret" "mysql-secret" "subchart" "true" "context" $` subchart field is optional and could be true or false it depends on where you will use mysql chart and the helper. | +| `common.validations.values.postgresql.passwords` | This helper will ensure required password for PostgreSQL are not empty. It returns a shared error for all the values. | `dict "secret" "postgresql-secret" "subchart" "true" "context" $` subchart field is optional and could be true or false it depends on where you will use postgresql chart and the helper. | +| `common.validations.values.redis.passwords` | This helper will ensure required password for Redis® are not empty. It returns a shared error for all the values. | `dict "secret" "redis-secret" "subchart" "true" "context" $` subchart field is optional and could be true or false it depends on where you will use redis chart and the helper. | +| `common.validations.values.cassandra.passwords` | This helper will ensure required password for Cassandra are not empty. It returns a shared error for all the values. | `dict "secret" "cassandra-secret" "subchart" "true" "context" $` subchart field is optional and could be true or false it depends on where you will use cassandra chart and the helper. | +| `common.validations.values.mongodb.passwords` | This helper will ensure required password for MongoDB® are not empty. It returns a shared error for all the values. | `dict "secret" "mongodb-secret" "subchart" "true" "context" $` subchart field is optional and could be true or false it depends on where you will use mongodb chart and the helper. | + +### Warnings + +| Helper identifier | Description | Expected Input | +|------------------------------|----------------------------------|------------------------------------------------------------| +| `common.warnings.rollingTag` | Warning about using rolling tag. | `ImageRoot` see [ImageRoot](#imageroot) for the structure. | + +## Special input schemas + +### ImageRoot + +```yaml +registry: + type: string + description: Docker registry where the image is located + example: docker.io + +repository: + type: string + description: Repository and image name + example: bitnami/nginx + +tag: + type: string + description: image tag + example: 1.16.1-debian-10-r63 + +pullPolicy: + type: string + description: Specify a imagePullPolicy. Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + +pullSecrets: + type: array + items: + type: string + description: Optionally specify an array of imagePullSecrets (evaluated as templates). + +debug: + type: boolean + description: Set to true if you would like to see extra information on logs + example: false + +## An instance would be: +# registry: docker.io +# repository: bitnami/nginx +# tag: 1.16.1-debian-10-r63 +# pullPolicy: IfNotPresent +# debug: false +``` + +### Persistence + +```yaml +enabled: + type: boolean + description: Whether enable persistence. + example: true + +storageClass: + type: string + description: Ghost data Persistent Volume Storage Class, If set to "-", storageClassName: "" which disables dynamic provisioning. + example: "-" + +accessMode: + type: string + description: Access mode for the Persistent Volume Storage. + example: ReadWriteOnce + +size: + type: string + description: Size the Persistent Volume Storage. + example: 8Gi + +path: + type: string + description: Path to be persisted. + example: /bitnami + +## An instance would be: +# enabled: true +# storageClass: "-" +# accessMode: ReadWriteOnce +# size: 8Gi +# path: /bitnami +``` + +### ExistingSecret + +```yaml +name: + type: string + description: Name of the existing secret. + example: mySecret +keyMapping: + description: Mapping between the expected key name and the name of the key in the existing secret. + type: object + +## An instance would be: +# name: mySecret +# keyMapping: +# password: myPasswordKey +``` + +#### Example of use + +When we store sensitive data for a deployment in a secret, some times we want to give to users the possibility of using theirs existing secrets. + +```yaml +# templates/secret.yaml +--- +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "common.names.fullname" . }} + labels: + app: {{ include "common.names.fullname" . }} +type: Opaque +data: + password: {{ .Values.password | b64enc | quote }} + +# templates/dpl.yaml +--- +... + env: + - name: PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "common.secrets.name" (dict "existingSecret" .Values.existingSecret "context" $) }} + key: {{ include "common.secrets.key" (dict "existingSecret" .Values.existingSecret "key" "password") }} +... + +# values.yaml +--- +name: mySecret +keyMapping: + password: myPasswordKey +``` + +### ValidateValue + +#### NOTES.txt + +```console +{{- $validateValueConf00 := (dict "valueKey" "path.to.value00" "secret" "secretName" "field" "password-00") -}} +{{- $validateValueConf01 := (dict "valueKey" "path.to.value01" "secret" "secretName" "field" "password-01") -}} + +{{ include "common.validations.values.multiple.empty" (dict "required" (list $validateValueConf00 $validateValueConf01) "context" $) }} +``` + +If we force those values to be empty we will see some alerts + +```console +$ helm install test mychart --set path.to.value00="",path.to.value01="" + 'path.to.value00' must not be empty, please add '--set path.to.value00=$PASSWORD_00' to the command. To get the current value: + + export PASSWORD_00=$(kubectl get secret --namespace default secretName -o jsonpath="{.data.password-00}" | base64 -d) + + 'path.to.value01' must not be empty, please add '--set path.to.value01=$PASSWORD_01' to the command. To get the current value: + + export PASSWORD_01=$(kubectl get secret --namespace default secretName -o jsonpath="{.data.password-01}" | base64 -d) +``` + +## Upgrading + +### To 1.0.0 + +[On November 13, 2020, Helm v2 support was formally finished](https://github.com/helm/charts#status-of-the-project), this major version is the result of the required changes applied to the Helm Chart to be able to incorporate the different features added in Helm v3 and to be consistent with the Helm project itself regarding the Helm v2 EOL. + +**What changes were introduced in this major version?** + +- Previous versions of this Helm Chart use `apiVersion: v1` (installable by both Helm 2 and 3), this Helm Chart was updated to `apiVersion: v2` (installable by Helm 3 only). [Here](https://helm.sh/docs/topics/charts/#the-apiversion-field) you can find more information about the `apiVersion` field. +- Use `type: library`. [Here](https://v3.helm.sh/docs/faq/#library-chart-support) you can find more information. +- The different fields present in the *Chart.yaml* file has been ordered alphabetically in a homogeneous way for all the Bitnami Helm Charts + +**Considerations when upgrading to this version** + +- If you want to upgrade to this version from a previous one installed with Helm v3, you shouldn't face any issues +- If you want to upgrade to this version using Helm v2, this scenario is not supported as this version doesn't support Helm v2 anymore +- If you installed the previous version with Helm v2 and wants to upgrade to this version with Helm v3, please refer to the [official Helm documentation](https://helm.sh/docs/topics/v2_v3_migration/#migration-use-cases) about migrating from Helm v2 to v3 + +**Useful links** + +- https://docs.bitnami.com/tutorials/resolve-helm2-helm3-post-migration-issues/ +- https://helm.sh/docs/topics/v2_v3_migration/ +- https://helm.sh/blog/migrate-from-helm-v2-to-helm-v3/ + +## License + +Copyright © 2022 Bitnami + +Licensed under the Apache License, Version 2.0 (the "License"); +you may not use this file except in compliance with the License. +You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + +Unless required by applicable law or agreed to in writing, software +distributed under the License is distributed on an "AS IS" BASIS, +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +See the License for the specific language governing permissions and +limitations under the License. diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_affinities.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_affinities.tpl new file mode 100644 index 0000000..2387be2 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_affinities.tpl @@ -0,0 +1,102 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Return a soft nodeAffinity definition +{{ include "common.affinities.nodes.soft" (dict "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.nodes.soft" -}} +preferredDuringSchedulingIgnoredDuringExecution: + - preference: + matchExpressions: + - key: {{ .key }} + operator: In + values: + {{- range .values }} + - {{ . | quote }} + {{- end }} + weight: 1 +{{- end -}} + +{{/* +Return a hard nodeAffinity definition +{{ include "common.affinities.nodes.hard" (dict "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.nodes.hard" -}} +requiredDuringSchedulingIgnoredDuringExecution: + nodeSelectorTerms: + - matchExpressions: + - key: {{ .key }} + operator: In + values: + {{- range .values }} + - {{ . | quote }} + {{- end }} +{{- end -}} + +{{/* +Return a nodeAffinity definition +{{ include "common.affinities.nodes" (dict "type" "soft" "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.nodes" -}} + {{- if eq .type "soft" }} + {{- include "common.affinities.nodes.soft" . -}} + {{- else if eq .type "hard" }} + {{- include "common.affinities.nodes.hard" . -}} + {{- end -}} +{{- end -}} + +{{/* +Return a soft podAffinity/podAntiAffinity definition +{{ include "common.affinities.pods.soft" (dict "component" "FOO" "extraMatchLabels" .Values.extraMatchLabels "context" $) -}} +*/}} +{{- define "common.affinities.pods.soft" -}} +{{- $component := default "" .component -}} +{{- $extraMatchLabels := default (dict) .extraMatchLabels -}} +preferredDuringSchedulingIgnoredDuringExecution: + - podAffinityTerm: + labelSelector: + matchLabels: {{- (include "common.labels.matchLabels" .context) | nindent 10 }} + {{- if not (empty $component) }} + {{ printf "app.kubernetes.io/component: %s" $component }} + {{- end }} + {{- range $key, $value := $extraMatchLabels }} + {{ $key }}: {{ $value | quote }} + {{- end }} + namespaces: + - {{ include "common.names.namespace" .context | quote }} + topologyKey: kubernetes.io/hostname + weight: 1 +{{- end -}} + +{{/* +Return a hard podAffinity/podAntiAffinity definition +{{ include "common.affinities.pods.hard" (dict "component" "FOO" "extraMatchLabels" .Values.extraMatchLabels "context" $) -}} +*/}} +{{- define "common.affinities.pods.hard" -}} +{{- $component := default "" .component -}} +{{- $extraMatchLabels := default (dict) .extraMatchLabels -}} +requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: {{- (include "common.labels.matchLabels" .context) | nindent 8 }} + {{- if not (empty $component) }} + {{ printf "app.kubernetes.io/component: %s" $component }} + {{- end }} + {{- range $key, $value := $extraMatchLabels }} + {{ $key }}: {{ $value | quote }} + {{- end }} + namespaces: + - {{ include "common.names.namespace" .context | quote }} + topologyKey: kubernetes.io/hostname +{{- end -}} + +{{/* +Return a podAffinity/podAntiAffinity definition +{{ include "common.affinities.pods" (dict "type" "soft" "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.pods" -}} + {{- if eq .type "soft" }} + {{- include "common.affinities.pods.soft" . -}} + {{- else if eq .type "hard" }} + {{- include "common.affinities.pods.hard" . -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_capabilities.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_capabilities.tpl new file mode 100644 index 0000000..9d9b760 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_capabilities.tpl @@ -0,0 +1,154 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Return the target Kubernetes version +*/}} +{{- define "common.capabilities.kubeVersion" -}} +{{- if .Values.global }} + {{- if .Values.global.kubeVersion }} + {{- .Values.global.kubeVersion -}} + {{- else }} + {{- default .Capabilities.KubeVersion.Version .Values.kubeVersion -}} + {{- end -}} +{{- else }} +{{- default .Capabilities.KubeVersion.Version .Values.kubeVersion -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for poddisruptionbudget. +*/}} +{{- define "common.capabilities.policy.apiVersion" -}} +{{- if semverCompare "<1.21-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "policy/v1beta1" -}} +{{- else -}} +{{- print "policy/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for networkpolicy. +*/}} +{{- define "common.capabilities.networkPolicy.apiVersion" -}} +{{- if semverCompare "<1.7-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for cronjob. +*/}} +{{- define "common.capabilities.cronjob.apiVersion" -}} +{{- if semverCompare "<1.21-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "batch/v1beta1" -}} +{{- else -}} +{{- print "batch/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for deployment. +*/}} +{{- define "common.capabilities.deployment.apiVersion" -}} +{{- if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else -}} +{{- print "apps/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for statefulset. +*/}} +{{- define "common.capabilities.statefulset.apiVersion" -}} +{{- if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "apps/v1beta1" -}} +{{- else -}} +{{- print "apps/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "common.capabilities.ingress.apiVersion" -}} +{{- if .Values.ingress -}} +{{- if .Values.ingress.apiVersion -}} +{{- .Values.ingress.apiVersion -}} +{{- else if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else if semverCompare "<1.19-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "networking.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end }} +{{- else if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else if semverCompare "<1.19-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "networking.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for RBAC resources. +*/}} +{{- define "common.capabilities.rbac.apiVersion" -}} +{{- if semverCompare "<1.17-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "rbac.authorization.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "rbac.authorization.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for CRDs. +*/}} +{{- define "common.capabilities.crd.apiVersion" -}} +{{- if semverCompare "<1.19-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "apiextensions.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "apiextensions.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for APIService. +*/}} +{{- define "common.capabilities.apiService.apiVersion" -}} +{{- if semverCompare "<1.10-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "apiregistration.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "apiregistration.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for Horizontal Pod Autoscaler. +*/}} +{{- define "common.capabilities.hpa.apiVersion" -}} +{{- if semverCompare "<1.23-0" (include "common.capabilities.kubeVersion" .context) -}} +{{- if .beta2 -}} +{{- print "autoscaling/v2beta2" -}} +{{- else -}} +{{- print "autoscaling/v2beta1" -}} +{{- end -}} +{{- else -}} +{{- print "autoscaling/v2" -}} +{{- end -}} +{{- end -}} + +{{/* +Returns true if the used Helm version is 3.3+. +A way to check the used Helm version was not introduced until version 3.3.0 with .Capabilities.HelmVersion, which contains an additional "{}}" structure. +This check is introduced as a regexMatch instead of {{ if .Capabilities.HelmVersion }} because checking for the key HelmVersion in <3.3 results in a "interface not found" error. +**To be removed when the catalog's minimun Helm version is 3.3** +*/}} +{{- define "common.capabilities.supportsHelmVersion" -}} +{{- if regexMatch "{(v[0-9])*[^}]*}}$" (.Capabilities | toString ) }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_errors.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_errors.tpl new file mode 100644 index 0000000..a79cc2e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_errors.tpl @@ -0,0 +1,23 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Through error when upgrading using empty passwords values that must not be empty. + +Usage: +{{- $validationError00 := include "common.validations.values.single.empty" (dict "valueKey" "path.to.password00" "secret" "secretName" "field" "password-00") -}} +{{- $validationError01 := include "common.validations.values.single.empty" (dict "valueKey" "path.to.password01" "secret" "secretName" "field" "password-01") -}} +{{ include "common.errors.upgrade.passwords.empty" (dict "validationErrors" (list $validationError00 $validationError01) "context" $) }} + +Required password params: + - validationErrors - String - Required. List of validation strings to be return, if it is empty it won't throw error. + - context - Context - Required. Parent context. +*/}} +{{- define "common.errors.upgrade.passwords.empty" -}} + {{- $validationErrors := join "" .validationErrors -}} + {{- if and $validationErrors .context.Release.IsUpgrade -}} + {{- $errorString := "\nPASSWORDS ERROR: You must provide your current passwords when upgrading the release." -}} + {{- $errorString = print $errorString "\n Note that even after reinstallation, old credentials may be needed as they may be kept in persistent volume claims." -}} + {{- $errorString = print $errorString "\n Further information can be obtained at https://docs.bitnami.com/general/how-to/troubleshoot-helm-chart-issues/#credential-errors-while-upgrading-chart-releases" -}} + {{- $errorString = print $errorString "\n%s" -}} + {{- printf $errorString $validationErrors | fail -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_images.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_images.tpl new file mode 100644 index 0000000..46c659e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_images.tpl @@ -0,0 +1,76 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Return the proper image name +{{ include "common.images.image" ( dict "imageRoot" .Values.path.to.the.image "global" $) }} +*/}} +{{- define "common.images.image" -}} +{{- $registryName := .imageRoot.registry -}} +{{- $repositoryName := .imageRoot.repository -}} +{{- $separator := ":" -}} +{{- $termination := .imageRoot.tag | toString -}} +{{- if .global }} + {{- if .global.imageRegistry }} + {{- $registryName = .global.imageRegistry -}} + {{- end -}} +{{- end -}} +{{- if .imageRoot.digest }} + {{- $separator = "@" -}} + {{- $termination = .imageRoot.digest | toString -}} +{{- end -}} +{{- printf "%s/%s%s%s" $registryName $repositoryName $separator $termination -}} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names (deprecated: use common.images.renderPullSecrets instead) +{{ include "common.images.pullSecrets" ( dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "global" .Values.global) }} +*/}} +{{- define "common.images.pullSecrets" -}} + {{- $pullSecrets := list }} + + {{- if .global }} + {{- range .global.imagePullSecrets -}} + {{- $pullSecrets = append $pullSecrets . -}} + {{- end -}} + {{- end -}} + + {{- range .images -}} + {{- range .pullSecrets -}} + {{- $pullSecrets = append $pullSecrets . -}} + {{- end -}} + {{- end -}} + + {{- if (not (empty $pullSecrets)) }} +imagePullSecrets: + {{- range $pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names evaluating values as templates +{{ include "common.images.renderPullSecrets" ( dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "context" $) }} +*/}} +{{- define "common.images.renderPullSecrets" -}} + {{- $pullSecrets := list }} + {{- $context := .context }} + + {{- if $context.Values.global }} + {{- range $context.Values.global.imagePullSecrets -}} + {{- $pullSecrets = append $pullSecrets (include "common.tplvalues.render" (dict "value" . "context" $context)) -}} + {{- end -}} + {{- end -}} + + {{- range .images -}} + {{- range .pullSecrets -}} + {{- $pullSecrets = append $pullSecrets (include "common.tplvalues.render" (dict "value" . "context" $context)) -}} + {{- end -}} + {{- end -}} + + {{- if (not (empty $pullSecrets)) }} +imagePullSecrets: + {{- range $pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_ingress.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_ingress.tpl new file mode 100644 index 0000000..8caf73a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_ingress.tpl @@ -0,0 +1,68 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Generate backend entry that is compatible with all Kubernetes API versions. + +Usage: +{{ include "common.ingress.backend" (dict "serviceName" "backendName" "servicePort" "backendPort" "context" $) }} + +Params: + - serviceName - String. Name of an existing service backend + - servicePort - String/Int. Port name (or number) of the service. It will be translated to different yaml depending if it is a string or an integer. + - context - Dict - Required. The context for the template evaluation. +*/}} +{{- define "common.ingress.backend" -}} +{{- $apiVersion := (include "common.capabilities.ingress.apiVersion" .context) -}} +{{- if or (eq $apiVersion "extensions/v1beta1") (eq $apiVersion "networking.k8s.io/v1beta1") -}} +serviceName: {{ .serviceName }} +servicePort: {{ .servicePort }} +{{- else -}} +service: + name: {{ .serviceName }} + port: + {{- if typeIs "string" .servicePort }} + name: {{ .servicePort }} + {{- else if or (typeIs "int" .servicePort) (typeIs "float64" .servicePort) }} + number: {{ .servicePort | int }} + {{- end }} +{{- end -}} +{{- end -}} + +{{/* +Print "true" if the API pathType field is supported +Usage: +{{ include "common.ingress.supportsPathType" . }} +*/}} +{{- define "common.ingress.supportsPathType" -}} +{{- if (semverCompare "<1.18-0" (include "common.capabilities.kubeVersion" .)) -}} +{{- print "false" -}} +{{- else -}} +{{- print "true" -}} +{{- end -}} +{{- end -}} + +{{/* +Returns true if the ingressClassname field is supported +Usage: +{{ include "common.ingress.supportsIngressClassname" . }} +*/}} +{{- define "common.ingress.supportsIngressClassname" -}} +{{- if semverCompare "<1.18-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "false" -}} +{{- else -}} +{{- print "true" -}} +{{- end -}} +{{- end -}} + +{{/* +Return true if cert-manager required annotations for TLS signed +certificates are set in the Ingress annotations +Ref: https://cert-manager.io/docs/usage/ingress/#supported-annotations +Usage: +{{ include "common.ingress.certManagerRequest" ( dict "annotations" .Values.path.to.the.ingress.annotations ) }} +*/}} +{{- define "common.ingress.certManagerRequest" -}} +{{ if or (hasKey .annotations "cert-manager.io/cluster-issuer") (hasKey .annotations "cert-manager.io/issuer") }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_labels.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_labels.tpl new file mode 100644 index 0000000..252066c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_labels.tpl @@ -0,0 +1,18 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Kubernetes standard labels +*/}} +{{- define "common.labels.standard" -}} +app.kubernetes.io/name: {{ include "common.names.name" . }} +helm.sh/chart: {{ include "common.names.chart" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end -}} + +{{/* +Labels to use on deploy.spec.selector.matchLabels and svc.spec.selector +*/}} +{{- define "common.labels.matchLabels" -}} +app.kubernetes.io/name: {{ include "common.names.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_names.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_names.tpl new file mode 100644 index 0000000..1bdac8b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_names.tpl @@ -0,0 +1,70 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "common.names.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "common.names.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "common.names.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Create a default fully qualified dependency name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +Usage: +{{ include "common.names.dependency.fullname" (dict "chartName" "dependency-chart-name" "chartValues" .Values.dependency-chart "context" $) }} +*/}} +{{- define "common.names.dependency.fullname" -}} +{{- if .chartValues.fullnameOverride -}} +{{- .chartValues.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .chartName .chartValues.nameOverride -}} +{{- if contains $name .context.Release.Name -}} +{{- .context.Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .context.Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts. +*/}} +{{- define "common.names.namespace" -}} +{{- if .Values.namespaceOverride -}} +{{- .Values.namespaceOverride -}} +{{- else -}} +{{- .Release.Namespace -}} +{{- end -}} +{{- end -}} + +{{/* +Create a fully qualified app name adding the installation's namespace. +*/}} +{{- define "common.names.fullname.namespace" -}} +{{- printf "%s-%s" (include "common.names.fullname" .) (include "common.names.namespace" .) | trunc 63 | trimSuffix "-" -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_secrets.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_secrets.tpl new file mode 100644 index 0000000..a53fb44 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_secrets.tpl @@ -0,0 +1,140 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Generate secret name. + +Usage: +{{ include "common.secrets.name" (dict "existingSecret" .Values.path.to.the.existingSecret "defaultNameSuffix" "mySuffix" "context" $) }} + +Params: + - existingSecret - ExistingSecret/String - Optional. The path to the existing secrets in the values.yaml given by the user + to be used instead of the default one. Allows for it to be of type String (just the secret name) for backwards compatibility. + +info: https://github.com/bitnami/charts/tree/master/bitnami/common#existingsecret + - defaultNameSuffix - String - Optional. It is used only if we have several secrets in the same deployment. + - context - Dict - Required. The context for the template evaluation. +*/}} +{{- define "common.secrets.name" -}} +{{- $name := (include "common.names.fullname" .context) -}} + +{{- if .defaultNameSuffix -}} +{{- $name = printf "%s-%s" $name .defaultNameSuffix | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{- with .existingSecret -}} +{{- if not (typeIs "string" .) -}} +{{- with .name -}} +{{- $name = . -}} +{{- end -}} +{{- else -}} +{{- $name = . -}} +{{- end -}} +{{- end -}} + +{{- printf "%s" $name -}} +{{- end -}} + +{{/* +Generate secret key. + +Usage: +{{ include "common.secrets.key" (dict "existingSecret" .Values.path.to.the.existingSecret "key" "keyName") }} + +Params: + - existingSecret - ExistingSecret/String - Optional. The path to the existing secrets in the values.yaml given by the user + to be used instead of the default one. Allows for it to be of type String (just the secret name) for backwards compatibility. + +info: https://github.com/bitnami/charts/tree/master/bitnami/common#existingsecret + - key - String - Required. Name of the key in the secret. +*/}} +{{- define "common.secrets.key" -}} +{{- $key := .key -}} + +{{- if .existingSecret -}} + {{- if not (typeIs "string" .existingSecret) -}} + {{- if .existingSecret.keyMapping -}} + {{- $key = index .existingSecret.keyMapping $.key -}} + {{- end -}} + {{- end }} +{{- end -}} + +{{- printf "%s" $key -}} +{{- end -}} + +{{/* +Generate secret password or retrieve one if already created. + +Usage: +{{ include "common.secrets.passwords.manage" (dict "secret" "secret-name" "key" "keyName" "providedValues" (list "path.to.password1" "path.to.password2") "length" 10 "strong" false "chartName" "chartName" "context" $) }} + +Params: + - secret - String - Required - Name of the 'Secret' resource where the password is stored. + - key - String - Required - Name of the key in the secret. + - providedValues - List - Required - The path to the validating value in the values.yaml, e.g: "mysql.password". Will pick first parameter with a defined value. + - length - int - Optional - Length of the generated random password. + - strong - Boolean - Optional - Whether to add symbols to the generated random password. + - chartName - String - Optional - Name of the chart used when said chart is deployed as a subchart. + - context - Context - Required - Parent context. + +The order in which this function returns a secret password: + 1. Already existing 'Secret' resource + (If a 'Secret' resource is found under the name provided to the 'secret' parameter to this function and that 'Secret' resource contains a key with the name passed as the 'key' parameter to this function then the value of this existing secret password will be returned) + 2. Password provided via the values.yaml + (If one of the keys passed to the 'providedValues' parameter to this function is a valid path to a key in the values.yaml and has a value, the value of the first key with a value will be returned) + 3. Randomly generated secret password + (A new random secret password with the length specified in the 'length' parameter will be generated and returned) + +*/}} +{{- define "common.secrets.passwords.manage" -}} + +{{- $password := "" }} +{{- $subchart := "" }} +{{- $chartName := default "" .chartName }} +{{- $passwordLength := default 10 .length }} +{{- $providedPasswordKey := include "common.utils.getKeyFromList" (dict "keys" .providedValues "context" $.context) }} +{{- $providedPasswordValue := include "common.utils.getValueFromKey" (dict "key" $providedPasswordKey "context" $.context) }} +{{- $secretData := (lookup "v1" "Secret" $.context.Release.Namespace .secret).data }} +{{- if $secretData }} + {{- if hasKey $secretData .key }} + {{- $password = index $secretData .key }} + {{- else }} + {{- printf "\nPASSWORDS ERROR: The secret \"%s\" does not contain the key \"%s\"\n" .secret .key | fail -}} + {{- end -}} +{{- else if $providedPasswordValue }} + {{- $password = $providedPasswordValue | toString | b64enc | quote }} +{{- else }} + + {{- if .context.Values.enabled }} + {{- $subchart = $chartName }} + {{- end -}} + + {{- $requiredPassword := dict "valueKey" $providedPasswordKey "secret" .secret "field" .key "subchart" $subchart "context" $.context -}} + {{- $requiredPasswordError := include "common.validations.values.single.empty" $requiredPassword -}} + {{- $passwordValidationErrors := list $requiredPasswordError -}} + {{- include "common.errors.upgrade.passwords.empty" (dict "validationErrors" $passwordValidationErrors "context" $.context) -}} + + {{- if .strong }} + {{- $subStr := list (lower (randAlpha 1)) (randNumeric 1) (upper (randAlpha 1)) | join "_" }} + {{- $password = randAscii $passwordLength }} + {{- $password = regexReplaceAllLiteral "\\W" $password "@" | substr 5 $passwordLength }} + {{- $password = printf "%s%s" $subStr $password | toString | shuffle | b64enc | quote }} + {{- else }} + {{- $password = randAlphaNum $passwordLength | b64enc | quote }} + {{- end }} +{{- end -}} +{{- printf "%s" $password -}} +{{- end -}} + +{{/* +Returns whether a previous generated secret already exists + +Usage: +{{ include "common.secrets.exists" (dict "secret" "secret-name" "context" $) }} + +Params: + - secret - String - Required - Name of the 'Secret' resource where the password is stored. + - context - Context - Required - Parent context. +*/}} +{{- define "common.secrets.exists" -}} +{{- $secret := (lookup "v1" "Secret" $.context.Release.Namespace .secret) }} +{{- if $secret }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_storage.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_storage.tpl new file mode 100644 index 0000000..60e2a84 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_storage.tpl @@ -0,0 +1,23 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Return the proper Storage Class +{{ include "common.storage.class" ( dict "persistence" .Values.path.to.the.persistence "global" $) }} +*/}} +{{- define "common.storage.class" -}} + +{{- $storageClass := .persistence.storageClass -}} +{{- if .global -}} + {{- if .global.storageClass -}} + {{- $storageClass = .global.storageClass -}} + {{- end -}} +{{- end -}} + +{{- if $storageClass -}} + {{- if (eq "-" $storageClass) -}} + {{- printf "storageClassName: \"\"" -}} + {{- else }} + {{- printf "storageClassName: %s" $storageClass -}} + {{- end -}} +{{- end -}} + +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_tplvalues.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_tplvalues.tpl new file mode 100644 index 0000000..2db1668 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_tplvalues.tpl @@ -0,0 +1,13 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Renders a value that contains template. +Usage: +{{ include "common.tplvalues.render" ( dict "value" .Values.path.to.the.Value "context" $) }} +*/}} +{{- define "common.tplvalues.render" -}} + {{- if typeIs "string" .value }} + {{- tpl .value .context }} + {{- else }} + {{- tpl (.value | toYaml) .context }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_utils.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_utils.tpl new file mode 100644 index 0000000..8c22b2a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_utils.tpl @@ -0,0 +1,62 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Print instructions to get a secret value. +Usage: +{{ include "common.utils.secret.getvalue" (dict "secret" "secret-name" "field" "secret-value-field" "context" $) }} +*/}} +{{- define "common.utils.secret.getvalue" -}} +{{- $varname := include "common.utils.fieldToEnvVar" . -}} +export {{ $varname }}=$(kubectl get secret --namespace {{ .context.Release.Namespace | quote }} {{ .secret }} -o jsonpath="{.data.{{ .field }}}" | base64 -d) +{{- end -}} + +{{/* +Build env var name given a field +Usage: +{{ include "common.utils.fieldToEnvVar" dict "field" "my-password" }} +*/}} +{{- define "common.utils.fieldToEnvVar" -}} + {{- $fieldNameSplit := splitList "-" .field -}} + {{- $upperCaseFieldNameSplit := list -}} + + {{- range $fieldNameSplit -}} + {{- $upperCaseFieldNameSplit = append $upperCaseFieldNameSplit ( upper . ) -}} + {{- end -}} + + {{ join "_" $upperCaseFieldNameSplit }} +{{- end -}} + +{{/* +Gets a value from .Values given +Usage: +{{ include "common.utils.getValueFromKey" (dict "key" "path.to.key" "context" $) }} +*/}} +{{- define "common.utils.getValueFromKey" -}} +{{- $splitKey := splitList "." .key -}} +{{- $value := "" -}} +{{- $latestObj := $.context.Values -}} +{{- range $splitKey -}} + {{- if not $latestObj -}} + {{- printf "please review the entire path of '%s' exists in values" $.key | fail -}} + {{- end -}} + {{- $value = ( index $latestObj . ) -}} + {{- $latestObj = $value -}} +{{- end -}} +{{- printf "%v" (default "" $value) -}} +{{- end -}} + +{{/* +Returns first .Values key with a defined value or first of the list if all non-defined +Usage: +{{ include "common.utils.getKeyFromList" (dict "keys" (list "path.to.key1" "path.to.key2") "context" $) }} +*/}} +{{- define "common.utils.getKeyFromList" -}} +{{- $key := first .keys -}} +{{- $reverseKeys := reverse .keys }} +{{- range $reverseKeys }} + {{- $value := include "common.utils.getValueFromKey" (dict "key" . "context" $.context ) }} + {{- if $value -}} + {{- $key = . }} + {{- end -}} +{{- end -}} +{{- printf "%s" $key -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_warnings.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_warnings.tpl new file mode 100644 index 0000000..ae10fa4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/_warnings.tpl @@ -0,0 +1,14 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Warning about using rolling tag. +Usage: +{{ include "common.warnings.rollingTag" .Values.path.to.the.imageRoot }} +*/}} +{{- define "common.warnings.rollingTag" -}} + +{{- if and (contains "bitnami/" .repository) (not (.tag | toString | regexFind "-r\\d+$|sha256:")) }} +WARNING: Rolling tag detected ({{ .repository }}:{{ .tag }}), please note that it is strongly recommended to avoid using rolling tags in a production environment. ++info https://docs.bitnami.com/containers/how-to/understand-rolling-tags-containers/ +{{- end }} + +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_cassandra.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_cassandra.tpl new file mode 100644 index 0000000..ded1ae3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_cassandra.tpl @@ -0,0 +1,72 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate Cassandra required passwords are not empty. + +Usage: +{{ include "common.validations.values.cassandra.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where Cassandra values are stored, e.g: "cassandra-passwords-secret" + - subchart - Boolean - Optional. Whether Cassandra is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.cassandra.passwords" -}} + {{- $existingSecret := include "common.cassandra.values.existingSecret" . -}} + {{- $enabled := include "common.cassandra.values.enabled" . -}} + {{- $dbUserPrefix := include "common.cassandra.values.key.dbUser" . -}} + {{- $valueKeyPassword := printf "%s.password" $dbUserPrefix -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "cassandra-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.cassandra.values.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether Cassandra is used as subchart or not. Default: false +*/}} +{{- define "common.cassandra.values.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.cassandra.dbUser.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.dbUser.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled cassandra. + +Usage: +{{ include "common.cassandra.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.cassandra.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.cassandra.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key dbUser + +Usage: +{{ include "common.cassandra.values.key.dbUser" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether Cassandra is used as subchart or not. Default: false +*/}} +{{- define "common.cassandra.values.key.dbUser" -}} + {{- if .subchart -}} + cassandra.dbUser + {{- else -}} + dbUser + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_mariadb.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_mariadb.tpl new file mode 100644 index 0000000..b6906ff --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_mariadb.tpl @@ -0,0 +1,103 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate MariaDB required passwords are not empty. + +Usage: +{{ include "common.validations.values.mariadb.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where MariaDB values are stored, e.g: "mysql-passwords-secret" + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.mariadb.passwords" -}} + {{- $existingSecret := include "common.mariadb.values.auth.existingSecret" . -}} + {{- $enabled := include "common.mariadb.values.enabled" . -}} + {{- $architecture := include "common.mariadb.values.architecture" . -}} + {{- $authPrefix := include "common.mariadb.values.key.auth" . -}} + {{- $valueKeyRootPassword := printf "%s.rootPassword" $authPrefix -}} + {{- $valueKeyUsername := printf "%s.username" $authPrefix -}} + {{- $valueKeyPassword := printf "%s.password" $authPrefix -}} + {{- $valueKeyReplicationPassword := printf "%s.replicationPassword" $authPrefix -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredRootPassword := dict "valueKey" $valueKeyRootPassword "secret" .secret "field" "mariadb-root-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRootPassword -}} + + {{- $valueUsername := include "common.utils.getValueFromKey" (dict "key" $valueKeyUsername "context" .context) }} + {{- if not (empty $valueUsername) -}} + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "mariadb-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + {{- end -}} + + {{- if (eq $architecture "replication") -}} + {{- $requiredReplicationPassword := dict "valueKey" $valueKeyReplicationPassword "secret" .secret "field" "mariadb-replication-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredReplicationPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.mariadb.values.auth.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.mariadb.values.auth.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.mariadb.auth.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.auth.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled mariadb. + +Usage: +{{ include "common.mariadb.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.mariadb.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.mariadb.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for architecture + +Usage: +{{ include "common.mariadb.values.architecture" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.mariadb.values.architecture" -}} + {{- if .subchart -}} + {{- .context.Values.mariadb.architecture -}} + {{- else -}} + {{- .context.Values.architecture -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key auth + +Usage: +{{ include "common.mariadb.values.key.auth" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.mariadb.values.key.auth" -}} + {{- if .subchart -}} + mariadb.auth + {{- else -}} + auth + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_mongodb.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_mongodb.tpl new file mode 100644 index 0000000..f820ec1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_mongodb.tpl @@ -0,0 +1,108 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate MongoDB® required passwords are not empty. + +Usage: +{{ include "common.validations.values.mongodb.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where MongoDB® values are stored, e.g: "mongodb-passwords-secret" + - subchart - Boolean - Optional. Whether MongoDB® is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.mongodb.passwords" -}} + {{- $existingSecret := include "common.mongodb.values.auth.existingSecret" . -}} + {{- $enabled := include "common.mongodb.values.enabled" . -}} + {{- $authPrefix := include "common.mongodb.values.key.auth" . -}} + {{- $architecture := include "common.mongodb.values.architecture" . -}} + {{- $valueKeyRootPassword := printf "%s.rootPassword" $authPrefix -}} + {{- $valueKeyUsername := printf "%s.username" $authPrefix -}} + {{- $valueKeyDatabase := printf "%s.database" $authPrefix -}} + {{- $valueKeyPassword := printf "%s.password" $authPrefix -}} + {{- $valueKeyReplicaSetKey := printf "%s.replicaSetKey" $authPrefix -}} + {{- $valueKeyAuthEnabled := printf "%s.enabled" $authPrefix -}} + + {{- $authEnabled := include "common.utils.getValueFromKey" (dict "key" $valueKeyAuthEnabled "context" .context) -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") (eq $authEnabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredRootPassword := dict "valueKey" $valueKeyRootPassword "secret" .secret "field" "mongodb-root-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRootPassword -}} + + {{- $valueUsername := include "common.utils.getValueFromKey" (dict "key" $valueKeyUsername "context" .context) }} + {{- $valueDatabase := include "common.utils.getValueFromKey" (dict "key" $valueKeyDatabase "context" .context) }} + {{- if and $valueUsername $valueDatabase -}} + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "mongodb-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + {{- end -}} + + {{- if (eq $architecture "replicaset") -}} + {{- $requiredReplicaSetKey := dict "valueKey" $valueKeyReplicaSetKey "secret" .secret "field" "mongodb-replica-set-key" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredReplicaSetKey -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.mongodb.values.auth.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MongoDb is used as subchart or not. Default: false +*/}} +{{- define "common.mongodb.values.auth.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.mongodb.auth.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.auth.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled mongodb. + +Usage: +{{ include "common.mongodb.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.mongodb.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.mongodb.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key auth + +Usage: +{{ include "common.mongodb.values.key.auth" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MongoDB® is used as subchart or not. Default: false +*/}} +{{- define "common.mongodb.values.key.auth" -}} + {{- if .subchart -}} + mongodb.auth + {{- else -}} + auth + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for architecture + +Usage: +{{ include "common.mongodb.values.architecture" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MongoDB® is used as subchart or not. Default: false +*/}} +{{- define "common.mongodb.values.architecture" -}} + {{- if .subchart -}} + {{- .context.Values.mongodb.architecture -}} + {{- else -}} + {{- .context.Values.architecture -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_mysql.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_mysql.tpl new file mode 100644 index 0000000..74472a0 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_mysql.tpl @@ -0,0 +1,103 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate MySQL required passwords are not empty. + +Usage: +{{ include "common.validations.values.mysql.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where MySQL values are stored, e.g: "mysql-passwords-secret" + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.mysql.passwords" -}} + {{- $existingSecret := include "common.mysql.values.auth.existingSecret" . -}} + {{- $enabled := include "common.mysql.values.enabled" . -}} + {{- $architecture := include "common.mysql.values.architecture" . -}} + {{- $authPrefix := include "common.mysql.values.key.auth" . -}} + {{- $valueKeyRootPassword := printf "%s.rootPassword" $authPrefix -}} + {{- $valueKeyUsername := printf "%s.username" $authPrefix -}} + {{- $valueKeyPassword := printf "%s.password" $authPrefix -}} + {{- $valueKeyReplicationPassword := printf "%s.replicationPassword" $authPrefix -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredRootPassword := dict "valueKey" $valueKeyRootPassword "secret" .secret "field" "mysql-root-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRootPassword -}} + + {{- $valueUsername := include "common.utils.getValueFromKey" (dict "key" $valueKeyUsername "context" .context) }} + {{- if not (empty $valueUsername) -}} + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "mysql-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + {{- end -}} + + {{- if (eq $architecture "replication") -}} + {{- $requiredReplicationPassword := dict "valueKey" $valueKeyReplicationPassword "secret" .secret "field" "mysql-replication-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredReplicationPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.mysql.values.auth.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.mysql.values.auth.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.mysql.auth.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.auth.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled mysql. + +Usage: +{{ include "common.mysql.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.mysql.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.mysql.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for architecture + +Usage: +{{ include "common.mysql.values.architecture" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.mysql.values.architecture" -}} + {{- if .subchart -}} + {{- .context.Values.mysql.architecture -}} + {{- else -}} + {{- .context.Values.architecture -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key auth + +Usage: +{{ include "common.mysql.values.key.auth" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.mysql.values.key.auth" -}} + {{- if .subchart -}} + mysql.auth + {{- else -}} + auth + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_postgresql.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_postgresql.tpl new file mode 100644 index 0000000..164ec0d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_postgresql.tpl @@ -0,0 +1,129 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate PostgreSQL required passwords are not empty. + +Usage: +{{ include "common.validations.values.postgresql.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where postgresql values are stored, e.g: "postgresql-passwords-secret" + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.postgresql.passwords" -}} + {{- $existingSecret := include "common.postgresql.values.existingSecret" . -}} + {{- $enabled := include "common.postgresql.values.enabled" . -}} + {{- $valueKeyPostgresqlPassword := include "common.postgresql.values.key.postgressPassword" . -}} + {{- $valueKeyPostgresqlReplicationEnabled := include "common.postgresql.values.key.replicationPassword" . -}} + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + {{- $requiredPostgresqlPassword := dict "valueKey" $valueKeyPostgresqlPassword "secret" .secret "field" "postgresql-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPostgresqlPassword -}} + + {{- $enabledReplication := include "common.postgresql.values.enabled.replication" . -}} + {{- if (eq $enabledReplication "true") -}} + {{- $requiredPostgresqlReplicationPassword := dict "valueKey" $valueKeyPostgresqlReplicationEnabled "secret" .secret "field" "postgresql-replication-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPostgresqlReplicationPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to decide whether evaluate global values. + +Usage: +{{ include "common.postgresql.values.use.global" (dict "key" "key-of-global" "context" $) }} +Params: + - key - String - Required. Field to be evaluated within global, e.g: "existingSecret" +*/}} +{{- define "common.postgresql.values.use.global" -}} + {{- if .context.Values.global -}} + {{- if .context.Values.global.postgresql -}} + {{- index .context.Values.global.postgresql .key | quote -}} + {{- end -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.postgresql.values.existingSecret" (dict "context" $) }} +*/}} +{{- define "common.postgresql.values.existingSecret" -}} + {{- $globalValue := include "common.postgresql.values.use.global" (dict "key" "existingSecret" "context" .context) -}} + + {{- if .subchart -}} + {{- default (.context.Values.postgresql.existingSecret | quote) $globalValue -}} + {{- else -}} + {{- default (.context.Values.existingSecret | quote) $globalValue -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled postgresql. + +Usage: +{{ include "common.postgresql.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.postgresql.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.postgresql.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key postgressPassword. + +Usage: +{{ include "common.postgresql.values.key.postgressPassword" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.postgresql.values.key.postgressPassword" -}} + {{- $globalValue := include "common.postgresql.values.use.global" (dict "key" "postgresqlUsername" "context" .context) -}} + + {{- if not $globalValue -}} + {{- if .subchart -}} + postgresql.postgresqlPassword + {{- else -}} + postgresqlPassword + {{- end -}} + {{- else -}} + global.postgresql.postgresqlPassword + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled.replication. + +Usage: +{{ include "common.postgresql.values.enabled.replication" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.postgresql.values.enabled.replication" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.postgresql.replication.enabled -}} + {{- else -}} + {{- printf "%v" .context.Values.replication.enabled -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key replication.password. + +Usage: +{{ include "common.postgresql.values.key.replicationPassword" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.postgresql.values.key.replicationPassword" -}} + {{- if .subchart -}} + postgresql.replication.password + {{- else -}} + replication.password + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_redis.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_redis.tpl new file mode 100644 index 0000000..dcccfc1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_redis.tpl @@ -0,0 +1,76 @@ + +{{/* vim: set filetype=mustache: */}} +{{/* +Validate Redis® required passwords are not empty. + +Usage: +{{ include "common.validations.values.redis.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where redis values are stored, e.g: "redis-passwords-secret" + - subchart - Boolean - Optional. Whether redis is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.redis.passwords" -}} + {{- $enabled := include "common.redis.values.enabled" . -}} + {{- $valueKeyPrefix := include "common.redis.values.keys.prefix" . -}} + {{- $standarizedVersion := include "common.redis.values.standarized.version" . }} + + {{- $existingSecret := ternary (printf "%s%s" $valueKeyPrefix "auth.existingSecret") (printf "%s%s" $valueKeyPrefix "existingSecret") (eq $standarizedVersion "true") }} + {{- $existingSecretValue := include "common.utils.getValueFromKey" (dict "key" $existingSecret "context" .context) }} + + {{- $valueKeyRedisPassword := ternary (printf "%s%s" $valueKeyPrefix "auth.password") (printf "%s%s" $valueKeyPrefix "password") (eq $standarizedVersion "true") }} + {{- $valueKeyRedisUseAuth := ternary (printf "%s%s" $valueKeyPrefix "auth.enabled") (printf "%s%s" $valueKeyPrefix "usePassword") (eq $standarizedVersion "true") }} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $useAuth := include "common.utils.getValueFromKey" (dict "key" $valueKeyRedisUseAuth "context" .context) -}} + {{- if eq $useAuth "true" -}} + {{- $requiredRedisPassword := dict "valueKey" $valueKeyRedisPassword "secret" .secret "field" "redis-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRedisPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled redis. + +Usage: +{{ include "common.redis.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.redis.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.redis.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right prefix path for the values + +Usage: +{{ include "common.redis.values.key.prefix" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether redis is used as subchart or not. Default: false +*/}} +{{- define "common.redis.values.keys.prefix" -}} + {{- if .subchart -}}redis.{{- else -}}{{- end -}} +{{- end -}} + +{{/* +Checks whether the redis chart's includes the standarizations (version >= 14) + +Usage: +{{ include "common.redis.values.standarized.version" (dict "context" $) }} +*/}} +{{- define "common.redis.values.standarized.version" -}} + + {{- $standarizedAuth := printf "%s%s" (include "common.redis.values.keys.prefix" .) "auth" -}} + {{- $standarizedAuthValues := include "common.utils.getValueFromKey" (dict "key" $standarizedAuth "context" .context) }} + + {{- if $standarizedAuthValues -}} + {{- true -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_validations.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_validations.tpl new file mode 100644 index 0000000..9a814cf --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/templates/validations/_validations.tpl @@ -0,0 +1,46 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate values must not be empty. + +Usage: +{{- $validateValueConf00 := (dict "valueKey" "path.to.value" "secret" "secretName" "field" "password-00") -}} +{{- $validateValueConf01 := (dict "valueKey" "path.to.value" "secret" "secretName" "field" "password-01") -}} +{{ include "common.validations.values.empty" (dict "required" (list $validateValueConf00 $validateValueConf01) "context" $) }} + +Validate value params: + - valueKey - String - Required. The path to the validating value in the values.yaml, e.g: "mysql.password" + - secret - String - Optional. Name of the secret where the validating value is generated/stored, e.g: "mysql-passwords-secret" + - field - String - Optional. Name of the field in the secret data, e.g: "mysql-password" +*/}} +{{- define "common.validations.values.multiple.empty" -}} + {{- range .required -}} + {{- include "common.validations.values.single.empty" (dict "valueKey" .valueKey "secret" .secret "field" .field "context" $.context) -}} + {{- end -}} +{{- end -}} + +{{/* +Validate a value must not be empty. + +Usage: +{{ include "common.validations.value.empty" (dict "valueKey" "mariadb.password" "secret" "secretName" "field" "my-password" "subchart" "subchart" "context" $) }} + +Validate value params: + - valueKey - String - Required. The path to the validating value in the values.yaml, e.g: "mysql.password" + - secret - String - Optional. Name of the secret where the validating value is generated/stored, e.g: "mysql-passwords-secret" + - field - String - Optional. Name of the field in the secret data, e.g: "mysql-password" + - subchart - String - Optional - Name of the subchart that the validated password is part of. +*/}} +{{- define "common.validations.values.single.empty" -}} + {{- $value := include "common.utils.getValueFromKey" (dict "key" .valueKey "context" .context) }} + {{- $subchart := ternary "" (printf "%s." .subchart) (empty .subchart) }} + + {{- if not $value -}} + {{- $varname := "my-value" -}} + {{- $getCurrentValue := "" -}} + {{- if and .secret .field -}} + {{- $varname = include "common.utils.fieldToEnvVar" . -}} + {{- $getCurrentValue = printf " To get the current value:\n\n %s\n" (include "common.utils.secret.getvalue" .) -}} + {{- end -}} + {{- printf "\n '%s' must not be empty, please add '--set %s%s=$%s' to the command.%s" .valueKey $subchart .valueKey $varname $getCurrentValue -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/values.yaml new file mode 100644 index 0000000..f2df68e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/charts/common/values.yaml @@ -0,0 +1,5 @@ +## bitnami/common +## It is required by CI/CD tools and processes. +## @skip exampleValue +## +exampleValue: common-chart diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/NOTES.txt new file mode 100644 index 0000000..e0474d4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/NOTES.txt @@ -0,0 +1,89 @@ +CHART NAME: {{ .Chart.Name }} +CHART VERSION: {{ .Chart.Version }} +APP VERSION: {{ .Chart.AppVersion }} + +** Please be patient while the chart is being deployed ** + +{{- if .Values.diagnosticMode.enabled }} +The chart has been deployed in diagnostic mode. All probes have been disabled and the command has been overwritten with: + + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 4 }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 4 }} + +Get the list of pods by executing: + + kubectl get pods --namespace {{ .Release.Namespace }} -l app.kubernetes.io/instance={{ .Release.Name }} + +Access the pod you want to debug by executing + + kubectl exec --namespace {{ .Release.Namespace }} -ti -- /opt/bitnami/scripts/postgresql/entrypoint.sh /bin/bash + +In order to replicate the container startup scripts execute this command: + + /opt/bitnami/scripts/postgresql/entrypoint.sh /opt/bitnami/scripts/postgresql/run.sh + +{{- else }} + +PostgreSQL can be accessed via port {{ include "postgresql.service.port" . }} on the following DNS names from within your cluster: + + {{ include "postgresql.primary.fullname" . }}.{{ .Release.Namespace }}.svc.cluster.local - Read/Write connection + +{{- if eq .Values.architecture "replication" }} + + {{ include "postgresql.readReplica.fullname" . }}.{{ .Release.Namespace }}.svc.cluster.local - Read only connection + +{{- end }} + +{{- $customUser := include "postgresql.username" . }} +{{- if and (not (empty $customUser)) (ne $customUser "postgres") .Values.auth.enablePostgresUser }} + +To get the password for "postgres" run: + + export POSTGRES_ADMIN_PASSWORD=$(kubectl get secret --namespace {{ .Release.Namespace }} {{ include "postgresql.secretName" . }} -o jsonpath="{.data.postgres-password}" | base64 -d) + +To get the password for "{{ $customUser }}" run: + + export POSTGRES_PASSWORD=$(kubectl get secret --namespace {{ .Release.Namespace }} {{ include "postgresql.secretName" . }} -o jsonpath="{.data.password}" | base64 -d) + +{{- else }} + +To get the password for "{{ default "postgres" $customUser }}" run: + + export POSTGRES_PASSWORD=$(kubectl get secret --namespace {{ .Release.Namespace }} {{ include "postgresql.secretName" . }} -o jsonpath="{.data.{{ ternary "password" "postgres-password" (and (not (empty $customUser)) (ne $customUser "postgres")) }}}" | base64 -d) + +{{- end }} + +To connect to your database run the following command: + + kubectl run {{ include "common.names.fullname" . }}-client --rm --tty -i --restart='Never' --namespace {{ .Release.Namespace }} --image {{ include "postgresql.image" . }} --env="PGPASSWORD=$POSTGRES_PASSWORD" \ + --command -- psql --host {{ include "postgresql.primary.fullname" . }} -U {{ default "postgres" $customUser }} -d {{- if include "postgresql.database" . }} {{ include "postgresql.database" . }}{{- else }} postgres{{- end }} -p {{ include "postgresql.service.port" . }} + + > NOTE: If you access the container using bash, make sure that you execute "/opt/bitnami/scripts/postgresql/entrypoint.sh /bin/bash" in order to avoid the error "psql: local user with ID {{ .Values.primary.containerSecurityContext.runAsUser }}} does not exist" + +To connect to your database from outside the cluster execute the following commands: + +{{- if contains "NodePort" .Values.primary.service.type }} + + export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}") + export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "postgresql.primary.fullname" . }}) + PGPASSWORD="$POSTGRES_PASSWORD" psql --host $NODE_IP --port $NODE_PORT -U {{ default "postgres" $customUser }} -d {{- if include "postgresql.database" . }} {{ include "postgresql.database" . }}{{- else }} postgres{{- end }} + +{{- else if contains "LoadBalancer" .Values.primary.service.type }} + + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + Watch the status with: 'kubectl get svc --namespace {{ .Release.Namespace }} -w {{ include "postgresql.primary.fullname" . }}' + + export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "postgresql.primary.fullname" . }} --template "{{ "{{ range (index .status.loadBalancer.ingress 0) }}{{ . }}{{ end }}" }}") + PGPASSWORD="$POSTGRES_PASSWORD" psql --host $SERVICE_IP --port {{ include "postgresql.service.port" . }} -U {{ default "postgres" $customUser }} -d {{- if include "postgresql.database" . }} {{ include "postgresql.database" . }}{{- else }} postgres{{- end }} + +{{- else if contains "ClusterIP" .Values.primary.service.type }} + + kubectl port-forward --namespace {{ .Release.Namespace }} svc/{{ include "postgresql.primary.fullname" . }} {{ include "postgresql.service.port" . }}:{{ include "postgresql.service.port" . }} & + PGPASSWORD="$POSTGRES_PASSWORD" psql --host 127.0.0.1 -U {{ default "postgres" $customUser }} -d {{- if include "postgresql.database" . }} {{ include "postgresql.database" . }}{{- else }} postgres{{- end }} -p {{ include "postgresql.service.port" . }} + +{{- end }} +{{- end }} + +{{- include "postgresql.validateValues" . -}} +{{- include "common.warnings.rollingTag" .Values.image -}} +{{- include "common.warnings.rollingTag" .Values.volumePermissions.image }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/_helpers.tpl new file mode 100644 index 0000000..fe123f5 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/_helpers.tpl @@ -0,0 +1,399 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Create a default fully qualified app name for PostgreSQL Primary objects +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "postgresql.primary.fullname" -}} +{{- if eq .Values.architecture "replication" }} + {{- printf "%s-%s" (include "common.names.fullname" .) .Values.primary.name | trunc 63 | trimSuffix "-" -}} +{{- else -}} + {{- include "common.names.fullname" . -}} +{{- end -}} +{{- end -}} + +{{/* +Create a default fully qualified app name for PostgreSQL read-only replicas objects +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "postgresql.readReplica.fullname" -}} +{{- printf "%s-%s" (include "common.names.fullname" .) .Values.readReplicas.name | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create the default FQDN for PostgreSQL primary headless service +We truncate at 63 chars because of the DNS naming spec. +*/}} +{{- define "postgresql.primary.svc.headless" -}} +{{- printf "%s-hl" (include "postgresql.primary.fullname" .) | trunc 63 | trimSuffix "-" }} +{{- end -}} + +{{/* +Create the default FQDN for PostgreSQL read-only replicas headless service +We truncate at 63 chars because of the DNS naming spec. +*/}} +{{- define "postgresql.readReplica.svc.headless" -}} +{{- printf "%s-hl" (include "postgresql.readReplica.fullname" .) | trunc 63 | trimSuffix "-" }} +{{- end -}} + +{{/* +Return the proper PostgreSQL image name +*/}} +{{- define "postgresql.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return the proper PostgreSQL metrics image name +*/}} +{{- define "postgresql.metrics.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.metrics.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return the proper image name (for the init container volume-permissions image) +*/}} +{{- define "postgresql.volumePermissions.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.volumePermissions.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names +*/}} +{{- define "postgresql.imagePullSecrets" -}} +{{ include "common.images.pullSecrets" (dict "images" (list .Values.image .Values.metrics.image .Values.volumePermissions.image) "global" .Values.global) }} +{{- end -}} + +{{/* +Return the name for a custom user to create +*/}} +{{- define "postgresql.username" -}} +{{- if .Values.global.postgresql.auth.username }} + {{- .Values.global.postgresql.auth.username -}} +{{- else -}} + {{- .Values.auth.username -}} +{{- end -}} +{{- end -}} + +{{/* +Return the name for a custom database to create +*/}} +{{- define "postgresql.database" -}} +{{- if .Values.global.postgresql.auth.database }} + {{- .Values.global.postgresql.auth.database -}} +{{- else if .Values.auth.database -}} + {{- .Values.auth.database -}} +{{- end -}} +{{- end -}} + +{{/* +Get the password secret. +*/}} +{{- define "postgresql.secretName" -}} +{{- if .Values.global.postgresql.auth.existingSecret }} + {{- printf "%s" (tpl .Values.global.postgresql.auth.existingSecret $) -}} +{{- else if .Values.auth.existingSecret -}} + {{- printf "%s" (tpl .Values.auth.existingSecret $) -}} +{{- else -}} + {{- printf "%s" (include "common.names.fullname" .) -}} +{{- end -}} +{{- end -}} + +{{/* +Get the replication-password key. +*/}} +{{- define "postgresql.replicationPasswordKey" -}} +{{- if or .Values.global.postgresql.auth.existingSecret .Values.auth.existingSecret }} + {{- if .Values.global.postgresql.auth.secretKeys.replicationPasswordKey }} + {{- printf "%s" (tpl .Values.global.postgresql.auth.secretKeys.replicationPasswordKey $) -}} + {{- else if .Values.auth.secretKeys.replicationPasswordKey -}} + {{- printf "%s" (tpl .Values.auth.secretKeys.replicationPasswordKey $) -}} + {{- else -}} + {{- "replication-password" -}} + {{- end -}} +{{- else -}} + {{- "replication-password" -}} +{{- end -}} +{{- end -}} + +{{/* +Get the admin-password key. +*/}} +{{- define "postgresql.adminPasswordKey" -}} +{{- if or .Values.global.postgresql.auth.existingSecret .Values.auth.existingSecret }} + {{- if .Values.global.postgresql.auth.secretKeys.adminPasswordKey }} + {{- printf "%s" (tpl .Values.global.postgresql.auth.secretKeys.adminPasswordKey $) -}} + {{- else if .Values.auth.secretKeys.adminPasswordKey -}} + {{- printf "%s" (tpl .Values.auth.secretKeys.adminPasswordKey $) -}} + {{- end -}} +{{- else -}} + {{- "postgres-password" -}} +{{- end -}} +{{- end -}} + +{{/* +Get the user-password key. +*/}} +{{- define "postgresql.userPasswordKey" -}} +{{- if or .Values.global.postgresql.auth.existingSecret .Values.auth.existingSecret }} + {{- if or (empty (include "postgresql.username" .)) (eq (include "postgresql.username" .) "postgres") }} + {{- printf "%s" (include "postgresql.adminPasswordKey" .) -}} + {{- else -}} + {{- if .Values.global.postgresql.auth.secretKeys.userPasswordKey }} + {{- printf "%s" (tpl .Values.global.postgresql.auth.secretKeys.userPasswordKey $) -}} + {{- else if .Values.auth.secretKeys.userPasswordKey -}} + {{- printf "%s" (tpl .Values.auth.secretKeys.userPasswordKey $) -}} + {{- end -}} + {{- end -}} +{{- else -}} + {{- ternary "password" "postgres-password" (and (not (empty (include "postgresql.username" .))) (ne (include "postgresql.username" .) "postgres")) -}} +{{- end -}} +{{- end -}} + +{{/* +Return true if a secret object should be created +*/}} +{{- define "postgresql.createSecret" -}} +{{- if not (or .Values.global.postgresql.auth.existingSecret .Values.auth.existingSecret) -}} + {{- true -}} +{{- end -}} +{{- end -}} + +{{/* +Return PostgreSQL service port +*/}} +{{- define "postgresql.service.port" -}} +{{- if .Values.global.postgresql.service.ports.postgresql }} + {{- .Values.global.postgresql.service.ports.postgresql -}} +{{- else -}} + {{- .Values.primary.service.ports.postgresql -}} +{{- end -}} +{{- end -}} + +{{/* +Return PostgreSQL service port +*/}} +{{- define "postgresql.readReplica.service.port" -}} +{{- if .Values.global.postgresql.service.ports.postgresql }} + {{- .Values.global.postgresql.service.ports.postgresql -}} +{{- else -}} + {{- .Values.readReplicas.service.ports.postgresql -}} +{{- end -}} +{{- end -}} + +{{/* +Get the PostgreSQL primary configuration ConfigMap name. +*/}} +{{- define "postgresql.primary.configmapName" -}} +{{- if .Values.primary.existingConfigmap -}} + {{- printf "%s" (tpl .Values.primary.existingConfigmap $) -}} +{{- else -}} + {{- printf "%s-configuration" (include "postgresql.primary.fullname" .) -}} +{{- end -}} +{{- end -}} + +{{/* +Return true if a configmap object should be created for PostgreSQL primary with the configuration +*/}} +{{- define "postgresql.primary.createConfigmap" -}} +{{- if and (or .Values.primary.configuration .Values.primary.pgHbaConfiguration) (not .Values.primary.existingConfigmap) }} + {{- true -}} +{{- else -}} +{{- end -}} +{{- end -}} + +{{/* +Get the PostgreSQL primary extended configuration ConfigMap name. +*/}} +{{- define "postgresql.primary.extendedConfigmapName" -}} +{{- if .Values.primary.existingExtendedConfigmap -}} + {{- printf "%s" (tpl .Values.primary.existingExtendedConfigmap $) -}} +{{- else -}} + {{- printf "%s-extended-configuration" (include "postgresql.primary.fullname" .) -}} +{{- end -}} +{{- end -}} + +{{/* +Get the PostgreSQL read replica extended configuration ConfigMap name. +*/}} +{{- define "postgresql.readReplicas.extendedConfigmapName" -}} + {{- printf "%s-extended-configuration" (include "postgresql.readReplica.fullname" .) -}} +{{- end -}} + +{{/* +Return true if a configmap object should be created for PostgreSQL primary with the extended configuration +*/}} +{{- define "postgresql.primary.createExtendedConfigmap" -}} +{{- if and .Values.primary.extendedConfiguration (not .Values.primary.existingExtendedConfigmap) }} + {{- true -}} +{{- else -}} +{{- end -}} +{{- end -}} + +{{/* +Return true if a configmap object should be created for PostgreSQL read replica with the extended configuration +*/}} +{{- define "postgresql.readReplicas.createExtendedConfigmap" -}} +{{- if .Values.readReplicas.extendedConfiguration }} + {{- true -}} +{{- else -}} +{{- end -}} +{{- end -}} + +{{/* + Create the name of the service account to use + */}} +{{- define "postgresql.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "common.names.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Return true if a configmap should be mounted with PostgreSQL configuration +*/}} +{{- define "postgresql.mountConfigurationCM" -}} +{{- if or .Values.primary.configuration .Values.primary.pgHbaConfiguration .Values.primary.existingConfigmap }} + {{- true -}} +{{- end -}} +{{- end -}} + +{{/* +Get the initialization scripts ConfigMap name. +*/}} +{{- define "postgresql.initdb.scriptsCM" -}} +{{- if .Values.primary.initdb.scriptsConfigMap -}} + {{- printf "%s" (tpl .Values.primary.initdb.scriptsConfigMap $) -}} +{{- else -}} + {{- printf "%s-init-scripts" (include "postgresql.primary.fullname" .) -}} +{{- end -}} +{{- end -}} + +{/* +Return true if TLS is enabled for LDAP connection +*/}} +{{- define "postgresql.ldap.tls.enabled" -}} +{{- if and (kindIs "string" .Values.ldap.tls) (not (empty .Values.ldap.tls)) }} + {{- true -}} +{{- else if and (kindIs "map" .Values.ldap.tls) .Values.ldap.tls.enabled }} + {{- true -}} +{{- end -}} +{{- end -}} + +{{/* +Get the readiness probe command +*/}} +{{- define "postgresql.readinessProbeCommand" -}} +{{- $customUser := include "postgresql.username" . }} +- | +{{- if (include "postgresql.database" .) }} + exec pg_isready -U {{ default "postgres" $customUser | quote }} -d "dbname={{ include "postgresql.database" . }} {{- if .Values.tls.enabled }} sslcert={{ include "postgresql.tlsCert" . }} sslkey={{ include "postgresql.tlsCertKey" . }}{{- end }}" -h 127.0.0.1 -p {{ .Values.containerPorts.postgresql }} +{{- else }} + exec pg_isready -U {{ default "postgres" $customUser | quote }} {{- if .Values.tls.enabled }} -d "sslcert={{ include "postgresql.tlsCert" . }} sslkey={{ include "postgresql.tlsCertKey" . }}"{{- end }} -h 127.0.0.1 -p {{ .Values.containerPorts.postgresql }} +{{- end }} +{{- if contains "bitnami/" .Values.image.repository }} + [ -f /opt/bitnami/postgresql/tmp/.initialized ] || [ -f /bitnami/postgresql/.initialized ] +{{- end -}} +{{- end -}} + +{{/* +Compile all warnings into a single message, and call fail. +*/}} +{{- define "postgresql.validateValues" -}} +{{- $messages := list -}} +{{- $messages := append $messages (include "postgresql.validateValues.ldapConfigurationMethod" .) -}} +{{- $messages := append $messages (include "postgresql.validateValues.psp" .) -}} +{{- $messages := without $messages "" -}} +{{- $message := join "\n" $messages -}} + +{{- if $message -}} +{{- printf "\nVALUES VALIDATION:\n%s" $message | fail -}} +{{- end -}} +{{- end -}} + +{{/* +Validate values of Postgresql - If ldap.url is used then you don't need the other settings for ldap +*/}} +{{- define "postgresql.validateValues.ldapConfigurationMethod" -}} +{{- if and .Values.ldap.enabled (and (not (empty .Values.ldap.url)) (not (empty .Values.ldap.server))) }} +postgresql: ldap.url, ldap.server + You cannot set both `ldap.url` and `ldap.server` at the same time. + Please provide a unique way to configure LDAP. + More info at https://www.postgresql.org/docs/current/auth-ldap.html +{{- end -}} +{{- end -}} + +{{/* +Validate values of Postgresql - If PSP is enabled RBAC should be enabled too +*/}} +{{- define "postgresql.validateValues.psp" -}} +{{- if and .Values.psp.create (not .Values.rbac.create) }} +postgresql: psp.create, rbac.create + RBAC should be enabled if PSP is enabled in order for PSP to work. + More info at https://kubernetes.io/docs/concepts/policy/pod-security-policy/#authorizing-policies +{{- end -}} +{{- end -}} + +{{/* +Return the path to the cert file. +*/}} +{{- define "postgresql.tlsCert" -}} +{{- if .Values.tls.autoGenerated }} + {{- printf "/opt/bitnami/postgresql/certs/tls.crt" -}} +{{- else -}} + {{- required "Certificate filename is required when TLS in enabled" .Values.tls.certFilename | printf "/opt/bitnami/postgresql/certs/%s" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the path to the cert key file. +*/}} +{{- define "postgresql.tlsCertKey" -}} +{{- if .Values.tls.autoGenerated }} + {{- printf "/opt/bitnami/postgresql/certs/tls.key" -}} +{{- else -}} +{{- required "Certificate Key filename is required when TLS in enabled" .Values.tls.certKeyFilename | printf "/opt/bitnami/postgresql/certs/%s" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the path to the CA cert file. +*/}} +{{- define "postgresql.tlsCACert" -}} +{{- if .Values.tls.autoGenerated }} + {{- printf "/opt/bitnami/postgresql/certs/ca.crt" -}} +{{- else -}} + {{- printf "/opt/bitnami/postgresql/certs/%s" .Values.tls.certCAFilename -}} +{{- end -}} +{{- end -}} + +{{/* +Return the path to the CRL file. +*/}} +{{- define "postgresql.tlsCRL" -}} +{{- if .Values.tls.crlFilename -}} +{{- printf "/opt/bitnami/postgresql/certs/%s" .Values.tls.crlFilename -}} +{{- end -}} +{{- end -}} + +{{/* +Return true if a TLS credentials secret object should be created +*/}} +{{- define "postgresql.createTlsSecret" -}} +{{- if and .Values.tls.autoGenerated (not .Values.tls.certificatesSecret) }} + {{- true -}} +{{- end -}} +{{- end -}} + +{{/* +Return the path to the CA cert file. +*/}} +{{- define "postgresql.tlsSecretName" -}} +{{- if .Values.tls.autoGenerated }} + {{- printf "%s-crt" (include "common.names.fullname" .) -}} +{{- else -}} + {{ required "A secret containing TLS certificates is required when TLS is enabled" .Values.tls.certificatesSecret }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/extra-list.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/extra-list.yaml new file mode 100644 index 0000000..9ac65f9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/extra-list.yaml @@ -0,0 +1,4 @@ +{{- range .Values.extraDeploy }} +--- +{{ include "common.tplvalues.render" (dict "value" . "context" $) }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/networkpolicy-egress.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/networkpolicy-egress.yaml new file mode 100644 index 0000000..e862147 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/networkpolicy-egress.yaml @@ -0,0 +1,32 @@ +{{- if and .Values.networkPolicy.enabled (or .Values.networkPolicy.egressRules.denyConnectionsToExternal .Values.networkPolicy.egressRules.customRules) }} +apiVersion: {{ include "common.capabilities.networkPolicy.apiVersion" . }} +kind: NetworkPolicy +metadata: + name: {{ printf "%s-egress" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + podSelector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + policyTypes: + - Egress + egress: + {{- if .Values.networkPolicy.egressRules.denyConnectionsToExternal }} + - ports: + - port: 53 + protocol: UDP + - port: 53 + protocol: TCP + - to: + - namespaceSelector: {} + {{- end }} + {{- if .Values.networkPolicy.egressRules.customRules }} + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.egressRules.customRules "context" $) | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/configmap.yaml new file mode 100644 index 0000000..d654a22 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/configmap.yaml @@ -0,0 +1,24 @@ +{{- if (include "postgresql.primary.createConfigmap" .) }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ printf "%s-configuration" (include "postgresql.primary.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: primary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: + {{- if .Values.primary.configuration }} + postgresql.conf: |- + {{- include "common.tplvalues.render" ( dict "value" .Values.primary.configuration "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.primary.pgHbaConfiguration }} + pg_hba.conf: | + {{- include "common.tplvalues.render" ( dict "value" .Values.primary.pgHbaConfiguration "context" $ ) | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/extended-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/extended-configmap.yaml new file mode 100644 index 0000000..d129bd3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/extended-configmap.yaml @@ -0,0 +1,18 @@ +{{- if (include "postgresql.primary.createExtendedConfigmap" .) }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ printf "%s-extended-configuration" (include "postgresql.primary.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: primary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: + override.conf: |- + {{- include "common.tplvalues.render" ( dict "value" .Values.primary.extendedConfiguration "context" $ ) | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/initialization-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/initialization-configmap.yaml new file mode 100644 index 0000000..d3d26cb --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/initialization-configmap.yaml @@ -0,0 +1,15 @@ +{{- if and .Values.primary.initdb.scripts (not .Values.primary.initdb.scriptsConfigMap) }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ printf "%s-init-scripts" (include "postgresql.primary.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: {{- include "common.tplvalues.render" (dict "value" .Values.primary.initdb.scripts "context" .) | nindent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/metrics-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/metrics-configmap.yaml new file mode 100644 index 0000000..8ad2f35 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/metrics-configmap.yaml @@ -0,0 +1,16 @@ +{{- if and .Values.metrics.enabled .Values.metrics.customMetrics }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ printf "%s-metrics" (include "postgresql.primary.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: + custom-metrics.yaml: {{ toYaml .Values.metrics.customMetrics | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/metrics-svc.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/metrics-svc.yaml new file mode 100644 index 0000000..75a1b81 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/metrics-svc.yaml @@ -0,0 +1,31 @@ +{{- if .Values.metrics.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ printf "%s-metrics" (include "postgresql.primary.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: metrics + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.metrics.service.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.service.annotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + sessionAffinity: {{ .Values.metrics.service.sessionAffinity }} + {{- if .Values.metrics.service.clusterIP }} + clusterIP: {{ .Values.metrics.service.clusterIP }} + {{- end }} + ports: + - name: http-metrics + port: {{ .Values.metrics.service.ports.metrics }} + targetPort: http-metrics + selector: {{- include "common.labels.matchLabels" . | nindent 4 }} + app.kubernetes.io/component: primary +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/networkpolicy.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/networkpolicy.yaml new file mode 100644 index 0000000..ce0052d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/networkpolicy.yaml @@ -0,0 +1,57 @@ +{{- if and .Values.networkPolicy.enabled (or .Values.networkPolicy.metrics.enabled .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.enabled) }} +apiVersion: {{ include "common.capabilities.networkPolicy.apiVersion" . }} +kind: NetworkPolicy +metadata: + name: {{ printf "%s-ingress" (include "postgresql.primary.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: primary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + podSelector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + app.kubernetes.io/component: primary + ingress: + {{- if and .Values.metrics.enabled .Values.networkPolicy.metrics.enabled (or .Values.networkPolicy.metrics.namespaceSelector .Values.networkPolicy.metrics.podSelector) }} + - from: + {{- if .Values.networkPolicy.metrics.namespaceSelector }} + - namespaceSelector: + matchLabels: {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.metrics.namespaceSelector "context" $) | nindent 14 }} + {{- end }} + {{- if .Values.networkPolicy.metrics.podSelector }} + - podSelector: + matchLabels: {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.metrics.podSelector "context" $) | nindent 14 }} + {{- end }} + ports: + - port: {{ .Values.metrics.containerPorts.metrics }} + {{- end }} + {{- if and .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.enabled (or .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.namespaceSelector .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.podSelector) }} + - from: + {{- if .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.namespaceSelector }} + - namespaceSelector: + matchLabels: {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.namespaceSelector "context" $) | nindent 14 }} + {{- end }} + {{- if .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.podSelector }} + - podSelector: + matchLabels: {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.podSelector "context" $) | nindent 14 }} + {{- end }} + ports: + - port: {{ .Values.containerPorts.postgresql }} + {{- end }} + {{- if and .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.enabled (eq .Values.architecture "replication") }} + - from: + - podSelector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 14 }} + app.kubernetes.io/component: read + ports: + - port: {{ .Values.containerPorts.postgresql }} + {{- end }} + {{- if .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.customRules }} + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.ingressRules.primaryAccessOnlyFrom.customRules "context" $) | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/servicemonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/servicemonitor.yaml new file mode 100644 index 0000000..c4a19fe --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/servicemonitor.yaml @@ -0,0 +1,48 @@ +{{- if and .Values.metrics.enabled .Values.metrics.serviceMonitor.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "postgresql.primary.fullname" . }} + namespace: {{ default .Release.Namespace .Values.metrics.serviceMonitor.namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: metrics + {{- if .Values.metrics.serviceMonitor.labels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.labels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + {{- if .Values.metrics.serviceMonitor.jobLabel }} + jobLabel: {{ .Values.metrics.serviceMonitor.jobLabel }} + {{- end }} + selector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + {{- if .Values.metrics.serviceMonitor.selector }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.serviceMonitor.selector "context" $) | nindent 6 }} + {{- end }} + app.kubernetes.io/component: metrics + endpoints: + - port: http-metrics + {{- if .Values.metrics.serviceMonitor.interval }} + interval: {{ .Values.metrics.serviceMonitor.interval }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.metrics.serviceMonitor.scrapeTimeout }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.relabelings }} + relabelings: {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.relabelings "context" $) | nindent 6 }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.metricRelabelings }} + metricRelabelings: {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.metricRelabelings "context" $) | nindent 6 }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.honorLabels }} + honorLabels: {{ .Values.metrics.serviceMonitor.honorLabels }} + {{- end }} + namespaceSelector: + matchNames: + - {{ .Release.Namespace | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/statefulset.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/statefulset.yaml new file mode 100644 index 0000000..3fd77f4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/statefulset.yaml @@ -0,0 +1,634 @@ +{{- $customUser := include "postgresql.username" . }} +apiVersion: {{ include "common.capabilities.statefulset.apiVersion" . }} +kind: StatefulSet +metadata: + name: {{ include "postgresql.primary.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: primary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.primary.labels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.primary.labels "context" $ ) | nindent 4 }} + {{- end }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.primary.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.primary.annotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + replicas: 1 + serviceName: {{ include "postgresql.primary.svc.headless" . }} + {{- if .Values.primary.updateStrategy }} + updateStrategy: {{- toYaml .Values.primary.updateStrategy | nindent 4 }} + {{- end }} + selector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + app.kubernetes.io/component: primary + template: + metadata: + name: {{ include "postgresql.primary.fullname" . }} + labels: {{- include "common.labels.standard" . | nindent 8 }} + app.kubernetes.io/component: primary + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 8 }} + {{- end }} + {{- if .Values.primary.podLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.primary.podLabels "context" $ ) | nindent 8 }} + {{- end }} + annotations: + {{- if (include "postgresql.primary.createConfigmap" .) }} + checksum/configuration: {{ include (print $.Template.BasePath "/primary/configmap.yaml") . | sha256sum }} + {{- end }} + {{- if (include "postgresql.primary.createExtendedConfigmap" .) }} + checksum/extended-configuration: {{ include (print $.Template.BasePath "/primary/extended-configmap.yaml") . | sha256sum }} + {{- end }} + {{- if .Values.primary.podAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.primary.podAnnotations "context" $ ) | nindent 8 }} + {{- end }} + spec: + {{- if .Values.primary.extraPodSpec }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.extraPodSpec "context" $) | nindent 6 }} + {{- end }} + serviceAccountName: {{ include "postgresql.serviceAccountName" . }} + {{- include "postgresql.imagePullSecrets" . | nindent 6 }} + {{- if .Values.primary.hostAliases }} + hostAliases: {{- include "common.tplvalues.render" (dict "value" .Values.primary.hostAliases "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.primary.affinity }} + affinity: {{- include "common.tplvalues.render" (dict "value" .Values.primary.affinity "context" $) | nindent 8 }} + {{- else }} + affinity: + podAffinity: {{- include "common.affinities.pods" (dict "type" .Values.primary.podAffinityPreset "component" "primary" "context" $) | nindent 10 }} + podAntiAffinity: {{- include "common.affinities.pods" (dict "type" .Values.primary.podAntiAffinityPreset "component" "primary" "context" $) | nindent 10 }} + nodeAffinity: {{- include "common.affinities.nodes" (dict "type" .Values.primary.nodeAffinityPreset.type "key" .Values.primary.nodeAffinityPreset.key "values" .Values.primary.nodeAffinityPreset.values) | nindent 10 }} + {{- end }} + {{- if .Values.primary.nodeSelector }} + nodeSelector: {{- include "common.tplvalues.render" (dict "value" .Values.primary.nodeSelector "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.primary.tolerations }} + tolerations: {{- include "common.tplvalues.render" (dict "value" .Values.primary.tolerations "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.primary.topologySpreadConstraints }} + topologySpreadConstraints: {{- include "common.tplvalues.render" (dict "value" .Values.primary.topologySpreadConstraints "context" .) | nindent 8 }} + {{- end }} + {{- if .Values.primary.priorityClassName }} + priorityClassName: {{ .Values.primary.priorityClassName }} + {{- end }} + {{- if .Values.primary.schedulerName }} + schedulerName: {{ .Values.primary.schedulerName | quote }} + {{- end }} + {{- if .Values.primary.terminationGracePeriodSeconds }} + terminationGracePeriodSeconds: {{ .Values.primary.terminationGracePeriodSeconds }} + {{- end }} + {{- if .Values.primary.podSecurityContext.enabled }} + securityContext: {{- omit .Values.primary.podSecurityContext "enabled" | toYaml | nindent 8 }} + {{- end }} + hostNetwork: {{ .Values.primary.hostNetwork }} + hostIPC: {{ .Values.primary.hostIPC }} + initContainers: + {{- if and .Values.tls.enabled (not .Values.volumePermissions.enabled) }} + - name: copy-certs + image: {{ include "postgresql.volumePermissions.image" . }} + imagePullPolicy: {{ .Values.volumePermissions.image.pullPolicy | quote }} + {{- if .Values.primary.resources }} + resources: {{- toYaml .Values.primary.resources | nindent 12 }} + {{- end }} + # We don't require a privileged container in this case + {{- if .Values.primary.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.primary.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + command: + - /bin/sh + - -ec + - | + cp /tmp/certs/* /opt/bitnami/postgresql/certs/ + chmod 600 {{ include "postgresql.tlsCertKey" . }} + volumeMounts: + - name: raw-certificates + mountPath: /tmp/certs + - name: postgresql-certificates + mountPath: /opt/bitnami/postgresql/certs + {{- else if and .Values.volumePermissions.enabled (or .Values.primary.persistence.enabled .Values.shmVolume.enabled) }} + - name: init-chmod-data + image: {{ include "postgresql.volumePermissions.image" . }} + imagePullPolicy: {{ .Values.volumePermissions.image.pullPolicy | quote }} + {{- if .Values.volumePermissions.resources }} + resources: {{- toYaml .Values.volumePermissions.resources | nindent 12 }} + {{- end }} + command: + - /bin/sh + - -ec + - | + {{- if .Values.primary.persistence.enabled }} + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + chown `id -u`:`id -G | cut -d " " -f2` {{ .Values.primary.persistence.mountPath }} + {{- else }} + chown {{ .Values.primary.containerSecurityContext.runAsUser }}:{{ .Values.primary.podSecurityContext.fsGroup }} {{ .Values.primary.persistence.mountPath }} + {{- end }} + mkdir -p {{ .Values.primary.persistence.mountPath }}/data {{- if (include "postgresql.mountConfigurationCM" .) }} {{ .Values.primary.persistence.mountPath }}/conf {{- end }} + chmod 700 {{ .Values.primary.persistence.mountPath }}/data {{- if (include "postgresql.mountConfigurationCM" .) }} {{ .Values.primary.persistence.mountPath }}/conf {{- end }} + find {{ .Values.primary.persistence.mountPath }} -mindepth 1 -maxdepth 1 {{- if not (include "postgresql.mountConfigurationCM" .) }} -not -name "conf" {{- end }} -not -name ".snapshot" -not -name "lost+found" | \ + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + xargs -r chown -R `id -u`:`id -G | cut -d " " -f2` + {{- else }} + xargs -r chown -R {{ .Values.primary.containerSecurityContext.runAsUser }}:{{ .Values.primary.podSecurityContext.fsGroup }} + {{- end }} + {{- end }} + {{- if .Values.shmVolume.enabled }} + chmod -R 777 /dev/shm + {{- end }} + {{- if .Values.tls.enabled }} + cp /tmp/certs/* /opt/bitnami/postgresql/certs/ + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + chown -R `id -u`:`id -G | cut -d " " -f2` /opt/bitnami/postgresql/certs/ + {{- else }} + chown -R {{ .Values.primary.containerSecurityContext.runAsUser }}:{{ .Values.primary.podSecurityContext.fsGroup }} /opt/bitnami/postgresql/certs/ + {{- end }} + chmod 600 {{ include "postgresql.tlsCertKey" . }} + {{- end }} + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + securityContext: {{- omit .Values.volumePermissions.containerSecurityContext "runAsUser" | toYaml | nindent 12 }} + {{- else }} + securityContext: {{- .Values.volumePermissions.containerSecurityContext | toYaml | nindent 12 }} + {{- end }} + volumeMounts: + {{- if .Values.primary.persistence.enabled }} + - name: data + mountPath: {{ .Values.primary.persistence.mountPath }} + {{- if .Values.primary.persistence.subPath }} + subPath: {{ .Values.primary.persistence.subPath }} + {{- end }} + {{- end }} + {{- if .Values.shmVolume.enabled }} + - name: dshm + mountPath: /dev/shm + {{- end }} + {{- if .Values.tls.enabled }} + - name: raw-certificates + mountPath: /tmp/certs + - name: postgresql-certificates + mountPath: /opt/bitnami/postgresql/certs + {{- end }} + {{- end }} + {{- if .Values.primary.initContainers }} + {{- include "common.tplvalues.render" ( dict "value" .Values.primary.initContainers "context" $ ) | nindent 8 }} + {{- end }} + containers: + - name: postgresql + image: {{ include "postgresql.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy | quote }} + {{- if .Values.primary.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.primary.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + {{- else if .Values.primary.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.primary.command "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else if .Values.primary.args }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.primary.args "context" $) | nindent 12 }} + {{- end }} + env: + - name: BITNAMI_DEBUG + value: {{ ternary "true" "false" (or .Values.image.debug .Values.diagnosticMode.enabled) | quote }} + - name: POSTGRESQL_PORT_NUMBER + value: {{ .Values.containerPorts.postgresql | quote }} + - name: POSTGRESQL_VOLUME_DIR + value: {{ .Values.primary.persistence.mountPath | quote }} + {{- if .Values.primary.persistence.mountPath }} + - name: PGDATA + value: {{ .Values.postgresqlDataDir | quote }} + {{- end }} + # Authentication + {{- if and (not (empty $customUser)) (ne $customUser "postgres") }} + - name: POSTGRES_USER + value: {{ $customUser | quote }} + {{- if .Values.auth.enablePostgresUser }} + {{- if .Values.auth.usePasswordFiles }} + - name: POSTGRES_POSTGRES_PASSWORD_FILE + value: "/opt/bitnami/postgresql/secrets/postgres-password" + {{- else }} + - name: POSTGRES_POSTGRES_PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "postgresql.secretName" . }} + key: {{ include "postgresql.adminPasswordKey" . }} + {{- end }} + {{- end }} + {{- end }} + {{- if .Values.auth.usePasswordFiles }} + - name: POSTGRES_PASSWORD_FILE + value: {{ printf "/opt/bitnami/postgresql/secrets/%s" (ternary "password" "postgres-password" (and (not (empty $customUser)) (ne $customUser "postgres"))) }} + {{- else }} + - name: POSTGRES_PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "postgresql.secretName" . }} + key: {{ include "postgresql.userPasswordKey" . }} + {{- end }} + {{- if (include "postgresql.database" .) }} + - name: POSTGRES_DB + value: {{ (include "postgresql.database" .) | quote }} + {{- end }} + # Replication + {{- if or (eq .Values.architecture "replication") .Values.primary.standby.enabled }} + - name: POSTGRES_REPLICATION_MODE + value: {{ ternary "slave" "master" .Values.primary.standby.enabled | quote }} + - name: POSTGRES_REPLICATION_USER + value: {{ .Values.auth.replicationUsername | quote }} + {{- if .Values.auth.usePasswordFiles }} + - name: POSTGRES_REPLICATION_PASSWORD_FILE + value: "/opt/bitnami/postgresql/secrets/replication-password" + {{- else }} + - name: POSTGRES_REPLICATION_PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "postgresql.secretName" . }} + key: {{ include "postgresql.replicationPasswordKey" . }} + {{- end }} + {{- if not (eq .Values.replication.synchronousCommit "off") }} + - name: POSTGRES_SYNCHRONOUS_COMMIT_MODE + value: {{ .Values.replication.synchronousCommit | quote }} + - name: POSTGRES_NUM_SYNCHRONOUS_REPLICAS + value: {{ .Values.replication.numSynchronousReplicas | quote }} + {{- end }} + - name: POSTGRES_CLUSTER_APP_NAME + value: {{ .Values.replication.applicationName }} + {{- end }} + # Initdb + {{- if .Values.primary.initdb.args }} + - name: POSTGRES_INITDB_ARGS + value: {{ .Values.primary.initdb.args | quote }} + {{- end }} + {{- if .Values.primary.initdb.postgresqlWalDir }} + - name: POSTGRES_INITDB_WALDIR + value: {{ .Values.primary.initdb.postgresqlWalDir | quote }} + {{- end }} + {{- if .Values.primary.initdb.user }} + - name: POSTGRESQL_INITSCRIPTS_USERNAME + value: {{ .Values.primary.initdb.user }} + {{- end }} + {{- if .Values.primary.initdb.password }} + - name: POSTGRESQL_INITSCRIPTS_PASSWORD + value: {{ .Values.primary.initdb.password | quote }} + {{- end }} + # Standby + {{- if .Values.primary.standby.enabled }} + - name: POSTGRES_MASTER_HOST + value: {{ .Values.primary.standby.primaryHost }} + - name: POSTGRES_MASTER_PORT_NUMBER + value: {{ .Values.primary.standby.primaryPort | quote }} + {{- end }} + # LDAP + - name: POSTGRESQL_ENABLE_LDAP + value: {{ ternary "yes" "no" .Values.ldap.enabled | quote }} + {{- if .Values.ldap.enabled }} + {{- if or .Values.ldap.url .Values.ldap.uri }} + - name: POSTGRESQL_LDAP_URL + value: {{ coalesce .Values.ldap.url .Values.ldap.uri }} + {{- else }} + - name: POSTGRESQL_LDAP_SERVER + value: {{ .Values.ldap.server }} + - name: POSTGRESQL_LDAP_PORT + value: {{ .Values.ldap.port | quote }} + - name: POSTGRESQL_LDAP_SCHEME + value: {{ .Values.ldap.scheme }} + {{- if (include "postgresql.ldap.tls.enabled" .) }} + - name: POSTGRESQL_LDAP_TLS + value: "1" + {{- end }} + - name: POSTGRESQL_LDAP_PREFIX + value: {{ .Values.ldap.prefix | quote }} + - name: POSTGRESQL_LDAP_SUFFIX + value: {{ .Values.ldap.suffix | quote }} + - name: POSTGRESQL_LDAP_BASE_DN + value: {{ coalesce .Values.ldap.baseDN .Values.ldap.basedn }} + - name: POSTGRESQL_LDAP_BIND_DN + value: {{ coalesce .Values.ldap.bindDN .Values.ldap.binddn}} + {{- if or (not (empty .Values.ldap.bind_password)) (not (empty .Values.ldap.bindpw)) }} + - name: POSTGRESQL_LDAP_BIND_PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "postgresql.secretName" . }} + key: ldap-password + {{- end }} + - name: POSTGRESQL_LDAP_SEARCH_ATTR + value: {{ coalesce .Values.ldap.search_attr .Values.ldap.searchAttribute }} + - name: POSTGRESQL_LDAP_SEARCH_FILTER + value: {{ coalesce .Values.ldap.search_filter .Values.ldap.searchFilter }} + {{- end }} + {{- end }} + # TLS + - name: POSTGRESQL_ENABLE_TLS + value: {{ ternary "yes" "no" .Values.tls.enabled | quote }} + {{- if .Values.tls.enabled }} + - name: POSTGRESQL_TLS_PREFER_SERVER_CIPHERS + value: {{ ternary "yes" "no" .Values.tls.preferServerCiphers | quote }} + - name: POSTGRESQL_TLS_CERT_FILE + value: {{ include "postgresql.tlsCert" . }} + - name: POSTGRESQL_TLS_KEY_FILE + value: {{ include "postgresql.tlsCertKey" . }} + {{- if .Values.tls.certCAFilename }} + - name: POSTGRESQL_TLS_CA_FILE + value: {{ include "postgresql.tlsCACert" . }} + {{- end }} + {{- if .Values.tls.crlFilename }} + - name: POSTGRESQL_TLS_CRL_FILE + value: {{ include "postgresql.tlsCRL" . }} + {{- end }} + {{- end }} + # Audit + - name: POSTGRESQL_LOG_HOSTNAME + value: {{ .Values.audit.logHostname | quote }} + - name: POSTGRESQL_LOG_CONNECTIONS + value: {{ .Values.audit.logConnections | quote }} + - name: POSTGRESQL_LOG_DISCONNECTIONS + value: {{ .Values.audit.logDisconnections | quote }} + {{- if .Values.audit.logLinePrefix }} + - name: POSTGRESQL_LOG_LINE_PREFIX + value: {{ .Values.audit.logLinePrefix | quote }} + {{- end }} + {{- if .Values.audit.logTimezone }} + - name: POSTGRESQL_LOG_TIMEZONE + value: {{ .Values.audit.logTimezone | quote }} + {{- end }} + {{- if .Values.audit.pgAuditLog }} + - name: POSTGRESQL_PGAUDIT_LOG + value: {{ .Values.audit.pgAuditLog | quote }} + {{- end }} + - name: POSTGRESQL_PGAUDIT_LOG_CATALOG + value: {{ .Values.audit.pgAuditLogCatalog | quote }} + # Others + - name: POSTGRESQL_CLIENT_MIN_MESSAGES + value: {{ .Values.audit.clientMinMessages | quote }} + - name: POSTGRESQL_SHARED_PRELOAD_LIBRARIES + value: {{ .Values.postgresqlSharedPreloadLibraries | quote }} + {{- if .Values.primary.extraEnvVars }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.extraEnvVars "context" $) | nindent 12 }} + {{- end }} + {{- if or .Values.primary.extraEnvVarsCM .Values.primary.extraEnvVarsSecret }} + envFrom: + {{- if .Values.primary.extraEnvVarsCM }} + - configMapRef: + name: {{ .Values.primary.extraEnvVarsCM }} + {{- end }} + {{- if .Values.primary.extraEnvVarsSecret }} + - secretRef: + name: {{ .Values.primary.extraEnvVarsSecret }} + {{- end }} + {{- end }} + ports: + - name: tcp-postgresql + containerPort: {{ .Values.containerPorts.postgresql }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.primary.customStartupProbe }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.primary.customStartupProbe "context" $) | nindent 12 }} + {{- else if .Values.primary.startupProbe.enabled }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.primary.startupProbe "enabled") "context" $) | nindent 12 }} + exec: + command: + - /bin/sh + - -c + {{- if (include "postgresql.database" .) }} + - exec pg_isready -U {{ default "postgres" $customUser | quote }} -d "dbname={{ include "postgresql.database" . }} {{- if and .Values.tls.enabled .Values.tls.certCAFilename }} sslcert={{ include "postgresql.tlsCert" . }} sslkey={{ include "postgresql.tlsCertKey" . }}{{- end }}" -h 127.0.0.1 -p {{ .Values.containerPorts.postgresql }} + {{- else }} + - exec pg_isready -U {{ default "postgres" $customUser | quote }} {{- if and .Values.tls.enabled .Values.tls.certCAFilename }} -d "sslcert={{ include "postgresql.tlsCert" . }} sslkey={{ include "postgresql.tlsCertKey" . }}"{{- end }} -h 127.0.0.1 -p {{ .Values.containerPorts.postgresql }} + {{- end }} + {{- end }} + {{- if .Values.primary.customLivenessProbe }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.primary.customLivenessProbe "context" $) | nindent 12 }} + {{- else if .Values.primary.livenessProbe.enabled }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.primary.livenessProbe "enabled") "context" $) | nindent 12 }} + exec: + command: + - /bin/sh + - -c + {{- if (include "postgresql.database" .) }} + - exec pg_isready -U {{ default "postgres" $customUser | quote }} -d "dbname={{ include "postgresql.database" . }} {{- if and .Values.tls.enabled .Values.tls.certCAFilename }} sslcert={{ include "postgresql.tlsCert" . }} sslkey={{ include "postgresql.tlsCertKey" . }}{{- end }}" -h 127.0.0.1 -p {{ .Values.containerPorts.postgresql }} + {{- else }} + - exec pg_isready -U {{ default "postgres" $customUser | quote }} {{- if and .Values.tls.enabled .Values.tls.certCAFilename }} -d "sslcert={{ include "postgresql.tlsCert" . }} sslkey={{ include "postgresql.tlsCertKey" . }}"{{- end }} -h 127.0.0.1 -p {{ .Values.containerPorts.postgresql }} + {{- end }} + {{- end }} + {{- if .Values.primary.customReadinessProbe }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.primary.customReadinessProbe "context" $) | nindent 12 }} + {{- else if .Values.primary.readinessProbe.enabled }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.primary.readinessProbe "enabled") "context" $) | nindent 12 }} + exec: + command: + - /bin/sh + - -c + - -e + {{- include "postgresql.readinessProbeCommand" . | nindent 16 }} + {{- end }} + {{- end }} + {{- if .Values.primary.resources }} + resources: {{- toYaml .Values.primary.resources | nindent 12 }} + {{- end }} + {{- if .Values.primary.lifecycleHooks }} + lifecycle: {{- include "common.tplvalues.render" (dict "value" .Values.primary.lifecycleHooks "context" $) | nindent 12 }} + {{- end }} + volumeMounts: + {{- if or .Values.primary.initdb.scriptsConfigMap .Values.primary.initdb.scripts }} + - name: custom-init-scripts + mountPath: /docker-entrypoint-initdb.d/ + {{- end }} + {{- if .Values.primary.initdb.scriptsSecret }} + - name: custom-init-scripts-secret + mountPath: /docker-entrypoint-initdb.d/secret + {{- end }} + {{- if or .Values.primary.extendedConfiguration .Values.primary.existingExtendedConfigmap }} + - name: postgresql-extended-config + mountPath: /bitnami/postgresql/conf/conf.d/ + {{- end }} + {{- if .Values.auth.usePasswordFiles }} + - name: postgresql-password + mountPath: /opt/bitnami/postgresql/secrets/ + {{- end }} + {{- if .Values.tls.enabled }} + - name: postgresql-certificates + mountPath: /opt/bitnami/postgresql/certs + readOnly: true + {{- end }} + {{- if .Values.shmVolume.enabled }} + - name: dshm + mountPath: /dev/shm + {{- end }} + {{- if .Values.primary.persistence.enabled }} + - name: data + mountPath: {{ .Values.primary.persistence.mountPath }} + {{- if .Values.primary.persistence.subPath }} + subPath: {{ .Values.primary.persistence.subPath }} + {{- end }} + {{- end }} + {{- if or .Values.primary.configuration .Values.primary.pgHbaConfiguration .Values.primary.existingConfigmap }} + - name: postgresql-config + mountPath: /bitnami/postgresql/conf + {{- end }} + {{- if .Values.primary.extraVolumeMounts }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.extraVolumeMounts "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.metrics.enabled }} + - name: metrics + image: {{ include "postgresql.metrics.image" . }} + imagePullPolicy: {{ .Values.metrics.image.pullPolicy | quote }} + {{- if .Values.metrics.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.metrics.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else if .Values.metrics.customMetrics }} + args: ["--extend.query-path", "/conf/custom-metrics.yaml"] + {{- end }} + env: + {{- $database := required "In order to enable metrics you need to specify a database (.Values.auth.database or .Values.global.postgresql.auth.database)" (include "postgresql.database" .) }} + - name: DATA_SOURCE_URI + value: {{ printf "127.0.0.1:%d/%s?sslmode=disable" (int (include "postgresql.service.port" .)) $database }} + {{- if .Values.auth.usePasswordFiles }} + - name: DATA_SOURCE_PASS_FILE + value: {{ printf "/opt/bitnami/postgresql/secrets/%s" (ternary "password" "postgres-password" (and (not (empty $customUser)) (ne $customUser "postgres"))) }} + {{- else }} + - name: DATA_SOURCE_PASS + valueFrom: + secretKeyRef: + name: {{ include "postgresql.secretName" . }} + key: {{ include "postgresql.userPasswordKey" . }} + {{- end }} + - name: DATA_SOURCE_USER + value: {{ default "postgres" $customUser | quote }} + {{- if .Values.metrics.extraEnvVars }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.extraEnvVars "context" $) | nindent 12 }} + {{- end }} + ports: + - name: http-metrics + containerPort: {{ .Values.metrics.containerPorts.metrics }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.metrics.customStartupProbe }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.metrics.customStartupProbe "context" $) | nindent 12 }} + {{- else if .Values.metrics.startupProbe.enabled }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.metrics.startupProbe "enabled") "context" $) | nindent 12 }} + tcpSocket: + port: http-metrics + {{- end }} + {{- if .Values.metrics.customLivenessProbe }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.metrics.customLivenessProbe "context" $) | nindent 12 }} + {{- else if .Values.metrics.livenessProbe.enabled }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.metrics.livenessProbe "enabled") "context" $) | nindent 12 }} + httpGet: + path: / + port: http-metrics + {{- end }} + {{- if .Values.metrics.customReadinessProbe }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.metrics.customReadinessProbe "context" $) | nindent 12 }} + {{- else if .Values.metrics.readinessProbe.enabled }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.metrics.readinessProbe "enabled") "context" $) | nindent 12 }} + httpGet: + path: / + port: http-metrics + {{- end }} + {{- end }} + volumeMounts: + {{- if .Values.auth.usePasswordFiles }} + - name: postgresql-password + mountPath: /opt/bitnami/postgresql/secrets/ + {{- end }} + {{- if .Values.metrics.customMetrics }} + - name: custom-metrics + mountPath: /conf + readOnly: true + {{- end }} + {{- if .Values.metrics.resources }} + resources: {{- toYaml .Values.metrics.resources | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.primary.sidecars }} + {{- include "common.tplvalues.render" ( dict "value" .Values.primary.sidecars "context" $ ) | nindent 8 }} + {{- end }} + volumes: + {{- if or .Values.primary.configuration .Values.primary.pgHbaConfiguration .Values.primary.existingConfigmap }} + - name: postgresql-config + configMap: + name: {{ include "postgresql.primary.configmapName" . }} + {{- end }} + {{- if or .Values.primary.extendedConfiguration .Values.primary.existingExtendedConfigmap }} + - name: postgresql-extended-config + configMap: + name: {{ include "postgresql.primary.extendedConfigmapName" . }} + {{- end }} + {{- if .Values.auth.usePasswordFiles }} + - name: postgresql-password + secret: + secretName: {{ include "postgresql.secretName" . }} + {{- end }} + {{- if or .Values.primary.initdb.scriptsConfigMap .Values.primary.initdb.scripts }} + - name: custom-init-scripts + configMap: + name: {{ include "postgresql.initdb.scriptsCM" . }} + {{- end }} + {{- if .Values.primary.initdb.scriptsSecret }} + - name: custom-init-scripts-secret + secret: + secretName: {{ tpl .Values.primary.initdb.scriptsSecret $ }} + {{- end }} + {{- if .Values.tls.enabled }} + - name: raw-certificates + secret: + secretName: {{ include "postgresql.tlsSecretName" . }} + - name: postgresql-certificates + emptyDir: {} + {{- end }} + {{- if .Values.primary.extraVolumes }} + {{- include "common.tplvalues.render" ( dict "value" .Values.primary.extraVolumes "context" $ ) | nindent 8 }} + {{- end }} + {{- if and .Values.metrics.enabled .Values.metrics.customMetrics }} + - name: custom-metrics + configMap: + name: {{ printf "%s-metrics" (include "common.names.fullname" .) }} + {{- end }} + {{- if .Values.shmVolume.enabled }} + - name: dshm + emptyDir: + medium: Memory + {{- if .Values.shmVolume.sizeLimit }} + sizeLimit: {{ .Values.shmVolume.sizeLimit }} + {{- end }} + {{- end }} + {{- if and .Values.primary.persistence.enabled .Values.primary.persistence.existingClaim }} + - name: data + persistentVolumeClaim: + claimName: {{ tpl .Values.primary.persistence.existingClaim $ }} + {{- else if not .Values.primary.persistence.enabled }} + - name: data + emptyDir: {} + {{- else }} + volumeClaimTemplates: + - metadata: + name: data + {{- if .Values.primary.persistence.annotations }} + annotations: {{- include "common.tplvalues.render" (dict "value" .Values.primary.persistence.annotations "context" $) | nindent 10 }} + {{- end }} + {{- if .Values.primary.persistence.labels }} + labels: {{- include "common.tplvalues.render" (dict "value" .Values.primary.persistence.labels "context" $) | nindent 10 }} + {{- end }} + spec: + accessModes: + {{- range .Values.primary.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + {{- if .Values.primary.persistence.dataSource }} + dataSource: {{- include "common.tplvalues.render" (dict "value" .Values.primary.persistence.dataSource "context" $) | nindent 10 }} + {{- end }} + resources: + requests: + storage: {{ .Values.primary.persistence.size | quote }} + {{- if .Values.primary.persistence.selector }} + selector: {{- include "common.tplvalues.render" (dict "value" .Values.primary.persistence.selector "context" $) | nindent 10 }} + {{- end }} + {{- include "common.storage.class" (dict "persistence" .Values.primary.persistence "global" .Values.global) | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/svc-headless.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/svc-headless.yaml new file mode 100644 index 0000000..b782631 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/svc-headless.yaml @@ -0,0 +1,31 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "postgresql.primary.svc.headless" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + app.kubernetes.io/component: primary + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + # Use this annotation in addition to the actual publishNotReadyAddresses + # field below because the annotation will stop being respected soon but the + # field is broken in some versions of Kubernetes: + # https://github.com/kubernetes/kubernetes/issues/58662 + service.alpha.kubernetes.io/tolerate-unready-endpoints: "true" +spec: + type: ClusterIP + clusterIP: None + # We want all pods in the StatefulSet to have their addresses published for + # the sake of the other Postgresql pods even before they're ready, since they + # have to be able to talk to each other in order to become ready. + publishNotReadyAddresses: true + ports: + - name: tcp-postgresql + port: {{ template "postgresql.service.port" . }} + targetPort: tcp-postgresql + selector: {{- include "common.labels.matchLabels" . | nindent 4 }} + app.kubernetes.io/component: primary diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/svc.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/svc.yaml new file mode 100644 index 0000000..cf18480 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/primary/svc.yaml @@ -0,0 +1,51 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "postgresql.primary.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + app.kubernetes.io/component: primary + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.primary.service.annotations }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.service.annotations "context" $) | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.primary.service.type }} + {{- if or (eq .Values.primary.service.type "LoadBalancer") (eq .Values.primary.service.type "NodePort") }} + externalTrafficPolicy: {{ .Values.primary.service.externalTrafficPolicy | quote }} + {{- end }} + {{- if and (eq .Values.primary.service.type "LoadBalancer") (not (empty .Values.primary.service.loadBalancerSourceRanges)) }} + loadBalancerSourceRanges: {{ .Values.primary.service.loadBalancerSourceRanges }} + {{- end }} + {{- if and (eq .Values.primary.service.type "LoadBalancer") (not (empty .Values.primary.service.loadBalancerIP)) }} + loadBalancerIP: {{ .Values.primary.service.loadBalancerIP }} + {{- end }} + {{- if and .Values.primary.service.clusterIP (eq .Values.primary.service.type "ClusterIP") }} + clusterIP: {{ .Values.primary.service.clusterIP }} + {{- end }} + {{- if .Values.primary.service.sessionAffinity }} + sessionAffinity: {{ .Values.primary.service.sessionAffinity }} + {{- end }} + {{- if .Values.primary.service.sessionAffinityConfig }} + sessionAffinityConfig: {{- include "common.tplvalues.render" (dict "value" .Values.primary.service.sessionAffinityConfig "context" $) | nindent 4 }} + {{- end }} + ports: + - name: tcp-postgresql + port: {{ template "postgresql.service.port" . }} + targetPort: tcp-postgresql + {{- if and (or (eq .Values.primary.service.type "NodePort") (eq .Values.primary.service.type "LoadBalancer")) (not (empty .Values.primary.service.nodePorts.postgresql)) }} + nodePort: {{ .Values.primary.service.nodePorts.postgresql }} + {{- else if eq .Values.primary.service.type "ClusterIP" }} + nodePort: null + {{- end }} + {{- if .Values.primary.service.extraPorts }} + {{- include "common.tplvalues.render" (dict "value" .Values.primary.service.extraPorts "context" $) | nindent 4 }} + {{- end }} + selector: {{- include "common.labels.matchLabels" . | nindent 4 }} + app.kubernetes.io/component: primary diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/prometheusrule.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/prometheusrule.yaml new file mode 100644 index 0000000..24be710 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/prometheusrule.yaml @@ -0,0 +1,22 @@ +{{- if and .Values.metrics.enabled .Values.metrics.prometheusRule.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ default .Release.Namespace .Values.metrics.prometheusRule.namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: metrics + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.metrics.prometheusRule.labels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.prometheusRule.labels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + groups: + - name: {{ include "common.names.fullname" . }} + rules: {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.prometheusRule.rules "context" $ ) | nindent 8 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/psp.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/psp.yaml new file mode 100644 index 0000000..48d1175 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/psp.yaml @@ -0,0 +1,41 @@ +{{- $pspAvailable := (semverCompare "<1.25-0" (include "common.capabilities.kubeVersion" .)) -}} +{{- if and $pspAvailable .Values.psp.create }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + privileged: false + volumes: + - 'configMap' + - 'secret' + - 'persistentVolumeClaim' + - 'emptyDir' + - 'projected' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + rule: 'RunAsAny' + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + - min: 1 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + - min: 1 + max: 65535 + readOnlyRootFilesystem: false +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/extended-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/extended-configmap.yaml new file mode 100644 index 0000000..e329d13 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/extended-configmap.yaml @@ -0,0 +1,18 @@ +{{- if (include "postgresql.readReplicas.createExtendedConfigmap" .) }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ printf "%s-extended-configuration" (include "postgresql.readReplica.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: read + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: + override.conf: |- + {{- include "common.tplvalues.render" ( dict "value" .Values.readReplicas.extendedConfiguration "context" $ ) | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/metrics-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/metrics-configmap.yaml new file mode 100644 index 0000000..b00a6ec --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/metrics-configmap.yaml @@ -0,0 +1,16 @@ +{{- if and .Values.metrics.enabled .Values.metrics.customMetrics (eq .Values.architecture "replication") }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ printf "%s-metrics" (include "postgresql.readReplica.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: + custom-metrics.yaml: {{ toYaml .Values.metrics.customMetrics | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/metrics-svc.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/metrics-svc.yaml new file mode 100644 index 0000000..b3e5497 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/metrics-svc.yaml @@ -0,0 +1,31 @@ +{{- if and .Values.metrics.enabled (eq .Values.architecture "replication") }} +apiVersion: v1 +kind: Service +metadata: + name: {{ printf "%s-metrics" (include "postgresql.readReplica.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: metrics-read + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.metrics.service.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.service.annotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + sessionAffinity: {{ .Values.metrics.service.sessionAffinity }} + {{- if .Values.metrics.service.clusterIP }} + clusterIP: {{ .Values.metrics.service.clusterIP }} + {{- end }} + ports: + - name: http-metrics + port: {{ .Values.metrics.service.ports.metrics }} + targetPort: http-metrics + selector: {{- include "common.labels.matchLabels" . | nindent 4 }} + app.kubernetes.io/component: read +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/networkpolicy.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/networkpolicy.yaml new file mode 100644 index 0000000..c969cd7 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/networkpolicy.yaml @@ -0,0 +1,36 @@ +{{- if and .Values.networkPolicy.enabled (eq .Values.architecture "replication") .Values.networkPolicy.ingressRules.readReplicasAccessOnlyFrom.enabled }} +apiVersion: {{ include "common.capabilities.networkPolicy.apiVersion" . }} +kind: NetworkPolicy +metadata: + name: {{ printf "%s-ingress" (include "postgresql.readReplica.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: read + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + podSelector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + app.kubernetes.io/component: read + ingress: + {{- if and .Values.networkPolicy.ingressRules.readReplicasAccessOnlyFrom.enabled (or .Values.networkPolicy.ingressRules.readReplicasAccessOnlyFrom.namespaceSelector .Values.networkPolicy.ingressRules.readReplicasAccessOnlyFrom.podSelector) }} + - from: + {{- if .Values.networkPolicy.ingressRules.readReplicasAccessOnlyFrom.namespaceSelector }} + - namespaceSelector: + matchLabels: {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.ingressRules.readReplicasAccessOnlyFrom.namespaceSelector "context" $) | nindent 14 }} + {{- end }} + {{- if .Values.networkPolicy.ingressRules.readReplicasAccessOnlyFrom.podSelector }} + - podSelector: + matchLabels: {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.ingressRules.readReplicasAccessOnlyFrom.podSelector "context" $) | nindent 14 }} + {{- end }} + ports: + - port: {{ .Values.containerPorts.postgresql }} + {{- end }} + {{- if .Values.networkPolicy.ingressRules.readReplicasAccessOnlyFrom.customRules }} + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.ingressRules.readReplicasAccessOnlyFrom.customRules "context" $) | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/servicemonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/servicemonitor.yaml new file mode 100644 index 0000000..d511d6b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/servicemonitor.yaml @@ -0,0 +1,48 @@ +{{- if and .Values.metrics.enabled .Values.metrics.serviceMonitor.enabled (eq .Values.architecture "replication") }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "postgresql.readReplica.fullname" . }} + namespace: {{ default .Release.Namespace .Values.metrics.serviceMonitor.namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: metrics-read + {{- if .Values.metrics.serviceMonitor.labels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.labels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + {{- if .Values.metrics.serviceMonitor.jobLabel }} + jobLabel: {{ .Values.metrics.serviceMonitor.jobLabel }} + {{- end }} + selector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + {{- if .Values.metrics.serviceMonitor.selector }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.serviceMonitor.selector "context" $) | nindent 6 }} + {{- end }} + app.kubernetes.io/component: metrics-read + endpoints: + - port: http-metrics + {{- if .Values.metrics.serviceMonitor.interval }} + interval: {{ .Values.metrics.serviceMonitor.interval }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.metrics.serviceMonitor.scrapeTimeout }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.relabelings }} + relabelings: {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.relabelings "context" $) | nindent 6 }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.metricRelabelings }} + metricRelabelings: {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.metricRelabelings "context" $) | nindent 6 }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.honorLabels }} + honorLabels: {{ .Values.metrics.serviceMonitor.honorLabels }} + {{- end }} + namespaceSelector: + matchNames: + - {{ .Release.Namespace | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/statefulset.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/statefulset.yaml new file mode 100644 index 0000000..b3ff1da --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/statefulset.yaml @@ -0,0 +1,531 @@ +{{- if eq .Values.architecture "replication" }} +{{- $customUser := include "postgresql.username" . }} +apiVersion: {{ include "common.capabilities.statefulset.apiVersion" . }} +kind: StatefulSet +metadata: + name: {{ include "postgresql.readReplica.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: read + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.readReplicas.labels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.readReplicas.labels "context" $ ) | nindent 4 }} + {{- end }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.readReplicas.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.readReplicas.annotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.readReplicas.replicaCount }} + serviceName: {{ include "postgresql.readReplica.svc.headless" . }} + {{- if .Values.readReplicas.updateStrategy }} + updateStrategy: {{- toYaml .Values.readReplicas.updateStrategy | nindent 4 }} + {{- end }} + selector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + app.kubernetes.io/component: read + template: + metadata: + name: {{ include "postgresql.readReplica.fullname" . }} + labels: {{- include "common.labels.standard" . | nindent 8 }} + app.kubernetes.io/component: read + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 8 }} + {{- end }} + {{- if .Values.readReplicas.podLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.readReplicas.podLabels "context" $ ) | nindent 8 }} + {{- end }} + annotations: + {{- if (include "postgresql.readReplicas.createExtendedConfigmap" .) }} + checksum/extended-configuration: {{ include (print $.Template.BasePath "/read/extended-configmap.yaml") . | sha256sum }} + {{- end }} + {{- if .Values.readReplicas.podAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.readReplicas.podAnnotations "context" $ ) | nindent 8 }} + {{- end }} + spec: + {{- if .Values.readReplicas.extraPodSpec }} + {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.extraPodSpec "context" $) | nindent 6 }} + {{- end }} + serviceAccountName: {{ include "postgresql.serviceAccountName" . }} + {{- include "postgresql.imagePullSecrets" . | nindent 6 }} + {{- if .Values.readReplicas.hostAliases }} + hostAliases: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.hostAliases "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.readReplicas.affinity }} + affinity: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.affinity "context" $) | nindent 8 }} + {{- else }} + affinity: + podAffinity: {{- include "common.affinities.pods" (dict "type" .Values.readReplicas.podAffinityPreset "component" "read" "context" $) | nindent 10 }} + podAntiAffinity: {{- include "common.affinities.pods" (dict "type" .Values.readReplicas.podAntiAffinityPreset "component" "read" "context" $) | nindent 10 }} + nodeAffinity: {{- include "common.affinities.nodes" (dict "type" .Values.readReplicas.nodeAffinityPreset.type "key" .Values.readReplicas.nodeAffinityPreset.key "values" .Values.readReplicas.nodeAffinityPreset.values) | nindent 10 }} + {{- end }} + {{- if .Values.readReplicas.nodeSelector }} + nodeSelector: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.nodeSelector "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.readReplicas.tolerations }} + tolerations: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.tolerations "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.readReplicas.topologySpreadConstraints }} + topologySpreadConstraints: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.topologySpreadConstraints "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.readReplicas.priorityClassName }} + priorityClassName: {{ .Values.readReplicas.priorityClassName }} + {{- end }} + {{- if .Values.readReplicas.schedulerName }} + schedulerName: {{ .Values.readReplicas.schedulerName | quote }} + {{- end }} + {{- if .Values.readReplicas.terminationGracePeriodSeconds }} + terminationGracePeriodSeconds: {{ .Values.readReplicas.terminationGracePeriodSeconds }} + {{- end }} + {{- if .Values.readReplicas.podSecurityContext.enabled }} + securityContext: {{- omit .Values.readReplicas.podSecurityContext "enabled" | toYaml | nindent 8 }} + {{- end }} + hostNetwork: {{ .Values.readReplicas.hostNetwork }} + hostIPC: {{ .Values.readReplicas.hostIPC }} + initContainers: + {{- if and .Values.tls.enabled (not .Values.volumePermissions.enabled) }} + - name: copy-certs + image: {{ include "postgresql.volumePermissions.image" . }} + imagePullPolicy: {{ .Values.volumePermissions.image.pullPolicy | quote }} + {{- if .Values.readReplicas.resources }} + resources: {{- toYaml .Values.readReplicas.resources | nindent 12 }} + {{- end }} + # We don't require a privileged container in this case + {{- if .Values.readReplicas.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.readReplicas.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + command: + - /bin/sh + - -ec + - | + cp /tmp/certs/* /opt/bitnami/postgresql/certs/ + chmod 600 {{ include "postgresql.tlsCertKey" . }} + volumeMounts: + - name: raw-certificates + mountPath: /tmp/certs + - name: postgresql-certificates + mountPath: /opt/bitnami/postgresql/certs + {{- else if and .Values.volumePermissions.enabled (or .Values.readReplicas.persistence.enabled .Values.shmVolume.enabled) }} + - name: init-chmod-data + image: {{ include "postgresql.volumePermissions.image" . }} + imagePullPolicy: {{ .Values.volumePermissions.image.pullPolicy | quote }} + {{- if .Values.readReplicas.resources }} + resources: {{- toYaml .Values.readReplicas.resources | nindent 12 }} + {{- end }} + command: + - /bin/sh + - -ec + - | + {{- if .Values.readReplicas.persistence.enabled }} + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + chown `id -u`:`id -G | cut -d " " -f2` {{ .Values.readReplicas.persistence.mountPath }} + {{- else }} + chown {{ .Values.readReplicas.containerSecurityContext.runAsUser }}:{{ .Values.readReplicas.podSecurityContext.fsGroup }} {{ .Values.readReplicas.persistence.mountPath }} + {{- end }} + mkdir -p {{ .Values.readReplicas.persistence.mountPath }}/data {{- if (include "postgresql.mountConfigurationCM" .) }} {{ .Values.readReplicas.persistence.mountPath }}/conf {{- end }} + chmod 700 {{ .Values.readReplicas.persistence.mountPath }}/data {{- if (include "postgresql.mountConfigurationCM" .) }} {{ .Values.readReplicas.persistence.mountPath }}/conf {{- end }} + find {{ .Values.readReplicas.persistence.mountPath }} -mindepth 1 -maxdepth 1 {{- if not (include "postgresql.mountConfigurationCM" .) }} -not -name "conf" {{- end }} -not -name ".snapshot" -not -name "lost+found" | \ + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + xargs -r chown -R `id -u`:`id -G | cut -d " " -f2` + {{- else }} + xargs -r chown -R {{ .Values.readReplicas.containerSecurityContext.runAsUser }}:{{ .Values.readReplicas.podSecurityContext.fsGroup }} + {{- end }} + {{- end }} + {{- if .Values.shmVolume.enabled }} + chmod -R 777 /dev/shm + {{- end }} + {{- if .Values.tls.enabled }} + cp /tmp/certs/* /opt/bitnami/postgresql/certs/ + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + chown -R `id -u`:`id -G | cut -d " " -f2` /opt/bitnami/postgresql/certs/ + {{- else }} + chown -R {{ .Values.readReplicas.containerSecurityContext.runAsUser }}:{{ .Values.readReplicas.podSecurityContext.fsGroup }} /opt/bitnami/postgresql/certs/ + {{- end }} + chmod 600 {{ include "postgresql.tlsCertKey" . }} + {{- end }} + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + securityContext: {{- omit .Values.volumePermissions.containerSecurityContext "runAsUser" | toYaml | nindent 12 }} + {{- else }} + securityContext: {{- .Values.volumePermissions.containerSecurityContext | toYaml | nindent 12 }} + {{- end }} + volumeMounts: + {{ if .Values.readReplicas.persistence.enabled }} + - name: data + mountPath: {{ .Values.readReplicas.persistence.mountPath }} + {{- if .Values.readReplicas.persistence.subPath }} + subPath: {{ .Values.readReplicas.persistence.subPath }} + {{- end }} + {{- end }} + {{- if .Values.shmVolume.enabled }} + - name: dshm + mountPath: /dev/shm + {{- end }} + {{- if .Values.tls.enabled }} + - name: raw-certificates + mountPath: /tmp/certs + - name: postgresql-certificates + mountPath: /opt/bitnami/postgresql/certs + {{- end }} + {{- end }} + {{- if .Values.readReplicas.initContainers }} + {{- include "common.tplvalues.render" ( dict "value" .Values.readReplicas.initContainers "context" $ ) | nindent 8 }} + {{- end }} + containers: + - name: postgresql + image: {{ include "postgresql.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy | quote }} + {{- if .Values.readReplicas.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.readReplicas.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + {{- else if .Values.readReplicas.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.command "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else if .Values.readReplicas.args }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.args "context" $) | nindent 12 }} + {{- end }} + env: + - name: BITNAMI_DEBUG + value: {{ ternary "true" "false" (or .Values.image.debug .Values.diagnosticMode.enabled) | quote }} + - name: POSTGRESQL_PORT_NUMBER + value: {{ .Values.containerPorts.postgresql | quote }} + - name: POSTGRESQL_VOLUME_DIR + value: {{ .Values.readReplicas.persistence.mountPath | quote }} + {{- if .Values.readReplicas.persistence.mountPath }} + - name: PGDATA + value: {{ .Values.postgresqlDataDir | quote }} + {{- end }} + # Authentication + {{- if and (not (empty $customUser)) (ne $customUser "postgres") .Values.auth.enablePostgresUser }} + {{- if .Values.auth.usePasswordFiles }} + - name: POSTGRES_POSTGRES_PASSWORD_FILE + value: "/opt/bitnami/postgresql/secrets/postgres-password" + {{- else }} + - name: POSTGRES_POSTGRES_PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "postgresql.secretName" . }} + key: {{ include "postgresql.adminPasswordKey" . }} + {{- end }} + {{- end }} + {{- if .Values.auth.usePasswordFiles }} + - name: POSTGRES_PASSWORD_FILE + value: {{ printf "/opt/bitnami/postgresql/secrets/%s" (ternary "password" "postgres-password" (and (not (empty $customUser)) (ne $customUser "postgres"))) }} + {{- else }} + - name: POSTGRES_PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "postgresql.secretName" . }} + key: {{ include "postgresql.userPasswordKey" . }} + {{- end }} + # Replication + - name: POSTGRES_REPLICATION_MODE + value: "slave" + - name: POSTGRES_REPLICATION_USER + value: {{ .Values.auth.replicationUsername | quote }} + {{- if .Values.auth.usePasswordFiles }} + - name: POSTGRES_REPLICATION_PASSWORD_FILE + value: "/opt/bitnami/postgresql/secrets/replication-password" + {{- else }} + - name: POSTGRES_REPLICATION_PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "postgresql.secretName" . }} + key: {{ include "postgresql.replicationPasswordKey" . }} + {{- end }} + - name: POSTGRES_CLUSTER_APP_NAME + value: {{ .Values.replication.applicationName }} + - name: POSTGRES_MASTER_HOST + value: {{ include "postgresql.primary.fullname" . }} + - name: POSTGRES_MASTER_PORT_NUMBER + value: {{ include "postgresql.service.port" . | quote }} + # TLS + - name: POSTGRESQL_ENABLE_TLS + value: {{ ternary "yes" "no" .Values.tls.enabled | quote }} + {{- if .Values.tls.enabled }} + - name: POSTGRESQL_TLS_PREFER_SERVER_CIPHERS + value: {{ ternary "yes" "no" .Values.tls.preferServerCiphers | quote }} + - name: POSTGRESQL_TLS_CERT_FILE + value: {{ include "postgresql.tlsCert" . }} + - name: POSTGRESQL_TLS_KEY_FILE + value: {{ include "postgresql.tlsCertKey" . }} + {{- if .Values.tls.certCAFilename }} + - name: POSTGRESQL_TLS_CA_FILE + value: {{ include "postgresql.tlsCACert" . }} + {{- end }} + {{- if .Values.tls.crlFilename }} + - name: POSTGRESQL_TLS_CRL_FILE + value: {{ include "postgresql.tlsCRL" . }} + {{- end }} + {{- end }} + # Audit + - name: POSTGRESQL_LOG_HOSTNAME + value: {{ .Values.audit.logHostname | quote }} + - name: POSTGRESQL_LOG_CONNECTIONS + value: {{ .Values.audit.logConnections | quote }} + - name: POSTGRESQL_LOG_DISCONNECTIONS + value: {{ .Values.audit.logDisconnections | quote }} + {{- if .Values.audit.logLinePrefix }} + - name: POSTGRESQL_LOG_LINE_PREFIX + value: {{ .Values.audit.logLinePrefix | quote }} + {{- end }} + {{- if .Values.audit.logTimezone }} + - name: POSTGRESQL_LOG_TIMEZONE + value: {{ .Values.audit.logTimezone | quote }} + {{- end }} + {{- if .Values.audit.pgAuditLog }} + - name: POSTGRESQL_PGAUDIT_LOG + value: {{ .Values.audit.pgAuditLog | quote }} + {{- end }} + - name: POSTGRESQL_PGAUDIT_LOG_CATALOG + value: {{ .Values.audit.pgAuditLogCatalog | quote }} + # Others + - name: POSTGRESQL_CLIENT_MIN_MESSAGES + value: {{ .Values.audit.clientMinMessages | quote }} + - name: POSTGRESQL_SHARED_PRELOAD_LIBRARIES + value: {{ .Values.postgresqlSharedPreloadLibraries | quote }} + {{- if .Values.readReplicas.extraEnvVars }} + {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.extraEnvVars "context" $) | nindent 12 }} + {{- end }} + {{- if or .Values.readReplicas.extraEnvVarsCM .Values.readReplicas.extraEnvVarsSecret }} + envFrom: + {{- if .Values.readReplicas.extraEnvVarsCM }} + - configMapRef: + name: {{ .Values.readReplicas.extraEnvVarsCM }} + {{- end }} + {{- if .Values.readReplicas.extraEnvVarsSecret }} + - secretRef: + name: {{ .Values.readReplicas.extraEnvVarsSecret }} + {{- end }} + {{- end }} + ports: + - name: tcp-postgresql + containerPort: {{ .Values.containerPorts.postgresql }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.readReplicas.customStartupProbe }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.customStartupProbe "context" $) | nindent 12 }} + {{- else if .Values.readReplicas.startupProbe.enabled }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.readReplicas.startupProbe "enabled") "context" $) | nindent 12 }} + exec: + command: + - /bin/sh + - -c + {{- if (include "postgresql.database" .) }} + - exec pg_isready -U {{ default "postgres" $customUser| quote }} -d "dbname={{ include "postgresql.database" . }} {{- if and .Values.tls.enabled .Values.tls.certCAFilename }} sslcert={{ include "postgresql.tlsCert" . }} sslkey={{ include "postgresql.tlsCertKey" . }}{{- end }}" -h 127.0.0.1 -p {{ .Values.containerPorts.postgresql }} + {{- else }} + - exec pg_isready -U {{ default "postgres" $customUser | quote }} {{- if and .Values.tls.enabled .Values.tls.certCAFilename }} -d "sslcert={{ include "postgresql.tlsCert" . }} sslkey={{ include "postgresql.tlsCertKey" . }}"{{- end }} -h 127.0.0.1 -p {{ .Values.containerPorts.postgresql }} + {{- end }} + {{- end }} + {{- if .Values.readReplicas.customLivenessProbe }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.customLivenessProbe "context" $) | nindent 12 }} + {{- else if .Values.readReplicas.livenessProbe.enabled }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.readReplicas.livenessProbe "enabled") "context" $) | nindent 12 }} + exec: + command: + - /bin/sh + - -c + {{- if (include "postgresql.database" .) }} + - exec pg_isready -U {{ default "postgres" $customUser | quote }} -d "dbname={{ include "postgresql.database" . }} {{- if and .Values.tls.enabled .Values.tls.certCAFilename }} sslcert={{ include "postgresql.tlsCert" . }} sslkey={{ include "postgresql.tlsCertKey" . }}{{- end }}" -h 127.0.0.1 -p {{ .Values.containerPorts.postgresql }} + {{- else }} + - exec pg_isready -U {{default "postgres" $customUser | quote }} {{- if and .Values.tls.enabled .Values.tls.certCAFilename }} -d "sslcert={{ include "postgresql.tlsCert" . }} sslkey={{ include "postgresql.tlsCertKey" . }}"{{- end }} -h 127.0.0.1 -p {{ .Values.containerPorts.postgresql }} + {{- end }} + {{- end }} + {{- if .Values.readReplicas.customReadinessProbe }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.customReadinessProbe "context" $) | nindent 12 }} + {{- else if .Values.readReplicas.readinessProbe.enabled }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.readReplicas.readinessProbe "enabled") "context" $) | nindent 12 }} + exec: + command: + - /bin/sh + - -c + - -e + {{- include "postgresql.readinessProbeCommand" . | nindent 16 }} + {{- end }} + {{- end }} + {{- if .Values.readReplicas.resources }} + resources: {{- toYaml .Values.readReplicas.resources | nindent 12 }} + {{- end }} + {{- if .Values.readReplicas.lifecycleHooks }} + lifecycle: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.lifecycleHooks "context" $) | nindent 12 }} + {{- end }} + volumeMounts: + {{- if .Values.auth.usePasswordFiles }} + - name: postgresql-password + mountPath: /opt/bitnami/postgresql/secrets/ + {{- end }} + {{- if .Values.readReplicas.extendedConfiguration }} + - name: postgresql-extended-config + mountPath: /bitnami/postgresql/conf/conf.d/ + {{- end }} + {{- if .Values.tls.enabled }} + - name: postgresql-certificates + mountPath: /opt/bitnami/postgresql/certs + readOnly: true + {{- end }} + {{- if .Values.shmVolume.enabled }} + - name: dshm + mountPath: /dev/shm + {{- end }} + {{- if .Values.readReplicas.persistence.enabled }} + - name: data + mountPath: {{ .Values.readReplicas.persistence.mountPath }} + {{- if .Values.readReplicas.persistence.subPath }} + subPath: {{ .Values.readReplicas.persistence.subPath }} + {{- end }} + {{- end }} + {{- if .Values.readReplicas.extraVolumeMounts }} + {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.extraVolumeMounts "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.metrics.enabled }} + - name: metrics + image: {{ include "postgresql.metrics.image" . }} + imagePullPolicy: {{ .Values.metrics.image.pullPolicy | quote }} + {{- if .Values.metrics.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.metrics.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else if .Values.metrics.customMetrics }} + args: [ "--extend.query-path", "/conf/custom-metrics.yaml" ] + {{- end }} + env: + {{- $database := required "In order to enable metrics you need to specify a database (.Values.auth.database or .Values.global.postgresql.auth.database)" (include "postgresql.database" .) }} + - name: DATA_SOURCE_URI + value: {{ printf "127.0.0.1:%d/%s?sslmode=disable" (int (include "postgresql.service.port" .)) $database }} + {{- if .Values.auth.usePasswordFiles }} + - name: DATA_SOURCE_PASS_FILE + value: {{ printf "/opt/bitnami/postgresql/secrets/%s" (ternary "password" "postgres-password" (and (not (empty $customUser)) (ne $customUser "postgres"))) }} + {{- else }} + - name: DATA_SOURCE_PASS + valueFrom: + secretKeyRef: + name: {{ include "postgresql.secretName" . }} + key: {{ include "postgresql.userPasswordKey" . }} + {{- end }} + - name: DATA_SOURCE_USER + value: {{ default "postgres" $customUser | quote }} + {{- if .Values.metrics.extraEnvVars }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.extraEnvVars "context" $) | nindent 12 }} + {{- end }} + ports: + - name: http-metrics + containerPort: {{ .Values.metrics.containerPorts.metrics }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.metrics.customStartupProbe }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.metrics.customStartupProbe "context" $) | nindent 12 }} + {{- else if .Values.metrics.startupProbe.enabled }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.metrics.startupProbe "enabled") "context" $) | nindent 12 }} + tcpSocket: + port: http-metrics + {{- end }} + {{- if .Values.metrics.customLivenessProbe }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.metrics.customLivenessProbe "context" $) | nindent 12 }} + {{- else if .Values.metrics.livenessProbe.enabled }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.metrics.livenessProbe "enabled") "context" $) | nindent 12 }} + httpGet: + path: / + port: http-metrics + {{- end }} + {{- if .Values.metrics.customReadinessProbe }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.metrics.customReadinessProbe "context" $) | nindent 12 }} + {{- else if .Values.metrics.readinessProbe.enabled }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.metrics.readinessProbe "enabled") "context" $) | nindent 12 }} + httpGet: + path: / + port: http-metrics + {{- end }} + {{- end }} + volumeMounts: + {{- if .Values.auth.usePasswordFiles }} + - name: postgresql-password + mountPath: /opt/bitnami/postgresql/secrets/ + {{- end }} + {{- if .Values.metrics.customMetrics }} + - name: custom-metrics + mountPath: /conf + readOnly: true + {{- end }} + {{- if .Values.metrics.resources }} + resources: {{- toYaml .Values.metrics.resources | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.readReplicas.sidecars }} + {{- include "common.tplvalues.render" ( dict "value" .Values.readReplicas.sidecars "context" $ ) | nindent 8 }} + {{- end }} + volumes: + {{- if .Values.readReplicas.extendedConfiguration }} + - name: postgresql-extended-config + configMap: + name: {{ include "postgresql.readReplicas.extendedConfigmapName" . }} + {{- end }} + {{- if .Values.auth.usePasswordFiles }} + - name: postgresql-password + secret: + secretName: {{ include "postgresql.secretName" . }} + {{- end }} + {{- if .Values.tls.enabled }} + - name: raw-certificates + secret: + secretName: {{ include "postgresql.tlsSecretName" . }} + - name: postgresql-certificates + emptyDir: {} + {{- end }} + {{- if and .Values.metrics.enabled .Values.metrics.customMetrics }} + - name: custom-metrics + configMap: + name: {{ printf "%s-metrics" (include "common.names.fullname" .) }} + {{- end }} + {{- if .Values.shmVolume.enabled }} + - name: dshm + emptyDir: + medium: Memory + {{- if .Values.shmVolume.sizeLimit }} + sizeLimit: {{ .Values.shmVolume.sizeLimit }} + {{- end }} + {{- end }} + {{- if .Values.readReplicas.extraVolumes }} + {{- include "common.tplvalues.render" ( dict "value" .Values.readReplicas.extraVolumes "context" $ ) | nindent 8 }} + {{- end }} + {{- if and .Values.readReplicas.persistence.enabled .Values.readReplicas.persistence.existingClaim }} + - name: data + persistentVolumeClaim: + claimName: {{ tpl .Values.readReplicas.persistence.existingClaim $ }} + {{- else if not .Values.readReplicas.persistence.enabled }} + - name: data + emptyDir: {} + {{- else }} + volumeClaimTemplates: + - metadata: + name: data + {{- if .Values.readReplicas.persistence.annotations }} + annotations: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.persistence.annotations "context" $) | nindent 10 }} + {{- end }} + {{- if .Values.readReplicas.persistence.labels }} + labels: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.persistence.labels "context" $) | nindent 10 }} + {{- end }} + spec: + accessModes: + {{- range .Values.readReplicas.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + {{- if .Values.readReplicas.persistence.dataSource }} + dataSource: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.persistence.dataSource "context" $) | nindent 10 }} + {{- end }} + resources: + requests: + storage: {{ .Values.readReplicas.persistence.size | quote }} + {{- if .Values.readReplicas.persistence.selector }} + selector: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.persistence.selector "context" $) | nindent 10 }} + {{- end -}} + {{- include "common.storage.class" (dict "persistence" .Values.readReplicas.persistence "global" .Values.global) | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/svc-headless.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/svc-headless.yaml new file mode 100644 index 0000000..0371e49 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/svc-headless.yaml @@ -0,0 +1,33 @@ +{{- if eq .Values.architecture "replication" }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "postgresql.readReplica.svc.headless" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + app.kubernetes.io/component: read + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + # Use this annotation in addition to the actual publishNotReadyAddresses + # field below because the annotation will stop being respected soon but the + # field is broken in some versions of Kubernetes: + # https://github.com/kubernetes/kubernetes/issues/58662 + service.alpha.kubernetes.io/tolerate-unready-endpoints: "true" +spec: + type: ClusterIP + clusterIP: None + # We want all pods in the StatefulSet to have their addresses published for + # the sake of the other Postgresql pods even before they're ready, since they + # have to be able to talk to each other in order to become ready. + publishNotReadyAddresses: true + ports: + - name: tcp-postgresql + port: {{ include "postgresql.readReplica.service.port" . }} + targetPort: tcp-postgresql + selector: {{- include "common.labels.matchLabels" . | nindent 4 }} + app.kubernetes.io/component: read +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/svc.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/svc.yaml new file mode 100644 index 0000000..3eece4d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/read/svc.yaml @@ -0,0 +1,53 @@ +{{- if eq .Values.architecture "replication" }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "postgresql.readReplica.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + app.kubernetes.io/component: read + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.readReplicas.service.annotations }} + {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.service.annotations "context" $) | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.readReplicas.service.type }} + {{- if or (eq .Values.readReplicas.service.type "LoadBalancer") (eq .Values.readReplicas.service.type "NodePort") }} + externalTrafficPolicy: {{ .Values.readReplicas.service.externalTrafficPolicy | quote }} + {{- end }} + {{- if and (eq .Values.readReplicas.service.type "LoadBalancer") (not (empty .Values.readReplicas.service.loadBalancerSourceRanges)) }} + loadBalancerSourceRanges: {{ .Values.readReplicas.service.loadBalancerSourceRanges }} + {{- end }} + {{- if and (eq .Values.readReplicas.service.type "LoadBalancer") (not (empty .Values.readReplicas.service.loadBalancerIP)) }} + loadBalancerIP: {{ .Values.readReplicas.service.loadBalancerIP }} + {{- end }} + {{- if and .Values.readReplicas.service.clusterIP (eq .Values.readReplicas.service.type "ClusterIP") }} + clusterIP: {{ .Values.readReplicas.service.clusterIP }} + {{- end }} + {{- if .Values.readReplicas.service.sessionAffinity }} + sessionAffinity: {{ .Values.readReplicas.service.sessionAffinity }} + {{- end }} + {{- if .Values.readReplicas.service.sessionAffinityConfig }} + sessionAffinityConfig: {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.service.sessionAffinityConfig "context" $) | nindent 4 }} + {{- end }} + ports: + - name: tcp-postgresql + port: {{ include "postgresql.readReplica.service.port" . }} + targetPort: tcp-postgresql + {{- if and (or (eq .Values.readReplicas.service.type "NodePort") (eq .Values.readReplicas.service.type "LoadBalancer")) (not (empty .Values.readReplicas.service.nodePorts.postgresql)) }} + nodePort: {{ .Values.readReplicas.service.nodePorts.postgresql }} + {{- else if eq .Values.readReplicas.service.type "ClusterIP" }} + nodePort: null + {{- end }} + {{- if .Values.readReplicas.service.extraPorts }} + {{- include "common.tplvalues.render" (dict "value" .Values.readReplicas.service.extraPorts "context" $) | nindent 4 }} + {{- end }} + selector: {{- include "common.labels.matchLabels" . | nindent 4 }} + app.kubernetes.io/component: read +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/role.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/role.yaml new file mode 100644 index 0000000..00f9222 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/role.yaml @@ -0,0 +1,31 @@ +{{- if .Values.rbac.create }} +kind: Role +apiVersion: {{ include "common.capabilities.rbac.apiVersion" . }} +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +# yamllint disable rule:indentation +rules: + {{- $pspAvailable := (semverCompare "<1.25-0" (include "common.capabilities.kubeVersion" .)) -}} + {{- if and $pspAvailable .Values.psp.create }} + - apiGroups: + - 'policy' + resources: + - 'podsecuritypolicies' + verbs: + - 'use' + resourceNames: + - {{ include "common.names.fullname" . }} + {{- end }} + {{- if .Values.rbac.rules }} + {{- include "common.tplvalues.render" ( dict "value" .Values.rbac.rules "context" $ ) | nindent 2 }} + {{- end }} +# yamllint enable rule:indentation +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/rolebinding.yaml new file mode 100644 index 0000000..0311c0e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/rolebinding.yaml @@ -0,0 +1,22 @@ +{{- if .Values.rbac.create }} +kind: RoleBinding +apiVersion: {{ include "common.capabilities.rbac.apiVersion" . }} +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +roleRef: + kind: Role + name: {{ include "common.names.fullname" . }} + apiGroup: rbac.authorization.k8s.io +subjects: + - kind: ServiceAccount + name: {{ include "postgresql.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/secrets.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/secrets.yaml new file mode 100644 index 0000000..5f28fb3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/secrets.yaml @@ -0,0 +1,29 @@ +{{- if (include "postgresql.createSecret" .) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: Opaque +data: + {{- if .Values.auth.enablePostgresUser }} + postgres-password: {{ include "common.secrets.passwords.manage" (dict "secret" (include "common.names.fullname" .) "key" "postgres-password" "providedValues" (list "global.postgresql.auth.postgresPassword" "auth.postgresPassword") "context" $) }} + {{- end }} + {{- if not (empty (include "postgresql.username" .)) }} + password: {{ include "common.secrets.passwords.manage" (dict "secret" (include "common.names.fullname" .) "key" "password" "providedValues" (list "global.postgresql.auth.password" "auth.password") "context" $) }} + {{- end }} + {{- if eq .Values.architecture "replication" }} + replication-password: {{ include "common.secrets.passwords.manage" (dict "secret" (include "common.names.fullname" .) "key" "replication-password" "providedValues" (list "auth.replicationPassword") "context" $) }} + {{- end }} + # We don't auto-generate LDAP password when it's not provided as we do for other passwords + {{- if and .Values.ldap.enabled (or .Values.ldap.bind_password .Values.ldap.bindpw) }} + ldap-password: {{ coalesce .Values.ldap.bind_password .Values.ldap.bindpw | b64enc | quote }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/serviceaccount.yaml new file mode 100644 index 0000000..179f8f2 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/serviceaccount.yaml @@ -0,0 +1,19 @@ +{{- if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "postgresql.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.serviceAccount.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.serviceAccount.annotations "context" $ ) | nindent 4 }} + {{- end }} +automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/tls-secrets.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/tls-secrets.yaml new file mode 100644 index 0000000..59c5776 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/templates/tls-secrets.yaml @@ -0,0 +1,27 @@ +{{- if (include "postgresql.createTlsSecret" . ) }} +{{- $ca := genCA "postgresql-ca" 365 }} +{{- $fullname := include "common.names.fullname" . }} +{{- $releaseNamespace := .Release.Namespace }} +{{- $clusterDomain := .Values.clusterDomain }} +{{- $primaryHeadlessServiceName := include "postgresql.primary.svc.headless" . }} +{{- $readHeadlessServiceName := include "postgresql.readReplica.svc.headless" . }} +{{- $altNames := list (printf "*.%s.%s.svc.%s" $fullname $releaseNamespace $clusterDomain) (printf "%s.%s.svc.%s" $fullname $releaseNamespace $clusterDomain) (printf "*.%s.%s.svc.%s" $primaryHeadlessServiceName $releaseNamespace $clusterDomain) (printf "%s.%s.svc.%s" $primaryHeadlessServiceName $releaseNamespace $clusterDomain) (printf "*.%s.%s.svc.%s" $readHeadlessServiceName $releaseNamespace $clusterDomain) (printf "%s.%s.svc.%s" $readHeadlessServiceName $releaseNamespace $clusterDomain) $fullname }} +{{- $crt := genSignedCert $fullname nil $altNames 365 $ca }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ printf "%s-crt" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: kubernetes.io/tls +data: + ca.crt: {{ $ca.Cert | b64enc | quote }} + tls.crt: {{ $crt.Cert | b64enc | quote }} + tls.key: {{ $crt.Key | b64enc | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/values.schema.json b/observability/lgtm-distributed/charts/oncall/charts/postgresql/values.schema.json new file mode 100644 index 0000000..fc41483 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/values.schema.json @@ -0,0 +1,156 @@ +{ + "$schema": "http://json-schema.org/schema#", + "type": "object", + "properties": { + "architecture": { + "type": "string", + "title": "PostgreSQL architecture", + "form": true, + "description": "Allowed values: `standalone` or `replication`" + }, + "auth": { + "type": "object", + "title": "Authentication configuration", + "form": true, + "properties": { + "enablePostgresUser": { + "type": "boolean", + "title": "Enable \"postgres\" admin user", + "description": "Assign a password to the \"postgres\" admin user. Otherwise, remote access will be blocked for this user", + "form": true + }, + "postgresPassword": { + "type": "string", + "title": "Password for the \"postgres\" admin user", + "description": "Defaults to a random 10-character alphanumeric string if not set", + "form": true + }, + "database": { + "type": "string", + "title": "PostgreSQL custom database", + "description": "Name of the custom database to be created during the 1st initialization of PostgreSQL", + "form": true + }, + "username": { + "type": "string", + "title": "PostgreSQL custom user", + "description": "Name of the custom user to be created during the 1st initialization of PostgreSQL. This user only has permissions on the PostgreSQL custom database", + "form": true + }, + "password": { + "type": "string", + "title": "Password for the custom user to create", + "description": "Defaults to a random 10-character alphanumeric string if not set", + "form": true + }, + "replicationUsername": { + "type": "string", + "title": "PostgreSQL replication user", + "description": "Name of user used to manage replication.", + "form": true, + "hidden": { + "value": "standalone", + "path": "architecture" + } + }, + "replicationPassword": { + "type": "string", + "title": "Password for PostgreSQL replication user", + "description": "Defaults to a random 10-character alphanumeric string if not set", + "form": true, + "hidden": { + "value": "standalone", + "path": "architecture" + } + } + } + }, + "persistence": { + "type": "object", + "properties": { + "size": { + "type": "string", + "title": "Persistent Volume Size", + "form": true, + "render": "slider", + "sliderMin": 1, + "sliderMax": 100, + "sliderUnit": "Gi" + } + } + }, + "resources": { + "type": "object", + "title": "Required Resources", + "description": "Configure resource requests", + "form": true, + "properties": { + "requests": { + "type": "object", + "properties": { + "memory": { + "type": "string", + "form": true, + "render": "slider", + "title": "Memory Request", + "sliderMin": 10, + "sliderMax": 2048, + "sliderUnit": "Mi" + }, + "cpu": { + "type": "string", + "form": true, + "render": "slider", + "title": "CPU Request", + "sliderMin": 10, + "sliderMax": 2000, + "sliderUnit": "m" + } + } + } + } + }, + "replication": { + "type": "object", + "form": true, + "title": "Replication Details", + "properties": { + "enabled": { + "type": "boolean", + "title": "Enable Replication", + "form": true + }, + "readReplicas": { + "type": "integer", + "title": "read Replicas", + "form": true, + "hidden": { + "value": "standalone", + "path": "architecture" + } + } + } + }, + "volumePermissions": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean", + "form": true, + "title": "Enable Init Containers", + "description": "Change the owner of the persist volume mountpoint to RunAsUser:fsGroup" + } + } + }, + "metrics": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean", + "title": "Configure metrics exporter", + "form": true + } + } + } + } +} diff --git a/observability/lgtm-distributed/charts/oncall/charts/postgresql/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/postgresql/values.yaml new file mode 100644 index 0000000..ab87002 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/postgresql/values.yaml @@ -0,0 +1,1399 @@ +## @section Global parameters +## Please, note that this will override the parameters, including dependencies, configured to use the global value +## +global: + ## @param global.imageRegistry Global Docker image registry + ## + imageRegistry: "" + ## @param global.imagePullSecrets Global Docker registry secret names as an array + ## e.g. + ## imagePullSecrets: + ## - myRegistryKeySecretName + ## + imagePullSecrets: [] + ## @param global.storageClass Global StorageClass for Persistent Volume(s) + ## + storageClass: "" + postgresql: + ## @param global.postgresql.auth.postgresPassword Password for the "postgres" admin user (overrides `auth.postgresPassword`) + ## @param global.postgresql.auth.username Name for a custom user to create (overrides `auth.username`) + ## @param global.postgresql.auth.password Password for the custom user to create (overrides `auth.password`) + ## @param global.postgresql.auth.database Name for a custom database to create (overrides `auth.database`) + ## @param global.postgresql.auth.existingSecret Name of existing secret to use for PostgreSQL credentials (overrides `auth.existingSecret`). + ## @param global.postgresql.auth.secretKeys.adminPasswordKey Name of key in existing secret to use for PostgreSQL credentials (overrides `auth.secretKeys.adminPasswordKey`). Only used when `global.postgresql.auth.existingSecret` is set. + ## @param global.postgresql.auth.secretKeys.userPasswordKey Name of key in existing secret to use for PostgreSQL credentials (overrides `auth.secretKeys.userPasswordKey`). Only used when `global.postgresql.auth.existingSecret` is set. + ## @param global.postgresql.auth.secretKeys.replicationPasswordKey Name of key in existing secret to use for PostgreSQL credentials (overrides `auth.secretKeys.replicationPasswordKey`). Only used when `global.postgresql.auth.existingSecret` is set. + ## + auth: + postgresPassword: "" + username: "" + password: "" + database: "" + existingSecret: "" + secretKeys: + adminPasswordKey: "" + userPasswordKey: "" + replicationPasswordKey: "" + ## @param global.postgresql.service.ports.postgresql PostgreSQL service port (overrides `service.ports.postgresql`) + ## + service: + ports: + postgresql: "" + +## @section Common parameters +## + +## @param kubeVersion Override Kubernetes version +## +kubeVersion: "" +## @param nameOverride String to partially override common.names.fullname template (will maintain the release name) +## +nameOverride: "" +## @param fullnameOverride String to fully override common.names.fullname template +## +fullnameOverride: "" +## @param clusterDomain Kubernetes Cluster Domain +## +clusterDomain: cluster.local +## @param extraDeploy Array of extra objects to deploy with the release (evaluated as a template) +## +extraDeploy: [] +## @param commonLabels Add labels to all the deployed resources +## +commonLabels: {} +## @param commonAnnotations Add annotations to all the deployed resources +## +commonAnnotations: {} +## Enable diagnostic mode in the statefulset +## +diagnosticMode: + ## @param diagnosticMode.enabled Enable diagnostic mode (all probes will be disabled and the command will be overridden) + ## + enabled: false + ## @param diagnosticMode.command Command to override all containers in the statefulset + ## + command: + - sleep + ## @param diagnosticMode.args Args to override all containers in the statefulset + ## + args: + - infinity + +## @section PostgreSQL common parameters +## + +## Bitnami PostgreSQL image version +## ref: https://hub.docker.com/r/bitnami/postgresql/tags/ +## @param image.registry PostgreSQL image registry +## @param image.repository PostgreSQL image repository +## @param image.tag PostgreSQL image tag (immutable tags are recommended) +## @param image.digest PostgreSQL image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag +## @param image.pullPolicy PostgreSQL image pull policy +## @param image.pullSecrets Specify image pull secrets +## @param image.debug Specify if debug values should be set +## +image: + registry: docker.io + repository: bitnami/postgresql + tag: 14.5.0-debian-11-r30 + digest: "" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## Set to true if you would like to see extra information on logs + ## + debug: false +## Authentication parameters +## ref: https://github.com/bitnami/containers/tree/main/bitnami/postgresql#setting-the-root-password-on-first-run +## ref: https://github.com/bitnami/containers/tree/main/bitnami/postgresql#creating-a-database-on-first-run +## ref: https://github.com/bitnami/containers/tree/main/bitnami/postgresql#creating-a-database-user-on-first-run +## +auth: + ## @param auth.enablePostgresUser Assign a password to the "postgres" admin user. Otherwise, remote access will be blocked for this user + ## + enablePostgresUser: true + ## @param auth.postgresPassword Password for the "postgres" admin user. Ignored if `auth.existingSecret` with key `postgres-password` is provided + ## + postgresPassword: "" + ## @param auth.username Name for a custom user to create + ## + username: "" + ## @param auth.password Password for the custom user to create. Ignored if `auth.existingSecret` with key `password` is provided + ## + password: "" + ## @param auth.database Name for a custom database to create + ## + database: "" + ## @param auth.replicationUsername Name of the replication user + ## + replicationUsername: repl_user + ## @param auth.replicationPassword Password for the replication user. Ignored if `auth.existingSecret` with key `replication-password` is provided + ## + replicationPassword: "" + ## @param auth.existingSecret Name of existing secret to use for PostgreSQL credentials. `auth.postgresPassword`, `auth.password`, and `auth.replicationPassword` will be ignored and picked up from this secret. The secret might also contains the key `ldap-password` if LDAP is enabled. `ldap.bind_password` will be ignored and picked from this secret in this case. + ## + existingSecret: "" + ## @param auth.secretKeys.adminPasswordKey Name of key in existing secret to use for PostgreSQL credentials. Only used when `auth.existingSecret` is set. + ## @param auth.secretKeys.userPasswordKey Name of key in existing secret to use for PostgreSQL credentials. Only used when `auth.existingSecret` is set. + ## @param auth.secretKeys.replicationPasswordKey Name of key in existing secret to use for PostgreSQL credentials. Only used when `auth.existingSecret` is set. + ## + secretKeys: + adminPasswordKey: postgres-password + userPasswordKey: password + replicationPasswordKey: replication-password + ## @param auth.usePasswordFiles Mount credentials as a files instead of using an environment variable + ## + usePasswordFiles: false +## @param architecture PostgreSQL architecture (`standalone` or `replication`) +## +architecture: standalone +## Replication configuration +## Ignored if `architecture` is `standalone` +## +replication: + ## @param replication.synchronousCommit Set synchronous commit mode. Allowed values: `on`, `remote_apply`, `remote_write`, `local` and `off` + ## @param replication.numSynchronousReplicas Number of replicas that will have synchronous replication. Note: Cannot be greater than `readReplicas.replicaCount`. + ## ref: https://www.postgresql.org/docs/current/runtime-config-wal.html#GUC-SYNCHRONOUS-COMMIT + ## + synchronousCommit: "off" + numSynchronousReplicas: 0 + ## @param replication.applicationName Cluster application name. Useful for advanced replication settings + ## + applicationName: my_application +## @param containerPorts.postgresql PostgreSQL container port +## +containerPorts: + postgresql: 5432 +## Audit settings +## https://github.com/bitnami/containers/tree/main/bitnami/postgresql#auditing +## @param audit.logHostname Log client hostnames +## @param audit.logConnections Add client log-in operations to the log file +## @param audit.logDisconnections Add client log-outs operations to the log file +## @param audit.pgAuditLog Add operations to log using the pgAudit extension +## @param audit.pgAuditLogCatalog Log catalog using pgAudit +## @param audit.clientMinMessages Message log level to share with the user +## @param audit.logLinePrefix Template for log line prefix (default if not set) +## @param audit.logTimezone Timezone for the log timestamps +## +audit: + logHostname: false + logConnections: false + logDisconnections: false + pgAuditLog: "" + pgAuditLogCatalog: "off" + clientMinMessages: error + logLinePrefix: "" + logTimezone: "" +## LDAP configuration +## @param ldap.enabled Enable LDAP support +## DEPRECATED ldap.url It will removed in a future, please use 'ldap.uri' instead +## @param ldap.server IP address or name of the LDAP server. +## @param ldap.port Port number on the LDAP server to connect to +## @param ldap.prefix String to prepend to the user name when forming the DN to bind +## @param ldap.suffix String to append to the user name when forming the DN to bind +## DEPRECATED ldap.baseDN It will removed in a future, please use 'ldap.basedn' instead +## DEPRECATED ldap.bindDN It will removed in a future, please use 'ldap.binddn' instead +## DEPRECATED ldap.bind_password It will removed in a future, please use 'ldap.bindpw' instead +## @param ldap.basedn Root DN to begin the search for the user in +## @param ldap.binddn DN of user to bind to LDAP +## @param ldap.bindpw Password for the user to bind to LDAP +## DEPRECATED ldap.search_attr It will removed in a future, please use 'ldap.searchAttribute' instead +## DEPRECATED ldap.search_filter It will removed in a future, please use 'ldap.searchFilter' instead +## @param ldap.searchAttribute Attribute to match against the user name in the search +## @param ldap.searchFilter The search filter to use when doing search+bind authentication +## @param ldap.scheme Set to `ldaps` to use LDAPS +## DEPRECATED ldap.tls as string is deprecated,please use 'ldap.tls.enabled' instead +## @param ldap.tls.enabled Se to true to enable TLS encryption +## +ldap: + enabled: false + server: "" + port: "" + prefix: "" + suffix: "" + basedn: "" + binddn: "" + bindpw: "" + searchAttribute: "" + searchFilter: "" + scheme: "" + tls: + enabled: false + ## @param ldap.uri LDAP URL beginning in the form `ldap[s]://host[:port]/basedn`. If provided, all the other LDAP parameters will be ignored. + ## Ref: https://www.postgresql.org/docs/current/auth-ldap.html + uri: "" +## @param postgresqlDataDir PostgreSQL data dir folder +## +postgresqlDataDir: /bitnami/postgresql/data +## @param postgresqlSharedPreloadLibraries Shared preload libraries (comma-separated list) +## +postgresqlSharedPreloadLibraries: "pgaudit" +## Start PostgreSQL pod(s) without limitations on shm memory. +## By default docker and containerd (and possibly other container runtimes) limit `/dev/shm` to `64M` +## ref: https://github.com/docker-library/postgres/issues/416 +## ref: https://github.com/containerd/containerd/issues/3654 +## +shmVolume: + ## @param shmVolume.enabled Enable emptyDir volume for /dev/shm for PostgreSQL pod(s) + ## + enabled: true + ## @param shmVolume.sizeLimit Set this to enable a size limit on the shm tmpfs + ## Note: the size of the tmpfs counts against container's memory limit + ## e.g: + ## sizeLimit: 1Gi + ## + sizeLimit: "" +## TLS configuration +## +tls: + ## @param tls.enabled Enable TLS traffic support + ## + enabled: false + ## @param tls.autoGenerated Generate automatically self-signed TLS certificates + ## + autoGenerated: false + ## @param tls.preferServerCiphers Whether to use the server's TLS cipher preferences rather than the client's + ## + preferServerCiphers: true + ## @param tls.certificatesSecret Name of an existing secret that contains the certificates + ## + certificatesSecret: "" + ## @param tls.certFilename Certificate filename + ## + certFilename: "" + ## @param tls.certKeyFilename Certificate key filename + ## + certKeyFilename: "" + ## @param tls.certCAFilename CA Certificate filename + ## If provided, PostgreSQL will authenticate TLS/SSL clients by requesting them a certificate + ## ref: https://www.postgresql.org/docs/9.6/auth-methods.html + ## + certCAFilename: "" + ## @param tls.crlFilename File containing a Certificate Revocation List + ## + crlFilename: "" + +## @section PostgreSQL Primary parameters +## +primary: + ## @param primary.name Name of the primary database (eg primary, master, leader, ...) + ## + name: primary + ## @param primary.configuration PostgreSQL Primary main configuration to be injected as ConfigMap + ## ref: https://www.postgresql.org/docs/current/static/runtime-config.html + ## + configuration: "" + ## @param primary.pgHbaConfiguration PostgreSQL Primary client authentication configuration + ## ref: https://www.postgresql.org/docs/current/static/auth-pg-hba-conf.html + ## e.g:# + ## pgHbaConfiguration: |- + ## local all all trust + ## host all all localhost trust + ## host mydatabase mysuser 192.168.0.0/24 md5 + ## + pgHbaConfiguration: "" + ## @param primary.existingConfigmap Name of an existing ConfigMap with PostgreSQL Primary configuration + ## NOTE: `primary.configuration` and `primary.pgHbaConfiguration` will be ignored + ## + existingConfigmap: "" + ## @param primary.extendedConfiguration Extended PostgreSQL Primary configuration (appended to main or default configuration) + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/postgresql#allow-settings-to-be-loaded-from-files-other-than-the-default-postgresqlconf + ## + extendedConfiguration: "" + ## @param primary.existingExtendedConfigmap Name of an existing ConfigMap with PostgreSQL Primary extended configuration + ## NOTE: `primary.extendedConfiguration` will be ignored + ## + existingExtendedConfigmap: "" + ## Initdb configuration + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/postgresql#specifying-initdb-arguments + ## + initdb: + ## @param primary.initdb.args PostgreSQL initdb extra arguments + ## + args: "" + ## @param primary.initdb.postgresqlWalDir Specify a custom location for the PostgreSQL transaction log + ## + postgresqlWalDir: "" + ## @param primary.initdb.scripts Dictionary of initdb scripts + ## Specify dictionary of scripts to be run at first boot + ## e.g: + ## scripts: + ## my_init_script.sh: | + ## #!/bin/sh + ## echo "Do something." + ## + scripts: {} + ## @param primary.initdb.scriptsConfigMap ConfigMap with scripts to be run at first boot + ## NOTE: This will override `primary.initdb.scripts` + ## + scriptsConfigMap: "" + ## @param primary.initdb.scriptsSecret Secret with scripts to be run at first boot (in case it contains sensitive information) + ## NOTE: This can work along `primary.initdb.scripts` or `primary.initdb.scriptsConfigMap` + ## + scriptsSecret: "" + ## @param primary.initdb.user Specify the PostgreSQL username to execute the initdb scripts + ## + user: "" + ## @param primary.initdb.password Specify the PostgreSQL password to execute the initdb scripts + ## + password: "" + ## Configure current cluster's primary server to be the standby server in other cluster. + ## This will allow cross cluster replication and provide cross cluster high availability. + ## You will need to configure pgHbaConfiguration if you want to enable this feature with local cluster replication enabled. + ## @param primary.standby.enabled Whether to enable current cluster's primary as standby server of another cluster or not + ## @param primary.standby.primaryHost The Host of replication primary in the other cluster + ## @param primary.standby.primaryPort The Port of replication primary in the other cluster + ## + standby: + enabled: false + primaryHost: "" + primaryPort: "" + ## @param primary.extraEnvVars Array with extra environment variables to add to PostgreSQL Primary nodes + ## e.g: + ## extraEnvVars: + ## - name: FOO + ## value: "bar" + ## + extraEnvVars: [] + ## @param primary.extraEnvVarsCM Name of existing ConfigMap containing extra env vars for PostgreSQL Primary nodes + ## + extraEnvVarsCM: "" + ## @param primary.extraEnvVarsSecret Name of existing Secret containing extra env vars for PostgreSQL Primary nodes + ## + extraEnvVarsSecret: "" + ## @param primary.command Override default container command (useful when using custom images) + ## + command: [] + ## @param primary.args Override default container args (useful when using custom images) + ## + args: [] + ## Configure extra options for PostgreSQL Primary containers' liveness, readiness and startup probes + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/#configure-probes + ## @param primary.livenessProbe.enabled Enable livenessProbe on PostgreSQL Primary containers + ## @param primary.livenessProbe.initialDelaySeconds Initial delay seconds for livenessProbe + ## @param primary.livenessProbe.periodSeconds Period seconds for livenessProbe + ## @param primary.livenessProbe.timeoutSeconds Timeout seconds for livenessProbe + ## @param primary.livenessProbe.failureThreshold Failure threshold for livenessProbe + ## @param primary.livenessProbe.successThreshold Success threshold for livenessProbe + ## + livenessProbe: + enabled: true + initialDelaySeconds: 30 + periodSeconds: 10 + timeoutSeconds: 5 + failureThreshold: 6 + successThreshold: 1 + ## @param primary.readinessProbe.enabled Enable readinessProbe on PostgreSQL Primary containers + ## @param primary.readinessProbe.initialDelaySeconds Initial delay seconds for readinessProbe + ## @param primary.readinessProbe.periodSeconds Period seconds for readinessProbe + ## @param primary.readinessProbe.timeoutSeconds Timeout seconds for readinessProbe + ## @param primary.readinessProbe.failureThreshold Failure threshold for readinessProbe + ## @param primary.readinessProbe.successThreshold Success threshold for readinessProbe + ## + readinessProbe: + enabled: true + initialDelaySeconds: 5 + periodSeconds: 10 + timeoutSeconds: 5 + failureThreshold: 6 + successThreshold: 1 + ## @param primary.startupProbe.enabled Enable startupProbe on PostgreSQL Primary containers + ## @param primary.startupProbe.initialDelaySeconds Initial delay seconds for startupProbe + ## @param primary.startupProbe.periodSeconds Period seconds for startupProbe + ## @param primary.startupProbe.timeoutSeconds Timeout seconds for startupProbe + ## @param primary.startupProbe.failureThreshold Failure threshold for startupProbe + ## @param primary.startupProbe.successThreshold Success threshold for startupProbe + ## + startupProbe: + enabled: false + initialDelaySeconds: 30 + periodSeconds: 10 + timeoutSeconds: 1 + failureThreshold: 15 + successThreshold: 1 + ## @param primary.customLivenessProbe Custom livenessProbe that overrides the default one + ## + customLivenessProbe: {} + ## @param primary.customReadinessProbe Custom readinessProbe that overrides the default one + ## + customReadinessProbe: {} + ## @param primary.customStartupProbe Custom startupProbe that overrides the default one + ## + customStartupProbe: {} + ## @param primary.lifecycleHooks for the PostgreSQL Primary container to automate configuration before or after startup + ## + lifecycleHooks: {} + ## PostgreSQL Primary resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## @param primary.resources.limits The resources limits for the PostgreSQL Primary containers + ## @param primary.resources.requests.memory The requested memory for the PostgreSQL Primary containers + ## @param primary.resources.requests.cpu The requested cpu for the PostgreSQL Primary containers + ## + resources: + limits: {} + requests: + memory: 256Mi + cpu: 250m + ## Pod Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ + ## @param primary.podSecurityContext.enabled Enable security context + ## @param primary.podSecurityContext.fsGroup Group ID for the pod + ## + podSecurityContext: + enabled: true + fsGroup: 1001 + ## Container Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ + ## @param primary.containerSecurityContext.enabled Enable container security context + ## @param primary.containerSecurityContext.runAsUser User ID for the container + ## + containerSecurityContext: + enabled: true + runAsUser: 1001 + ## @param primary.hostAliases PostgreSQL primary pods host aliases + ## https://kubernetes.io/docs/concepts/services-networking/add-entries-to-pod-etc-hosts-with-host-aliases/ + ## + hostAliases: [] + ## @param primary.hostNetwork Specify if host network should be enabled for PostgreSQL pod (postgresql primary) + ## + hostNetwork: false + ## @param primary.hostIPC Specify if host IPC should be enabled for PostgreSQL pod (postgresql primary) + ## + hostIPC: false + ## @param primary.labels Map of labels to add to the statefulset (postgresql primary) + ## + labels: {} + ## @param primary.annotations Annotations for PostgreSQL primary pods + ## + annotations: {} + ## @param primary.podLabels Map of labels to add to the pods (postgresql primary) + ## + podLabels: {} + ## @param primary.podAnnotations Map of annotations to add to the pods (postgresql primary) + ## + podAnnotations: {} + ## @param primary.podAffinityPreset PostgreSQL primary pod affinity preset. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity + ## + podAffinityPreset: "" + ## @param primary.podAntiAffinityPreset PostgreSQL primary pod anti-affinity preset. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity + ## + podAntiAffinityPreset: soft + ## PostgreSQL Primary node affinity preset + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#node-affinity + ## + nodeAffinityPreset: + ## @param primary.nodeAffinityPreset.type PostgreSQL primary node affinity preset type. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` + ## + type: "" + ## @param primary.nodeAffinityPreset.key PostgreSQL primary node label key to match Ignored if `primary.affinity` is set. + ## E.g. + ## key: "kubernetes.io/e2e-az-name" + ## + key: "" + ## @param primary.nodeAffinityPreset.values PostgreSQL primary node label values to match. Ignored if `primary.affinity` is set. + ## E.g. + ## values: + ## - e2e-az1 + ## - e2e-az2 + ## + values: [] + ## @param primary.affinity Affinity for PostgreSQL primary pods assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + ## Note: primary.podAffinityPreset, primary.podAntiAffinityPreset, and primary.nodeAffinityPreset will be ignored when it's set + ## + affinity: {} + ## @param primary.nodeSelector Node labels for PostgreSQL primary pods assignment + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + ## + nodeSelector: {} + ## @param primary.tolerations Tolerations for PostgreSQL primary pods assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + ## + tolerations: [] + ## @param primary.topologySpreadConstraints Topology Spread Constraints for pod assignment spread across your cluster among failure-domains. Evaluated as a template + ## Ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/#spread-constraints-for-pods + ## + topologySpreadConstraints: [] + ## @param primary.priorityClassName Priority Class to use for each pod (postgresql primary) + ## + priorityClassName: "" + ## @param primary.schedulerName Use an alternate scheduler, e.g. "stork". + ## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ + ## + schedulerName: "" + ## @param primary.terminationGracePeriodSeconds Seconds PostgreSQL primary pod needs to terminate gracefully + ## ref: https://kubernetes.io/docs/concepts/workloads/pods/pod/#termination-of-pods + ## + terminationGracePeriodSeconds: "" + ## @param primary.updateStrategy.type PostgreSQL Primary statefulset strategy type + ## @param primary.updateStrategy.rollingUpdate PostgreSQL Primary statefulset rolling update configuration parameters + ## ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#update-strategies + ## + updateStrategy: + type: RollingUpdate + rollingUpdate: {} + ## @param primary.extraVolumeMounts Optionally specify extra list of additional volumeMounts for the PostgreSQL Primary container(s) + ## + extraVolumeMounts: [] + ## @param primary.extraVolumes Optionally specify extra list of additional volumes for the PostgreSQL Primary pod(s) + ## + extraVolumes: [] + ## @param primary.sidecars Add additional sidecar containers to the PostgreSQL Primary pod(s) + ## For example: + ## sidecars: + ## - name: your-image-name + ## image: your-image + ## imagePullPolicy: Always + ## ports: + ## - name: portname + ## containerPort: 1234 + ## + sidecars: [] + ## @param primary.initContainers Add additional init containers to the PostgreSQL Primary pod(s) + ## Example + ## + ## initContainers: + ## - name: do-something + ## image: busybox + ## command: ['do', 'something'] + ## + initContainers: [] + ## @param primary.extraPodSpec Optionally specify extra PodSpec for the PostgreSQL Primary pod(s) + ## + extraPodSpec: {} + ## PostgreSQL Primary service configuration + ## + service: + ## @param primary.service.type Kubernetes Service type + ## + type: ClusterIP + ## @param primary.service.ports.postgresql PostgreSQL service port + ## + ports: + postgresql: 5432 + ## Node ports to expose + ## NOTE: choose port between <30000-32767> + ## @param primary.service.nodePorts.postgresql Node port for PostgreSQL + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#type-nodeport + ## + nodePorts: + postgresql: "" + ## @param primary.service.clusterIP Static clusterIP or None for headless services + ## e.g: + ## clusterIP: None + ## + clusterIP: "" + ## @param primary.service.annotations Annotations for PostgreSQL primary service + ## + annotations: {} + ## @param primary.service.loadBalancerIP Load balancer IP if service type is `LoadBalancer` + ## Set the LoadBalancer service type to internal only + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#internal-load-balancer + ## + loadBalancerIP: "" + ## @param primary.service.externalTrafficPolicy Enable client source IP preservation + ## ref https://kubernetes.io/docs/tasks/access-application-cluster/create-external-load-balancer/#preserving-the-client-source-ip + ## + externalTrafficPolicy: Cluster + ## @param primary.service.loadBalancerSourceRanges Addresses that are allowed when service is LoadBalancer + ## https://kubernetes.io/docs/tasks/access-application-cluster/configure-cloud-provider-firewall/#restrict-access-for-loadbalancer-service + ## + ## loadBalancerSourceRanges: + ## - 10.10.10.0/24 + ## + loadBalancerSourceRanges: [] + ## @param primary.service.extraPorts Extra ports to expose in the PostgreSQL primary service + ## + extraPorts: [] + ## @param primary.service.sessionAffinity Session Affinity for Kubernetes service, can be "None" or "ClientIP" + ## If "ClientIP", consecutive client requests will be directed to the same Pod + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#virtual-ips-and-service-proxies + ## + sessionAffinity: None + ## @param primary.service.sessionAffinityConfig Additional settings for the sessionAffinity + ## sessionAffinityConfig: + ## clientIP: + ## timeoutSeconds: 300 + ## + sessionAffinityConfig: {} + ## PostgreSQL Primary persistence configuration + ## + persistence: + ## @param primary.persistence.enabled Enable PostgreSQL Primary data persistence using PVC + ## + enabled: true + ## @param primary.persistence.existingClaim Name of an existing PVC to use + ## + existingClaim: "" + ## @param primary.persistence.mountPath The path the volume will be mounted at + ## Note: useful when using custom PostgreSQL images + ## + mountPath: /bitnami/postgresql + ## @param primary.persistence.subPath The subdirectory of the volume to mount to + ## Useful in dev environments and one PV for multiple services + ## + subPath: "" + ## @param primary.persistence.storageClass PVC Storage Class for PostgreSQL Primary data volume + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is + ## set, choosing the default provisioner. (gp2 on AWS, standard on + ## GKE, AWS & OpenStack) + ## + storageClass: "" + ## @param primary.persistence.accessModes PVC Access Mode for PostgreSQL volume + ## + accessModes: + - ReadWriteOnce + ## @param primary.persistence.size PVC Storage Request for PostgreSQL volume + ## + size: 8Gi + ## @param primary.persistence.annotations Annotations for the PVC + ## + annotations: {} + ## @param primary.persistence.labels Labels for the PVC + ## + labels: {} + ## @param primary.persistence.selector Selector to match an existing Persistent Volume (this value is evaluated as a template) + ## selector: + ## matchLabels: + ## app: my-app + ## + selector: {} + ## @param primary.persistence.dataSource Custom PVC data source + ## + dataSource: {} + +## @section PostgreSQL read only replica parameters (only used when `architecture` is set to `replication`) +## +readReplicas: + ## @param readReplicas.name Name of the read replicas database (eg secondary, slave, ...) + ## + name: read + ## @param readReplicas.replicaCount Number of PostgreSQL read only replicas + ## + replicaCount: 1 + ## @param readReplicas.extendedConfiguration Extended PostgreSQL read only replicas configuration (appended to main or default configuration) + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/postgresql#allow-settings-to-be-loaded-from-files-other-than-the-default-postgresqlconf + ## + extendedConfiguration: "" + ## @param readReplicas.extraEnvVars Array with extra environment variables to add to PostgreSQL read only nodes + ## e.g: + ## extraEnvVars: + ## - name: FOO + ## value: "bar" + ## + extraEnvVars: [] + ## @param readReplicas.extraEnvVarsCM Name of existing ConfigMap containing extra env vars for PostgreSQL read only nodes + ## + extraEnvVarsCM: "" + ## @param readReplicas.extraEnvVarsSecret Name of existing Secret containing extra env vars for PostgreSQL read only nodes + ## + extraEnvVarsSecret: "" + ## @param readReplicas.command Override default container command (useful when using custom images) + ## + command: [] + ## @param readReplicas.args Override default container args (useful when using custom images) + ## + args: [] + ## Configure extra options for PostgreSQL read only containers' liveness, readiness and startup probes + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/#configure-probes + ## @param readReplicas.livenessProbe.enabled Enable livenessProbe on PostgreSQL read only containers + ## @param readReplicas.livenessProbe.initialDelaySeconds Initial delay seconds for livenessProbe + ## @param readReplicas.livenessProbe.periodSeconds Period seconds for livenessProbe + ## @param readReplicas.livenessProbe.timeoutSeconds Timeout seconds for livenessProbe + ## @param readReplicas.livenessProbe.failureThreshold Failure threshold for livenessProbe + ## @param readReplicas.livenessProbe.successThreshold Success threshold for livenessProbe + ## + livenessProbe: + enabled: true + initialDelaySeconds: 30 + periodSeconds: 10 + timeoutSeconds: 5 + failureThreshold: 6 + successThreshold: 1 + ## @param readReplicas.readinessProbe.enabled Enable readinessProbe on PostgreSQL read only containers + ## @param readReplicas.readinessProbe.initialDelaySeconds Initial delay seconds for readinessProbe + ## @param readReplicas.readinessProbe.periodSeconds Period seconds for readinessProbe + ## @param readReplicas.readinessProbe.timeoutSeconds Timeout seconds for readinessProbe + ## @param readReplicas.readinessProbe.failureThreshold Failure threshold for readinessProbe + ## @param readReplicas.readinessProbe.successThreshold Success threshold for readinessProbe + ## + readinessProbe: + enabled: true + initialDelaySeconds: 5 + periodSeconds: 10 + timeoutSeconds: 5 + failureThreshold: 6 + successThreshold: 1 + ## @param readReplicas.startupProbe.enabled Enable startupProbe on PostgreSQL read only containers + ## @param readReplicas.startupProbe.initialDelaySeconds Initial delay seconds for startupProbe + ## @param readReplicas.startupProbe.periodSeconds Period seconds for startupProbe + ## @param readReplicas.startupProbe.timeoutSeconds Timeout seconds for startupProbe + ## @param readReplicas.startupProbe.failureThreshold Failure threshold for startupProbe + ## @param readReplicas.startupProbe.successThreshold Success threshold for startupProbe + ## + startupProbe: + enabled: false + initialDelaySeconds: 30 + periodSeconds: 10 + timeoutSeconds: 1 + failureThreshold: 15 + successThreshold: 1 + ## @param readReplicas.customLivenessProbe Custom livenessProbe that overrides the default one + ## + customLivenessProbe: {} + ## @param readReplicas.customReadinessProbe Custom readinessProbe that overrides the default one + ## + customReadinessProbe: {} + ## @param readReplicas.customStartupProbe Custom startupProbe that overrides the default one + ## + customStartupProbe: {} + ## @param readReplicas.lifecycleHooks for the PostgreSQL read only container to automate configuration before or after startup + ## + lifecycleHooks: {} + ## PostgreSQL read only resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## @param readReplicas.resources.limits The resources limits for the PostgreSQL read only containers + ## @param readReplicas.resources.requests.memory The requested memory for the PostgreSQL read only containers + ## @param readReplicas.resources.requests.cpu The requested cpu for the PostgreSQL read only containers + ## + resources: + limits: {} + requests: + memory: 256Mi + cpu: 250m + ## Pod Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ + ## @param readReplicas.podSecurityContext.enabled Enable security context + ## @param readReplicas.podSecurityContext.fsGroup Group ID for the pod + ## + podSecurityContext: + enabled: true + fsGroup: 1001 + ## Container Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/ + ## @param readReplicas.containerSecurityContext.enabled Enable container security context + ## @param readReplicas.containerSecurityContext.runAsUser User ID for the container + ## + containerSecurityContext: + enabled: true + runAsUser: 1001 + ## @param readReplicas.hostAliases PostgreSQL read only pods host aliases + ## https://kubernetes.io/docs/concepts/services-networking/add-entries-to-pod-etc-hosts-with-host-aliases/ + ## + hostAliases: [] + ## @param readReplicas.hostNetwork Specify if host network should be enabled for PostgreSQL pod (PostgreSQL read only) + ## + hostNetwork: false + ## @param readReplicas.hostIPC Specify if host IPC should be enabled for PostgreSQL pod (postgresql primary) + ## + hostIPC: false + ## @param readReplicas.labels Map of labels to add to the statefulset (PostgreSQL read only) + ## + labels: {} + ## @param readReplicas.annotations Annotations for PostgreSQL read only pods + ## + annotations: {} + ## @param readReplicas.podLabels Map of labels to add to the pods (PostgreSQL read only) + ## + podLabels: {} + ## @param readReplicas.podAnnotations Map of annotations to add to the pods (PostgreSQL read only) + ## + podAnnotations: {} + ## @param readReplicas.podAffinityPreset PostgreSQL read only pod affinity preset. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity + ## + podAffinityPreset: "" + ## @param readReplicas.podAntiAffinityPreset PostgreSQL read only pod anti-affinity preset. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity + ## + podAntiAffinityPreset: soft + ## PostgreSQL read only node affinity preset + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#node-affinity + ## + nodeAffinityPreset: + ## @param readReplicas.nodeAffinityPreset.type PostgreSQL read only node affinity preset type. Ignored if `primary.affinity` is set. Allowed values: `soft` or `hard` + ## + type: "" + ## @param readReplicas.nodeAffinityPreset.key PostgreSQL read only node label key to match Ignored if `primary.affinity` is set. + ## E.g. + ## key: "kubernetes.io/e2e-az-name" + ## + key: "" + ## @param readReplicas.nodeAffinityPreset.values PostgreSQL read only node label values to match. Ignored if `primary.affinity` is set. + ## E.g. + ## values: + ## - e2e-az1 + ## - e2e-az2 + ## + values: [] + ## @param readReplicas.affinity Affinity for PostgreSQL read only pods assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + ## Note: primary.podAffinityPreset, primary.podAntiAffinityPreset, and primary.nodeAffinityPreset will be ignored when it's set + ## + affinity: {} + ## @param readReplicas.nodeSelector Node labels for PostgreSQL read only pods assignment + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + ## + nodeSelector: {} + ## @param readReplicas.tolerations Tolerations for PostgreSQL read only pods assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + ## + tolerations: [] + ## @param readReplicas.topologySpreadConstraints Topology Spread Constraints for pod assignment spread across your cluster among failure-domains. Evaluated as a template + ## Ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/#spread-constraints-for-pods + ## + topologySpreadConstraints: [] + ## @param readReplicas.priorityClassName Priority Class to use for each pod (PostgreSQL read only) + ## + priorityClassName: "" + ## @param readReplicas.schedulerName Use an alternate scheduler, e.g. "stork". + ## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ + ## + schedulerName: "" + ## @param readReplicas.terminationGracePeriodSeconds Seconds PostgreSQL read only pod needs to terminate gracefully + ## ref: https://kubernetes.io/docs/concepts/workloads/pods/pod/#termination-of-pods + ## + terminationGracePeriodSeconds: "" + ## @param readReplicas.updateStrategy.type PostgreSQL read only statefulset strategy type + ## @param readReplicas.updateStrategy.rollingUpdate PostgreSQL read only statefulset rolling update configuration parameters + ## ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#update-strategies + ## + updateStrategy: + type: RollingUpdate + rollingUpdate: {} + ## @param readReplicas.extraVolumeMounts Optionally specify extra list of additional volumeMounts for the PostgreSQL read only container(s) + ## + extraVolumeMounts: [] + ## @param readReplicas.extraVolumes Optionally specify extra list of additional volumes for the PostgreSQL read only pod(s) + ## + extraVolumes: [] + ## @param readReplicas.sidecars Add additional sidecar containers to the PostgreSQL read only pod(s) + ## For example: + ## sidecars: + ## - name: your-image-name + ## image: your-image + ## imagePullPolicy: Always + ## ports: + ## - name: portname + ## containerPort: 1234 + ## + sidecars: [] + ## @param readReplicas.initContainers Add additional init containers to the PostgreSQL read only pod(s) + ## Example + ## + ## initContainers: + ## - name: do-something + ## image: busybox + ## command: ['do', 'something'] + ## + initContainers: [] + ## @param readReplicas.extraPodSpec Optionally specify extra PodSpec for the PostgreSQL read only pod(s) + ## + extraPodSpec: {} + ## PostgreSQL read only service configuration + ## + service: + ## @param readReplicas.service.type Kubernetes Service type + ## + type: ClusterIP + ## @param readReplicas.service.ports.postgresql PostgreSQL service port + ## + ports: + postgresql: 5432 + ## Node ports to expose + ## NOTE: choose port between <30000-32767> + ## @param readReplicas.service.nodePorts.postgresql Node port for PostgreSQL + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#type-nodeport + ## + nodePorts: + postgresql: "" + ## @param readReplicas.service.clusterIP Static clusterIP or None for headless services + ## e.g: + ## clusterIP: None + ## + clusterIP: "" + ## @param readReplicas.service.annotations Annotations for PostgreSQL read only service + ## + annotations: {} + ## @param readReplicas.service.loadBalancerIP Load balancer IP if service type is `LoadBalancer` + ## Set the LoadBalancer service type to internal only + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#internal-load-balancer + ## + loadBalancerIP: "" + ## @param readReplicas.service.externalTrafficPolicy Enable client source IP preservation + ## ref https://kubernetes.io/docs/tasks/access-application-cluster/create-external-load-balancer/#preserving-the-client-source-ip + ## + externalTrafficPolicy: Cluster + ## @param readReplicas.service.loadBalancerSourceRanges Addresses that are allowed when service is LoadBalancer + ## https://kubernetes.io/docs/tasks/access-application-cluster/configure-cloud-provider-firewall/#restrict-access-for-loadbalancer-service + ## + ## loadBalancerSourceRanges: + ## - 10.10.10.0/24 + ## + loadBalancerSourceRanges: [] + ## @param readReplicas.service.extraPorts Extra ports to expose in the PostgreSQL read only service + ## + extraPorts: [] + ## @param readReplicas.service.sessionAffinity Session Affinity for Kubernetes service, can be "None" or "ClientIP" + ## If "ClientIP", consecutive client requests will be directed to the same Pod + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#virtual-ips-and-service-proxies + ## + sessionAffinity: None + ## @param readReplicas.service.sessionAffinityConfig Additional settings for the sessionAffinity + ## sessionAffinityConfig: + ## clientIP: + ## timeoutSeconds: 300 + ## + sessionAffinityConfig: {} + ## PostgreSQL read only persistence configuration + ## + persistence: + ## @param readReplicas.persistence.enabled Enable PostgreSQL read only data persistence using PVC + ## + enabled: true + ## @param readReplicas.persistence.existingClaim Name of an existing PVC to use + ## + existingClaim: "" + ## @param readReplicas.persistence.mountPath The path the volume will be mounted at + ## Note: useful when using custom PostgreSQL images + ## + mountPath: /bitnami/postgresql + ## @param readReplicas.persistence.subPath The subdirectory of the volume to mount to + ## Useful in dev environments and one PV for multiple services + ## + subPath: "" + ## @param readReplicas.persistence.storageClass PVC Storage Class for PostgreSQL read only data volume + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is + ## set, choosing the default provisioner. (gp2 on AWS, standard on + ## GKE, AWS & OpenStack) + ## + storageClass: "" + ## @param readReplicas.persistence.accessModes PVC Access Mode for PostgreSQL volume + ## + accessModes: + - ReadWriteOnce + ## @param readReplicas.persistence.size PVC Storage Request for PostgreSQL volume + ## + size: 8Gi + ## @param readReplicas.persistence.annotations Annotations for the PVC + ## + annotations: {} + ## @param readReplicas.persistence.labels Labels for the PVC + ## + labels: {} + ## @param readReplicas.persistence.selector Selector to match an existing Persistent Volume (this value is evaluated as a template) + ## selector: + ## matchLabels: + ## app: my-app + ## + selector: {} + ## @param readReplicas.persistence.dataSource Custom PVC data source + ## + dataSource: {} + +## @section NetworkPolicy parameters + +## Add networkpolicies +## +networkPolicy: + ## @param networkPolicy.enabled Enable network policies + ## + enabled: false + ## @param networkPolicy.metrics.enabled Enable network policies for metrics (prometheus) + ## @param networkPolicy.metrics.namespaceSelector [object] Monitoring namespace selector labels. These labels will be used to identify the prometheus' namespace. + ## @param networkPolicy.metrics.podSelector [object] Monitoring pod selector labels. These labels will be used to identify the Prometheus pods. + ## + metrics: + enabled: false + ## e.g: + ## namespaceSelector: + ## label: monitoring + ## + namespaceSelector: {} + ## e.g: + ## podSelector: + ## label: monitoring + ## + podSelector: {} + ## Ingress Rules + ## + ingressRules: + ## @param networkPolicy.ingressRules.primaryAccessOnlyFrom.enabled Enable ingress rule that makes PostgreSQL primary node only accessible from a particular origin. + ## @param networkPolicy.ingressRules.primaryAccessOnlyFrom.namespaceSelector [object] Namespace selector label that is allowed to access the PostgreSQL primary node. This label will be used to identified the allowed namespace(s). + ## @param networkPolicy.ingressRules.primaryAccessOnlyFrom.podSelector [object] Pods selector label that is allowed to access the PostgreSQL primary node. This label will be used to identified the allowed pod(s). + ## @param networkPolicy.ingressRules.primaryAccessOnlyFrom.customRules [object] Custom network policy for the PostgreSQL primary node. + ## + primaryAccessOnlyFrom: + enabled: false + ## e.g: + ## namespaceSelector: + ## label: ingress + ## + namespaceSelector: {} + ## e.g: + ## podSelector: + ## label: access + ## + podSelector: {} + ## custom ingress rules + ## e.g: + ## customRules: + ## - from: + ## - namespaceSelector: + ## matchLabels: + ## label: example + customRules: {} + ## @param networkPolicy.ingressRules.readReplicasAccessOnlyFrom.enabled Enable ingress rule that makes PostgreSQL read-only nodes only accessible from a particular origin. + ## @param networkPolicy.ingressRules.readReplicasAccessOnlyFrom.namespaceSelector [object] Namespace selector label that is allowed to access the PostgreSQL read-only nodes. This label will be used to identified the allowed namespace(s). + ## @param networkPolicy.ingressRules.readReplicasAccessOnlyFrom.podSelector [object] Pods selector label that is allowed to access the PostgreSQL read-only nodes. This label will be used to identified the allowed pod(s). + ## @param networkPolicy.ingressRules.readReplicasAccessOnlyFrom.customRules [object] Custom network policy for the PostgreSQL read-only nodes. + ## + readReplicasAccessOnlyFrom: + enabled: false + ## e.g: + ## namespaceSelector: + ## label: ingress + ## + namespaceSelector: {} + ## e.g: + ## podSelector: + ## label: access + ## + podSelector: {} + ## custom ingress rules + ## e.g: + ## CustomRules: + ## - from: + ## - namespaceSelector: + ## matchLabels: + ## label: example + customRules: {} + ## @param networkPolicy.egressRules.denyConnectionsToExternal Enable egress rule that denies outgoing traffic outside the cluster, except for DNS (port 53). + ## @param networkPolicy.egressRules.customRules [object] Custom network policy rule + ## + egressRules: + # Deny connections to external. This is not compatible with an external database. + denyConnectionsToExternal: false + ## Additional custom egress rules + ## e.g: + ## customRules: + ## - to: + ## - namespaceSelector: + ## matchLabels: + ## label: example + customRules: {} + +## @section Volume Permissions parameters + +## Init containers parameters: +## volumePermissions: Change the owner and group of the persistent volume(s) mountpoint(s) to 'runAsUser:fsGroup' on each node +## +volumePermissions: + ## @param volumePermissions.enabled Enable init container that changes the owner and group of the persistent volume + ## + enabled: false + ## @param volumePermissions.image.registry Init container volume-permissions image registry + ## @param volumePermissions.image.repository Init container volume-permissions image repository + ## @param volumePermissions.image.tag Init container volume-permissions image tag (immutable tags are recommended) + ## @param volumePermissions.image.digest Init container volume-permissions image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag + ## @param volumePermissions.image.pullPolicy Init container volume-permissions image pull policy + ## @param volumePermissions.image.pullSecrets Init container volume-permissions image pull secrets + ## + image: + registry: docker.io + repository: bitnami/bitnami-shell + tag: 11-debian-11-r42 + digest: "" + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## Init container resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## @param volumePermissions.resources.limits Init container volume-permissions resource limits + ## @param volumePermissions.resources.requests Init container volume-permissions resource requests + ## + resources: + limits: {} + requests: {} + ## Init container' Security Context + ## Note: the chown of the data folder is done to containerSecurityContext.runAsUser + ## and not the below volumePermissions.containerSecurityContext.runAsUser + ## @param volumePermissions.containerSecurityContext.runAsUser User ID for the init container + ## + containerSecurityContext: + runAsUser: 0 + +## @section Other Parameters + +## Service account for PostgreSQL to use. +## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/ +## +serviceAccount: + ## @param serviceAccount.create Enable creation of ServiceAccount for PostgreSQL pod + ## + create: false + ## @param serviceAccount.name The name of the ServiceAccount to use. + ## If not set and create is true, a name is generated using the common.names.fullname template + ## + name: "" + ## @param serviceAccount.automountServiceAccountToken Allows auto mount of ServiceAccountToken on the serviceAccount created + ## Can be set to false if pods using this serviceAccount do not need to use K8s API + ## + automountServiceAccountToken: true + ## @param serviceAccount.annotations Additional custom annotations for the ServiceAccount + ## + annotations: {} +## Creates role for ServiceAccount +## @param rbac.create Create Role and RoleBinding (required for PSP to work) +## +rbac: + create: false + ## @param rbac.rules Custom RBAC rules to set + ## e.g: + ## rules: + ## - apiGroups: + ## - "" + ## resources: + ## - pods + ## verbs: + ## - get + ## - list + ## + rules: [] +## Pod Security Policy +## ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/ +## @param psp.create Whether to create a PodSecurityPolicy. WARNING: PodSecurityPolicy is deprecated in Kubernetes v1.21 or later, unavailable in v1.25 or later +## +psp: + create: false + +## @section Metrics Parameters + +metrics: + ## @param metrics.enabled Start a prometheus exporter + ## + enabled: false + ## @param metrics.image.registry PostgreSQL Prometheus Exporter image registry + ## @param metrics.image.repository PostgreSQL Prometheus Exporter image repository + ## @param metrics.image.tag PostgreSQL Prometheus Exporter image tag (immutable tags are recommended) + ## @param metrics.image.digest PostgreSQL image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag + ## @param metrics.image.pullPolicy PostgreSQL Prometheus Exporter image pull policy + ## @param metrics.image.pullSecrets Specify image pull secrets + ## + image: + registry: docker.io + repository: bitnami/postgres-exporter + tag: 0.11.1-debian-11-r19 + digest: "" + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## @param metrics.customMetrics Define additional custom metrics + ## ref: https://github.com/wrouesnel/postgres_exporter#adding-new-metrics-via-a-config-file + ## customMetrics: + ## pg_database: + ## query: "SELECT d.datname AS name, CASE WHEN pg_catalog.has_database_privilege(d.datname, 'CONNECT') THEN pg_catalog.pg_database_size(d.datname) ELSE 0 END AS size_bytes FROM pg_catalog.pg_database d where datname not in ('template0', 'template1', 'postgres')" + ## metrics: + ## - name: + ## usage: "LABEL" + ## description: "Name of the database" + ## - size_bytes: + ## usage: "GAUGE" + ## description: "Size of the database in bytes" + ## + customMetrics: {} + ## @param metrics.extraEnvVars Extra environment variables to add to PostgreSQL Prometheus exporter + ## see: https://github.com/wrouesnel/postgres_exporter#environment-variables + ## For example: + ## extraEnvVars: + ## - name: PG_EXPORTER_DISABLE_DEFAULT_METRICS + ## value: "true" + ## + extraEnvVars: [] + ## PostgreSQL Prometheus exporter containers' Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-container + ## @param metrics.containerSecurityContext.enabled Enable PostgreSQL Prometheus exporter containers' Security Context + ## @param metrics.containerSecurityContext.runAsUser Set PostgreSQL Prometheus exporter containers' Security Context runAsUser + ## @param metrics.containerSecurityContext.runAsNonRoot Set PostgreSQL Prometheus exporter containers' Security Context runAsNonRoot + ## + containerSecurityContext: + enabled: true + runAsUser: 1001 + runAsNonRoot: true + ## Configure extra options for PostgreSQL Prometheus exporter containers' liveness, readiness and startup probes + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/#configure-probes + ## @param metrics.livenessProbe.enabled Enable livenessProbe on PostgreSQL Prometheus exporter containers + ## @param metrics.livenessProbe.initialDelaySeconds Initial delay seconds for livenessProbe + ## @param metrics.livenessProbe.periodSeconds Period seconds for livenessProbe + ## @param metrics.livenessProbe.timeoutSeconds Timeout seconds for livenessProbe + ## @param metrics.livenessProbe.failureThreshold Failure threshold for livenessProbe + ## @param metrics.livenessProbe.successThreshold Success threshold for livenessProbe + ## + livenessProbe: + enabled: true + initialDelaySeconds: 5 + periodSeconds: 10 + timeoutSeconds: 5 + failureThreshold: 6 + successThreshold: 1 + ## @param metrics.readinessProbe.enabled Enable readinessProbe on PostgreSQL Prometheus exporter containers + ## @param metrics.readinessProbe.initialDelaySeconds Initial delay seconds for readinessProbe + ## @param metrics.readinessProbe.periodSeconds Period seconds for readinessProbe + ## @param metrics.readinessProbe.timeoutSeconds Timeout seconds for readinessProbe + ## @param metrics.readinessProbe.failureThreshold Failure threshold for readinessProbe + ## @param metrics.readinessProbe.successThreshold Success threshold for readinessProbe + ## + readinessProbe: + enabled: true + initialDelaySeconds: 5 + periodSeconds: 10 + timeoutSeconds: 5 + failureThreshold: 6 + successThreshold: 1 + ## @param metrics.startupProbe.enabled Enable startupProbe on PostgreSQL Prometheus exporter containers + ## @param metrics.startupProbe.initialDelaySeconds Initial delay seconds for startupProbe + ## @param metrics.startupProbe.periodSeconds Period seconds for startupProbe + ## @param metrics.startupProbe.timeoutSeconds Timeout seconds for startupProbe + ## @param metrics.startupProbe.failureThreshold Failure threshold for startupProbe + ## @param metrics.startupProbe.successThreshold Success threshold for startupProbe + ## + startupProbe: + enabled: false + initialDelaySeconds: 10 + periodSeconds: 10 + timeoutSeconds: 1 + failureThreshold: 15 + successThreshold: 1 + ## @param metrics.customLivenessProbe Custom livenessProbe that overrides the default one + ## + customLivenessProbe: {} + ## @param metrics.customReadinessProbe Custom readinessProbe that overrides the default one + ## + customReadinessProbe: {} + ## @param metrics.customStartupProbe Custom startupProbe that overrides the default one + ## + customStartupProbe: {} + ## @param metrics.containerPorts.metrics PostgreSQL Prometheus exporter metrics container port + ## + containerPorts: + metrics: 9187 + ## PostgreSQL Prometheus exporter resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## @param metrics.resources.limits The resources limits for the PostgreSQL Prometheus exporter container + ## @param metrics.resources.requests The requested resources for the PostgreSQL Prometheus exporter container + ## + resources: + limits: {} + requests: {} + ## Service configuration + ## + service: + ## @param metrics.service.ports.metrics PostgreSQL Prometheus Exporter service port + ## + ports: + metrics: 9187 + ## @param metrics.service.clusterIP Static clusterIP or None for headless services + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#choosing-your-own-ip-address + ## + clusterIP: "" + ## @param metrics.service.sessionAffinity Control where client requests go, to the same pod or round-robin + ## Values: ClientIP or None + ## ref: https://kubernetes.io/docs/user-guide/services/ + ## + sessionAffinity: None + ## @param metrics.service.annotations [object] Annotations for Prometheus to auto-discover the metrics endpoint + ## + annotations: + prometheus.io/scrape: "true" + prometheus.io/port: "{{ .Values.metrics.service.ports.metrics }}" + ## Prometheus Operator ServiceMonitor configuration + ## + serviceMonitor: + ## @param metrics.serviceMonitor.enabled Create ServiceMonitor Resource for scraping metrics using Prometheus Operator + ## + enabled: false + ## @param metrics.serviceMonitor.namespace Namespace for the ServiceMonitor Resource (defaults to the Release Namespace) + ## + namespace: "" + ## @param metrics.serviceMonitor.interval Interval at which metrics should be scraped. + ## ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#endpoint + ## + interval: "" + ## @param metrics.serviceMonitor.scrapeTimeout Timeout after which the scrape is ended + ## ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#endpoint + ## + scrapeTimeout: "" + ## @param metrics.serviceMonitor.labels Additional labels that can be used so ServiceMonitor will be discovered by Prometheus + ## + labels: {} + ## @param metrics.serviceMonitor.selector Prometheus instance selector labels + ## ref: https://github.com/bitnami/charts/tree/main/bitnami/prometheus-operator#prometheus-configuration + ## + selector: {} + ## @param metrics.serviceMonitor.relabelings RelabelConfigs to apply to samples before scraping + ## + relabelings: [] + ## @param metrics.serviceMonitor.metricRelabelings MetricRelabelConfigs to apply to samples before ingestion + ## + metricRelabelings: [] + ## @param metrics.serviceMonitor.honorLabels Specify honorLabels parameter to add the scrape endpoint + ## + honorLabels: false + ## @param metrics.serviceMonitor.jobLabel The name of the label on the target service to use as the job name in prometheus. + ## + jobLabel: "" + ## Custom PrometheusRule to be defined + ## The value is evaluated as a template, so, for example, the value can depend on .Release or .Chart + ## ref: https://github.com/coreos/prometheus-operator#customresourcedefinitions + ## + prometheusRule: + ## @param metrics.prometheusRule.enabled Create a PrometheusRule for Prometheus Operator + ## + enabled: false + ## @param metrics.prometheusRule.namespace Namespace for the PrometheusRule Resource (defaults to the Release Namespace) + ## + namespace: "" + ## @param metrics.prometheusRule.labels Additional labels that can be used so PrometheusRule will be discovered by Prometheus + ## + labels: {} + ## @param metrics.prometheusRule.rules PrometheusRule definitions + ## Make sure to constraint the rules to the current postgresql service. + ## rules: + ## - alert: HugeReplicationLag + ## expr: pg_replication_lag{service="{{ printf "%s-metrics" (include "common.names.fullname" .) }}"} / 3600 > 1 + ## for: 1m + ## labels: + ## severity: critical + ## annotations: + ## description: replication for {{ include "common.names.fullname" . }} PostgreSQL is lagging by {{ "{{ $value }}" }} hour(s). + ## summary: PostgreSQL replication is lagging by {{ "{{ $value }}" }} hour(s). + ## + rules: [] diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/prometheus/.helmignore new file mode 100644 index 0000000..825c007 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/.helmignore @@ -0,0 +1,23 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj + +OWNERS diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/Chart.lock b/observability/lgtm-distributed/charts/oncall/charts/prometheus/Chart.lock new file mode 100644 index 0000000..83e5660 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/Chart.lock @@ -0,0 +1,15 @@ +dependencies: +- name: alertmanager + repository: https://prometheus-community.github.io/helm-charts + version: 1.7.0 +- name: kube-state-metrics + repository: https://prometheus-community.github.io/helm-charts + version: 5.15.2 +- name: prometheus-node-exporter + repository: https://prometheus-community.github.io/helm-charts + version: 4.24.0 +- name: prometheus-pushgateway + repository: https://prometheus-community.github.io/helm-charts + version: 2.4.2 +digest: sha256:83aa9d98623ddd76cceaf5a17b69372ae34ab715db5ccb84dbc472d5fb78a01e +generated: "2023-11-17T18:47:14.928659+02:00" diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/Chart.yaml new file mode 100644 index 0000000..48ed9af --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/Chart.yaml @@ -0,0 +1,53 @@ +annotations: + artifacthub.io/license: Apache-2.0 + artifacthub.io/links: | + - name: Chart Source + url: https://github.com/prometheus-community/helm-charts + - name: Upstream Project + url: https://github.com/prometheus/prometheus +apiVersion: v2 +appVersion: v2.48.1 +dependencies: +- condition: alertmanager.enabled + name: alertmanager + repository: https://prometheus-community.github.io/helm-charts + version: 1.7.* +- condition: kube-state-metrics.enabled + name: kube-state-metrics + repository: https://prometheus-community.github.io/helm-charts + version: 5.15.* +- condition: prometheus-node-exporter.enabled + name: prometheus-node-exporter + repository: https://prometheus-community.github.io/helm-charts + version: 4.24.* +- condition: prometheus-pushgateway.enabled + name: prometheus-pushgateway + repository: https://prometheus-community.github.io/helm-charts + version: 2.4.* +description: Prometheus is a monitoring system and time series database. +home: https://prometheus.io/ +icon: https://raw.githubusercontent.com/prometheus/prometheus.github.io/master/assets/prometheus_logo-cb55bb5c346.png +keywords: +- monitoring +- prometheus +kubeVersion: '>=1.19.0-0' +maintainers: +- email: gianrubio@gmail.com + name: gianrubio +- email: zanhsieh@gmail.com + name: zanhsieh +- email: miroslav.hadzhiev@gmail.com + name: Xtigyro +- email: naseem@transit.app + name: naseemkullah +- email: rootsandtrees@posteo.de + name: zeritti +name: prometheus +sources: +- https://github.com/prometheus/alertmanager +- https://github.com/prometheus/prometheus +- https://github.com/prometheus/pushgateway +- https://github.com/prometheus/node_exporter +- https://github.com/kubernetes/kube-state-metrics +type: application +version: 25.8.2 diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/README.md b/observability/lgtm-distributed/charts/oncall/charts/prometheus/README.md new file mode 100644 index 0000000..2cb744c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/README.md @@ -0,0 +1,382 @@ +# Prometheus + +[Prometheus](https://prometheus.io/), a [Cloud Native Computing Foundation](https://cncf.io/) project, is a systems and service monitoring system. It collects metrics from configured targets at given intervals, evaluates rule expressions, displays the results, and can trigger alerts if some condition is observed to be true. + +This chart bootstraps a [Prometheus](https://prometheus.io/) deployment on a [Kubernetes](http://kubernetes.io) cluster using the [Helm](https://helm.sh) package manager. + +## Prerequisites + +- Kubernetes 1.19+ +- Helm 3.7+ + +## Get Repository Info + +```console +helm repo add prometheus-community https://prometheus-community.github.io/helm-charts +helm repo update +``` + +_See [helm repository](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Install Chart + +Starting with version 16.0, the Prometheus chart requires Helm 3.7+ in order to install successfully. Please check your `helm` release before installation. + +```console +helm install [RELEASE_NAME] prometheus-community/prometheus +``` + +_See [configuration](#configuration) below._ + +_See [helm install](https://helm.sh/docs/helm/helm_install/) for command documentation._ + +## Dependencies + +By default this chart installs additional, dependent charts: + +- [alertmanager](https://github.com/prometheus-community/helm-charts/tree/main/charts/alertmanager) +- [kube-state-metrics](https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-state-metrics) +- [prometheus-node-exporter](https://github.com/prometheus-community/helm-charts/tree/main/charts/prometheus-node-exporter) +- [prometheus-pushgateway](https://github.com/walker-tom/helm-charts/tree/main/charts/prometheus-pushgateway) + +To disable the dependency during installation, set `alertmanager.enabled`, `kube-state-metrics.enabled`, `prometheus-node-exporter.enabled` and `prometheus-pushgateway.enabled` to `false`. + +_See [helm dependency](https://helm.sh/docs/helm/helm_dependency/) for command documentation._ + +## Uninstall Chart + +```console +helm uninstall [RELEASE_NAME] +``` + +This removes all the Kubernetes components associated with the chart and deletes the release. + +_See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall/) for command documentation._ + +## Updating values.schema.json + +A [`values.schema.json`](https://helm.sh/docs/topics/charts/#schema-files) file has been added to validate chart values. When `values.yaml` file has a structure change (i.e. add a new field, change value type, etc.), modify `values.schema.json` file manually or run `helm schema-gen values.yaml > values.schema.json` to ensure the schema is aligned with the latest values. Refer to [helm plugin `helm-schema-gen`](https://github.com/karuppiah7890/helm-schema-gen) for plugin installation instructions. + +## Upgrading Chart + +```console +helm upgrade [RELEASE_NAME] prometheus-community/prometheus --install +``` + +_See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documentation._ + +### To 25.0 + +The `server.remoteRead[].url` and `server.remoteWrite[].url` fields now support templating. Allowing for `url` values such as `https://{{ .Release.Name }}.example.com`. + +Any entries in these which previously included `{{` or `}}` must be escaped with `{{ "{{" }}` and `{{ "}}" }}` respectively. Entries which did not previously include the template-like syntax will not be affected. + +### To 24.0 + +Require Kubernetes 1.19+ + +Release 1.0.0 of the _alertmanager_ replaced [configmap-reload](https://github.com/jimmidyson/configmap-reload) with [prometheus-config-reloader](https://github.com/prometheus-operator/prometheus-operator/tree/main/cmd/prometheus-config-reloader). +Extra command-line arguments specified via `configmapReload.prometheus.extraArgs` are not compatible and will break with the new prometheus-config-reloader. Please, refer to the [sources](https://github.com/prometheus-operator/prometheus-operator/blob/main/cmd/prometheus-config-reloader/main.go) in order to make the appropriate adjustment to the extra command-line arguments. + +### To 23.0 + +Release 5.0.0 of the _kube-state-metrics_ chart introduced a separation of the `image.repository` value in two distinct values: + +```console + image: + registry: registry.k8s.io + repository: kube-state-metrics/kube-state-metrics +``` + +If a custom values file or CLI flags set `kube-state.metrics.image.repository`, please, set the new values accordingly. + +If you are upgrading _prometheus-pushgateway_ with the chart and _prometheus-pushgateway_ has been deployed as a statefulset with a persistent volume, the statefulset must be deleted before upgrading the chart, e.g.: + +```bash +kubectl delete sts -l app.kubernetes.io/name=prometheus-pushgateway -n monitoring --cascade=orphan +``` + +Users are advised to review changes in the corresponding chart releases before upgrading. + +### To 22.0 + +The `app.kubernetes.io/version` label has been removed from the pod selector. + +Therefore, you must delete the previous StatefulSet or Deployment before upgrading. Performing this operation will cause **Prometheus to stop functioning** until the upgrade is complete. + +```console +kubectl delete deploy,sts -l app.kubernetes.io/name=prometheus +``` + +### To 21.0 + +The Kubernetes labels have been updated to follow [Helm 3 label and annotation best practices](https://helm.sh/docs/chart_best_practices/labels/). +Specifically, labels mapping is listed below: + +| OLD | NEW | +|--------------------|------------------------------| +|heritage | app.kubernetes.io/managed-by | +|chart | helm.sh/chart | +|[container version] | app.kubernetes.io/version | +|app | app.kubernetes.io/name | +|release | app.kubernetes.io/instance | + +Therefore, depending on the way you've configured the chart, the previous StatefulSet or Deployment need to be deleted before upgrade. + +If `runAsStatefulSet: false` (this is the default): + +```console +kubectl delete deploy -l app=prometheus +``` + +If `runAsStatefulSet: true`: + +```console +kubectl delete sts -l app=prometheus +``` + +After that do the actual upgrade: + +```console +helm upgrade -i prometheus prometheus-community/prometheus +``` + +### To 20.0 + +The [configmap-reload](https://github.com/jimmidyson/configmap-reload) container was replaced by the [prometheus-config-reloader](https://github.com/prometheus-operator/prometheus-operator/tree/main/cmd/prometheus-config-reloader). +Extra command-line arguments specified via configmapReload.prometheus.extraArgs are not compatible and will break with the new prometheus-config-reloader, refer to the [sources](https://github.com/prometheus-operator/prometheus-operator/blob/main/cmd/prometheus-config-reloader/main.go) in order to make the appropriate adjustment to the extra command-line arguments. + +### To 19.0 + +Prometheus has been updated to version v2.40.5. + +Prometheus-pushgateway was updated to version 2.0.0 which adapted [Helm label and annotation best practices](https://helm.sh/docs/chart_best_practices/labels/). +See the [upgrade docs of the prometheus-pushgateway chart](https://github.com/prometheus-community/helm-charts/tree/main/charts/prometheus-pushgateway#to-200) to see whats to do, before you upgrade Prometheus! + +The condition in Chart.yaml to disable kube-state-metrics has been changed from `kubeStateMetrics.enabled` to `kube-state-metrics.enabled` + +The Docker image tag is used from appVersion field in Chart.yaml by default. + +Unused subchart configs has been removed and subchart config is now on the bottom of the config file. + +If Prometheus is used as deployment the updatestrategy has been changed to "Recreate" by default, so Helm updates work out of the box. + +`.Values.server.extraTemplates` & `.Values.server.extraObjects` has been removed in favour of `.Values.extraManifests`, which can do the same. + +`.Values.server.enabled` has been removed as it's useless now that all components are created by subcharts. + +All files in `templates/server` directory has been moved to `templates` directory. + +```bash +helm upgrade [RELEASE_NAME] prometheus-community/prometheus --version 19.0.0 +``` + +### To 18.0 + +Version 18.0.0 uses alertmanager service from the [alertmanager chart](https://github.com/prometheus-community/helm-charts/tree/main/charts/alertmanager). If you've made some config changes, please check the old `alertmanager` and the new `alertmanager` configuration section in values.yaml for differences. + +Note that the `configmapReload` section for `alertmanager` was moved out of dedicated section (`configmapReload.alertmanager`) to alertmanager embedded (`alertmanager.configmapReload`). + +Before you update, please scale down the `prometheus-server` deployment to `0` then perform upgrade: + +```bash +# In 17.x +kubectl scale deploy prometheus-server --replicas=0 +# Upgrade +helm upgrade [RELEASE_NAME] prometheus-community/prometheus --version 18.0.0 +``` + +### To 17.0 + +Version 17.0.0 uses pushgateway service from the [prometheus-pushgateway chart](https://github.com/prometheus-community/helm-charts/tree/main/charts/prometheus-pushgateway). If you've made some config changes, please check the old `pushgateway` and the new `prometheus-pushgateway` configuration section in values.yaml for differences. + +Before you update, please scale down the `prometheus-server` deployment to `0` then perform upgrade: + +```bash +# In 16.x +kubectl scale deploy prometheus-server --replicas=0 +# Upgrade +helm upgrade [RELEASE_NAME] prometheus-community/prometheus --version 17.0.0 +``` + +### To 16.0 + +Starting from version 16.0 embedded services (like alertmanager, node-exporter etc.) are moved out of Prometheus chart and the respecting charts from this repository are used as dependencies. Version 16.0.0 moves node-exporter service to [prometheus-node-exporter chart](https://github.com/prometheus-community/helm-charts/tree/main/charts/prometheus-node-exporter). If you've made some config changes, please check the old `nodeExporter` and the new `prometheus-node-exporter` configuration section in values.yaml for differences. + +Before you update, please scale down the `prometheus-server` deployment to `0` then perform upgrade: + +```bash +# In 15.x +kubectl scale deploy prometheus-server --replicas=0 +# Upgrade +helm upgrade [RELEASE_NAME] prometheus-community/prometheus --version 16.0.0 +``` + +### To 15.0 + +Version 15.0.0 changes the relabeling config, aligning it with the [Prometheus community conventions](https://github.com/prometheus/prometheus/pull/9832). If you've made manual changes to the relabeling config, you have to adapt your changes. + +Before you update please execute the following command, to be able to update kube-state-metrics: + +```bash +kubectl delete deployments.apps -l app.kubernetes.io/instance=prometheus,app.kubernetes.io/name=kube-state-metrics --cascade=orphan +``` + +### To 9.0 + +Version 9.0 adds a new option to enable or disable the Prometheus Server. This supports the use case of running a Prometheus server in one k8s cluster and scraping exporters in another cluster while using the same chart for each deployment. To install the server `server.enabled` must be set to `true`. + +### To 5.0 + +As of version 5.0, this chart uses Prometheus 2.x. This version of prometheus introduces a new data format and is not compatible with prometheus 1.x. It is recommended to install this as a new release, as updating existing releases will not work. See the [prometheus docs](https://prometheus.io/docs/prometheus/latest/migration/#storage) for instructions on retaining your old data. + +Prometheus version 2.x has made changes to alertmanager, storage and recording rules. Check out the migration guide [here](https://prometheus.io/docs/prometheus/2.0/migration/). + +Users of this chart will need to update their alerting rules to the new format before they can upgrade. + +### Example Migration + +Assuming you have an existing release of the prometheus chart, named `prometheus-old`. In order to update to prometheus 2.x while keeping your old data do the following: + +1. Update the `prometheus-old` release. Disable scraping on every component besides the prometheus server, similar to the configuration below: + + ```yaml + alertmanager: + enabled: false + alertmanagerFiles: + alertmanager.yml: "" + kubeStateMetrics: + enabled: false + nodeExporter: + enabled: false + pushgateway: + enabled: false + server: + extraArgs: + storage.local.retention: 720h + serverFiles: + alerts: "" + prometheus.yml: "" + rules: "" + ``` + +1. Deploy a new release of the chart with version 5.0+ using prometheus 2.x. In the values.yaml set the scrape config as usual, and also add the `prometheus-old` instance as a remote-read target. + + ```yaml + prometheus.yml: + ... + remote_read: + - url: http://prometheus-old/api/v1/read + ... + ``` + + Old data will be available when you query the new prometheus instance. + +## Configuration + +See [Customizing the Chart Before Installing](https://helm.sh/docs/intro/using_helm/#customizing-the-chart-before-installing). To see all configurable options with detailed comments, visit the chart's [values.yaml](./values.yaml), or run these configuration commands: + +```console +helm show values prometheus-community/prometheus +``` + +You may similarly use the above configuration commands on each chart [dependency](#dependencies) to see its configurations. + +### Scraping Pod Metrics via Annotations + +This chart uses a default configuration that causes prometheus to scrape a variety of kubernetes resource types, provided they have the correct annotations. In this section we describe how to configure pods to be scraped; for information on how other resource types can be scraped you can do a `helm template` to get the kubernetes resource definitions, and then reference the prometheus configuration in the ConfigMap against the prometheus documentation for [relabel_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config) and [kubernetes_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#kubernetes_sd_config). + +In order to get prometheus to scrape pods, you must add annotations to the pods as below: + +```yaml +metadata: + annotations: + prometheus.io/scrape: "true" + prometheus.io/path: /metrics + prometheus.io/port: "8080" +``` + +You should adjust `prometheus.io/path` based on the URL that your pod serves metrics from. `prometheus.io/port` should be set to the port that your pod serves metrics from. Note that the values for `prometheus.io/scrape` and `prometheus.io/port` must be enclosed in double quotes. + +### Sharing Alerts Between Services + +Note that when [installing](#install-chart) or [upgrading](#upgrading-chart) you may use multiple values override files. This is particularly useful when you have alerts belonging to multiple services in the cluster. For example, + +```yaml +# values.yaml +# ... + +# service1-alert.yaml +serverFiles: + alerts: + service1: + - alert: anAlert + # ... + +# service2-alert.yaml +serverFiles: + alerts: + service2: + - alert: anAlert + # ... +``` + +```console +helm install [RELEASE_NAME] prometheus-community/prometheus -f values.yaml -f service1-alert.yaml -f service2-alert.yaml +``` + +### RBAC Configuration + +Roles and RoleBindings resources will be created automatically for `server` service. + +To manually setup RBAC you need to set the parameter `rbac.create=false` and specify the service account to be used for each service by setting the parameters: `serviceAccounts.{{ component }}.create` to `false` and `serviceAccounts.{{ component }}.name` to the name of a pre-existing service account. + +> **Tip**: You can refer to the default `*-clusterrole.yaml` and `*-clusterrolebinding.yaml` files in [templates](templates/) to customize your own. + +### ConfigMap Files + +AlertManager is configured through [alertmanager.yml](https://prometheus.io/docs/alerting/configuration/). This file (and any others listed in `alertmanagerFiles`) will be mounted into the `alertmanager` pod. + +Prometheus is configured through [prometheus.yml](https://prometheus.io/docs/operating/configuration/). This file (and any others listed in `serverFiles`) will be mounted into the `server` pod. + +### Ingress TLS + +If your cluster allows automatic creation/retrieval of TLS certificates (e.g. [cert-manager](https://github.com/jetstack/cert-manager)), please refer to the documentation for that mechanism. + +To manually configure TLS, first create/retrieve a key & certificate pair for the address(es) you wish to protect. Then create a TLS secret in the namespace: + +```console +kubectl create secret tls prometheus-server-tls --cert=path/to/tls.cert --key=path/to/tls.key +``` + +Include the secret's name, along with the desired hostnames, in the alertmanager/server Ingress TLS section of your custom `values.yaml` file: + +```yaml +server: + ingress: + ## If true, Prometheus server Ingress will be created + ## + enabled: true + + ## Prometheus server Ingress hostnames + ## Must be provided if Ingress is enabled + ## + hosts: + - prometheus.domain.com + + ## Prometheus server Ingress TLS configuration + ## Secrets must be manually created in the namespace + ## + tls: + - secretName: prometheus-server-tls + hosts: + - prometheus.domain.com +``` + +### NetworkPolicy + +Enabling Network Policy for Prometheus will secure connections to Alert Manager and Kube State Metrics by only accepting connections from Prometheus Server. All inbound connections to Prometheus Server are still allowed. + +To enable network policy for Prometheus, install a networking plugin that implements the Kubernetes NetworkPolicy spec, and set `networkPolicy.enabled` to true. + +If NetworkPolicy is enabled for Prometheus' scrape targets, you may also need to manually create a networkpolicy which allows it. diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/.helmignore new file mode 100644 index 0000000..7653e97 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/.helmignore @@ -0,0 +1,25 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*.orig +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ + +unittests/ diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/Chart.yaml new file mode 100644 index 0000000..08fdd03 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/Chart.yaml @@ -0,0 +1,24 @@ +annotations: + artifacthub.io/license: Apache-2.0 + artifacthub.io/links: | + - name: Chart Source + url: https://github.com/prometheus-community/helm-charts +apiVersion: v2 +appVersion: v0.26.0 +description: The Alertmanager handles alerts sent by client applications such as the + Prometheus server. +home: https://prometheus.io/ +icon: https://raw.githubusercontent.com/prometheus/prometheus.github.io/master/assets/prometheus_logo-cb55bb5c346.png +keywords: +- monitoring +kubeVersion: '>=1.19.0-0' +maintainers: +- email: monotek23@gmail.com + name: monotek +- email: naseem@transit.app + name: naseemkullah +name: alertmanager +sources: +- https://github.com/prometheus/alertmanager +type: application +version: 1.7.0 diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/README.md b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/README.md new file mode 100644 index 0000000..d3f4df7 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/README.md @@ -0,0 +1,62 @@ +# Alertmanager + +As per [prometheus.io documentation](https://prometheus.io/docs/alerting/latest/alertmanager/): +> The Alertmanager handles alerts sent by client applications such as the +> Prometheus server. It takes care of deduplicating, grouping, and routing them +> to the correct receiver integration such as email, PagerDuty, or OpsGenie. It +> also takes care of silencing and inhibition of alerts. + +## Prerequisites + +Kubernetes 1.14+ + +## Get Repository Info + +```console +helm repo add prometheus-community https://prometheus-community.github.io/helm-charts +helm repo update +``` + +_See [`helm repo`](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Install Chart + +```console +helm install [RELEASE_NAME] prometheus-community/alertmanager +``` + +_See [configuration](#configuration) below._ + +_See [helm install](https://helm.sh/docs/helm/helm_install/) for command documentation._ + +## Uninstall Chart + +```console +helm uninstall [RELEASE_NAME] +``` + +This removes all the Kubernetes components associated with the chart and deletes the release. + +_See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall/) for command documentation._ + +## Upgrading Chart + +```console +helm upgrade [RELEASE_NAME] [CHART] --install +``` + +_See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documentation._ + +### To 1.0 + +The [configmap-reload](https://github.com/jimmidyson/configmap-reload) container was replaced by the [prometheus-config-reloader](https://github.com/prometheus-operator/prometheus-operator/tree/main/cmd/prometheus-config-reloader). +Extra command-line arguments specified via configmapReload.prometheus.extraArgs are not compatible and will break with the new prometheus-config-reloader, refer to the [sources](https://github.com/prometheus-operator/prometheus-operator/blob/main/cmd/prometheus-config-reloader/main.go) in order to make the appropriate adjustment to the extea command-line arguments. +The `networking.k8s.io/v1beta1` is no longer supported. use [`networking.k8s.io/v1`](https://kubernetes.io/docs/reference/using-api/deprecation-guide/#ingressclass-v122). + +## Configuration + +See [Customizing the Chart Before Installing](https://helm.sh/docs/intro/using_helm/#customizing-the-chart-before-installing). To see all configurable options with detailed comments, visit the chart's [values.yaml](./values.yaml), or run these configuration commands: + +```console +helm show values prometheus-community/alertmanager +``` diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/ci/config-reload-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/ci/config-reload-values.yaml new file mode 100644 index 0000000..cba5de8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/ci/config-reload-values.yaml @@ -0,0 +1,2 @@ +configmapReload: + enabled: true diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/NOTES.txt new file mode 100644 index 0000000..46ea5be --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/NOTES.txt @@ -0,0 +1,21 @@ +1. Get the application URL by running these commands: +{{- if .Values.ingress.enabled }} +{{- range $host := .Values.ingress.hosts }} + {{- range .paths }} + http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }} + {{- end }} +{{- end }} +{{- else if contains "NodePort" .Values.service.type }} + export NODE_PORT=$(kubectl get --namespace {{ include "alertmanager.namespace" . }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "alertmanager.fullname" . }}) + export NODE_IP=$(kubectl get nodes --namespace {{ include "alertmanager.namespace" . }} -o jsonpath="{.items[0].status.addresses[0].address}") + echo http://$NODE_IP:$NODE_PORT +{{- else if contains "LoadBalancer" .Values.service.type }} + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + You can watch the status of by running 'kubectl get --namespace {{ include "alertmanager.namespace" . }} svc -w {{ include "alertmanager.fullname" . }}' + export SERVICE_IP=$(kubectl get svc --namespace {{ include "alertmanager.namespace" . }} {{ include "alertmanager.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}") + echo http://$SERVICE_IP:{{ .Values.service.port }} +{{- else if contains "ClusterIP" .Values.service.type }} + export POD_NAME=$(kubectl get pods --namespace {{ include "alertmanager.namespace" . }} -l "app.kubernetes.io/name={{ include "alertmanager.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") + echo "Visit http://127.0.0.1:{{ .Values.service.port }} to use your application" + kubectl --namespace {{ include "alertmanager.namespace" . }} port-forward $POD_NAME {{ .Values.service.port }}:80 +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/_helpers.tpl new file mode 100644 index 0000000..827b6ee --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/_helpers.tpl @@ -0,0 +1,92 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "alertmanager.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "alertmanager.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default .Chart.Name .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "alertmanager.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "alertmanager.labels" -}} +helm.sh/chart: {{ include "alertmanager.chart" . }} +{{ include "alertmanager.selectorLabels" . }} +{{- with .Chart.AppVersion }} +app.kubernetes.io/version: {{ . | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "alertmanager.selectorLabels" -}} +app.kubernetes.io/name: {{ include "alertmanager.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Create the name of the service account to use +*/}} +{{- define "alertmanager.serviceAccountName" -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "alertmanager.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} + +{{/* +Define Ingress apiVersion +*/}} +{{- define "alertmanager.ingress.apiVersion" -}} +{{- printf "networking.k8s.io/v1" }} +{{- end }} + +{{/* +Define Pdb apiVersion +*/}} +{{- define "alertmanager.pdb.apiVersion" -}} +{{- if $.Capabilities.APIVersions.Has "policy/v1/PodDisruptionBudget" }} +{{- printf "policy/v1" }} +{{- else }} +{{- printf "policy/v1beta1" }} +{{- end }} +{{- end }} + +{{/* +Allow overriding alertmanager namespace +*/}} +{{- define "alertmanager.namespace" -}} +{{- if .Values.namespaceOverride -}} +{{- .Values.namespaceOverride -}} +{{- else -}} +{{- .Release.Namespace -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/configmap.yaml new file mode 100644 index 0000000..9e5882d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/configmap.yaml @@ -0,0 +1,21 @@ +{{- if .Values.config.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "alertmanager.fullname" . }} + labels: + {{- include "alertmanager.labels" . | nindent 4 }} + {{- with .Values.configAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ include "alertmanager.namespace" . }} +data: + alertmanager.yml: | + {{- $config := omit .Values.config "enabled" }} + {{- toYaml $config | default "{}" | nindent 4 }} + {{- range $key, $value := .Values.templates }} + {{ $key }}: |- + {{- $value | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/ingress.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/ingress.yaml new file mode 100644 index 0000000..e729a8a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/ingress.yaml @@ -0,0 +1,44 @@ +{{- if .Values.ingress.enabled }} +{{- $fullName := include "alertmanager.fullname" . }} +{{- $svcPort := .Values.service.port }} +apiVersion: {{ include "alertmanager.ingress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ $fullName }} + labels: + {{- include "alertmanager.labels" . | nindent 4 }} + {{- with .Values.ingress.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ include "alertmanager.namespace" . }} +spec: + {{- if .Values.ingress.className }} + ingressClassName: {{ .Values.ingress.className }} + {{- end }} + {{- if .Values.ingress.tls }} + tls: + {{- range .Values.ingress.tls }} + - hosts: + {{- range .hosts }} + - {{ . | quote }} + {{- end }} + secretName: {{ .secretName }} + {{- end }} + {{- end }} + rules: + {{- range .Values.ingress.hosts }} + - host: {{ .host | quote }} + http: + paths: + {{- range .paths }} + - path: {{ .path }} + pathType: {{ .pathType }} + backend: + service: + name: {{ $fullName }} + port: + number: {{ $svcPort }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/ingressperreplica.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/ingressperreplica.yaml new file mode 100644 index 0000000..6f5a023 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/ingressperreplica.yaml @@ -0,0 +1,56 @@ +{{- if and .Values.servicePerReplica.enabled .Values.ingressPerReplica.enabled }} +{{- $pathType := .Values.ingressPerReplica.pathType }} +{{- $count := .Values.replicaCount | int -}} +{{- $servicePort := .Values.service.port -}} +{{- $ingressValues := .Values.ingressPerReplica -}} +{{- $fullName := include "alertmanager.fullname" . }} +apiVersion: v1 +kind: List +metadata: + name: {{ $fullName }}-ingressperreplica + namespace: {{ include "alertmanager.namespace" . }} +items: +{{- range $i, $e := until $count }} + - kind: Ingress + apiVersion: {{ include "alertmanager.ingress.apiVersion" $ }} + metadata: + name: {{ $fullName }}-{{ $i }} + namespace: {{ include "alertmanager.namespace" $ }} + labels: + {{- include "alertmanager.labels" $ | nindent 8 }} + {{- if $ingressValues.labels }} +{{ toYaml $ingressValues.labels | indent 8 }} + {{- end }} + {{- if $ingressValues.annotations }} + annotations: +{{ toYaml $ingressValues.annotations | indent 8 }} + {{- end }} + spec: + {{- if $ingressValues.className }} + ingressClassName: {{ $ingressValues.className }} + {{- end }} + rules: + - host: {{ $ingressValues.hostPrefix }}-{{ $i }}.{{ $ingressValues.hostDomain }} + http: + paths: + {{- range $p := $ingressValues.paths }} + - path: {{ tpl $p $ }} + pathType: {{ $pathType }} + backend: + service: + name: {{ $fullName }}-{{ $i }} + port: + name: http + {{- end -}} + {{- if or $ingressValues.tlsSecretName $ingressValues.tlsSecretPerReplica.enabled }} + tls: + - hosts: + - {{ $ingressValues.hostPrefix }}-{{ $i }}.{{ $ingressValues.hostDomain }} + {{- if $ingressValues.tlsSecretPerReplica.enabled }} + secretName: {{ $ingressValues.tlsSecretPerReplica.prefix }}-{{ $i }} + {{- else }} + secretName: {{ $ingressValues.tlsSecretName }} + {{- end }} + {{- end }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/pdb.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/pdb.yaml new file mode 100644 index 0000000..103e9ec --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/pdb.yaml @@ -0,0 +1,14 @@ +{{- if .Values.podDisruptionBudget }} +apiVersion: {{ include "alertmanager.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "alertmanager.fullname" . }} + labels: + {{- include "alertmanager.labels" . | nindent 4 }} + namespace: {{ include "alertmanager.namespace" . }} +spec: + selector: + matchLabels: + {{- include "alertmanager.selectorLabels" . | nindent 6 }} + {{- toYaml .Values.podDisruptionBudget | nindent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/serviceaccount.yaml new file mode 100644 index 0000000..bc9ccaa --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/serviceaccount.yaml @@ -0,0 +1,14 @@ +{{- if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "alertmanager.serviceAccountName" . }} + labels: + {{- include "alertmanager.labels" . | nindent 4 }} + {{- with .Values.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ include "alertmanager.namespace" . }} +automountServiceAccountToken: {{ .Values.automountServiceAccountToken }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/serviceperreplica.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/serviceperreplica.yaml new file mode 100644 index 0000000..faa75b3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/serviceperreplica.yaml @@ -0,0 +1,44 @@ +{{- if and .Values.servicePerReplica.enabled }} +{{- $count := .Values.replicaCount | int -}} +{{- $serviceValues := .Values.servicePerReplica -}} +apiVersion: v1 +kind: List +metadata: + name: {{ include "alertmanager.fullname" . }}-serviceperreplica + namespace: {{ include "alertmanager.namespace" . }} +items: +{{- range $i, $e := until $count }} + - apiVersion: v1 + kind: Service + metadata: + name: {{ include "alertmanager.fullname" $ }}-{{ $i }} + namespace: {{ include "alertmanager.namespace" $ }} + labels: + {{- include "alertmanager.labels" $ | nindent 8 }} + {{- if $serviceValues.annotations }} + annotations: +{{ toYaml $serviceValues.annotations | indent 8 }} + {{- end }} + spec: + {{- if $serviceValues.clusterIP }} + clusterIP: {{ $serviceValues.clusterIP }} + {{- end }} + {{- if $serviceValues.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- range $cidr := $serviceValues.loadBalancerSourceRanges }} + - {{ $cidr }} + {{- end }} + {{- end }} + {{- if ne $serviceValues.type "ClusterIP" }} + externalTrafficPolicy: {{ $serviceValues.externalTrafficPolicy }} + {{- end }} + ports: + - name: http + port: {{ $.Values.service.port }} + targetPort: http + selector: + {{- include "alertmanager.selectorLabels" $ | nindent 8 }} + statefulset.kubernetes.io/pod-name: {{ include "alertmanager.fullname" $ }}-{{ $i }} + type: "{{ $serviceValues.type }}" +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/services.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/services.yaml new file mode 100644 index 0000000..9637ae7 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/services.yaml @@ -0,0 +1,71 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "alertmanager.fullname" . }} + labels: + {{- include "alertmanager.labels" . | nindent 4 }} + {{- with .Values.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ include "alertmanager.namespace" . }} +spec: + type: {{ .Values.service.type }} + {{- with .Values.service.loadBalancerIP }} + loadBalancerIP: {{ . }} + {{- end }} + {{- with .Values.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- range $cidr := . }} + - {{ $cidr }} + {{- end }} + {{- end }} + ports: + - port: {{ .Values.service.port }} + targetPort: http + protocol: TCP + name: http + {{- if (and (eq .Values.service.type "NodePort") .Values.service.nodePort) }} + nodePort: {{ .Values.service.nodePort }} + {{- end }} + {{- with .Values.service.extraPorts }} + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + {{- include "alertmanager.selectorLabels" . | nindent 4 }} +--- +apiVersion: v1 +kind: Service +metadata: + name: {{ include "alertmanager.fullname" . }}-headless + labels: + {{- include "alertmanager.labels" . | nindent 4 }} + {{- with .Values.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ include "alertmanager.namespace" . }} +spec: + clusterIP: None + ports: + - port: {{ .Values.service.port }} + targetPort: http + protocol: TCP + name: http + {{- if or (gt (int .Values.replicaCount) 1) (.Values.additionalPeers) }} + - port: {{ .Values.service.clusterPort }} + targetPort: clusterpeer-tcp + protocol: TCP + name: cluster-tcp + - port: {{ .Values.service.clusterPort }} + targetPort: clusterpeer-udp + protocol: UDP + name: cluster-udp + {{- end }} + {{- with .Values.service.extraPorts }} + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + {{- include "alertmanager.selectorLabels" . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/statefulset.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/statefulset.yaml new file mode 100644 index 0000000..25d81a9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/statefulset.yaml @@ -0,0 +1,247 @@ +{{- $svcClusterPort := .Values.service.clusterPort }} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "alertmanager.fullname" . }} + labels: + {{- include "alertmanager.labels" . | nindent 4 }} + {{- with .Values.statefulSet.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ include "alertmanager.namespace" . }} +spec: + replicas: {{ .Values.replicaCount }} + revisionHistoryLimit: {{ .Values.revisionHistoryLimit }} + selector: + matchLabels: + {{- include "alertmanager.selectorLabels" . | nindent 6 }} + serviceName: {{ include "alertmanager.fullname" . }}-headless + template: + metadata: + labels: + {{- include "alertmanager.selectorLabels" . | nindent 8 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + {{- if not .Values.configmapReload.enabled }} + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + {{- end }} + {{- with .Values.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + automountServiceAccountToken: {{ .Values.automountServiceAccountToken }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "alertmanager.serviceAccountName" . }} + {{- with .Values.dnsConfig }} + dnsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.schedulerName }} + schedulerName: {{ . }} + {{- end }} + {{- if or .Values.podAntiAffinity .Values.affinity }} + affinity: + {{- end }} + {{- with .Values.affinity }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if eq .Values.podAntiAffinity "hard" }} + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - topologyKey: {{ .Values.podAntiAffinityTopologyKey }} + labelSelector: + matchExpressions: + - {key: app.kubernetes.io/name, operator: In, values: [{{ include "alertmanager.name" . }}]} + {{- else if eq .Values.podAntiAffinity "soft" }} + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + topologyKey: {{ .Values.podAntiAffinityTopologyKey }} + labelSelector: + matchExpressions: + - {key: app.kubernetes.io/name, operator: In, values: [{{ include "alertmanager.name" . }}]} + {{- end }} + {{- with .Values.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.topologySpreadConstraints }} + topologySpreadConstraints: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + securityContext: + {{- toYaml .Values.podSecurityContext | nindent 8 }} + {{- with .Values.extraInitContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + {{- if .Values.configmapReload.enabled }} + - name: {{ .Chart.Name }}-{{ .Values.configmapReload.name }} + image: "{{ .Values.configmapReload.image.repository }}:{{ .Values.configmapReload.image.tag }}" + imagePullPolicy: "{{ .Values.configmapReload.image.pullPolicy }}" + {{- with .Values.configmapReload.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + args: + {{- if and (hasKey .Values.configmapReload.extraArgs "config-file" | not) (hasKey .Values.configmapReload.extraArgs "watched-dir" | not) }} + - --watched-dir=/etc/alertmanager + {{- end }} + {{- if not (hasKey .Values.configmapReload.extraArgs "reload-url") }} + - --reload-url=http://127.0.0.1:9093/-/reload + {{- end }} + {{- range $key, $value := .Values.configmapReload.extraArgs }} + - --{{ $key }}={{ $value }} + {{- end }} + resources: + {{- toYaml .Values.configmapReload.resources | nindent 12 }} + {{- with .Values.configmapReload.containerPort }} + ports: + - containerPort: {{ . }} + {{- end }} + {{- with .Values.configmapReload.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - name: config + mountPath: /etc/alertmanager + {{- if .Values.configmapReload.extraVolumeMounts }} + {{- toYaml .Values.configmapReload.extraVolumeMounts | nindent 12 }} + {{- end }} + {{- end }} + - name: {{ .Chart.Name }} + securityContext: + {{- toYaml .Values.securityContext | nindent 12 }} + image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + env: + - name: POD_IP + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: status.podIP + {{- if .Values.extraEnv }} + {{- toYaml .Values.extraEnv | nindent 12 }} + {{- end }} + {{- with .Values.command }} + command: + {{- toYaml . | nindent 12 }} + {{- end }} + args: + - --storage.path=/alertmanager + {{- if not (hasKey .Values.extraArgs "config.file") }} + - --config.file=/etc/alertmanager/alertmanager.yml + {{- end }} + {{- if or (gt (int .Values.replicaCount) 1) (.Values.additionalPeers) }} + - --cluster.advertise-address=[$(POD_IP)]:{{ $svcClusterPort }} + - --cluster.listen-address=0.0.0.0:{{ $svcClusterPort }} + {{- end }} + {{- if gt (int .Values.replicaCount) 1}} + {{- $fullName := include "alertmanager.fullname" . }} + {{- range $i := until (int .Values.replicaCount) }} + - --cluster.peer={{ $fullName }}-{{ $i }}.{{ $fullName }}-headless:{{ $svcClusterPort }} + {{- end }} + {{- end }} + {{- if .Values.additionalPeers }} + {{- range $item := .Values.additionalPeers }} + - --cluster.peer={{ $item }} + {{- end }} + {{- end }} + {{- range $key, $value := .Values.extraArgs }} + - --{{ $key }}={{ $value }} + {{- end }} + ports: + - name: http + containerPort: 9093 + protocol: TCP + {{- if or (gt (int .Values.replicaCount) 1) (.Values.additionalPeers) }} + - name: clusterpeer-tcp + containerPort: {{ $svcClusterPort }} + protocol: TCP + - name: clusterpeer-udp + containerPort: {{ $svcClusterPort }} + protocol: UDP + {{- end }} + livenessProbe: + {{- toYaml .Values.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.resources | nindent 12 }} + volumeMounts: + {{- if .Values.config.enabled }} + - name: config + mountPath: /etc/alertmanager + {{- end }} + {{- range .Values.extraSecretMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath }} + readOnly: {{ .readOnly }} + {{- end }} + - name: storage + mountPath: /alertmanager + {{- if .Values.extraVolumeMounts }} + {{- toYaml .Values.extraVolumeMounts | nindent 12 }} + {{- end }} + {{- with .Values.extraContainers }} + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + {{- if .Values.config.enabled }} + - name: config + configMap: + name: {{ include "alertmanager.fullname" . }} + {{- end }} + {{- range .Values.extraSecretMounts }} + - name: {{ .name }} + secret: + secretName: {{ .secretName }} + {{- with .optional }} + optional: {{ . }} + {{- end }} + {{- end }} + {{- if .Values.extraVolumes }} + {{- toYaml .Values.extraVolumes | nindent 8 }} + {{- end }} + {{- if .Values.persistence.enabled }} + volumeClaimTemplates: + - metadata: + name: storage + spec: + accessModes: + {{- toYaml .Values.persistence.accessModes | nindent 10 }} + resources: + requests: + storage: {{ .Values.persistence.size }} + {{- if .Values.persistence.storageClass }} + {{- if (eq "-" .Values.persistence.storageClass) }} + storageClassName: "" + {{- else }} + storageClassName: {{ .Values.persistence.storageClass }} + {{- end }} + {{- end }} + {{- else }} + - name: storage + emptyDir: {} + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/tests/test-connection.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/tests/test-connection.yaml new file mode 100644 index 0000000..410eba5 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/templates/tests/test-connection.yaml @@ -0,0 +1,20 @@ +{{- if .Values.testFramework.enabled }} +apiVersion: v1 +kind: Pod +metadata: + name: "{{ include "alertmanager.fullname" . }}-test-connection" + labels: + {{- include "alertmanager.labels" . | nindent 4 }} + {{- with .Values.testFramework.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ include "alertmanager.namespace" . }} +spec: + containers: + - name: wget + image: busybox + command: ['wget'] + args: ['{{ include "alertmanager.fullname" . }}:{{ .Values.service.port }}'] + restartPolicy: Never +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/values.schema.json b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/values.schema.json new file mode 100644 index 0000000..172dbcf --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/values.schema.json @@ -0,0 +1,915 @@ +{ + "$schema": "http://json-schema.org/draft-07/schema", + "title": "alertmanager", + "description": "The Alertmanager handles alerts sent by client applications such as the Prometheus server.", + "type": "object", + "required": [ + "replicaCount", + "image", + "serviceAccount", + "service", + "persistence", + "config" + ], + "definitions": { + "image": { + "description": "Container image parameters.", + "type": "object", + "required": ["repository"], + "additionalProperties": false, + "properties": { + "repository": { + "description": "Image repository. Path to the image with registry(quay.io) or without(prometheus/alertmanager) for docker.io.", + "type": "string" + }, + "pullPolicy": { + "description": "Image pull policy. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated.", + "type": "string", + "enum": [ + "Never", + "IfNotPresent", + "Always" + ], + "default": "IfNotPresent" + }, + "tag": { + "description": "Use chart appVersion by default.", + "type": "string", + "default": "" + } + } + }, + "resources": { + "description": "Resource limits and requests for the Container.", + "type": "object", + "properties": { + "limits": { + "description": "Resource limits for the Container.", + "type": "object", + "properties": { + "cpu": { + "description": "CPU request for the Container.", + "type": "string" + }, + "memory": { + "description": "Memory request for the Container.", + "type": "string" + } + } + }, + "requests": { + "description": "Resource requests for the Container.", + "type": "object", + "properties": { + "cpu": { + "description": "CPU request for the Container.", + "type": "string" + }, + "memory": { + "description": "Memory request for the Container.", + "type": "string" + } + } + } + } + }, + "securityContext": { + "description": "Security context for the container.", + "type": "object", + "properties": { + "capabilities": { + "description": "Specifies the capabilities to be dropped by the container.", + "type": "object", + "properties": { + "drop": { + "description": "List of capabilities to be dropped.", + "type": "array", + "items": { + "type": "string" + } + } + } + }, + "readOnlyRootFilesystem": { + "description": "Specifies whether the root file system should be mounted as read-only.", + "type": "boolean" + }, + "runAsUser": { + "description": "Specifies the UID (User ID) to run the container as.", + "type": "integer" + }, + "runAsNonRoot": { + "description": "Specifies whether to run the container as a non-root user.", + "type": "boolean" + }, + "runAsGroup": { + "description": "Specifies the GID (Group ID) to run the container as.", + "type": "integer" + } + } + }, + "volumeMounts": { + "description": "List of volume mounts for the Container.", + "type": "array", + "items": { + "description": "Volume mounts for the Container.", + "type": "object", + "required": ["name", "mountPath"], + "properties": { + "name": { + "description": "The name of the volume to mount.", + "type": "string" + }, + "mountPath": { + "description": "The mount path for the volume.", + "type": "string" + }, + "readOnly": { + "description": "Specifies if the volume should be mounted in read-only mode.", + "type": "boolean" + } + } + } + }, + "env": { + "description": "List of environment variables for the Container.", + "type": "array", + "items": { + "description": "Environment variables for the Container.", + "type": "object", + "required": ["name"], + "properties": { + "name": { + "description": "The name of the environment variable.", + "type": "string" + }, + "value": { + "description": "The value of the environment variable.", + "type": "string" + } + } + } + }, + "config": { + "description": "https://prometheus.io/docs/alerting/latest/configuration/", + "duration": { + "type": "string", + "pattern": "^((([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?|0)$" + }, + "labelname": { + "type": "string", + "pattern": "^[a-zA-Z_][a-zA-Z0-9_]*$|^...$" + }, + "route": { + "description": "Alert routing configuration.", + "type": "object", + "properties": { + "receiver": { + "description": "The default receiver to send alerts to.", + "type": "string" + }, + "group_by": { + "description": "The labels by which incoming alerts are grouped together.", + "type": "array", + "items": { + "type": "string", + "$ref": "#/definitions/config/labelname" + } + }, + "continue": { + "description": "Whether an alert should continue matching subsequent sibling nodes.", + "type": "boolean", + "default": false + }, + "matchers": { + "description": "A list of matchers that an alert has to fulfill to match the node.", + "type": "array", + "items": { + "type": "string" + } + }, + "group_wait": { + "description": "How long to initially wait to send a notification for a group of alerts.", + "$ref": "#/definitions/config/duration" + }, + "group_interval": { + "description": "How long to wait before sending a notification about new alerts that are added to a group of alerts for which an initial notification has already been sent.", + "$ref": "#/definitions/config/duration" + }, + "repeat_interval": { + "description": "How long to wait before sending a notification again if it has already been sent successfully for an alert.", + "$ref": "#/definitions/config/duration" + }, + "mute_time_intervals": { + "description": "Times when the route should be muted.", + "type": "array", + "items": { + "type": "string" + } + }, + "active_time_intervals": { + "description": "Times when the route should be active.", + "type": "array", + "items": { + "type": "string" + } + }, + "routes": { + "description": "Zero or more child routes.", + "type": "array", + "items": { + "type": "object", + "$ref": "#/definitions/config/route" + } + } + } + } + } + }, + "properties": { + "replicaCount": { + "description": "Number of desired pods.", + "type": "integer", + "default": 1, + "minimum": 0 + }, + "image": { + "description": "Container image parameters.", + "$ref": "#/definitions/image" + }, + "extraArgs": { + "description": "Additional alertmanager container arguments. Use args without '--', only 'key: value' syntax.", + "type": "object", + "default": {} + }, + "extraSecretMounts": { + "description": "Additional Alertmanager Secret mounts.", + "type": "array", + "default": [], + "items": { + "type": "object", + "required": ["name", "mountPath", "secretName"], + "properties": { + "name": { + "type": "string" + }, + "mountPath": { + "type": "string" + }, + "subPath": { + "type": "string", + "default": "" + }, + "secretName": { + "type": "string" + }, + "readOnly": { + "type": "boolean", + "default": false + } + } + } + }, + "imagePullSecrets": { + "description": "The property allows you to configure multiple image pull secrets.", + "type": "array", + "default": [], + "items": { + "type": "object", + "required": ["name"], + "properties": { + "name": { + "description": "Specifies the Secret name of the image pull secret.", + "type": "string" + } + } + } + }, + "nameOverride": { + "description": "Override value for the name of the Helm chart.", + "type": "string", + "default": "" + }, + "fullnameOverride": { + "description": "Override value for the fully qualified app name.", + "type": "string", + "default": "" + }, + "namespaceOverride": { + "description": "Override deployment namespace.", + "type": "string", + "default": "" + }, + "automountServiceAccountToken": { + "description": "Specifies whether to automatically mount the ServiceAccount token into the Pod's filesystem.", + "type": "boolean", + "default": true + }, + "serviceAccount": { + "description": "Contains properties related to the service account configuration.", + "type": "object", + "required": ["create"], + "properties": { + "create": { + "description": "Specifies whether a service account should be created.", + "type": "boolean", + "default": true + }, + "annotations": { + "description": "Annotations to add to the service account.", + "type": "object", + "default": {} + }, + "name": { + "description": "The name of the service account to use. If not set and create is true, a name is generated using the fullname template.", + "type": "string", + "default": "" + } + } + }, + "schedulerName": { + "description": "Sets the schedulerName in the alertmanager pod.", + "type": "string", + "default": "" + }, + "priorityClassName": { + "description": "Sets the priorityClassName in the alertmanager pod.", + "type": "string", + "default": "" + }, + "podSecurityContext": { + "description": "Pod security context configuration.", + "type": "object", + "properties": { + "fsGroup": { + "description": "The fsGroup value for the pod's security context.", + "type": "integer", + "default": 65534 + }, + "runAsUser": { + "description": "The UID to run the pod's containers as.", + "type": "integer" + }, + "runAsGroup": { + "description": "The GID to run the pod's containers as.", + "type": "integer" + } + } + }, + "dnsConfig": { + "description": "DNS configuration for the pod.", + "type": "object", + "properties": { + "nameservers": { + "description": "List of DNS server IP addresses.", + "type": "array", + "items": { + "type": "string" + } + }, + "searches": { + "description": "List of DNS search domains.", + "type": "array", + "items": { + "type": "string" + } + }, + "options": { + "description": "List of DNS options.", + "type": "array", + "items": { + "description": "DNS options.", + "type": "object", + "required": ["name"], + "properties": { + "name": { + "description": "The name of the DNS option.", + "type": "string" + }, + "value": { + "description": "The value of the DNS option.", + "type": "string" + } + } + } + } + } + }, + "hostAliases": { + "description": "List of host aliases.", + "type": "array", + "items": { + "description": "Host aliases configuration.", + "type": "object", + "required": ["ip", "hostnames"], + "properties": { + "ip": { + "description": "IP address associated with the host alias.", + "type": "string" + }, + "hostnames": { + "description": "List of hostnames associated with the IP address.", + "type": "array", + "items": { + "type": "string" + } + } + } + } + }, + "securityContext": { + "description": "Security context for the container.", + "$ref": "#/definitions/securityContext" + }, + "additionalPeers": { + "description": "Additional peers for a alertmanager.", + "type": "array", + "items": { + "type": "string" + } + }, + "extraInitContainers": { + "description": "Additional InitContainers to initialize the pod.", + "type": "array", + "default": [], + "items": { + "required": ["name", "image"], + "properties": { + "name": { + "description": "The name of the InitContainer.", + "type": "string" + }, + "image": { + "description": "The container image to use for the InitContainer.", + "type": "string" + }, + "pullPolicy": { + "description": "Image pull policy. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated.", + "type": "string", + "enum": [ + "Never", + "IfNotPresent", + "Always" + ], + "default": "IfNotPresent" + }, + "command": { + "description": "The command to run in the InitContainer.", + "type": "array", + "items": { + "type": "string" + } + }, + "args": { + "description": "Additional command arguments for the InitContainer.", + "type": "array", + "items": { + "type": "string" + } + }, + "ports": { + "description": "List of ports to expose from the container.", + "type": "array", + "items": { + "type": "object" + } + }, + "env": { + "description": "List of environment variables for the InitContainer.", + "$ref": "#/definitions/env" + }, + "envFrom": { + "description": "List of sources to populate environment variables in the container.", + "type": "array", + "items": { + "type": "object" + } + }, + "volumeMounts": { + "description": "List of volume mounts for the InitContainer.", + "$ref": "#/definitions/volumeMounts" + }, + "resources": { + "description": "Resource requirements for the InitContainer.", + "$ref": "#/definitions/resources" + }, + "securityContext": { + "$ref": "#/definitions/securityContext", + "description": "The security context for the InitContainer." + } + } + } + }, + "extraContainers": { + "description": "Additional containers to add to the stateful set.", + "type": "array", + "default": [], + "items": { + "required": ["name", "image"], + "properties": { + "name": { + "description": "The name of the InitContainer.", + "type": "string" + }, + "image": { + "description": "The container image to use for the InitContainer.", + "type": "string" + }, + "pullPolicy": { + "description": "Image pull policy. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated.", + "type": "string", + "enum": [ + "Never", + "IfNotPresent", + "Always" + ], + "default": "IfNotPresent" + }, + "command": { + "description": "The command to run in the InitContainer.", + "type": "array", + "items": { + "type": "string" + } + }, + "args": { + "description": "Additional command arguments for the InitContainer.", + "type": "array", + "items": { + "type": "string" + } + }, + "ports": { + "description": "List of ports to expose from the container.", + "type": "array", + "items": { + "type": "object" + } + }, + "env": { + "description": "List of environment variables for the InitContainer.", + "$ref": "#/definitions/env" + }, + "envFrom": { + "description": "List of sources to populate environment variables in the container.", + "type": "array", + "items": { + "type": "object" + } + }, + "volumeMounts": { + "description": "List of volume mounts for the InitContainer.", + "$ref": "#/definitions/volumeMounts" + }, + "resources": { + "description": "Resource requirements for the InitContainer.", + "$ref": "#/definitions/resources" + }, + "securityContext": { + "$ref": "#/definitions/securityContext", + "description": "The security context for the InitContainer." + } + } + } + }, + "resources": { + "description": "Resource limits and requests for the pod.", + "$ref": "#/definitions/resources" + }, + "livenessProbe": { + "description": "Liveness probe configuration.", + "type": "object" + }, + "readinessProbe": { + "description": "Readiness probe configuration.", + "type": "object" + }, + "service": { + "description": "Service configuration.", + "type": "object", + "required": ["type", "port"], + "properties": { + "annotations": { + "description": "Annotations to add to the service.", + "type": "object" + }, + "type": { + "description": "Service type.", + "type": "string" + }, + "port": { + "description": "Port number for the service.", + "type": "integer" + }, + "clusterPort": { + "description": "Port number for the cluster.", + "type": "integer" + }, + "loadBalancerIP": { + "description": "External IP to assign when the service type is LoadBalancer.", + "type": "string" + }, + "loadBalancerSourceRanges": { + "description": "IP ranges to allow access to the loadBalancerIP.", + "type": "array", + "items": { + "type": "string" + } + }, + "nodePort": { + "description": "Specific nodePort to force when service type is NodePort.", + "type": "integer" + } + } + }, + "ingress": { + "description": "Ingress configuration.", + "type": "object", + "properties": { + "enabled": { + "description": "Indicates if Ingress is enabled.", + "type": "boolean" + }, + "className": { + "description": "Ingress class name.", + "type": "string" + }, + "annotations": { + "description": "Annotations to add to the Ingress.", + "type": "object" + }, + "hosts": { + "description": "Host and path configuration for the Ingress.", + "type": "array", + "items": { + "type": "object", + "properties": { + "host": { + "description": "Host name for the Ingress.", + "type": "string" + }, + "paths": { + "description": "Path configuration for the Ingress.", + "type": "array", + "items": { + "type": "object", + "properties": { + "path": { + "description": "Path for the Ingress.", + "type": "string" + }, + "pathType": { + "description": "Path type for the Ingress.", + "type": "string" + } + } + } + } + } + } + }, + "tls": { + "description": "TLS configuration for the Ingress.", + "type": "array", + "items": { + "type": "object", + "properties": { + "secretName": { + "description": "Name of the secret for TLS.", + "type": "string" + }, + "hosts": { + "description": "Host names for the TLS configuration.", + "type": "array", + "items": { + "type": "string" + } + } + } + } + } + } + }, + "nodeSelector": { + "description": "Node selector for pod assignment.", + "type": "object" + }, + "tolerations": { + "description": "Tolerations for pod assignment.", + "type": "array" + }, + "affinity": { + "description": "Affinity rules for pod assignment.", + "type": "object" + }, + "podAntiAffinity": { + "description": "Pod anti-affinity configuration.", + "type": "string", + "enum": ["", "soft", "hard"], + "default": "" + }, + "podAntiAffinityTopologyKey": { + "description": "Topology key to use for pod anti-affinity.", + "type": "string" + }, + "topologySpreadConstraints": { + "description": "Topology spread constraints for pod assignment.", + "type": "array", + "items": { + "type": "object", + "required": ["maxSkew", "topologyKey", "whenUnsatisfiable", "labelSelector"], + "properties": { + "maxSkew": { + "type": "integer" + }, + "topologyKey": { + "type": "string" + }, + "whenUnsatisfiable": { + "type": "string", + "enum": ["DoNotSchedule", "ScheduleAnyway"] + }, + "labelSelector": { + "type": "object", + "required": ["matchLabels"], + "properties": { + "matchLabels": { + "type": "object" + } + } + } + } + } + }, + "statefulSet": { + "description": "StatefulSet configuration for managing pods.", + "type": "object", + "properties": { + "annotations": { + "type": "object" + } + } + }, + "podAnnotations": { + "description": "Annotations to add to the pods.", + "type": "object" + }, + "podLabels": { + "description": "Labels to add to the pods.", + "type": "object" + }, + "podDisruptionBudget": { + "description": "Pod disruption budget configuration.", + "type": "object", + "properties": { + "maxUnavailable": { + "type": "integer" + }, + "minAvailable": { + "type": "integer" + } + } + }, + "command": { + "description": "The command to be executed in the container.", + "type": "array", + "items": { + "type": "string" + } + }, + "persistence": { + "description": "Persistence configuration for storing data.", + "type": "object", + "required": ["enabled", "size"], + "properties": { + "enabled": { + "type": "boolean" + }, + "storageClass": { + "type": "string" + }, + "accessModes": { + "type": "array", + "items": { + "type": "string" + } + }, + "size": { + "type": "string" + } + } + }, + "configAnnotations": { + "description": "Annotations to be added to the Alertmanager configuration.", + "type": "object" + }, + "config": { + "description": "Alertmanager configuration.", + "type": "object", + "properties": { + "enabled": { + "description": "Whether to create alermanager configmap or not.", + "type": "boolean" + }, + "global": { + "description": "Global configuration options.", + "type": "object" + }, + "templates": { + "description": "Alertmanager template files.", + "type": "array", + "items": { + "type": "string" + } + }, + "receivers": { + "description": "Alert receivers configuration.", + "type": "array", + "items": { + "type": "object", + "required": ["name"], + "properties": { + "name": { + "description": "The unique name of the receiver.", + "type": "string" + } + } + } + }, + "route": { + "description": "Alert routing configuration.", + "type": "object", + "$ref": "#/definitions/config/route" + } + } + }, + "configmapReload": { + "description": "Monitors ConfigMap changes and POSTs to a URL.", + "type": "object", + "properties": { + "enabled": { + "description": "Specifies whether the configmap-reload container should be deployed.", + "type": "boolean", + "default": false + }, + "name": { + "description": "The name of the configmap-reload container.", + "type": "string" + }, + "image": { + "description": "The container image for the configmap-reload container.", + "$ref": "#/definitions/image" + }, + "containerPort": { + "description": "Port number for the configmap-reload container.", + "type": "integer" + }, + "resources": { + "description": "Resource requests and limits for the configmap-reload container.", + "$ref": "#/definitions/resources" + } + } + }, + "templates": { + "description": "Custom templates used by Alertmanager.", + "type": "object" + }, + "extraVolumeMounts": { + "description": "List of volume mounts for the Container.", + "$ref": "#/definitions/volumeMounts" + }, + "extraVolumes": { + "description": "Additional volumes to be mounted in the Alertmanager pod.", + "type": "array", + "default": [], + "items": { + "type": "object", + "required": ["name"], + "properties": { + "name": { + "type": "string" + } + } + } + }, + "extraEnv": { + "description": "List of environment variables for the Container.", + "$ref": "#/definitions/env" + }, + "testFramework": { + "description": "Configuration for the test Pod.", + "type": "object", + "properties": { + "enabled": { + "description": "Specifies whether the test Pod is enabled.", + "type": "boolean", + "default": false + }, + "annotations": { + "description": "Annotations to be added to the test Pod.", + "type": "object" + } + } + } + } +} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/values.yaml new file mode 100644 index 0000000..fa3b355 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/alertmanager/values.yaml @@ -0,0 +1,363 @@ +# yaml-language-server: $schema=values.schema.json +# Default values for alertmanager. +# This is a YAML-formatted file. +# Declare variables to be passed into your templates. + +replicaCount: 1 + +# Number of old history to retain to allow rollback +# Default Kubernetes value is set to 10 +revisionHistoryLimit: 10 + +image: + repository: quay.io/prometheus/alertmanager + pullPolicy: IfNotPresent + # Overrides the image tag whose default is the chart appVersion. + tag: "" + +extraArgs: {} + +## Additional Alertmanager Secret mounts +# Defines additional mounts with secrets. Secrets must be manually created in the namespace. +extraSecretMounts: [] + # - name: secret-files + # mountPath: /etc/secrets + # subPath: "" + # secretName: alertmanager-secret-files + # readOnly: true + +imagePullSecrets: [] +nameOverride: "" +fullnameOverride: "" +## namespaceOverride overrides the namespace which the resources will be deployed in +namespaceOverride: "" + +automountServiceAccountToken: true + +serviceAccount: + # Specifies whether a service account should be created + create: true + # Annotations to add to the service account + annotations: {} + # The name of the service account to use. + # If not set and create is true, a name is generated using the fullname template + name: "" + +# Sets priorityClassName in alertmanager pod +priorityClassName: "" + +# Sets schedulerName in alertmanager pod +schedulerName: "" + +podSecurityContext: + fsGroup: 65534 +dnsConfig: {} + # nameservers: + # - 1.2.3.4 + # searches: + # - ns1.svc.cluster-domain.example + # - my.dns.search.suffix + # options: + # - name: ndots + # value: "2" + # - name: edns0 +hostAliases: [] + # - ip: "127.0.0.1" + # hostnames: + # - "foo.local" + # - "bar.local" + # - ip: "10.1.2.3" + # hostnames: + # - "foo.remote" + # - "bar.remote" +securityContext: + # capabilities: + # drop: + # - ALL + # readOnlyRootFilesystem: true + runAsUser: 65534 + runAsNonRoot: true + runAsGroup: 65534 + +additionalPeers: [] + +## Additional InitContainers to initialize the pod +## +extraInitContainers: [] + +## Additional containers to add to the stateful set. This will allow to setup sidecarContainers like a proxy to integrate +## alertmanager with an external tool like teams that has not direct integration. +## +extraContainers: [] + +livenessProbe: + httpGet: + path: / + port: http + +readinessProbe: + httpGet: + path: / + port: http + +service: + annotations: {} + labels: {} + type: ClusterIP + port: 9093 + clusterPort: 9094 + loadBalancerIP: "" # Assign ext IP when Service type is LoadBalancer + loadBalancerSourceRanges: [] # Only allow access to loadBalancerIP from these IPs + # if you want to force a specific nodePort. Must be use with service.type=NodePort + # nodePort: + + # Optionally specify extra list of additional ports exposed on both services + extraPorts: [] + +# Configuration for creating a separate Service for each statefulset Alertmanager replica +# +servicePerReplica: + enabled: false + annotations: {} + + # Loadbalancer source IP ranges + # Only used if servicePerReplica.type is "LoadBalancer" + loadBalancerSourceRanges: [] + + # Denotes if this Service desires to route external traffic to node-local or cluster-wide endpoints + # + externalTrafficPolicy: Cluster + + # Service type + # + type: ClusterIP + +ingress: + enabled: false + className: "" + annotations: {} + # kubernetes.io/ingress.class: nginx + # kubernetes.io/tls-acme: "true" + hosts: + - host: alertmanager.domain.com + paths: + - path: / + pathType: ImplementationSpecific + tls: [] + # - secretName: chart-example-tls + # hosts: + # - alertmanager.domain.com + +# Configuration for creating an Ingress that will map to each Alertmanager replica service +# alertmanager.servicePerReplica must be enabled +# +ingressPerReplica: + enabled: false + + # className for the ingresses + # + className: "" + + annotations: {} + labels: {} + + # Final form of the hostname for each per replica ingress is + # {{ ingressPerReplica.hostPrefix }}-{{ $replicaNumber }}.{{ ingressPerReplica.hostDomain }} + # + # Prefix for the per replica ingress that will have `-$replicaNumber` + # appended to the end + hostPrefix: "alertmanager" + # Domain that will be used for the per replica ingress + hostDomain: "domain.com" + + # Paths to use for ingress rules + # + paths: + - / + + # PathType for ingress rules + # + pathType: ImplementationSpecific + + # Secret name containing the TLS certificate for alertmanager per replica ingress + # Secret must be manually created in the namespace + tlsSecretName: "" + + # Separated secret for each per replica Ingress. Can be used together with cert-manager + # + tlsSecretPerReplica: + enabled: false + # Final form of the secret for each per replica ingress is + # {{ tlsSecretPerReplica.prefix }}-{{ $replicaNumber }} + # + prefix: "alertmanager" + +resources: {} + # We usually recommend not to specify default resources and to leave this as a conscious + # choice for the user. This also increases chances charts run on environments with little + # resources, such as Minikube. If you do want to specify resources, uncomment the following + # lines, adjust them as necessary, and remove the curly braces after 'resources:'. + # limits: + # cpu: 100m + # memory: 128Mi + # requests: + # cpu: 10m + # memory: 32Mi + +nodeSelector: {} + +tolerations: [] + +affinity: {} + +## Pod anti-affinity can prevent the scheduler from placing Alertmanager replicas on the same node. +## The default value "soft" means that the scheduler should *prefer* to not schedule two replica pods onto the same node but no guarantee is provided. +## The value "hard" means that the scheduler is *required* to not schedule two replica pods onto the same node. +## The value "" will disable pod anti-affinity so that no anti-affinity rules will be configured. +## +podAntiAffinity: "" + +## If anti-affinity is enabled sets the topologyKey to use for anti-affinity. +## This can be changed to, for example, failure-domain.beta.kubernetes.io/zone +## +podAntiAffinityTopologyKey: kubernetes.io/hostname + +## Topology spread constraints rely on node labels to identify the topology domain(s) that each Node is in. +## Ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ +topologySpreadConstraints: [] + # - maxSkew: 1 + # topologyKey: failure-domain.beta.kubernetes.io/zone + # whenUnsatisfiable: DoNotSchedule + # labelSelector: + # matchLabels: + # app.kubernetes.io/instance: alertmanager + +statefulSet: + annotations: {} + +podAnnotations: {} +podLabels: {} + +# Ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/ +podDisruptionBudget: {} + # maxUnavailable: 1 + # minAvailable: 1 + +command: [] + +persistence: + enabled: true + ## Persistent Volume Storage Class + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is + ## set, choosing the default provisioner. + ## + # storageClass: "-" + accessModes: + - ReadWriteOnce + size: 50Mi + +configAnnotations: {} + ## For example if you want to provide private data from a secret vault + ## https://github.com/banzaicloud/bank-vaults/tree/main/charts/vault-secrets-webhook + ## P.s.: Add option `configMapMutation: true` for vault-secrets-webhook + # vault.security.banzaicloud.io/vault-role: "admin" + # vault.security.banzaicloud.io/vault-addr: "https://vault.vault.svc.cluster.local:8200" + # vault.security.banzaicloud.io/vault-skip-verify: "true" + # vault.security.banzaicloud.io/vault-path: "kubernetes" + ## Example for inject secret + # slack_api_url: '${vault:secret/data/slack-hook-alerts#URL}' + +config: + enabled: true + global: {} + # slack_api_url: '' + + templates: + - '/etc/alertmanager/*.tmpl' + + receivers: + - name: default-receiver + # slack_configs: + # - channel: '@you' + # send_resolved: true + + route: + group_wait: 10s + group_interval: 5m + receiver: default-receiver + repeat_interval: 3h + +## Monitors ConfigMap changes and POSTs to a URL +## Ref: https://github.com/prometheus-operator/prometheus-operator/tree/main/cmd/prometheus-config-reloader +## +configmapReload: + ## If false, the configmap-reload container will not be deployed + ## + enabled: false + + ## configmap-reload container name + ## + name: configmap-reload + + ## configmap-reload container image + ## + image: + repository: quay.io/prometheus-operator/prometheus-config-reloader + tag: v0.66.0 + pullPolicy: IfNotPresent + + # containerPort: 9533 + + ## configmap-reload resource requests and limits + ## Ref: http://kubernetes.io/docs/user-guide/compute-resources/ + ## + resources: {} + + extraArgs: {} + + ## Optionally specify extra list of additional volumeMounts + extraVolumeMounts: [] + # - name: extras + # mountPath: /usr/share/extras + # readOnly: true + + ## Optionally specify extra environment variables to add to alertmanager container + extraEnv: [] + # - name: FOO + # value: BAR + + securityContext: {} + # capabilities: + # drop: + # - ALL + # readOnlyRootFilesystem: true + # runAsUser: 65534 + # runAsNonRoot: true + # runAsGroup: 65534 + +templates: {} +# alertmanager.tmpl: |- + +## Optionally specify extra list of additional volumeMounts +extraVolumeMounts: [] + # - name: extras + # mountPath: /usr/share/extras + # readOnly: true + +## Optionally specify extra list of additional volumes +extraVolumes: [] + # - name: extras + # emptyDir: {} + +## Optionally specify extra environment variables to add to alertmanager container +extraEnv: [] + # - name: FOO + # value: BAR + +testFramework: + enabled: false + annotations: + "helm.sh/hook": test-success + # "helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded" diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/.helmignore new file mode 100644 index 0000000..f0c1319 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/.helmignore @@ -0,0 +1,21 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/Chart.yaml new file mode 100644 index 0000000..4342ac8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/Chart.yaml @@ -0,0 +1,26 @@ +annotations: + artifacthub.io/license: Apache-2.0 + artifacthub.io/links: | + - name: Chart Source + url: https://github.com/prometheus-community/helm-charts +apiVersion: v2 +appVersion: 2.10.1 +description: Install kube-state-metrics to generate and expose cluster-level metrics +home: https://github.com/kubernetes/kube-state-metrics/ +keywords: +- metric +- monitoring +- prometheus +- kubernetes +maintainers: +- email: tariq.ibrahim@mulesoft.com + name: tariq1890 +- email: manuel@rueg.eu + name: mrueg +- email: david@0xdc.me + name: dotdc +name: kube-state-metrics +sources: +- https://github.com/kubernetes/kube-state-metrics/ +type: application +version: 5.15.2 diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/README.md b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/README.md new file mode 100644 index 0000000..843be89 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/README.md @@ -0,0 +1,85 @@ +# kube-state-metrics Helm Chart + +Installs the [kube-state-metrics agent](https://github.com/kubernetes/kube-state-metrics). + +## Get Repository Info + +```console +helm repo add prometheus-community https://prometheus-community.github.io/helm-charts +helm repo update +``` + +_See [helm repo](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + + +## Install Chart + +```console +helm install [RELEASE_NAME] prometheus-community/kube-state-metrics [flags] +``` + +_See [configuration](#configuration) below._ + +_See [helm install](https://helm.sh/docs/helm/helm_install/) for command documentation._ + +## Uninstall Chart + +```console +helm uninstall [RELEASE_NAME] +``` + +This removes all the Kubernetes components associated with the chart and deletes the release. + +_See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall/) for command documentation._ + +## Upgrading Chart + +```console +helm upgrade [RELEASE_NAME] prometheus-community/kube-state-metrics [flags] +``` + +_See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documentation._ + +### Migrating from stable/kube-state-metrics and kubernetes/kube-state-metrics + +You can upgrade in-place: + +1. [get repository info](#get-repository-info) +1. [upgrade](#upgrading-chart) your existing release name using the new chart repository + +## Upgrading to v3.0.0 + +v3.0.0 includes kube-state-metrics v2.0, see the [changelog](https://github.com/kubernetes/kube-state-metrics/blob/release-2.0/CHANGELOG.md) for major changes on the application-side. + +The upgraded chart now the following changes: + +* Dropped support for helm v2 (helm v3 or later is required) +* collectors key was renamed to resources +* namespace key was renamed to namespaces + +## Configuration + +See [Customizing the Chart Before Installing](https://helm.sh/docs/intro/using_helm/#customizing-the-chart-before-installing). To see all configurable options with detailed comments: + +```console +helm show values prometheus-community/kube-state-metrics +``` + +### kube-rbac-proxy + +You can enable `kube-state-metrics` endpoint protection using `kube-rbac-proxy`. By setting `kubeRBACProxy.enabled: true`, this chart will deploy one RBAC proxy container per endpoint (metrics & telemetry). +To authorize access, authenticate your requests (via a `ServiceAccount` for example) with a `ClusterRole` attached such as: + +```yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: kube-state-metrics-read +rules: + - apiGroups: [ "" ] + resources: ["services/kube-state-metrics"] + verbs: + - get +``` + +See [kube-rbac-proxy examples](https://github.com/brancz/kube-rbac-proxy/tree/master/examples/resource-attributes) for more details. diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/NOTES.txt new file mode 100644 index 0000000..3589c24 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/NOTES.txt @@ -0,0 +1,23 @@ +kube-state-metrics is a simple service that listens to the Kubernetes API server and generates metrics about the state of the objects. +The exposed metrics can be found here: +https://github.com/kubernetes/kube-state-metrics/blob/master/docs/README.md#exposed-metrics + +The metrics are exported on the HTTP endpoint /metrics on the listening port. +In your case, {{ template "kube-state-metrics.fullname" . }}.{{ template "kube-state-metrics.namespace" . }}.svc.cluster.local:{{ .Values.service.port }}/metrics + +They are served either as plaintext or protobuf depending on the Accept header. +They are designed to be consumed either by Prometheus itself or by a scraper that is compatible with scraping a Prometheus client endpoint. + +{{- if .Values.kubeRBACProxy.enabled}} + +kube-rbac-proxy endpoint protections is enabled: +- Metrics endpoints are now HTTPS +- Ensure that the client authenticates the requests (e.g. via service account) with the following role permissions: +``` +rules: + - apiGroups: [ "" ] + resources: ["services/{{ template "kube-state-metrics.fullname" . }}"] + verbs: + - get +``` +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/_helpers.tpl new file mode 100644 index 0000000..a4358c8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/_helpers.tpl @@ -0,0 +1,156 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "kube-state-metrics.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "kube-state-metrics.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Create the name of the service account to use +*/}} +{{- define "kube-state-metrics.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "kube-state-metrics.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts +*/}} +{{- define "kube-state-metrics.namespace" -}} + {{- if .Values.namespaceOverride -}} + {{- .Values.namespaceOverride -}} + {{- else -}} + {{- .Release.Namespace -}} + {{- end -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "kube-state-metrics.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Generate basic labels +*/}} +{{- define "kube-state-metrics.labels" }} +helm.sh/chart: {{ template "kube-state-metrics.chart" . }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +app.kubernetes.io/component: metrics +app.kubernetes.io/part-of: {{ template "kube-state-metrics.name" . }} +{{- include "kube-state-metrics.selectorLabels" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +{{- if .Values.customLabels }} +{{ toYaml .Values.customLabels }} +{{- end }} +{{- if .Values.releaseLabel }} +release: {{ .Release.Name }} +{{- end }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "kube-state-metrics.selectorLabels" }} +{{- if .Values.selectorOverride }} +{{ toYaml .Values.selectorOverride }} +{{- else }} +app.kubernetes.io/name: {{ include "kube-state-metrics.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} +{{- end }} + +{{/* Sets default scrape limits for servicemonitor */}} +{{- define "servicemonitor.scrapeLimits" -}} +{{- with .sampleLimit }} +sampleLimit: {{ . }} +{{- end }} +{{- with .targetLimit }} +targetLimit: {{ . }} +{{- end }} +{{- with .labelLimit }} +labelLimit: {{ . }} +{{- end }} +{{- with .labelNameLengthLimit }} +labelNameLengthLimit: {{ . }} +{{- end }} +{{- with .labelValueLengthLimit }} +labelValueLengthLimit: {{ . }} +{{- end }} +{{- end -}} + +{{/* +Formats imagePullSecrets. Input is (dict "Values" .Values "imagePullSecrets" .{specific imagePullSecrets}) +*/}} +{{- define "kube-state-metrics.imagePullSecrets" -}} +{{- range (concat .Values.global.imagePullSecrets .imagePullSecrets) }} + {{- if eq (typeOf .) "map[string]interface {}" }} +- {{ toYaml . | trim }} + {{- else }} +- name: {{ . }} + {{- end }} +{{- end }} +{{- end -}} + +{{/* +The image to use for kube-state-metrics +*/}} +{{- define "kube-state-metrics.image" -}} +{{- if .Values.image.sha }} +{{- if .Values.global.imageRegistry }} +{{- printf "%s/%s:%s@%s" .Values.global.imageRegistry .Values.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.image.tag) .Values.image.sha }} +{{- else }} +{{- printf "%s/%s:%s@%s" .Values.image.registry .Values.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.image.tag) .Values.image.sha }} +{{- end }} +{{- else }} +{{- if .Values.global.imageRegistry }} +{{- printf "%s/%s:%s" .Values.global.imageRegistry .Values.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.image.tag) }} +{{- else }} +{{- printf "%s/%s:%s" .Values.image.registry .Values.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.image.tag) }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +The image to use for kubeRBACProxy +*/}} +{{- define "kubeRBACProxy.image" -}} +{{- if .Values.kubeRBACProxy.image.sha }} +{{- if .Values.global.imageRegistry }} +{{- printf "%s/%s:%s@%s" .Values.global.imageRegistry .Values.kubeRBACProxy.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.kubeRBACProxy.image.tag) .Values.kubeRBACProxy.image.sha }} +{{- else }} +{{- printf "%s/%s:%s@%s" .Values.kubeRBACProxy.image.registry .Values.kubeRBACProxy.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.kubeRBACProxy.image.tag) .Values.kubeRBACProxy.image.sha }} +{{- end }} +{{- else }} +{{- if .Values.global.imageRegistry }} +{{- printf "%s/%s:%s" .Values.global.imageRegistry .Values.kubeRBACProxy.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.kubeRBACProxy.image.tag) }} +{{- else }} +{{- printf "%s/%s:%s" .Values.kubeRBACProxy.image.registry .Values.kubeRBACProxy.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.kubeRBACProxy.image.tag) }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/ciliumnetworkpolicy.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/ciliumnetworkpolicy.yaml new file mode 100644 index 0000000..025cd47 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/ciliumnetworkpolicy.yaml @@ -0,0 +1,33 @@ +{{- if and .Values.networkPolicy.enabled (eq .Values.networkPolicy.flavor "cilium") }} +apiVersion: cilium.io/v2 +kind: CiliumNetworkPolicy +metadata: + {{- if .Values.annotations }} + annotations: + {{ toYaml .Values.annotations | nindent 4 }} + {{- end }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} +spec: + endpointSelector: + matchLabels: + {{- include "kube-state-metrics.selectorLabels" . | indent 6 }} + egress: + {{- if and .Values.networkPolicy.cilium .Values.networkPolicy.cilium.kubeApiServerSelector }} + {{ toYaml .Values.networkPolicy.cilium.kubeApiServerSelector | nindent 6 }} + {{- else }} + - toEntities: + - kube-apiserver + {{- end }} + ingress: + - toPorts: + - ports: + - port: {{ .Values.service.port | quote }} + protocol: TCP + {{- if .Values.selfMonitor.enabled }} + - port: {{ .Values.selfMonitor.telemetryPort | default 8081 | quote }} + protocol: TCP + {{ end }} +{{ end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/clusterrolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/clusterrolebinding.yaml new file mode 100644 index 0000000..cf9f628 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/clusterrolebinding.yaml @@ -0,0 +1,20 @@ +{{- if and .Values.rbac.create .Values.rbac.useClusterRole -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} + name: {{ template "kube-state-metrics.fullname" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole +{{- if .Values.rbac.useExistingRole }} + name: {{ .Values.rbac.useExistingRole }} +{{- else }} + name: {{ template "kube-state-metrics.fullname" . }} +{{- end }} +subjects: +- kind: ServiceAccount + name: {{ template "kube-state-metrics.serviceAccountName" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/crs-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/crs-configmap.yaml new file mode 100644 index 0000000..d38a75a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/crs-configmap.yaml @@ -0,0 +1,16 @@ +{{- if .Values.customResourceState.enabled}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ template "kube-state-metrics.fullname" . }}-customresourcestate-config + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} + {{- if .Values.annotations }} + annotations: + {{ toYaml .Values.annotations | nindent 4 }} + {{- end }} +data: + config.yaml: | + {{- toYaml .Values.customResourceState.config | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/deployment.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/deployment.yaml new file mode 100644 index 0000000..2aedc92 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/deployment.yaml @@ -0,0 +1,290 @@ +apiVersion: apps/v1 +{{- if .Values.autosharding.enabled }} +kind: StatefulSet +{{- else }} +kind: Deployment +{{- end }} +metadata: + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} + {{- if .Values.annotations }} + annotations: +{{ toYaml .Values.annotations | indent 4 }} + {{- end }} +spec: + selector: + matchLabels: + {{- include "kube-state-metrics.selectorLabels" . | indent 6 }} + replicas: {{ .Values.replicas }} + {{- if not .Values.autosharding.enabled }} + strategy: + type: {{ .Values.updateStrategy | default "RollingUpdate" }} + {{- end }} + revisionHistoryLimit: {{ .Values.revisionHistoryLimit }} + {{- if .Values.autosharding.enabled }} + serviceName: {{ template "kube-state-metrics.fullname" . }} + volumeClaimTemplates: [] + {{- end }} + template: + metadata: + labels: + {{- include "kube-state-metrics.labels" . | indent 8 }} + {{- if .Values.podAnnotations }} + annotations: +{{ toYaml .Values.podAnnotations | indent 8 }} + {{- end }} + spec: + hostNetwork: {{ .Values.hostNetwork }} + serviceAccountName: {{ template "kube-state-metrics.serviceAccountName" . }} + {{- if .Values.securityContext.enabled }} + securityContext: {{- omit .Values.securityContext "enabled" | toYaml | nindent 8 }} + {{- end }} + {{- if .Values.priorityClassName }} + priorityClassName: {{ .Values.priorityClassName }} + {{- end }} + {{- with .Values.initContainers }} + initContainers: + {{- toYaml . | nindent 6 }} + {{- end }} + containers: + {{- $httpPort := ternary 9090 (.Values.service.port | default 8080) .Values.kubeRBACProxy.enabled}} + {{- $telemetryPort := ternary 9091 (.Values.selfMonitor.telemetryPort | default 8081) .Values.kubeRBACProxy.enabled}} + - name: {{ template "kube-state-metrics.name" . }} + {{- if .Values.autosharding.enabled }} + env: + - name: POD_NAME + valueFrom: + fieldRef: + fieldPath: metadata.name + - name: POD_NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + {{- end }} + args: + {{- if .Values.extraArgs }} + {{- .Values.extraArgs | toYaml | nindent 8 }} + {{- end }} + - --port={{ $httpPort }} + {{- if .Values.collectors }} + - --resources={{ .Values.collectors | join "," }} + {{- end }} + {{- if .Values.metricLabelsAllowlist }} + - --metric-labels-allowlist={{ .Values.metricLabelsAllowlist | join "," }} + {{- end }} + {{- if .Values.metricAnnotationsAllowList }} + - --metric-annotations-allowlist={{ .Values.metricAnnotationsAllowList | join "," }} + {{- end }} + {{- if .Values.metricAllowlist }} + - --metric-allowlist={{ .Values.metricAllowlist | join "," }} + {{- end }} + {{- if .Values.metricDenylist }} + - --metric-denylist={{ .Values.metricDenylist | join "," }} + {{- end }} + {{- $namespaces := list }} + {{- if .Values.namespaces }} + {{- range $ns := join "," .Values.namespaces | split "," }} + {{- $namespaces = append $namespaces (tpl $ns $) }} + {{- end }} + {{- end }} + {{- if .Values.releaseNamespace }} + {{- $namespaces = append $namespaces ( include "kube-state-metrics.namespace" . ) }} + {{- end }} + {{- if $namespaces }} + - --namespaces={{ $namespaces | mustUniq | join "," }} + {{- end }} + {{- if .Values.namespacesDenylist }} + - --namespaces-denylist={{ tpl (.Values.namespacesDenylist | join ",") $ }} + {{- end }} + {{- if .Values.autosharding.enabled }} + - --pod=$(POD_NAME) + - --pod-namespace=$(POD_NAMESPACE) + {{- end }} + {{- if .Values.kubeconfig.enabled }} + - --kubeconfig=/opt/k8s/.kube/config + {{- end }} + {{- if .Values.kubeRBACProxy.enabled }} + - --telemetry-host=127.0.0.1 + - --telemetry-port={{ $telemetryPort }} + {{- else }} + {{- if .Values.selfMonitor.telemetryHost }} + - --telemetry-host={{ .Values.selfMonitor.telemetryHost }} + {{- end }} + {{- if .Values.selfMonitor.telemetryPort }} + - --telemetry-port={{ $telemetryPort }} + {{- end }} + {{- if .Values.customResourceState.enabled }} + - --custom-resource-state-config-file=/etc/customresourcestate/config.yaml + {{- end }} + {{- end }} + {{- if or (.Values.kubeconfig.enabled) (.Values.customResourceState.enabled) (.Values.volumeMounts) }} + volumeMounts: + {{- if .Values.kubeconfig.enabled }} + - name: kubeconfig + mountPath: /opt/k8s/.kube/ + readOnly: true + {{- end }} + {{- if .Values.customResourceState.enabled }} + - name: customresourcestate-config + mountPath: /etc/customresourcestate + readOnly: true + {{- end }} + {{- if .Values.volumeMounts }} +{{ toYaml .Values.volumeMounts | indent 8 }} + {{- end }} + {{- end }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + image: {{ include "kube-state-metrics.image" . }} + {{- if eq .Values.kubeRBACProxy.enabled false }} + ports: + - containerPort: {{ .Values.service.port | default 8080}} + name: "http" + {{- if .Values.selfMonitor.enabled }} + - containerPort: {{ $telemetryPort }} + name: "metrics" + {{- end }} + {{- end }} + livenessProbe: + httpGet: + path: /healthz + port: {{ $httpPort }} + initialDelaySeconds: 5 + timeoutSeconds: 5 + readinessProbe: + httpGet: + path: / + port: {{ $httpPort }} + initialDelaySeconds: 5 + timeoutSeconds: 5 + {{- if .Values.resources }} + resources: +{{ toYaml .Values.resources | indent 10 }} +{{- end }} +{{- if .Values.containerSecurityContext }} + securityContext: +{{ toYaml .Values.containerSecurityContext | indent 10 }} +{{- end }} + {{- if .Values.kubeRBACProxy.enabled }} + - name: kube-rbac-proxy-http + args: + {{- if .Values.kubeRBACProxy.extraArgs }} + {{- .Values.kubeRBACProxy.extraArgs | toYaml | nindent 8 }} + {{- end }} + - --secure-listen-address=:{{ .Values.service.port | default 8080}} + - --upstream=http://127.0.0.1:{{ $httpPort }}/ + - --proxy-endpoints-port=8888 + - --config-file=/etc/kube-rbac-proxy-config/config-file.yaml + volumeMounts: + - name: kube-rbac-proxy-config + mountPath: /etc/kube-rbac-proxy-config + {{- with .Values.kubeRBACProxy.volumeMounts }} + {{- toYaml . | nindent 10 }} + {{- end }} + imagePullPolicy: {{ .Values.kubeRBACProxy.image.pullPolicy }} + image: {{ include "kubeRBACProxy.image" . }} + ports: + - containerPort: {{ .Values.service.port | default 8080}} + name: "http" + - containerPort: 8888 + name: "http-healthz" + readinessProbe: + httpGet: + scheme: HTTPS + port: 8888 + path: healthz + initialDelaySeconds: 5 + timeoutSeconds: 5 + {{- if .Values.kubeRBACProxy.resources }} + resources: +{{ toYaml .Values.kubeRBACProxy.resources | indent 10 }} +{{- end }} +{{- if .Values.kubeRBACProxy.containerSecurityContext }} + securityContext: +{{ toYaml .Values.kubeRBACProxy.containerSecurityContext | indent 10 }} +{{- end }} + {{- if .Values.selfMonitor.enabled }} + - name: kube-rbac-proxy-telemetry + args: + {{- if .Values.kubeRBACProxy.extraArgs }} + {{- .Values.kubeRBACProxy.extraArgs | toYaml | nindent 8 }} + {{- end }} + - --secure-listen-address=:{{ .Values.selfMonitor.telemetryPort | default 8081 }} + - --upstream=http://127.0.0.1:{{ $telemetryPort }}/ + - --proxy-endpoints-port=8889 + - --config-file=/etc/kube-rbac-proxy-config/config-file.yaml + volumeMounts: + - name: kube-rbac-proxy-config + mountPath: /etc/kube-rbac-proxy-config + {{- with .Values.kubeRBACProxy.volumeMounts }} + {{- toYaml . | nindent 10 }} + {{- end }} + imagePullPolicy: {{ .Values.kubeRBACProxy.image.pullPolicy }} + image: {{ include "kubeRBACProxy.image" . }} + ports: + - containerPort: {{ .Values.selfMonitor.telemetryPort | default 8081 }} + name: "metrics" + - containerPort: 8889 + name: "metrics-healthz" + readinessProbe: + httpGet: + scheme: HTTPS + port: 8889 + path: healthz + initialDelaySeconds: 5 + timeoutSeconds: 5 + {{- if .Values.kubeRBACProxy.resources }} + resources: +{{ toYaml .Values.kubeRBACProxy.resources | indent 10 }} +{{- end }} +{{- if .Values.kubeRBACProxy.containerSecurityContext }} + securityContext: +{{ toYaml .Values.kubeRBACProxy.containerSecurityContext | indent 10 }} +{{- end }} + {{- end }} + {{- end }} + {{- with .Values.containers }} + {{- toYaml . | nindent 6 }} + {{- end }} +{{- if or .Values.imagePullSecrets .Values.global.imagePullSecrets }} + imagePullSecrets: + {{- include "kube-state-metrics.imagePullSecrets" (dict "Values" .Values "imagePullSecrets" .Values.imagePullSecrets) | indent 8 }} + {{- end }} + {{- if .Values.affinity }} + affinity: +{{ toYaml .Values.affinity | indent 8 }} + {{- end }} + {{- if .Values.nodeSelector }} + nodeSelector: +{{ toYaml .Values.nodeSelector | indent 8 }} + {{- end }} + {{- if .Values.tolerations }} + tolerations: +{{ toYaml .Values.tolerations | indent 8 }} + {{- end }} + {{- if .Values.topologySpreadConstraints }} + topologySpreadConstraints: +{{ toYaml .Values.topologySpreadConstraints | indent 8 }} + {{- end }} + {{- if or (.Values.kubeconfig.enabled) (.Values.customResourceState.enabled) (.Values.volumes) (.Values.kubeRBACProxy.enabled) }} + volumes: + {{- if .Values.kubeconfig.enabled}} + - name: kubeconfig + secret: + secretName: {{ template "kube-state-metrics.fullname" . }}-kubeconfig + {{- end }} + {{- if .Values.kubeRBACProxy.enabled}} + - name: kube-rbac-proxy-config + configMap: + name: {{ template "kube-state-metrics.fullname" . }}-rbac-config + {{- end }} + {{- if .Values.customResourceState.enabled}} + - name: customresourcestate-config + configMap: + name: {{ template "kube-state-metrics.fullname" . }}-customresourcestate-config + {{- end }} + {{- if .Values.volumes }} +{{ toYaml .Values.volumes | indent 8 }} + {{- end }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/extra-manifests.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/extra-manifests.yaml new file mode 100644 index 0000000..567f7bf --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/extra-manifests.yaml @@ -0,0 +1,4 @@ +{{ range .Values.extraManifests }} +--- +{{ tpl (toYaml .) $ }} +{{ end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/kubeconfig-secret.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/kubeconfig-secret.yaml new file mode 100644 index 0000000..6af0084 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/kubeconfig-secret.yaml @@ -0,0 +1,12 @@ +{{- if .Values.kubeconfig.enabled -}} +apiVersion: v1 +kind: Secret +metadata: + name: {{ template "kube-state-metrics.fullname" . }}-kubeconfig + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} +type: Opaque +data: + config: '{{ .Values.kubeconfig.secret }}' +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/networkpolicy.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/networkpolicy.yaml new file mode 100644 index 0000000..309b38e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/networkpolicy.yaml @@ -0,0 +1,43 @@ +{{- if and .Values.networkPolicy.enabled (eq .Values.networkPolicy.flavor "kubernetes") }} +kind: NetworkPolicy +apiVersion: networking.k8s.io/v1 +metadata: + {{- if .Values.annotations }} + annotations: + {{ toYaml .Values.annotations | nindent 4 }} + {{- end }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} +spec: + {{- if .Values.networkPolicy.egress }} + ## Deny all egress by default + egress: + {{- toYaml .Values.networkPolicy.egress | nindent 4 }} + {{- end }} + ingress: + {{- if .Values.networkPolicy.ingress }} + {{- toYaml .Values.networkPolicy.ingress | nindent 4 }} + {{- else }} + ## Allow ingress on default ports by default + - ports: + - port: {{ .Values.service.port | default 8080 }} + protocol: TCP + {{- if .Values.selfMonitor.enabled }} + {{- $telemetryPort := ternary 9091 (.Values.selfMonitor.telemetryPort | default 8081) .Values.kubeRBACProxy.enabled}} + - port: {{ $telemetryPort }} + protocol: TCP + {{- end }} + {{- end }} + podSelector: + {{- if .Values.networkPolicy.podSelector }} + {{- toYaml .Values.networkPolicy.podSelector | nindent 4 }} + {{- else }} + matchLabels: + {{- include "kube-state-metrics.selectorLabels" . | indent 6 }} + {{- end }} + policyTypes: + - Ingress + - Egress +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/pdb.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/pdb.yaml new file mode 100644 index 0000000..3771b51 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/pdb.yaml @@ -0,0 +1,18 @@ +{{- if .Values.podDisruptionBudget -}} +{{ if $.Capabilities.APIVersions.Has "policy/v1/PodDisruptionBudget" -}} +apiVersion: policy/v1 +{{- else -}} +apiVersion: policy/v1beta1 +{{- end }} +kind: PodDisruptionBudget +metadata: + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} +spec: + selector: + matchLabels: + app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }} +{{ toYaml .Values.podDisruptionBudget | indent 2 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/podsecuritypolicy.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/podsecuritypolicy.yaml new file mode 100644 index 0000000..8905e11 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/podsecuritypolicy.yaml @@ -0,0 +1,39 @@ +{{- if and .Values.podSecurityPolicy.enabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "kube-state-metrics.fullname" . }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} +{{- if .Values.podSecurityPolicy.annotations }} + annotations: +{{ toYaml .Values.podSecurityPolicy.annotations | indent 4 }} +{{- end }} +spec: + privileged: false + volumes: + - 'secret' +{{- if .Values.podSecurityPolicy.additionalVolumes }} +{{ toYaml .Values.podSecurityPolicy.additionalVolumes | indent 4 }} +{{- end }} + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + rule: 'MustRunAsNonRoot' + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 1 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 1 + max: 65535 + readOnlyRootFilesystem: false +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/psp-clusterrole.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/psp-clusterrole.yaml new file mode 100644 index 0000000..654e4a3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/psp-clusterrole.yaml @@ -0,0 +1,19 @@ +{{- if and .Values.podSecurityPolicy.enabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} + name: psp-{{ template "kube-state-metrics.fullname" . }} +rules: +{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }} +{{- if semverCompare "> 1.15.0-0" $kubeTargetVersion }} +- apiGroups: ['policy'] +{{- else }} +- apiGroups: ['extensions'] +{{- end }} + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ template "kube-state-metrics.fullname" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/psp-clusterrolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/psp-clusterrolebinding.yaml new file mode 100644 index 0000000..5b62a18 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/psp-clusterrolebinding.yaml @@ -0,0 +1,16 @@ +{{- if and .Values.podSecurityPolicy.enabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} + name: psp-{{ template "kube-state-metrics.fullname" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: psp-{{ template "kube-state-metrics.fullname" . }} +subjects: + - kind: ServiceAccount + name: {{ template "kube-state-metrics.serviceAccountName" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/rbac-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/rbac-configmap.yaml new file mode 100644 index 0000000..671dc9d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/rbac-configmap.yaml @@ -0,0 +1,22 @@ +{{- if .Values.kubeRBACProxy.enabled}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ template "kube-state-metrics.fullname" . }}-rbac-config + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} + {{- if .Values.annotations }} + annotations: + {{ toYaml .Values.annotations | nindent 4 }} + {{- end }} +data: + config-file.yaml: |+ + authorization: + resourceAttributes: + namespace: {{ template "kube-state-metrics.namespace" . }} + apiVersion: v1 + resource: services + subresource: {{ template "kube-state-metrics.fullname" . }} + name: {{ template "kube-state-metrics.fullname" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/role.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/role.yaml new file mode 100644 index 0000000..d33687f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/role.yaml @@ -0,0 +1,212 @@ +{{- if and (eq .Values.rbac.create true) (not .Values.rbac.useExistingRole) -}} +{{- range (ternary (join "," .Values.namespaces | split "," ) (list "") (eq $.Values.rbac.useClusterRole false)) }} +--- +apiVersion: rbac.authorization.k8s.io/v1 +{{- if eq $.Values.rbac.useClusterRole false }} +kind: Role +{{- else }} +kind: ClusterRole +{{- end }} +metadata: + labels: + {{- include "kube-state-metrics.labels" $ | indent 4 }} + name: {{ template "kube-state-metrics.fullname" $ }} +{{- if eq $.Values.rbac.useClusterRole false }} + namespace: {{ . }} +{{- end }} +rules: +{{ if has "certificatesigningrequests" $.Values.collectors }} +- apiGroups: ["certificates.k8s.io"] + resources: + - certificatesigningrequests + verbs: ["list", "watch"] +{{ end -}} +{{ if has "configmaps" $.Values.collectors }} +- apiGroups: [""] + resources: + - configmaps + verbs: ["list", "watch"] +{{ end -}} +{{ if has "cronjobs" $.Values.collectors }} +- apiGroups: ["batch"] + resources: + - cronjobs + verbs: ["list", "watch"] +{{ end -}} +{{ if has "daemonsets" $.Values.collectors }} +- apiGroups: ["extensions", "apps"] + resources: + - daemonsets + verbs: ["list", "watch"] +{{ end -}} +{{ if has "deployments" $.Values.collectors }} +- apiGroups: ["extensions", "apps"] + resources: + - deployments + verbs: ["list", "watch"] +{{ end -}} +{{ if has "endpoints" $.Values.collectors }} +- apiGroups: [""] + resources: + - endpoints + verbs: ["list", "watch"] +{{ end -}} +{{ if has "endpointslices" $.Values.collectors }} +- apiGroups: ["discovery.k8s.io"] + resources: + - endpointslices + verbs: ["list", "watch"] +{{ end -}} +{{ if has "horizontalpodautoscalers" $.Values.collectors }} +- apiGroups: ["autoscaling"] + resources: + - horizontalpodautoscalers + verbs: ["list", "watch"] +{{ end -}} +{{ if has "ingresses" $.Values.collectors }} +- apiGroups: ["extensions", "networking.k8s.io"] + resources: + - ingresses + verbs: ["list", "watch"] +{{ end -}} +{{ if has "jobs" $.Values.collectors }} +- apiGroups: ["batch"] + resources: + - jobs + verbs: ["list", "watch"] +{{ end -}} +{{ if has "leases" $.Values.collectors }} +- apiGroups: ["coordination.k8s.io"] + resources: + - leases + verbs: ["list", "watch"] +{{ end -}} +{{ if has "limitranges" $.Values.collectors }} +- apiGroups: [""] + resources: + - limitranges + verbs: ["list", "watch"] +{{ end -}} +{{ if has "mutatingwebhookconfigurations" $.Values.collectors }} +- apiGroups: ["admissionregistration.k8s.io"] + resources: + - mutatingwebhookconfigurations + verbs: ["list", "watch"] +{{ end -}} +{{ if has "namespaces" $.Values.collectors }} +- apiGroups: [""] + resources: + - namespaces + verbs: ["list", "watch"] +{{ end -}} +{{ if has "networkpolicies" $.Values.collectors }} +- apiGroups: ["networking.k8s.io"] + resources: + - networkpolicies + verbs: ["list", "watch"] +{{ end -}} +{{ if has "nodes" $.Values.collectors }} +- apiGroups: [""] + resources: + - nodes + verbs: ["list", "watch"] +{{ end -}} +{{ if has "persistentvolumeclaims" $.Values.collectors }} +- apiGroups: [""] + resources: + - persistentvolumeclaims + verbs: ["list", "watch"] +{{ end -}} +{{ if has "persistentvolumes" $.Values.collectors }} +- apiGroups: [""] + resources: + - persistentvolumes + verbs: ["list", "watch"] +{{ end -}} +{{ if has "poddisruptionbudgets" $.Values.collectors }} +- apiGroups: ["policy"] + resources: + - poddisruptionbudgets + verbs: ["list", "watch"] +{{ end -}} +{{ if has "pods" $.Values.collectors }} +- apiGroups: [""] + resources: + - pods + verbs: ["list", "watch"] +{{ end -}} +{{ if has "replicasets" $.Values.collectors }} +- apiGroups: ["extensions", "apps"] + resources: + - replicasets + verbs: ["list", "watch"] +{{ end -}} +{{ if has "replicationcontrollers" $.Values.collectors }} +- apiGroups: [""] + resources: + - replicationcontrollers + verbs: ["list", "watch"] +{{ end -}} +{{ if has "resourcequotas" $.Values.collectors }} +- apiGroups: [""] + resources: + - resourcequotas + verbs: ["list", "watch"] +{{ end -}} +{{ if has "secrets" $.Values.collectors }} +- apiGroups: [""] + resources: + - secrets + verbs: ["list", "watch"] +{{ end -}} +{{ if has "services" $.Values.collectors }} +- apiGroups: [""] + resources: + - services + verbs: ["list", "watch"] +{{ end -}} +{{ if has "statefulsets" $.Values.collectors }} +- apiGroups: ["apps"] + resources: + - statefulsets + verbs: ["list", "watch"] +{{ end -}} +{{ if has "storageclasses" $.Values.collectors }} +- apiGroups: ["storage.k8s.io"] + resources: + - storageclasses + verbs: ["list", "watch"] +{{ end -}} +{{ if has "validatingwebhookconfigurations" $.Values.collectors }} +- apiGroups: ["admissionregistration.k8s.io"] + resources: + - validatingwebhookconfigurations + verbs: ["list", "watch"] +{{ end -}} +{{ if has "volumeattachments" $.Values.collectors }} +- apiGroups: ["storage.k8s.io"] + resources: + - volumeattachments + verbs: ["list", "watch"] +{{ end -}} +{{- if $.Values.kubeRBACProxy.enabled }} +- apiGroups: ["authentication.k8s.io"] + resources: + - tokenreviews + verbs: ["create"] +- apiGroups: ["authorization.k8s.io"] + resources: + - subjectaccessreviews + verbs: ["create"] +{{- end }} +{{- if $.Values.customResourceState.enabled }} +- apiGroups: ["apiextensions.k8s.io"] + resources: + - customresourcedefinitions + verbs: ["list", "watch"] +{{- end }} +{{ if $.Values.rbac.extraRules }} +{{ toYaml $.Values.rbac.extraRules }} +{{ end }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/rolebinding.yaml new file mode 100644 index 0000000..330651b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/rolebinding.yaml @@ -0,0 +1,24 @@ +{{- if and (eq .Values.rbac.create true) (eq .Values.rbac.useClusterRole false) -}} +{{- range (join "," $.Values.namespaces) | split "," }} +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + labels: + {{- include "kube-state-metrics.labels" $ | indent 4 }} + name: {{ template "kube-state-metrics.fullname" $ }} + namespace: {{ . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role +{{- if (not $.Values.rbac.useExistingRole) }} + name: {{ template "kube-state-metrics.fullname" $ }} +{{- else }} + name: {{ $.Values.rbac.useExistingRole }} +{{- end }} +subjects: +- kind: ServiceAccount + name: {{ template "kube-state-metrics.serviceAccountName" $ }} + namespace: {{ template "kube-state-metrics.namespace" $ }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/service.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/service.yaml new file mode 100644 index 0000000..6c486a6 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/service.yaml @@ -0,0 +1,49 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} + annotations: + {{- if .Values.prometheusScrape }} + prometheus.io/scrape: '{{ .Values.prometheusScrape }}' + {{- end }} + {{- if .Values.service.annotations }} + {{- toYaml .Values.service.annotations | nindent 4 }} + {{- end }} +spec: + type: "{{ .Values.service.type }}" + ports: + - name: "http" + protocol: TCP + port: {{ .Values.service.port | default 8080}} + {{- if .Values.service.nodePort }} + nodePort: {{ .Values.service.nodePort }} + {{- end }} + targetPort: {{ .Values.service.port | default 8080}} + {{ if .Values.selfMonitor.enabled }} + - name: "metrics" + protocol: TCP + port: {{ .Values.selfMonitor.telemetryPort | default 8081 }} + targetPort: {{ .Values.selfMonitor.telemetryPort | default 8081 }} + {{- if .Values.selfMonitor.telemetryNodePort }} + nodePort: {{ .Values.selfMonitor.telemetryNodePort }} + {{- end }} + {{ end }} +{{- if .Values.service.loadBalancerIP }} + loadBalancerIP: "{{ .Values.service.loadBalancerIP }}" +{{- end }} +{{- if .Values.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- range $cidr := .Values.service.loadBalancerSourceRanges }} + - {{ $cidr }} + {{- end }} +{{- end }} +{{- if .Values.autosharding.enabled }} + clusterIP: None +{{- else if .Values.service.clusterIP }} + clusterIP: "{{ .Values.service.clusterIP }}" +{{- end }} + selector: + {{- include "kube-state-metrics.selectorLabels" . | indent 4 }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/serviceaccount.yaml new file mode 100644 index 0000000..a7ff4dd --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/serviceaccount.yaml @@ -0,0 +1,15 @@ +{{- if .Values.serviceAccount.create -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} + name: {{ template "kube-state-metrics.serviceAccountName" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} +{{- if .Values.serviceAccount.annotations }} + annotations: +{{ toYaml .Values.serviceAccount.annotations | indent 4 }} +{{- end }} +imagePullSecrets: + {{- include "kube-state-metrics.imagePullSecrets" (dict "Values" .Values "imagePullSecrets" .Values.serviceAccount.imagePullSecrets) | indent 2 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/servicemonitor.yaml new file mode 100644 index 0000000..e2cde64 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/servicemonitor.yaml @@ -0,0 +1,120 @@ +{{- if .Values.prometheus.monitor.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} + {{- with .Values.prometheus.monitor.additionalLabels }} + {{- tpl (toYaml . | nindent 4) $ }} + {{- end }} + {{- with .Values.prometheus.monitor.annotations }} + annotations: + {{- tpl (toYaml . | nindent 4) $ }} + {{- end }} +spec: + jobLabel: {{ default "app.kubernetes.io/name" .Values.prometheus.monitor.jobLabel }} + {{- with .Values.prometheus.monitor.targetLabels }} + targetLabels: + {{- toYaml . | trim | nindent 4 }} + {{- end }} + {{- with .Values.prometheus.monitor.podTargetLabels }} + podTargetLabels: + {{- toYaml . | trim | nindent 4 }} + {{- end }} + {{- include "servicemonitor.scrapeLimits" .Values.prometheus.monitor | indent 2 }} + {{- if .Values.prometheus.monitor.namespaceSelector }} + namespaceSelector: + matchNames: + {{- with .Values.prometheus.monitor.namespaceSelector }} + {{- toYaml . | nindent 6 }} + {{- end }} + {{- end }} + selector: + matchLabels: + {{- with .Values.prometheus.monitor.selectorOverride }} + {{- toYaml . | nindent 6 }} + {{- else }} + {{- include "kube-state-metrics.selectorLabels" . | indent 6 }} + {{- end }} + endpoints: + - port: http + {{- if .Values.prometheus.monitor.interval }} + interval: {{ .Values.prometheus.monitor.interval }} + {{- end }} + {{- if .Values.prometheus.monitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.prometheus.monitor.scrapeTimeout }} + {{- end }} + {{- if .Values.prometheus.monitor.proxyUrl }} + proxyUrl: {{ .Values.prometheus.monitor.proxyUrl}} + {{- end }} + {{- if .Values.prometheus.monitor.enableHttp2 }} + enableHttp2: {{ .Values.prometheus.monitor.enableHttp2}} + {{- end }} + {{- if .Values.prometheus.monitor.honorLabels }} + honorLabels: true + {{- end }} + {{- if .Values.prometheus.monitor.metricRelabelings }} + metricRelabelings: + {{- toYaml .Values.prometheus.monitor.metricRelabelings | nindent 8 }} + {{- end }} + {{- if .Values.prometheus.monitor.relabelings }} + relabelings: + {{- toYaml .Values.prometheus.monitor.relabelings | nindent 8 }} + {{- end }} + {{- if .Values.prometheus.monitor.scheme }} + scheme: {{ .Values.prometheus.monitor.scheme }} + {{- end }} + {{- if .Values.prometheus.monitor.tlsConfig }} + tlsConfig: + {{- toYaml .Values.prometheus.monitor.tlsConfig | nindent 8 }} + {{- end }} + {{- if .Values.prometheus.monitor.bearerTokenFile }} + bearerTokenFile: {{ .Values.prometheus.monitor.bearerTokenFile }} + {{- end }} + {{- with .Values.prometheus.monitor.bearerTokenSecret }} + bearerTokenSecret: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.selfMonitor.enabled }} + - port: metrics + {{- if .Values.prometheus.monitor.interval }} + interval: {{ .Values.prometheus.monitor.interval }} + {{- end }} + {{- if .Values.prometheus.monitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.prometheus.monitor.scrapeTimeout }} + {{- end }} + {{- if .Values.prometheus.monitor.proxyUrl }} + proxyUrl: {{ .Values.prometheus.monitor.proxyUrl}} + {{- end }} + {{- if .Values.prometheus.monitor.enableHttp2 }} + enableHttp2: {{ .Values.prometheus.monitor.enableHttp2}} + {{- end }} + {{- if .Values.prometheus.monitor.honorLabels }} + honorLabels: true + {{- end }} + {{- if .Values.prometheus.monitor.metricRelabelings }} + metricRelabelings: + {{- toYaml .Values.prometheus.monitor.metricRelabelings | nindent 8 }} + {{- end }} + {{- if .Values.prometheus.monitor.relabelings }} + relabelings: + {{- toYaml .Values.prometheus.monitor.relabelings | nindent 8 }} + {{- end }} + {{- if .Values.prometheus.monitor.scheme }} + scheme: {{ .Values.prometheus.monitor.scheme }} + {{- end }} + {{- if .Values.prometheus.monitor.tlsConfig }} + tlsConfig: + {{- toYaml .Values.prometheus.monitor.tlsConfig | nindent 8 }} + {{- end }} + {{- if .Values.prometheus.monitor.bearerTokenFile }} + bearerTokenFile: {{ .Values.prometheus.monitor.bearerTokenFile }} + {{- end }} + {{- with .Values.prometheus.monitor.bearerTokenSecret }} + bearerTokenSecret: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/stsdiscovery-role.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/stsdiscovery-role.yaml new file mode 100644 index 0000000..489de14 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/stsdiscovery-role.yaml @@ -0,0 +1,26 @@ +{{- if and .Values.autosharding.enabled .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: stsdiscovery-{{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} +rules: +- apiGroups: + - "" + resources: + - pods + verbs: + - get +- apiGroups: + - apps + resourceNames: + - {{ template "kube-state-metrics.fullname" . }} + resources: + - statefulsets + verbs: + - get + - list + - watch +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/stsdiscovery-rolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/stsdiscovery-rolebinding.yaml new file mode 100644 index 0000000..73b37a4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/stsdiscovery-rolebinding.yaml @@ -0,0 +1,17 @@ +{{- if and .Values.autosharding.enabled .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: stsdiscovery-{{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: stsdiscovery-{{ template "kube-state-metrics.fullname" . }} +subjects: + - kind: ServiceAccount + name: {{ template "kube-state-metrics.serviceAccountName" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/verticalpodautoscaler.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/verticalpodautoscaler.yaml new file mode 100644 index 0000000..f46305b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/templates/verticalpodautoscaler.yaml @@ -0,0 +1,44 @@ +{{- if and (.Capabilities.APIVersions.Has "autoscaling.k8s.io/v1") (.Values.verticalPodAutoscaler.enabled) }} +apiVersion: autoscaling.k8s.io/v1 +kind: VerticalPodAutoscaler +metadata: + name: {{ template "kube-state-metrics.fullname" . }} + namespace: {{ template "kube-state-metrics.namespace" . }} + labels: + {{- include "kube-state-metrics.labels" . | indent 4 }} +spec: + {{- with .Values.verticalPodAutoscaler.recommenders }} + recommenders: + {{- toYaml . | nindent 4 }} + {{- end }} + resourcePolicy: + containerPolicies: + - containerName: {{ template "kube-state-metrics.name" . }} + {{- with .Values.verticalPodAutoscaler.controlledResources }} + controlledResources: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.verticalPodAutoscaler.controlledValues }} + controlledValues: {{ .Values.verticalPodAutoscaler.controlledValues }} + {{- end }} + {{- if .Values.verticalPodAutoscaler.maxAllowed }} + maxAllowed: + {{ toYaml .Values.verticalPodAutoscaler.maxAllowed | nindent 8 }} + {{- end }} + {{- if .Values.verticalPodAutoscaler.minAllowed }} + minAllowed: + {{ toYaml .Values.verticalPodAutoscaler.minAllowed | nindent 8 }} + {{- end }} + targetRef: + apiVersion: apps/v1 + {{- if .Values.autosharding.enabled }} + kind: StatefulSet + {{- else }} + kind: Deployment + {{- end }} + name: {{ template "kube-state-metrics.fullname" . }} + {{- with .Values.verticalPodAutoscaler.updatePolicy }} + updatePolicy: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/values.yaml new file mode 100644 index 0000000..ee6e1a9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/kube-state-metrics/values.yaml @@ -0,0 +1,456 @@ +# Default values for kube-state-metrics. +prometheusScrape: true +image: + registry: registry.k8s.io + repository: kube-state-metrics/kube-state-metrics + # If unset use v + .Charts.appVersion + tag: "" + sha: "" + pullPolicy: IfNotPresent + +imagePullSecrets: [] +# - name: "image-pull-secret" + +global: + # To help compatibility with other charts which use global.imagePullSecrets. + # Allow either an array of {name: pullSecret} maps (k8s-style), or an array of strings (more common helm-style). + # global: + # imagePullSecrets: + # - name: pullSecret1 + # - name: pullSecret2 + # or + # global: + # imagePullSecrets: + # - pullSecret1 + # - pullSecret2 + imagePullSecrets: [] + # + # Allow parent charts to override registry hostname + imageRegistry: "" + +# If set to true, this will deploy kube-state-metrics as a StatefulSet and the data +# will be automatically sharded across <.Values.replicas> pods using the built-in +# autodiscovery feature: https://github.com/kubernetes/kube-state-metrics#automated-sharding +# This is an experimental feature and there are no stability guarantees. +autosharding: + enabled: false + +replicas: 1 + +# Change the deployment strategy when autosharding is disabled +# updateStrategy: Recreate + +# Number of old history to retain to allow rollback +# Default Kubernetes value is set to 10 +revisionHistoryLimit: 10 + +# List of additional cli arguments to configure kube-state-metrics +# for example: --enable-gzip-encoding, --log-file, etc. +# all the possible args can be found here: https://github.com/kubernetes/kube-state-metrics/blob/master/docs/cli-arguments.md +extraArgs: [] + +service: + port: 8080 + # Default to clusterIP for backward compatibility + type: ClusterIP + nodePort: 0 + loadBalancerIP: "" + # Only allow access to the loadBalancerIP from these IPs + loadBalancerSourceRanges: [] + clusterIP: "" + annotations: {} + +## Additional labels to add to all resources +customLabels: {} + # app: kube-state-metrics + +## Override selector labels +selectorOverride: {} + +## set to true to add the release label so scraping of the servicemonitor with kube-prometheus-stack works out of the box +releaseLabel: false + +hostNetwork: false + +rbac: + # If true, create & use RBAC resources + create: true + + # Set to a rolename to use existing role - skipping role creating - but still doing serviceaccount and rolebinding to it, rolename set here. + # useExistingRole: your-existing-role + + # If set to false - Run without Cluteradmin privs needed - ONLY works if namespace is also set (if useExistingRole is set this name is used as ClusterRole or Role to bind to) + useClusterRole: true + + # Add permissions for CustomResources' apiGroups in Role/ClusterRole. Should be used in conjunction with Custom Resource State Metrics configuration + # Example: + # - apiGroups: ["monitoring.coreos.com"] + # resources: ["prometheuses"] + # verbs: ["list", "watch"] + extraRules: [] + +# Configure kube-rbac-proxy. When enabled, creates one kube-rbac-proxy container per exposed HTTP endpoint (metrics and telemetry if enabled). +# The requests are served through the same service but requests are then HTTPS. +kubeRBACProxy: + enabled: false + image: + registry: quay.io + repository: brancz/kube-rbac-proxy + tag: v0.14.0 + sha: "" + pullPolicy: IfNotPresent + + # List of additional cli arguments to configure kube-rbac-prxy + # for example: --tls-cipher-suites, --log-file, etc. + # all the possible args can be found here: https://github.com/brancz/kube-rbac-proxy#usage + extraArgs: [] + + ## Specify security settings for a Container + ## Allows overrides and additional options compared to (Pod) securityContext + ## Ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-container + containerSecurityContext: {} + + resources: {} + # We usually recommend not to specify default resources and to leave this as a conscious + # choice for the user. This also increases chances charts run on environments with little + # resources, such as Minikube. If you do want to specify resources, uncomment the following + # lines, adjust them as necessary, and remove the curly braces after 'resources:'. + # limits: + # cpu: 100m + # memory: 64Mi + # requests: + # cpu: 10m + # memory: 32Mi + + ## volumeMounts enables mounting custom volumes in rbac-proxy containers + ## Useful for TLS certificates and keys + volumeMounts: [] + # - mountPath: /etc/tls + # name: kube-rbac-proxy-tls + # readOnly: true + +serviceAccount: + # Specifies whether a ServiceAccount should be created, require rbac true + create: true + # The name of the ServiceAccount to use. + # If not set and create is true, a name is generated using the fullname template + name: + # Reference to one or more secrets to be used when pulling images + # ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + imagePullSecrets: [] + # ServiceAccount annotations. + # Use case: AWS EKS IAM roles for service accounts + # ref: https://docs.aws.amazon.com/eks/latest/userguide/specify-service-account-role.html + annotations: {} + +prometheus: + monitor: + enabled: false + annotations: {} + additionalLabels: {} + namespace: "" + namespaceSelector: [] + jobLabel: "" + targetLabels: [] + podTargetLabels: [] + interval: "" + ## SampleLimit defines per-scrape limit on number of scraped samples that will be accepted. + ## + sampleLimit: 0 + + ## TargetLimit defines a limit on the number of scraped targets that will be accepted. + ## + targetLimit: 0 + + ## Per-scrape limit on number of labels that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelLimit: 0 + + ## Per-scrape limit on length of labels name that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelNameLengthLimit: 0 + + ## Per-scrape limit on length of labels value that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelValueLengthLimit: 0 + scrapeTimeout: "" + proxyUrl: "" + ## Whether to enable HTTP2 for servicemonitor + # enableHttp2: false + selectorOverride: {} + honorLabels: false + metricRelabelings: [] + relabelings: [] + scheme: "" + ## File to read bearer token for scraping targets + bearerTokenFile: "" + ## Secret to mount to read bearer token for scraping targets. The secret needs + ## to be in the same namespace as the service monitor and accessible by the + ## Prometheus Operator + bearerTokenSecret: {} + # name: secret-name + # key: key-name + tlsConfig: {} + +## Specify if a Pod Security Policy for kube-state-metrics must be created +## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/ +## +podSecurityPolicy: + enabled: false + annotations: {} + ## Specify pod annotations + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#apparmor + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#seccomp + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#sysctl + ## + # seccomp.security.alpha.kubernetes.io/allowedProfileNames: '*' + # seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default' + # apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default' + + additionalVolumes: [] + +## Configure network policy for kube-state-metrics +networkPolicy: + enabled: false + # networkPolicy.flavor -- Flavor of the network policy to use. + # Can be: + # * kubernetes for networking.k8s.io/v1/NetworkPolicy + # * cilium for cilium.io/v2/CiliumNetworkPolicy + flavor: kubernetes + + ## Configure the cilium network policy kube-apiserver selector + # cilium: + # kubeApiServerSelector: + # - toEntities: + # - kube-apiserver + + # egress: + # - {} + # ingress: + # - {} + # podSelector: + # matchLabels: + # app.kubernetes.io/name: kube-state-metrics + +securityContext: + enabled: true + runAsGroup: 65534 + runAsUser: 65534 + fsGroup: 65534 + runAsNonRoot: true + seccompProfile: + type: RuntimeDefault + +## Specify security settings for a Container +## Allows overrides and additional options compared to (Pod) securityContext +## Ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-container +containerSecurityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + +## Node labels for pod assignment +## Ref: https://kubernetes.io/docs/user-guide/node-selection/ +nodeSelector: {} + +## Affinity settings for pod assignment +## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/ +affinity: {} + +## Tolerations for pod assignment +## Ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ +tolerations: [] + +## Topology spread constraints for pod assignment +## Ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ +topologySpreadConstraints: [] + +# Annotations to be added to the deployment/statefulset +annotations: {} + +# Annotations to be added to the pod +podAnnotations: {} + +## Assign a PriorityClassName to pods if set +# priorityClassName: "" + +# Ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/ +podDisruptionBudget: {} + +# Comma-separated list of metrics to be exposed. +# This list comprises of exact metric names and/or regex patterns. +# The allowlist and denylist are mutually exclusive. +metricAllowlist: [] + +# Comma-separated list of metrics not to be enabled. +# This list comprises of exact metric names and/or regex patterns. +# The allowlist and denylist are mutually exclusive. +metricDenylist: [] + +# Comma-separated list of additional Kubernetes label keys that will be used in the resource's +# labels metric. By default the metric contains only name and namespace labels. +# To include additional labels, provide a list of resource names in their plural form and Kubernetes +# label keys you would like to allow for them (Example: '=namespaces=[k8s-label-1,k8s-label-n,...],pods=[app],...)'. +# A single '*' can be provided per resource instead to allow any labels, but that has +# severe performance implications (Example: '=pods=[*]'). +metricLabelsAllowlist: [] + # - namespaces=[k8s-label-1,k8s-label-n] + +# Comma-separated list of Kubernetes annotations keys that will be used in the resource' +# labels metric. By default the metric contains only name and namespace labels. +# To include additional annotations provide a list of resource names in their plural form and Kubernetes +# annotation keys you would like to allow for them (Example: '=namespaces=[kubernetes.io/team,...],pods=[kubernetes.io/team],...)'. +# A single '*' can be provided per resource instead to allow any annotations, but that has +# severe performance implications (Example: '=pods=[*]'). +metricAnnotationsAllowList: [] + # - pods=[k8s-annotation-1,k8s-annotation-n] + +# Available collectors for kube-state-metrics. +# By default, all available resources are enabled, comment out to disable. +collectors: + - certificatesigningrequests + - configmaps + - cronjobs + - daemonsets + - deployments + - endpoints + - horizontalpodautoscalers + - ingresses + - jobs + - leases + - limitranges + - mutatingwebhookconfigurations + - namespaces + - networkpolicies + - nodes + - persistentvolumeclaims + - persistentvolumes + - poddisruptionbudgets + - pods + - replicasets + - replicationcontrollers + - resourcequotas + - secrets + - services + - statefulsets + - storageclasses + - validatingwebhookconfigurations + - volumeattachments + +# Enabling kubeconfig will pass the --kubeconfig argument to the container +kubeconfig: + enabled: false + # base64 encoded kube-config file + secret: + +# Enabling support for customResourceState, will create a configMap including your config that will be read from kube-state-metrics +customResourceState: + enabled: false + # Add (Cluster)Role permissions to list/watch the customResources defined in the config to rbac.extraRules + config: {} + +# Enable only the release namespace for collecting resources. By default all namespaces are collected. +# If releaseNamespace and namespaces are both set a merged list will be collected. +releaseNamespace: false + +# Comma-separated list(string) or yaml list of namespaces to be enabled for collecting resources. By default all namespaces are collected. +namespaces: "" + +# Comma-separated list of namespaces not to be enabled. If namespaces and namespaces-denylist are both set, +# only namespaces that are excluded in namespaces-denylist will be used. +namespacesDenylist: "" + +## Override the deployment namespace +## +namespaceOverride: "" + +resources: {} + # We usually recommend not to specify default resources and to leave this as a conscious + # choice for the user. This also increases chances charts run on environments with little + # resources, such as Minikube. If you do want to specify resources, uncomment the following + # lines, adjust them as necessary, and remove the curly braces after 'resources:'. + # limits: + # cpu: 100m + # memory: 64Mi + # requests: + # cpu: 10m + # memory: 32Mi + +## Provide a k8s version to define apiGroups for podSecurityPolicy Cluster Role. +## For example: kubeTargetVersionOverride: 1.14.9 +## +kubeTargetVersionOverride: "" + +# Enable self metrics configuration for service and Service Monitor +# Default values for telemetry configuration can be overridden +# If you set telemetryNodePort, you must also set service.type to NodePort +selfMonitor: + enabled: false + # telemetryHost: 0.0.0.0 + # telemetryPort: 8081 + # telemetryNodePort: 0 + +# Enable vertical pod autoscaler support for kube-state-metrics +verticalPodAutoscaler: + enabled: false + + # Recommender responsible for generating recommendation for the object. + # List should be empty (then the default recommender will generate the recommendation) + # or contain exactly one recommender. + # recommenders: [] + # - name: custom-recommender-performance + + # List of resources that the vertical pod autoscaler can control. Defaults to cpu and memory + controlledResources: [] + # Specifies which resource values should be controlled: RequestsOnly or RequestsAndLimits. + # controlledValues: RequestsAndLimits + + # Define the max allowed resources for the pod + maxAllowed: {} + # cpu: 200m + # memory: 100Mi + # Define the min allowed resources for the pod + minAllowed: {} + # cpu: 200m + # memory: 100Mi + + # updatePolicy: + # Specifies minimal number of replicas which need to be alive for VPA Updater to attempt pod eviction + # minReplicas: 1 + # Specifies whether recommended updates are applied when a Pod is started and whether recommended updates + # are applied during the life of a Pod. Possible values are "Off", "Initial", "Recreate", and "Auto". + # updateMode: Auto + +# volumeMounts are used to add custom volume mounts to deployment. +# See example below +volumeMounts: [] +# - mountPath: /etc/config +# name: config-volume + +# volumes are used to add custom volumes to deployment +# See example below +volumes: [] +# - configMap: +# name: cm-for-volume +# name: config-volume + +# Extra manifests to deploy as an array +extraManifests: [] + # - apiVersion: v1 + # kind: ConfigMap + # metadata: + # labels: + # name: prometheus-extra + # data: + # extra-data: "value" + +## Containers allows injecting additional containers. +containers: [] + # - name: crd-init + # image: kiwigrid/k8s-sidecar:latest + +## InitContainers allows injecting additional initContainers. +initContainers: [] + # - name: crd-sidecar + # image: kiwigrid/k8s-sidecar:latest diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/.helmignore new file mode 100644 index 0000000..f0c1319 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/.helmignore @@ -0,0 +1,21 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/Chart.yaml new file mode 100644 index 0000000..ae934c9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/Chart.yaml @@ -0,0 +1,25 @@ +annotations: + artifacthub.io/license: Apache-2.0 + artifacthub.io/links: | + - name: Chart Source + url: https://github.com/prometheus-community/helm-charts +apiVersion: v2 +appVersion: 1.7.0 +description: A Helm chart for prometheus node-exporter +home: https://github.com/prometheus/node_exporter/ +keywords: +- node-exporter +- prometheus +- exporter +maintainers: +- email: gianrubio@gmail.com + name: gianrubio +- email: zanhsieh@gmail.com + name: zanhsieh +- email: rootsandtrees@posteo.de + name: zeritti +name: prometheus-node-exporter +sources: +- https://github.com/prometheus/node_exporter/ +type: application +version: 4.24.0 diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/README.md b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/README.md new file mode 100644 index 0000000..ef83844 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/README.md @@ -0,0 +1,96 @@ +# Prometheus Node Exporter + +Prometheus exporter for hardware and OS metrics exposed by *NIX kernels, written in Go with pluggable metric collectors. + +This chart bootstraps a Prometheus [Node Exporter](http://github.com/prometheus/node_exporter) daemonset on a [Kubernetes](http://kubernetes.io) cluster using the [Helm](https://helm.sh) package manager. + +## Get Repository Info + +```console +helm repo add prometheus-community https://prometheus-community.github.io/helm-charts +helm repo update +``` + +_See [helm repo](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Install Chart + +```console +helm install [RELEASE_NAME] prometheus-community/prometheus-node-exporter +``` + +_See [configuration](#configuring) below._ + +_See [helm install](https://helm.sh/docs/helm/helm_install/) for command documentation._ + +## Uninstall Chart + +```console +helm uninstall [RELEASE_NAME] +``` + +This removes all the Kubernetes components associated with the chart and deletes the release. + +_See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall/) for command documentation._ + +## Upgrading Chart + +```console +helm upgrade [RELEASE_NAME] prometheus-community/prometheus-node-exporter --install +``` + +_See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documentation._ + +### 3.x to 4.x + +Starting from version 4.0.0, the `node exporter` chart is using the [Kubernetes recommended labels](https://kubernetes.io/docs/concepts/overview/working-with-objects/common-labels/). Therefore you have to delete the daemonset before you upgrade. + +```console +kubectl delete daemonset -l app=prometheus-node-exporter +helm upgrade -i prometheus-node-exporter prometheus-community/prometheus-node-exporter +``` + +If you use your own custom [ServiceMonitor](https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#servicemonitor) or [PodMonitor](https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#podmonitor), please ensure to upgrade their `selector` fields accordingly to the new labels. + +### From 2.x to 3.x + +Change the following: + +```yaml +hostRootFsMount: true +``` + +to: + +```yaml +hostRootFsMount: + enabled: true + mountPropagation: HostToContainer +``` + +## Configuring + +See [Customizing the Chart Before Installing](https://helm.sh/docs/intro/using_helm/#customizing-the-chart-before-installing). To see all configurable options with detailed comments, visit the chart's [values.yaml](./values.yaml), or run these configuration commands: + +```console +helm show values prometheus-community/prometheus-node-exporter +``` + +### kube-rbac-proxy + +You can enable `prometheus-node-exporter` endpoint protection using `kube-rbac-proxy`. By setting `kubeRBACProxy.enabled: true`, this chart will deploy a RBAC proxy container protecting the node-exporter endpoint. +To authorize access, authenticate your requests (via a `ServiceAccount` for example) with a `ClusterRole` attached such as: + +```yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: prometheus-node-exporter-read +rules: + - apiGroups: [ "" ] + resources: ["services/node-exporter-prometheus-node-exporter"] + verbs: + - get +``` + +See [kube-rbac-proxy examples](https://github.com/brancz/kube-rbac-proxy/tree/master/examples/resource-attributes) for more details. diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/ci/port-values.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/ci/port-values.yaml new file mode 100644 index 0000000..dbfb4b6 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/ci/port-values.yaml @@ -0,0 +1,3 @@ +service: + targetPort: 9102 + port: 9102 diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/NOTES.txt new file mode 100644 index 0000000..db8584d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/NOTES.txt @@ -0,0 +1,29 @@ +1. Get the application URL by running these commands: +{{- if contains "NodePort" .Values.service.type }} + export NODE_PORT=$(kubectl get --namespace {{ template "prometheus-node-exporter.namespace" . }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ template "prometheus-node-exporter.fullname" . }}) + export NODE_IP=$(kubectl get nodes --namespace {{ template "prometheus-node-exporter.namespace" . }} -o jsonpath="{.items[0].status.addresses[0].address}") + echo http://$NODE_IP:$NODE_PORT +{{- else if contains "LoadBalancer" .Values.service.type }} + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + You can watch the status of by running 'kubectl get svc -w {{ template "prometheus-node-exporter.fullname" . }}' + export SERVICE_IP=$(kubectl get svc --namespace {{ template "prometheus-node-exporter.namespace" . }} {{ template "prometheus-node-exporter.fullname" . }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}') + echo http://$SERVICE_IP:{{ .Values.service.port }} +{{- else if contains "ClusterIP" .Values.service.type }} + export POD_NAME=$(kubectl get pods --namespace {{ template "prometheus-node-exporter.namespace" . }} -l "app.kubernetes.io/name={{ template "prometheus-node-exporter.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") + echo "Visit http://127.0.0.1:9100 to use your application" + kubectl port-forward --namespace {{ template "prometheus-node-exporter.namespace" . }} $POD_NAME 9100 +{{- end }} + +{{- if .Values.kubeRBACProxy.enabled}} + +kube-rbac-proxy endpoint protections is enabled: +- Metrics endpoints is now HTTPS +- Ensure that the client authenticates the requests (e.g. via service account) with the following role permissions: +``` +rules: + - apiGroups: [ "" ] + resources: ["services/{{ template "prometheus-node-exporter.fullname" . }}"] + verbs: + - get +``` +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/_helpers.tpl new file mode 100644 index 0000000..84552fe --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/_helpers.tpl @@ -0,0 +1,185 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "prometheus-node-exporter.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "prometheus-node-exporter.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default .Chart.Name .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "prometheus-node-exporter.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "prometheus-node-exporter.labels" -}} +helm.sh/chart: {{ include "prometheus-node-exporter.chart" . }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +app.kubernetes.io/component: metrics +app.kubernetes.io/part-of: {{ include "prometheus-node-exporter.name" . }} +{{ include "prometheus-node-exporter.selectorLabels" . }} +{{- with .Chart.AppVersion }} +app.kubernetes.io/version: {{ . | quote }} +{{- end }} +{{- with .Values.podLabels }} +{{ toYaml . }} +{{- end }} +{{- if .Values.releaseLabel }} +release: {{ .Release.Name }} +{{- end }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "prometheus-node-exporter.selectorLabels" -}} +app.kubernetes.io/name: {{ include "prometheus-node-exporter.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + + +{{/* +Create the name of the service account to use +*/}} +{{- define "prometheus-node-exporter.serviceAccountName" -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "prometheus-node-exporter.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} + +{{/* +The image to use +*/}} +{{- define "prometheus-node-exporter.image" -}} +{{- if .Values.image.sha }} +{{- fail "image.sha forbidden. Use image.digest instead" }} +{{- else if .Values.image.digest }} +{{- if .Values.global.imageRegistry }} +{{- printf "%s/%s:%s@%s" .Values.global.imageRegistry .Values.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.image.tag) .Values.image.digest }} +{{- else }} +{{- printf "%s/%s:%s@%s" .Values.image.registry .Values.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.image.tag) .Values.image.digest }} +{{- end }} +{{- else }} +{{- if .Values.global.imageRegistry }} +{{- printf "%s/%s:%s" .Values.global.imageRegistry .Values.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.image.tag) }} +{{- else }} +{{- printf "%s/%s:%s" .Values.image.registry .Values.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.image.tag) }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts +*/}} +{{- define "prometheus-node-exporter.namespace" -}} +{{- if .Values.namespaceOverride }} +{{- .Values.namespaceOverride }} +{{- else }} +{{- .Release.Namespace }} +{{- end }} +{{- end }} + +{{/* +Create the namespace name of the service monitor +*/}} +{{- define "prometheus-node-exporter.monitor-namespace" -}} +{{- if .Values.namespaceOverride }} +{{- .Values.namespaceOverride }} +{{- else }} +{{- if .Values.prometheus.monitor.namespace }} +{{- .Values.prometheus.monitor.namespace }} +{{- else }} +{{- .Release.Namespace }} +{{- end }} +{{- end }} +{{- end }} + +{{/* Sets default scrape limits for servicemonitor */}} +{{- define "servicemonitor.scrapeLimits" -}} +{{- with .sampleLimit }} +sampleLimit: {{ . }} +{{- end }} +{{- with .targetLimit }} +targetLimit: {{ . }} +{{- end }} +{{- with .labelLimit }} +labelLimit: {{ . }} +{{- end }} +{{- with .labelNameLengthLimit }} +labelNameLengthLimit: {{ . }} +{{- end }} +{{- with .labelValueLengthLimit }} +labelValueLengthLimit: {{ . }} +{{- end }} +{{- end }} + +{{/* +Formats imagePullSecrets. Input is (dict "Values" .Values "imagePullSecrets" .{specific imagePullSecrets}) +*/}} +{{- define "prometheus-node-exporter.imagePullSecrets" -}} +{{- range (concat .Values.global.imagePullSecrets .imagePullSecrets) }} + {{- if eq (typeOf .) "map[string]interface {}" }} +- {{ toYaml . | trim }} + {{- else }} +- name: {{ . }} + {{- end }} +{{- end }} +{{- end -}} + +{{/* +Create the namespace name of the pod monitor +*/}} +{{- define "prometheus-node-exporter.podmonitor-namespace" -}} +{{- if .Values.namespaceOverride }} +{{- .Values.namespaceOverride }} +{{- else }} +{{- if .Values.prometheus.podMonitor.namespace }} +{{- .Values.prometheus.podMonitor.namespace }} +{{- else }} +{{- .Release.Namespace }} +{{- end }} +{{- end }} +{{- end }} + +{{/* Sets default scrape limits for podmonitor */}} +{{- define "podmonitor.scrapeLimits" -}} +{{- with .sampleLimit }} +sampleLimit: {{ . }} +{{- end }} +{{- with .targetLimit }} +targetLimit: {{ . }} +{{- end }} +{{- with .labelLimit }} +labelLimit: {{ . }} +{{- end }} +{{- with .labelNameLengthLimit }} +labelNameLengthLimit: {{ . }} +{{- end }} +{{- with .labelValueLengthLimit }} +labelValueLengthLimit: {{ . }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/clusterrole.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/clusterrole.yaml new file mode 100644 index 0000000..c256dba --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/clusterrole.yaml @@ -0,0 +1,19 @@ +{{- if and (eq .Values.rbac.create true) (eq .Values.kubeRBACProxy.enabled true) -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ include "prometheus-node-exporter.fullname" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} +rules: + {{- if $.Values.kubeRBACProxy.enabled }} + - apiGroups: [ "authentication.k8s.io" ] + resources: + - tokenreviews + verbs: [ "create" ] + - apiGroups: [ "authorization.k8s.io" ] + resources: + - subjectaccessreviews + verbs: [ "create" ] + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/clusterrolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/clusterrolebinding.yaml new file mode 100644 index 0000000..653305a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/clusterrolebinding.yaml @@ -0,0 +1,20 @@ +{{- if and (eq .Values.rbac.create true) (eq .Values.kubeRBACProxy.enabled true) -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} + name: {{ template "prometheus-node-exporter.fullname" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole +{{- if .Values.rbac.useExistingRole }} + name: {{ .Values.rbac.useExistingRole }} +{{- else }} + name: {{ template "prometheus-node-exporter.fullname" . }} +{{- end }} +subjects: +- kind: ServiceAccount + name: {{ template "prometheus-node-exporter.serviceAccountName" . }} + namespace: {{ template "prometheus-node-exporter.namespace" . }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/daemonset.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/daemonset.yaml new file mode 100644 index 0000000..a5116a8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/daemonset.yaml @@ -0,0 +1,285 @@ +apiVersion: apps/v1 +kind: DaemonSet +metadata: + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} + {{- with .Values.daemonsetAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + selector: + matchLabels: + {{- include "prometheus-node-exporter.selectorLabels" . | nindent 6 }} + revisionHistoryLimit: {{ .Values.revisionHistoryLimit }} + {{- with .Values.updateStrategy }} + updateStrategy: + {{- toYaml . | nindent 4 }} + {{- end }} + template: + metadata: + {{- with .Values.podAnnotations }} + annotations: + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 8 }} + spec: + automountServiceAccountToken: {{ ternary true false (or .Values.serviceAccount.automountServiceAccountToken .Values.kubeRBACProxy.enabled) }} + {{- with .Values.securityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.extraInitContainers }} + initContainers: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "prometheus-node-exporter.serviceAccountName" . }} + containers: + {{- $servicePort := ternary 8100 .Values.service.port .Values.kubeRBACProxy.enabled }} + - name: node-exporter + image: {{ include "prometheus-node-exporter.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - --path.procfs=/host/proc + - --path.sysfs=/host/sys + {{- if .Values.hostRootFsMount.enabled }} + - --path.rootfs=/host/root + {{- if semverCompare ">=1.4.0" (default .Chart.AppVersion .Values.image.tag) }} + - --path.udev.data=/host/root/run/udev/data + {{- end }} + {{- end }} + - --web.listen-address=[$(HOST_IP)]:{{ $servicePort }} + {{- with .Values.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + env: + - name: HOST_IP + {{- if .Values.kubeRBACProxy.enabled }} + value: 127.0.0.1 + {{- else if .Values.service.listenOnAllInterfaces }} + value: 0.0.0.0 + {{- else }} + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: status.hostIP + {{- end }} + {{- range $key, $value := .Values.env }} + - name: {{ $key }} + value: {{ $value | quote }} + {{- end }} + {{- if eq .Values.kubeRBACProxy.enabled false }} + ports: + - name: {{ .Values.service.portName }} + containerPort: {{ .Values.service.port }} + protocol: TCP + {{- end }} + livenessProbe: + failureThreshold: {{ .Values.livenessProbe.failureThreshold }} + httpGet: + {{- if .Values.kubeRBACProxy.enabled }} + host: 127.0.0.1 + {{- end }} + httpHeaders: + {{- range $_, $header := .Values.livenessProbe.httpGet.httpHeaders }} + - name: {{ $header.name }} + value: {{ $header.value }} + {{- end }} + path: / + port: {{ $servicePort }} + scheme: {{ upper .Values.livenessProbe.httpGet.scheme }} + initialDelaySeconds: {{ .Values.livenessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.livenessProbe.periodSeconds }} + successThreshold: {{ .Values.livenessProbe.successThreshold }} + timeoutSeconds: {{ .Values.livenessProbe.timeoutSeconds }} + readinessProbe: + failureThreshold: {{ .Values.readinessProbe.failureThreshold }} + httpGet: + {{- if .Values.kubeRBACProxy.enabled }} + host: 127.0.0.1 + {{- end }} + httpHeaders: + {{- range $_, $header := .Values.readinessProbe.httpGet.httpHeaders }} + - name: {{ $header.name }} + value: {{ $header.value }} + {{- end }} + path: / + port: {{ $servicePort }} + scheme: {{ upper .Values.readinessProbe.httpGet.scheme }} + initialDelaySeconds: {{ .Values.readinessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.readinessProbe.periodSeconds }} + successThreshold: {{ .Values.readinessProbe.successThreshold }} + timeoutSeconds: {{ .Values.readinessProbe.timeoutSeconds }} + {{- with .Values.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - name: proc + mountPath: /host/proc + readOnly: true + - name: sys + mountPath: /host/sys + readOnly: true + {{- if .Values.hostRootFsMount.enabled }} + - name: root + mountPath: /host/root + {{- with .Values.hostRootFsMount.mountPropagation }} + mountPropagation: {{ . }} + {{- end }} + readOnly: true + {{- end }} + {{- range $_, $mount := .Values.extraHostVolumeMounts }} + - name: {{ $mount.name }} + mountPath: {{ $mount.mountPath }} + readOnly: {{ $mount.readOnly }} + {{- with $mount.mountPropagation }} + mountPropagation: {{ . }} + {{- end }} + {{- end }} + {{- range $_, $mount := .Values.sidecarVolumeMount }} + - name: {{ $mount.name }} + mountPath: {{ $mount.mountPath }} + readOnly: true + {{- end }} + {{- range $_, $mount := .Values.configmaps }} + - name: {{ $mount.name }} + mountPath: {{ $mount.mountPath }} + {{- end }} + {{- range $_, $mount := .Values.secrets }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + {{- end }} + {{- with .Values.sidecars }} + {{- toYaml . | nindent 8 }} + {{- if or $.Values.sidecarVolumeMount $.Values.sidecarHostVolumeMounts }} + volumeMounts: + {{- range $_, $mount := $.Values.sidecarVolumeMount }} + - name: {{ $mount.name }} + mountPath: {{ $mount.mountPath }} + readOnly: {{ $mount.readOnly }} + {{- end }} + {{- range $_, $mount := $.Values.sidecarHostVolumeMounts }} + - name: {{ $mount.name }} + mountPath: {{ $mount.mountPath }} + readOnly: {{ $mount.readOnly }} + {{- if $mount.mountPropagation }} + mountPropagation: {{ $mount.mountPropagation }} + {{- end }} + {{- end }} + {{- end }} + {{- end }} + {{- if .Values.kubeRBACProxy.enabled }} + - name: kube-rbac-proxy + args: + {{- if .Values.kubeRBACProxy.extraArgs }} + {{- .Values.kubeRBACProxy.extraArgs | toYaml | nindent 12 }} + {{- end }} + - --secure-listen-address=:{{ .Values.service.port}} + - --upstream=http://127.0.0.1:{{ $servicePort }}/ + - --proxy-endpoints-port=8888 + - --config-file=/etc/kube-rbac-proxy-config/config-file.yaml + volumeMounts: + - name: kube-rbac-proxy-config + mountPath: /etc/kube-rbac-proxy-config + imagePullPolicy: {{ .Values.kubeRBACProxy.image.pullPolicy }} + {{- if .Values.kubeRBACProxy.image.sha }} + image: "{{ .Values.global.imageRegistry | default .Values.kubeRBACProxy.image.registry}}/{{ .Values.kubeRBACProxy.image.repository }}:{{ .Values.kubeRBACProxy.image.tag }}@sha256:{{ .Values.kubeRBACProxy.image.sha }}" + {{- else }} + image: "{{ .Values.global.imageRegistry | default .Values.kubeRBACProxy.image.registry}}/{{ .Values.kubeRBACProxy.image.repository }}:{{ .Values.kubeRBACProxy.image.tag }}" + {{- end }} + ports: + - containerPort: {{ .Values.service.port}} + name: "http" + - containerPort: 8888 + name: "http-healthz" + readinessProbe: + httpGet: + scheme: HTTPS + port: 8888 + path: healthz + initialDelaySeconds: 5 + timeoutSeconds: 5 + {{- if .Values.kubeRBACProxy.resources }} + resources: + {{ toYaml .Values.kubeRBACProxy.resources | nindent 12 }} + {{- end }} + {{- if .Values.kubeRBACProxy.containerSecurityContext }} + securityContext: + {{ toYaml .Values.kubeRBACProxy.containerSecurityContext | nindent 12 }} + {{- end }} + {{- end }} + {{- if or .Values.imagePullSecrets .Values.global.imagePullSecrets }} + imagePullSecrets: + {{- include "prometheus-node-exporter.imagePullSecrets" (dict "Values" .Values "imagePullSecrets" .Values.imagePullSecrets) | indent 8 }} + {{- end }} + hostNetwork: {{ .Values.hostNetwork }} + hostPID: {{ .Values.hostPID }} + {{- with .Values.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.dnsConfig }} + dnsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: proc + hostPath: + path: /proc + - name: sys + hostPath: + path: /sys + {{- if .Values.hostRootFsMount.enabled }} + - name: root + hostPath: + path: / + {{- end }} + {{- range $_, $mount := .Values.extraHostVolumeMounts }} + - name: {{ $mount.name }} + hostPath: + path: {{ $mount.hostPath }} + {{- end }} + {{- range $_, $mount := .Values.sidecarVolumeMount }} + - name: {{ $mount.name }} + emptyDir: + medium: Memory + {{- end }} + {{- range $_, $mount := .Values.sidecarHostVolumeMounts }} + - name: {{ $mount.name }} + hostPath: + path: {{ $mount.hostPath }} + {{- end }} + {{- range $_, $mount := .Values.configmaps }} + - name: {{ $mount.name }} + configMap: + name: {{ $mount.name }} + {{- end }} + {{- range $_, $mount := .Values.secrets }} + - name: {{ $mount.name }} + secret: + secretName: {{ $mount.name }} + {{- end }} + {{- if .Values.kubeRBACProxy.enabled }} + - name: kube-rbac-proxy-config + configMap: + name: {{ template "prometheus-node-exporter.fullname" . }}-rbac-config + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/endpoints.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/endpoints.yaml new file mode 100644 index 0000000..45eeb8d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/endpoints.yaml @@ -0,0 +1,18 @@ +{{- if .Values.endpoints }} +apiVersion: v1 +kind: Endpoints +metadata: + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} +subsets: + - addresses: + {{- range .Values.endpoints }} + - ip: {{ . }} + {{- end }} + ports: + - name: {{ .Values.service.portName }} + port: 9100 + protocol: TCP +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/extra-manifests.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/extra-manifests.yaml new file mode 100644 index 0000000..2b21b71 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/extra-manifests.yaml @@ -0,0 +1,4 @@ +{{ range .Values.extraManifests }} +--- +{{ tpl . $ }} +{{ end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/networkpolicy.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/networkpolicy.yaml new file mode 100644 index 0000000..8257227 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/networkpolicy.yaml @@ -0,0 +1,23 @@ +{{- if .Values.networkPolicy.enabled }} +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" $ | nindent 4 }} + {{- with .Values.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + ingress: + - ports: + - port: {{ .Values.service.port }} + policyTypes: + - Egress + - Ingress + podSelector: + matchLabels: + {{- include "prometheus-node-exporter.selectorLabels" . | nindent 6 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/podmonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/podmonitor.yaml new file mode 100644 index 0000000..f88da6a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/podmonitor.yaml @@ -0,0 +1,91 @@ +{{- if .Values.prometheus.podMonitor.enabled }} +apiVersion: {{ .Values.prometheus.podMonitor.apiVersion | default "monitoring.coreos.com/v1" }} +kind: PodMonitor +metadata: + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.podmonitor-namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} + {{- with .Values.prometheus.podMonitor.additionalLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + jobLabel: {{ default "app.kubernetes.io/name" .Values.prometheus.podMonitor.jobLabel }} + {{- include "podmonitor.scrapeLimits" .Values.prometheus.podMonitor | nindent 2 }} + selector: + matchLabels: + {{- with .Values.prometheus.podMonitor.selectorOverride }} + {{- toYaml . | nindent 6 }} + {{- else }} + {{- include "prometheus-node-exporter.selectorLabels" . | nindent 6 }} + {{- end }} + namespaceSelector: + matchNames: + - {{ include "prometheus-node-exporter.namespace" . }} + {{- with .Values.prometheus.podMonitor.attachMetadata }} + attachMetadata: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.prometheus.podMonitor.podTargetLabels }} + podTargetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} + podMetricsEndpoints: + - port: {{ .Values.service.portName }} + {{- with .Values.prometheus.podMonitor.scheme }} + scheme: {{ . }} + {{- end }} + {{- with .Values.prometheus.podMonitor.path }} + path: {{ . }} + {{- end }} + {{- with .Values.prometheus.podMonitor.basicAuth }} + basicAuth: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.prometheus.podMonitor.bearerTokenSecret }} + bearerTokenSecret: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.prometheus.podMonitor.tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.prometheus.podMonitor.authorization }} + authorization: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.prometheus.podMonitor.oauth2 }} + oauth2: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.prometheus.podMonitor.proxyUrl }} + proxyUrl: {{ . }} + {{- end }} + {{- with .Values.prometheus.podMonitor.interval }} + interval: {{ . }} + {{- end }} + {{- with .Values.prometheus.podMonitor.honorTimestamps }} + honorTimestamps: {{ . }} + {{- end }} + {{- with .Values.prometheus.podMonitor.honorLabels }} + honorLabels: {{ . }} + {{- end }} + {{- with .Values.prometheus.podMonitor.scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .Values.prometheus.podMonitor.relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.prometheus.podMonitor.metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + enableHttp2: {{ default false .Values.prometheus.podMonitor.enableHttp2 }} + filterRunning: {{ default true .Values.prometheus.podMonitor.filterRunning }} + followRedirects: {{ default false .Values.prometheus.podMonitor.followRedirects }} + {{- with .Values.prometheus.podMonitor.params }} + params: + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/psp-clusterrole.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/psp-clusterrole.yaml new file mode 100644 index 0000000..8957317 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/psp-clusterrole.yaml @@ -0,0 +1,14 @@ +{{- if and .Values.rbac.create .Values.rbac.pspEnabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: psp-{{ include "prometheus-node-exporter.fullname" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} +rules: +- apiGroups: ['extensions'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: + - {{ include "prometheus-node-exporter.fullname" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/psp-clusterrolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/psp-clusterrolebinding.yaml new file mode 100644 index 0000000..3333701 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/psp-clusterrolebinding.yaml @@ -0,0 +1,16 @@ +{{- if and .Values.rbac.create .Values.rbac.pspEnabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: psp-{{ include "prometheus-node-exporter.fullname" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: psp-{{ include "prometheus-node-exporter.fullname" . }} +subjects: + - kind: ServiceAccount + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/psp.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/psp.yaml new file mode 100644 index 0000000..4896c84 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/psp.yaml @@ -0,0 +1,49 @@ +{{- if and .Values.rbac.create .Values.rbac.pspEnabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} + {{- with .Values.rbac.pspAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + privileged: false + # Allow core volume types. + volumes: + - 'configMap' + - 'emptyDir' + - 'projected' + - 'secret' + - 'downwardAPI' + - 'persistentVolumeClaim' + - 'hostPath' + hostNetwork: true + hostIPC: false + hostPID: true + hostPorts: + - min: 0 + max: 65535 + runAsUser: + # Permits the container to run with root privileges as well. + rule: 'RunAsAny' + seLinux: + # This policy assumes the nodes are using AppArmor rather than SELinux. + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + # Allow adding the root group. + - min: 0 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + # Allow adding the root group. + - min: 0 + max: 65535 + readOnlyRootFilesystem: false +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/rbac-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/rbac-configmap.yaml new file mode 100644 index 0000000..814e110 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/rbac-configmap.yaml @@ -0,0 +1,16 @@ +{{- if .Values.kubeRBACProxy.enabled}} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ template "prometheus-node-exporter.fullname" . }}-rbac-config + namespace: {{ include "prometheus-node-exporter.namespace" . }} +data: + config-file.yaml: |+ + authorization: + resourceAttributes: + namespace: {{ template "prometheus-node-exporter.namespace" . }} + apiVersion: v1 + resource: services + subresource: {{ template "prometheus-node-exporter.fullname" . }} + name: {{ template "prometheus-node-exporter.fullname" . }} +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/service.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/service.yaml new file mode 100644 index 0000000..a065e46 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/service.yaml @@ -0,0 +1,29 @@ +{{- if .Values.service.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" $ | nindent 4 }} + {{- with .Values.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: +{{- if .Values.service.ipDualStack.enabled }} + ipFamilies: {{ toYaml .Values.service.ipDualStack.ipFamilies | nindent 4 }} + ipFamilyPolicy: {{ .Values.service.ipDualStack.ipFamilyPolicy }} +{{- end }} + type: {{ .Values.service.type }} + ports: + - port: {{ .Values.service.port }} + {{- if ( and (eq .Values.service.type "NodePort" ) (not (empty .Values.service.nodePort)) ) }} + nodePort: {{ .Values.service.nodePort }} + {{- end }} + targetPort: {{ .Values.service.targetPort }} + protocol: TCP + name: {{ .Values.service.portName }} + selector: + {{- include "prometheus-node-exporter.selectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/serviceaccount.yaml new file mode 100644 index 0000000..5c3348c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/serviceaccount.yaml @@ -0,0 +1,17 @@ +{{- if and .Values.rbac.create .Values.serviceAccount.create -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "prometheus-node-exporter.serviceAccountName" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} + {{- with .Values.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- if or .Values.serviceAccount.imagePullSecrets .Values.global.imagePullSecrets }} +imagePullSecrets: + {{- include "prometheus-node-exporter.imagePullSecrets" (dict "Values" .Values "imagePullSecrets" .Values.serviceAccount.imagePullSecrets) | indent 2 }} +{{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/servicemonitor.yaml new file mode 100644 index 0000000..0d7a42e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/servicemonitor.yaml @@ -0,0 +1,61 @@ +{{- if .Values.prometheus.monitor.enabled }} +apiVersion: {{ .Values.prometheus.monitor.apiVersion | default "monitoring.coreos.com/v1" }} +kind: ServiceMonitor +metadata: + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.monitor-namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} + {{- with .Values.prometheus.monitor.additionalLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + jobLabel: {{ default "app.kubernetes.io/name" .Values.prometheus.monitor.jobLabel }} + {{- include "servicemonitor.scrapeLimits" .Values.prometheus.monitor | nindent 2 }} + {{- with .Values.prometheus.monitor.podTargetLabels }} + podTargetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- with .Values.prometheus.monitor.selectorOverride }} + {{- toYaml . | nindent 6 }} + {{- else }} + {{- include "prometheus-node-exporter.selectorLabels" . | nindent 6 }} + {{- end }} + {{- with .Values.prometheus.monitor.attachMetadata }} + attachMetadata: + {{- toYaml . | nindent 4 }} + {{- end }} + endpoints: + - port: {{ .Values.service.portName }} + scheme: {{ .Values.prometheus.monitor.scheme }} + {{- with .Values.prometheus.monitor.basicAuth }} + basicAuth: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.prometheus.monitor.bearerTokenFile }} + bearerTokenFile: {{ . }} + {{- end }} + {{- with .Values.prometheus.monitor.tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.prometheus.monitor.proxyUrl }} + proxyUrl: {{ . }} + {{- end }} + {{- with .Values.prometheus.monitor.interval }} + interval: {{ . }} + {{- end }} + {{- with .Values.prometheus.monitor.scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .Values.prometheus.monitor.relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.prometheus.monitor.metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/verticalpodautoscaler.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/verticalpodautoscaler.yaml new file mode 100644 index 0000000..2c2705f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/templates/verticalpodautoscaler.yaml @@ -0,0 +1,40 @@ +{{- if and (.Capabilities.APIVersions.Has "autoscaling.k8s.io/v1") (.Values.verticalPodAutoscaler.enabled) }} +apiVersion: autoscaling.k8s.io/v1 +kind: VerticalPodAutoscaler +metadata: + name: {{ include "prometheus-node-exporter.fullname" . }} + namespace: {{ include "prometheus-node-exporter.namespace" . }} + labels: + {{- include "prometheus-node-exporter.labels" . | nindent 4 }} +spec: + {{- with .Values.verticalPodAutoscaler.recommenders }} + recommenders: + {{- toYaml . | nindent 4 }} + {{- end }} + resourcePolicy: + containerPolicies: + - containerName: node-exporter + {{- with .Values.verticalPodAutoscaler.controlledResources }} + controlledResources: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.verticalPodAutoscaler.controlledValues }} + controlledValues: {{ . }} + {{- end }} + {{- with .Values.verticalPodAutoscaler.maxAllowed }} + maxAllowed: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.verticalPodAutoscaler.minAllowed }} + minAllowed: + {{- toYaml . | nindent 8 }} + {{- end }} + targetRef: + apiVersion: apps/v1 + kind: DaemonSet + name: {{ include "prometheus-node-exporter.fullname" . }} + {{- with .Values.verticalPodAutoscaler.updatePolicy }} + updatePolicy: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/values.yaml new file mode 100644 index 0000000..6e4665c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-node-exporter/values.yaml @@ -0,0 +1,480 @@ +# Default values for prometheus-node-exporter. +# This is a YAML-formatted file. +# Declare variables to be passed into your templates. +image: + registry: quay.io + repository: prometheus/node-exporter + # Overrides the image tag whose default is {{ printf "v%s" .Chart.AppVersion }} + tag: "" + pullPolicy: IfNotPresent + digest: "" + +imagePullSecrets: [] +# - name: "image-pull-secret" +nameOverride: "" +fullnameOverride: "" + +# Number of old history to retain to allow rollback +# Default Kubernetes value is set to 10 +revisionHistoryLimit: 10 + +global: + # To help compatibility with other charts which use global.imagePullSecrets. + # Allow either an array of {name: pullSecret} maps (k8s-style), or an array of strings (more common helm-style). + # global: + # imagePullSecrets: + # - name: pullSecret1 + # - name: pullSecret2 + # or + # global: + # imagePullSecrets: + # - pullSecret1 + # - pullSecret2 + imagePullSecrets: [] + # + # Allow parent charts to override registry hostname + imageRegistry: "" + +# Configure kube-rbac-proxy. When enabled, creates a kube-rbac-proxy to protect the node-exporter http endpoint. +# The requests are served through the same service but requests are HTTPS. +kubeRBACProxy: + enabled: false + image: + registry: quay.io + repository: brancz/kube-rbac-proxy + tag: v0.15.0 + sha: "" + pullPolicy: IfNotPresent + + # List of additional cli arguments to configure kube-rbac-prxy + # for example: --tls-cipher-suites, --log-file, etc. + # all the possible args can be found here: https://github.com/brancz/kube-rbac-proxy#usage + extraArgs: [] + + ## Specify security settings for a Container + ## Allows overrides and additional options compared to (Pod) securityContext + ## Ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-container + containerSecurityContext: {} + + resources: {} + # We usually recommend not to specify default resources and to leave this as a conscious + # choice for the user. This also increases chances charts run on environments with little + # resources, such as Minikube. If you do want to specify resources, uncomment the following + # lines, adjust them as necessary, and remove the curly braces after 'resources:'. + # limits: + # cpu: 100m + # memory: 64Mi + # requests: + # cpu: 10m + # memory: 32Mi + +service: + enabled: true + type: ClusterIP + port: 9100 + targetPort: 9100 + nodePort: + portName: metrics + listenOnAllInterfaces: true + annotations: + prometheus.io/scrape: "true" + ipDualStack: + enabled: false + ipFamilies: ["IPv6", "IPv4"] + ipFamilyPolicy: "PreferDualStack" + +# Set a NetworkPolicy with: +# ingress only on service.port +# no egress permitted +networkPolicy: + enabled: false + +# Additional environment variables that will be passed to the daemonset +env: {} +## env: +## VARIABLE: value + +prometheus: + monitor: + enabled: false + additionalLabels: {} + namespace: "" + + jobLabel: "" + + # List of pod labels to add to node exporter metrics + # https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#servicemonitor + podTargetLabels: [] + + scheme: http + basicAuth: {} + bearerTokenFile: + tlsConfig: {} + + ## proxyUrl: URL of a proxy that should be used for scraping. + ## + proxyUrl: "" + + ## Override serviceMonitor selector + ## + selectorOverride: {} + + ## Attach node metadata to discovered targets. Requires Prometheus v2.35.0 and above. + ## + attachMetadata: + node: false + + relabelings: [] + metricRelabelings: [] + interval: "" + scrapeTimeout: 10s + ## prometheus.monitor.apiVersion ApiVersion for the serviceMonitor Resource(defaults to "monitoring.coreos.com/v1") + apiVersion: "" + + ## SampleLimit defines per-scrape limit on number of scraped samples that will be accepted. + ## + sampleLimit: 0 + + ## TargetLimit defines a limit on the number of scraped targets that will be accepted. + ## + targetLimit: 0 + + ## Per-scrape limit on number of labels that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelLimit: 0 + + ## Per-scrape limit on length of labels name that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelNameLengthLimit: 0 + + ## Per-scrape limit on length of labels value that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + ## + labelValueLengthLimit: 0 + + # PodMonitor defines monitoring for a set of pods. + # ref. https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#monitoring.coreos.com/v1.PodMonitor + # Using a PodMonitor may be preferred in some environments where there is very large number + # of Node Exporter endpoints (1000+) behind a single service. + # The PodMonitor is disabled by default. When switching from ServiceMonitor to PodMonitor, + # the time series resulting from the configuration through PodMonitor may have different labels. + # For instance, there will not be the service label any longer which might + # affect PromQL queries selecting that label. + podMonitor: + enabled: false + # Namespace in which to deploy the pod monitor. Defaults to the release namespace. + namespace: "" + # Additional labels, e.g. setting a label for pod monitor selector as set in prometheus + additionalLabels: {} + # release: kube-prometheus-stack + # PodTargetLabels transfers labels of the Kubernetes Pod onto the target. + podTargetLabels: [] + # apiVersion defaults to monitoring.coreos.com/v1. + apiVersion: "" + # Override pod selector to select pod objects. + selectorOverride: {} + # Attach node metadata to discovered targets. Requires Prometheus v2.35.0 and above. + attachMetadata: + node: false + # The label to use to retrieve the job name from. Defaults to label app.kubernetes.io/name. + jobLabel: "" + + # Scheme/protocol to use for scraping. + scheme: "http" + # Path to scrape metrics at. + path: "/metrics" + + # BasicAuth allow an endpoint to authenticate over basic authentication. + # More info: https://prometheus.io/docs/operating/configuration/#endpoint + basicAuth: {} + # Secret to mount to read bearer token for scraping targets. + # The secret needs to be in the same namespace as the pod monitor and accessible by the Prometheus Operator. + # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.24/#secretkeyselector-v1-core + bearerTokenSecret: {} + # TLS configuration to use when scraping the endpoint. + tlsConfig: {} + # Authorization section for this endpoint. + # https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#monitoring.coreos.com/v1.SafeAuthorization + authorization: {} + # OAuth2 for the URL. Only valid in Prometheus versions 2.27.0 and newer. + # https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#monitoring.coreos.com/v1.OAuth2 + oauth2: {} + + # ProxyURL eg http://proxyserver:2195. Directs scrapes through proxy to this endpoint. + proxyUrl: "" + # Interval at which endpoints should be scraped. If not specified Prometheus’ global scrape interval is used. + interval: "" + # Timeout after which the scrape is ended. If not specified, the Prometheus global scrape interval is used. + scrapeTimeout: "" + # HonorTimestamps controls whether Prometheus respects the timestamps present in scraped data. + honorTimestamps: true + # HonorLabels chooses the metric’s labels on collisions with target labels. + honorLabels: true + # Whether to enable HTTP2. Default false. + enableHttp2: "" + # Drop pods that are not running. (Failed, Succeeded). + # Enabled by default. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#pod-phase + filterRunning: "" + # FollowRedirects configures whether scrape requests follow HTTP 3xx redirects. Default false. + followRedirects: "" + # Optional HTTP URL parameters + params: {} + + # RelabelConfigs to apply to samples before scraping. Prometheus Operator automatically adds + # relabelings for a few standard Kubernetes fields. The original scrape job’s name + # is available via the __tmp_prometheus_job_name label. + # More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config + relabelings: [] + # MetricRelabelConfigs to apply to samples before ingestion. + metricRelabelings: [] + + # SampleLimit defines per-scrape limit on number of scraped samples that will be accepted. + sampleLimit: 0 + # TargetLimit defines a limit on the number of scraped targets that will be accepted. + targetLimit: 0 + # Per-scrape limit on number of labels that will be accepted for a sample. + # Only valid in Prometheus versions 2.27.0 and newer. + labelLimit: 0 + # Per-scrape limit on length of labels name that will be accepted for a sample. + # Only valid in Prometheus versions 2.27.0 and newer. + labelNameLengthLimit: 0 + # Per-scrape limit on length of labels value that will be accepted for a sample. + # Only valid in Prometheus versions 2.27.0 and newer. + labelValueLengthLimit: 0 + +## Customize the updateStrategy if set +updateStrategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 1 + +resources: {} + # We usually recommend not to specify default resources and to leave this as a conscious + # choice for the user. This also increases chances charts run on environments with little + # resources, such as Minikube. If you do want to specify resources, uncomment the following + # lines, adjust them as necessary, and remove the curly braces after 'resources:'. + # limits: + # cpu: 200m + # memory: 50Mi + # requests: + # cpu: 100m + # memory: 30Mi + +serviceAccount: + # Specifies whether a ServiceAccount should be created + create: true + # The name of the ServiceAccount to use. + # If not set and create is true, a name is generated using the fullname template + name: + annotations: {} + imagePullSecrets: [] + automountServiceAccountToken: false + +securityContext: + fsGroup: 65534 + runAsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + +containerSecurityContext: + readOnlyRootFilesystem: true + # capabilities: + # add: + # - SYS_TIME + +rbac: + ## If true, create & use RBAC resources + ## + create: true + ## If true, create & use Pod Security Policy resources + ## https://kubernetes.io/docs/concepts/policy/pod-security-policy/ + pspEnabled: true + pspAnnotations: {} + +# for deployments that have node_exporter deployed outside of the cluster, list +# their addresses here +endpoints: [] + +# Expose the service to the host network +hostNetwork: true + +# Share the host process ID namespace +hostPID: true + +# Mount the node's root file system (/) at /host/root in the container +hostRootFsMount: + enabled: true + # Defines how new mounts in existing mounts on the node or in the container + # are propagated to the container or node, respectively. Possible values are + # None, HostToContainer, and Bidirectional. If this field is omitted, then + # None is used. More information on: + # https://kubernetes.io/docs/concepts/storage/volumes/#mount-propagation + mountPropagation: HostToContainer + +## Assign a group of affinity scheduling rules +## +affinity: {} +# nodeAffinity: +# requiredDuringSchedulingIgnoredDuringExecution: +# nodeSelectorTerms: +# - matchFields: +# - key: metadata.name +# operator: In +# values: +# - target-host-name + +# Annotations to be added to node exporter pods +podAnnotations: + # Fix for very slow GKE cluster upgrades + cluster-autoscaler.kubernetes.io/safe-to-evict: "true" + +# Extra labels to be added to node exporter pods +podLabels: {} + +# Annotations to be added to node exporter daemonset +daemonsetAnnotations: {} + +## set to true to add the release label so scraping of the servicemonitor with kube-prometheus-stack works out of the box +releaseLabel: false + +# Custom DNS configuration to be added to prometheus-node-exporter pods +dnsConfig: {} +# nameservers: +# - 1.2.3.4 +# searches: +# - ns1.svc.cluster-domain.example +# - my.dns.search.suffix +# options: +# - name: ndots +# value: "2" +# - name: edns0 + +## Assign a nodeSelector if operating a hybrid cluster +## +nodeSelector: + kubernetes.io/os: linux + # kubernetes.io/arch: amd64 + +tolerations: + - effect: NoSchedule + operator: Exists + +## Assign a PriorityClassName to pods if set +# priorityClassName: "" + +## Additional container arguments +## +extraArgs: [] +# - --collector.diskstats.ignored-devices=^(ram|loop|fd|(h|s|v)d[a-z]|nvme\\d+n\\d+p)\\d+$ +# - --collector.textfile.directory=/run/prometheus + +## Additional mounts from the host to node-exporter container +## +extraHostVolumeMounts: [] +# - name: +# hostPath: +# mountPath: +# readOnly: true|false +# mountPropagation: None|HostToContainer|Bidirectional + +## Additional configmaps to be mounted. +## +configmaps: [] +# - name: +# mountPath: +secrets: [] +# - name: +# mountPath: +## Override the deployment namespace +## +namespaceOverride: "" + +## Additional containers for export metrics to text file +## +sidecars: [] +## - name: nvidia-dcgm-exporter +## image: nvidia/dcgm-exporter:1.4.3 + +## Volume for sidecar containers +## +sidecarVolumeMount: [] +## - name: collector-textfiles +## mountPath: /run/prometheus +## readOnly: false + +## Additional mounts from the host to sidecar containers +## +sidecarHostVolumeMounts: [] +# - name: +# hostPath: +# mountPath: +# readOnly: true|false +# mountPropagation: None|HostToContainer|Bidirectional + +## Additional InitContainers to initialize the pod +## +extraInitContainers: [] + +## Liveness probe +## +livenessProbe: + failureThreshold: 3 + httpGet: + httpHeaders: [] + scheme: http + initialDelaySeconds: 0 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + +## Readiness probe +## +readinessProbe: + failureThreshold: 3 + httpGet: + httpHeaders: [] + scheme: http + initialDelaySeconds: 0 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + +# Enable vertical pod autoscaler support for prometheus-node-exporter +verticalPodAutoscaler: + enabled: false + + # Recommender responsible for generating recommendation for the object. + # List should be empty (then the default recommender will generate the recommendation) + # or contain exactly one recommender. + # recommenders: + # - name: custom-recommender-performance + + # List of resources that the vertical pod autoscaler can control. Defaults to cpu and memory + controlledResources: [] + # Specifies which resource values should be controlled: RequestsOnly or RequestsAndLimits. + # controlledValues: RequestsAndLimits + + # Define the max allowed resources for the pod + maxAllowed: {} + # cpu: 200m + # memory: 100Mi + # Define the min allowed resources for the pod + minAllowed: {} + # cpu: 200m + # memory: 100Mi + + # updatePolicy: + # Specifies minimal number of replicas which need to be alive for VPA Updater to attempt pod eviction + # minReplicas: 1 + # Specifies whether recommended updates are applied when a Pod is started and whether recommended updates + # are applied during the life of a Pod. Possible values are "Off", "Initial", "Recreate", and "Auto". + # updateMode: Auto + +# Extra manifests to deploy as an array +extraManifests: [] + # - | + # apiVersion: v1 + # kind: ConfigMap + # metadata: + # name: prometheus-extra + # data: + # extra-data: "value" diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/.helmignore new file mode 100644 index 0000000..e90c9f6 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/.helmignore @@ -0,0 +1,24 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj + +# OWNERS file for Kubernetes +OWNERS \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/Chart.yaml new file mode 100644 index 0000000..3351215 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/Chart.yaml @@ -0,0 +1,24 @@ +annotations: + artifacthub.io/license: Apache-2.0 + artifacthub.io/links: | + - name: Chart Source + url: https://github.com/prometheus-community/helm-charts +apiVersion: v2 +appVersion: v1.6.2 +description: A Helm chart for prometheus pushgateway +home: https://github.com/prometheus/pushgateway +keywords: +- pushgateway +- prometheus +maintainers: +- email: gianrubio@gmail.com + name: gianrubio +- email: christian.staude@staffbase.com + name: cstaud +- email: rootsandtrees@posteo.de + name: zeritti +name: prometheus-pushgateway +sources: +- https://github.com/prometheus/pushgateway +type: application +version: 2.4.2 diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/README.md b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/README.md new file mode 100644 index 0000000..1865d47 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/README.md @@ -0,0 +1,88 @@ +# Prometheus Pushgateway + +This chart bootstraps a prometheus [pushgateway](http://github.com/prometheus/pushgateway) deployment on a [Kubernetes](http://kubernetes.io) cluster using the [Helm](https://helm.sh) package manager. + +An optional prometheus `ServiceMonitor` can be enabled, should you wish to use this gateway with a [Prometheus Operator](https://github.com/coreos/prometheus-operator). + +## Get Repository Info + +```console +helm repo add prometheus-community https://prometheus-community.github.io/helm-charts +helm repo update +``` + +_See [`helm repo`](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Install Chart + +```console +helm install [RELEASE_NAME] prometheus-community/prometheus-pushgateway +``` + +_See [configuration](#configuration) below._ + +_See [helm install](https://helm.sh/docs/helm/helm_install/) for command documentation._ + +## Uninstall Chart + +```console +helm uninstall [RELEASE_NAME] +``` + +This removes all the Kubernetes components associated with the chart and deletes the release. + +_See [helm uninstall](https://helm.sh/docs/helm/helm_uninstall/) for command documentation._ + +## Upgrading Chart + +```console +helm upgrade [RELEASE_NAME] [CHART] --install +``` + +_See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documentation._ + +### To 2.0.0 + +Chart API version has been upgraded to v2 so Helm 3 is needed from now on. + +Docker image tag is used from Chart.yaml appVersion field by default now. + +Version 2.0.0 also adapted [Helm label and annotation best practices](https://helm.sh/docs/chart_best_practices/labels/). Specifically, labels mapping is listed below: + +```console +OLD => NEW +---------------------------------------- +heritage => app.kubernetes.io/managed-by +chart => helm.sh/chart +[container version] => app.kubernetes.io/version +app => app.kubernetes.io/name +release => app.kubernetes.io/instance +``` + +Therefore, depending on the way you've configured the chart, the previous StatefulSet or Deployment need to be deleted before upgrade. + +If `runAsStatefulSet: false` (this is the default): + +```console +kubectl delete deploy -l app=prometheus-pushgateway +``` + +If `runAsStatefulSet: true`: + +```console +kubectl delete sts -l app=prometheus-pushgateway +``` + +After that do the actual upgrade: + +```console +helm upgrade -i prometheus-pushgateway prometheus-community/prometheus-pushgateway +``` + +## Configuration + +See [Customizing the Chart Before Installing](https://helm.sh/docs/intro/using_helm/#customizing-the-chart-before-installing). To see all configurable options with detailed comments, visit the chart's [values.yaml](./values.yaml), or run these configuration commands: + +```console +helm show values prometheus-community/prometheus-pushgateway +``` diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/NOTES.txt new file mode 100644 index 0000000..0196e2b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/NOTES.txt @@ -0,0 +1,19 @@ +1. Get the application URL by running these commands: +{{- if .Values.ingress.enabled }} +{{- range .Values.ingress.hosts }} + http{{ if $.Values.ingress.tls }}s{{ end }}://{{ . }}{{ $.Values.ingress.path }} +{{- end }} +{{- else if contains "NodePort" .Values.service.type }} + export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ template "prometheus-pushgateway.fullname" . }}) + export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}") + echo http://$NODE_IP:$NODE_PORT +{{- else if contains "LoadBalancer" .Values.service.type }} + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + You can watch the status of by running 'kubectl get svc -w {{ template "prometheus-pushgateway.fullname" . }}' + export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ template "prometheus-pushgateway.fullname" . }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}') + echo http://$SERVICE_IP:{{ .Values.service.port }} +{{- else if contains "ClusterIP" .Values.service.type }} + export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app={{ template "prometheus-pushgateway.name" . }},release={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") + echo "Visit http://127.0.0.1:9091 to use your application" + kubectl port-forward $POD_NAME 9091 +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/_helpers.tpl new file mode 100644 index 0000000..b56a2da --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/_helpers.tpl @@ -0,0 +1,208 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "prometheus-pushgateway.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Namespace to set on the resources +*/}} +{{- define "prometheus-pushgateway.namespace" -}} + {{- if .Values.namespaceOverride -}} + {{- .Values.namespaceOverride -}} + {{- else -}} + {{- .Release.Namespace -}} + {{- end -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "prometheus-pushgateway.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default .Chart.Name .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "prometheus-pushgateway.chart" -}} +{{ printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create the name of the service account to use +*/}} +{{- define "prometheus-pushgateway.serviceAccountName" -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "prometheus-pushgateway.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} + +{{/* +Create default labels +*/}} +{{- define "prometheus-pushgateway.defaultLabels" -}} +helm.sh/chart: {{ include "prometheus-pushgateway.chart" . }} +{{ include "prometheus-pushgateway.selectorLabels" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- with .Values.podLabels }} +{{ toYaml . }} +{{- end }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "prometheus-pushgateway.selectorLabels" -}} +app.kubernetes.io/name: {{ include "prometheus-pushgateway.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Return the appropriate apiVersion for networkpolicy. +*/}} +{{- define "prometheus-pushgateway.networkPolicy.apiVersion" -}} +{{- if semverCompare ">=1.4-0, <1.7-0" .Capabilities.KubeVersion.GitVersion }} +{{- print "extensions/v1beta1" }} +{{- else if semverCompare "^1.7-0" .Capabilities.KubeVersion.GitVersion }} +{{- print "networking.k8s.io/v1" }} +{{- end }} +{{- end }} + +{{/* +Define PDB apiVersion +*/}} +{{- define "prometheus-pushgateway.pdb.apiVersion" -}} +{{- if $.Capabilities.APIVersions.Has "policy/v1/PodDisruptionBudget" }} +{{- print "policy/v1" }} +{{- else }} +{{- print "policy/v1beta1" }} +{{- end }} +{{- end }} + +{{/* +Define Ingress apiVersion +*/}} +{{- define "prometheus-pushgateway.ingress.apiVersion" -}} +{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }} +{{- print "networking.k8s.io/v1" }} +{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion }} +{{- print "networking.k8s.io/v1beta1" }} +{{- else }} +{{- print "extensions/v1beta1" }} +{{- end }} +{{- end }} + +{{/* +Returns pod spec +*/}} +{{- define "prometheus-pushgateway.podSpec" -}} +serviceAccountName: {{ include "prometheus-pushgateway.serviceAccountName" . }} +{{- with .Values.priorityClassName }} +priorityClassName: {{ . | quote }} +{{- end }} +{{- with .Values.imagePullSecrets }} +imagePullSecrets: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.extraInitContainers }} +initContainers: + {{- toYaml . | nindent 2 }} +{{- end }} +containers: + {{- with .Values.extraContainers }} + {{- toYaml . | nindent 2 }} + {{- end }} + - name: pushgateway + image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + {{- with .Values.extraVars }} + env: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.extraArgs }} + args: + {{- toYaml . | nindent 6 }} + {{- end }} + ports: + - name: metrics + containerPort: 9091 + protocol: TCP + {{- if .Values.liveness.enabled }} + livenessProbe: + {{- toYaml .Values.liveness.probe | nindent 6 }} + {{- end }} + {{- if .Values.readiness.enabled }} + readinessProbe: + {{- toYaml .Values.readiness.probe | nindent 6 }} + {{- end }} + {{- with .Values.resources }} + resources: + {{- toYaml . | nindent 6 }} + {{- end }} + {{- with .Values.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 6 }} + {{- end }} + volumeMounts: + - name: storage-volume + mountPath: "{{ .Values.persistentVolume.mountPath }}" + subPath: "{{ .Values.persistentVolume.subPath }}" + {{- with .Values.extraVolumeMounts }} + {{- toYaml . | nindent 6 }} + {{- end }} +{{- with .Values.nodeSelector }} +nodeSelector: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.tolerations }} +tolerations: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.affinity }} +affinity: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.topologySpreadConstraints }} +topologySpreadConstraints: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- with .Values.securityContext }} +securityContext: + {{- toYaml . | nindent 2 }} +{{- end }} +volumes: + {{- $storageVolumeAsPVCTemplate := and .Values.runAsStatefulSet .Values.persistentVolume.enabled -}} + {{- if not $storageVolumeAsPVCTemplate }} + - name: storage-volume + {{- if .Values.persistentVolume.enabled }} + persistentVolumeClaim: + claimName: {{ if .Values.persistentVolume.existingClaim }}{{ .Values.persistentVolume.existingClaim }}{{- else }}{{ include "prometheus-pushgateway.fullname" . }}{{- end }} + {{- else }} + emptyDir: {} + {{- end }} + {{- end }} + {{- if .Values.extraVolumes }} + {{- toYaml .Values.extraVolumes | nindent 2 }} + {{- else if $storageVolumeAsPVCTemplate }} + [] + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/deployment.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/deployment.yaml new file mode 100644 index 0000000..557ca6f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/deployment.yaml @@ -0,0 +1,28 @@ +{{- if not .Values.runAsStatefulSet }} +apiVersion: apps/v1 +kind: Deployment +metadata: + labels: + {{- include "prometheus-pushgateway.defaultLabels" . | nindent 4 }} + name: {{ include "prometheus-pushgateway.fullname" . }} + namespace: {{ template "prometheus-pushgateway.namespace" . }} +spec: + replicas: {{ .Values.replicaCount }} + {{- with .Values.strategy }} + strategy: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "prometheus-pushgateway.selectorLabels" . | nindent 6 }} + template: + metadata: + {{- with .Values.podAnnotations }} + annotations: + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "prometheus-pushgateway.defaultLabels" . | nindent 8 }} + spec: + {{- include "prometheus-pushgateway.podSpec" . | nindent 6 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/ingress.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/ingress.yaml new file mode 100644 index 0000000..237ac4a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/ingress.yaml @@ -0,0 +1,50 @@ +{{- if .Values.ingress.enabled }} +{{- $serviceName := include "prometheus-pushgateway.fullname" . }} +{{- $servicePort := .Values.service.port }} +{{- $ingressPath := .Values.ingress.path }} +{{- $ingressClassName := .Values.ingress.className }} +{{- $ingressPathType := .Values.ingress.pathType }} +{{- $extraPaths := .Values.ingress.extraPaths }} +apiVersion: {{ include "prometheus-pushgateway.ingress.apiVersion" . }} +kind: Ingress +metadata: + {{- with .Values.ingress.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "prometheus-pushgateway.defaultLabels" . | nindent 4 }} + name: {{ include "prometheus-pushgateway.fullname" . }} + namespace: {{ template "prometheus-pushgateway.namespace" . }} +spec: + {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }} + ingressClassName: {{ $ingressClassName }} + {{- end }} + rules: + {{- range $host := .Values.ingress.hosts }} + - host: {{ $host }} + http: + paths: + {{- with $extraPaths }} + {{- toYaml . | nindent 10 }} + {{- end }} + - path: {{ $ingressPath }} + {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }} + pathType: {{ $ingressPathType }} + {{- end }} + backend: + {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }} + service: + name: {{ $serviceName }} + port: + number: {{ $servicePort }} + {{- else }} + serviceName: {{ $serviceName }} + servicePort: {{ $servicePort }} + {{- end }} + {{- end -}} + {{- with .Values.ingress.tls }} + tls: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/networkpolicy.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/networkpolicy.yaml new file mode 100644 index 0000000..d3b8019 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/networkpolicy.yaml @@ -0,0 +1,26 @@ +{{- if .Values.networkPolicy }} +apiVersion: {{ include "prometheus-pushgateway.networkPolicy.apiVersion" . }} +kind: NetworkPolicy +metadata: + labels: + {{- include "prometheus-pushgateway.defaultLabels" . | nindent 4 }} + {{- if .Values.networkPolicy.customSelectors }} + name: ingress-allow-customselector-{{ template "prometheus-pushgateway.name" . }} + {{- else if .Values.networkPolicy.allowAll }} + name: ingress-allow-all-{{ template "prometheus-pushgateway.name" . }} + {{- else -}} + {{- fail "One of `allowAll` or `customSelectors` must be specified." }} + {{- end }} + namespace: {{ template "prometheus-pushgateway.namespace" . }} +spec: + podSelector: + matchLabels: + {{- include "prometheus-pushgateway.selectorLabels" . | nindent 6 }} + ingress: + - ports: + - port: {{ .Values.service.targetPort }} + {{- with .Values.networkPolicy.customSelectors }} + from: + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/pdb.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/pdb.yaml new file mode 100644 index 0000000..6051133 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/pdb.yaml @@ -0,0 +1,14 @@ +{{- if .Values.podDisruptionBudget }} +apiVersion: {{ include "prometheus-pushgateway.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + labels: + {{- include "prometheus-pushgateway.defaultLabels" . | nindent 4 }} + name: {{ include "prometheus-pushgateway.fullname" . }} + namespace: {{ template "prometheus-pushgateway.namespace" . }} +spec: + selector: + matchLabels: + {{- include "prometheus-pushgateway.selectorLabels" . | nindent 6 }} + {{- toYaml .Values.podDisruptionBudget | nindent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/pushgateway-pvc.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/pushgateway-pvc.yaml new file mode 100644 index 0000000..d2a85f4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/pushgateway-pvc.yaml @@ -0,0 +1,29 @@ +{{- if and (not .Values.runAsStatefulSet) .Values.persistentVolume.enabled (not .Values.persistentVolume.existingClaim) }} +apiVersion: v1 +kind: PersistentVolumeClaim +metadata: + {{- with .Values.persistentVolume.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "prometheus-pushgateway.defaultLabels" . | nindent 4 }} + {{- with .Values.persistentVolumeLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "prometheus-pushgateway.fullname" . }} + namespace: {{ template "prometheus-pushgateway.namespace" . }} +spec: + accessModes: + {{- toYaml .Values.persistentVolume.accessModes | nindent 4 }} + {{- if .Values.persistentVolume.storageClass }} + {{- if (eq "-" .Values.persistentVolume.storageClass) }} + storageClassName: "" + {{- else }} + storageClassName: "{{ .Values.persistentVolume.storageClass }}" + {{- end }} + {{- end }} + resources: + requests: + storage: "{{ .Values.persistentVolume.size }}" +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/service.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/service.yaml new file mode 100644 index 0000000..7a3562c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/service.yaml @@ -0,0 +1,41 @@ +{{- $stsNoHeadlessSvcTypes := list "LoadBalancer" "NodePort" -}} +apiVersion: v1 +kind: Service +metadata: + {{- with .Values.serviceAnnotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "prometheus-pushgateway.defaultLabels" . | nindent 4 }} + {{- with .Values.serviceLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "prometheus-pushgateway.fullname" . }} + namespace: {{ template "prometheus-pushgateway.namespace" . }} +spec: + {{- if .Values.service.clusterIP }} + clusterIP: {{ .Values.service.clusterIP }} + {{ else if and .Values.runAsStatefulSet (not (has .Values.service.type $stsNoHeadlessSvcTypes)) }} + clusterIP: None # Headless service + {{- end }} + type: {{ .Values.service.type }} + {{- with .Values.service.loadBalancerIP }} + loadBalancerIP: {{ . }} + {{- end }} + {{- if .Values.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- range $cidr := .Values.service.loadBalancerSourceRanges }} + - {{ $cidr }} + {{- end }} + {{- end }} + ports: + - port: {{ .Values.service.port }} + targetPort: {{ .Values.service.targetPort }} + {{- if and (eq .Values.service.type "NodePort") .Values.service.nodePort }} + nodePort: {{ .Values.service.nodePort }} + {{- end }} + protocol: TCP + name: http + selector: + {{- include "prometheus-pushgateway.selectorLabels" . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/serviceaccount.yaml new file mode 100644 index 0000000..ab5e245 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/serviceaccount.yaml @@ -0,0 +1,16 @@ +{{- if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + {{- with .Values.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "prometheus-pushgateway.defaultLabels" . | nindent 4 }} + {{- with .Values.serviceAccountLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ include "prometheus-pushgateway.serviceAccountName" . }} + namespace: {{ template "prometheus-pushgateway.namespace" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/servicemonitor.yaml new file mode 100644 index 0000000..5e3f75a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/servicemonitor.yaml @@ -0,0 +1,51 @@ +{{- if .Values.serviceMonitor.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + {{- include "prometheus-pushgateway.defaultLabels" . | nindent 4 }} + {{- if .Values.serviceMonitor.additionalLabels }} + {{- toYaml .Values.serviceMonitor.additionalLabels | nindent 4 }} + {{- end }} + name: {{ include "prometheus-pushgateway.fullname" . }} + {{- if .Values.serviceMonitor.namespace }} + namespace: {{ .Values.serviceMonitor.namespace }} + {{- else }} + namespace: {{ template "prometheus-pushgateway.namespace" . }} + {{- end }} +spec: + endpoints: + - port: http + {{- with .Values.serviceMonitor.interval }} + interval: {{ . }} + {{- end }} + {{- with .Values.serviceMonitor.scheme }} + scheme: {{ . }} + {{- end }} + {{- with .Values.serviceMonitor.bearerTokenFile }} + bearerTokenFile: {{ . }} + {{- end }} + {{- with .Values.serviceMonitor.tlsConfig }} + tlsConfig: + {{- toYaml .| nindent 6 }} + {{- end }} + {{- with .Values.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + path: {{ .Values.serviceMonitor.telemetryPath }} + honorLabels: {{ .Values.serviceMonitor.honorLabels }} + {{- with .Values.serviceMonitor.metricRelabelings }} + metricRelabelings: + {{- tpl (toYaml . | nindent 6) $ }} + {{- end }} + {{- with .Values.serviceMonitor.relabelings }} + relabelings: + {{- toYaml . | nindent 6 }} + {{- end }} + namespaceSelector: + matchNames: + - {{ template "prometheus-pushgateway.namespace" . }} + selector: + matchLabels: + {{- include "prometheus-pushgateway.selectorLabels" . | nindent 6 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/statefulset.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/statefulset.yaml new file mode 100644 index 0000000..8d486a3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/templates/statefulset.yaml @@ -0,0 +1,49 @@ +{{- if .Values.runAsStatefulSet }} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + labels: + {{- include "prometheus-pushgateway.defaultLabels" . | nindent 4 }} + name: {{ include "prometheus-pushgateway.fullname" . }} + namespace: {{ template "prometheus-pushgateway.namespace" . }} +spec: + replicas: {{ .Values.replicaCount }} + serviceName: {{ include "prometheus-pushgateway.fullname" . }} + selector: + matchLabels: + {{- include "prometheus-pushgateway.selectorLabels" . | nindent 6 }} + template: + metadata: + {{- with .Values.podAnnotations }} + annotations: + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "prometheus-pushgateway.defaultLabels" . | nindent 8 }} + spec: + {{- include "prometheus-pushgateway.podSpec" . | nindent 6 }} + {{- if .Values.persistentVolume.enabled }} + volumeClaimTemplates: + - metadata: + {{- with .Values.persistentVolume.annotations }} + annotations: + {{- toYaml . | nindent 10 }} + {{- end }} + labels: + {{- include "prometheus-pushgateway.defaultLabels" . | nindent 10 }} + name: storage-volume + spec: + accessModes: + {{ toYaml .Values.persistentVolume.accessModes }} + {{- if .Values.persistentVolume.storageClass }} + {{- if (eq "-" .Values.persistentVolume.storageClass) }} + storageClassName: "" + {{- else }} + storageClassName: "{{ .Values.persistentVolume.storageClass }}" + {{- end }} + {{- end }} + resources: + requests: + storage: "{{ .Values.persistentVolume.size }}" + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/values.yaml new file mode 100644 index 0000000..02e5c0b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/charts/prometheus-pushgateway/values.yaml @@ -0,0 +1,330 @@ +# Default values for prometheus-pushgateway. +# This is a YAML-formatted file. +# Declare variables to be passed into your templates. + +# Provide a name in place of prometheus-pushgateway for `app:` labels +nameOverride: "" + +# Provide a name to substitute for the full names of resources +fullnameOverride: "" + +# Provide a namespace to substitude for the namespace on resources +namespaceOverride: "" + +image: + repository: quay.io/prometheus/pushgateway + # if not set appVersion field from Chart.yaml is used + tag: "" + pullPolicy: IfNotPresent + +# Optional pod imagePullSecrets +imagePullSecrets: [] + +service: + type: ClusterIP + port: 9091 + targetPort: 9091 + # nodePort: 32100 + + # Optional - Can be used for headless if value is "None" + clusterIP: "" + + loadBalancerIP: "" + loadBalancerSourceRanges: [] + +# Optional pod annotations +podAnnotations: {} + +# Optional pod labels +podLabels: {} + +# Optional service annotations +serviceAnnotations: {} + +# Optional service labels +serviceLabels: {} + +# Optional serviceAccount labels +serviceAccountLabels: {} + +# Optional persistentVolume labels +persistentVolumeLabels: {} + +# Optional additional environment variables +extraVars: [] + +## Additional pushgateway container arguments +## +## example: +## extraArgs: +## - --persistence.file=/data/pushgateway.data +## - --persistence.interval=5m +extraArgs: [] + +## Additional InitContainers to initialize the pod +## +extraInitContainers: [] + +# Optional additional containers (sidecar) +extraContainers: [] + # - name: oAuth2-proxy + # args: + # - -https-address=:9092 + # - -upstream=http://localhost:9091 + # - -skip-auth-regex=^/metrics + # - -openshift-delegate-urls={"/":{"group":"monitoring.coreos.com","resource":"prometheuses","verb":"get"}} + # image: openshift/oauth-proxy:v1.1.0 + # ports: + # - containerPort: 9092 + # name: proxy + # resources: + # limits: + # memory: 16Mi + # requests: + # memory: 4Mi + # cpu: 20m + # volumeMounts: + # - mountPath: /etc/prometheus/secrets/pushgateway-tls + # name: secret-pushgateway-tls + +resources: {} + # We usually recommend not to specify default resources and to leave this as a conscious + # choice for the user. This also increases chances charts run on environments with little + # resources, such as Minikube. If you do want to specify resources, uncomment the following + # lines, adjust them as necessary, and remove the curly braces after 'resources:'. + # limits: + # cpu: 200m + # memory: 50Mi + # requests: + # cpu: 100m + # memory: 30Mi + +liveness: + enabled: true + probe: + httpGet: + path: /-/healthy + port: 9091 + initialDelaySeconds: 10 + timeoutSeconds: 10 + +readiness: + enabled: true + probe: + httpGet: + path: /-/ready + port: 9091 + initialDelaySeconds: 10 + timeoutSeconds: 10 + +serviceAccount: + # Specifies whether a ServiceAccount should be created + create: true + # The name of the ServiceAccount to use. + # If not set and create is true, a name is generated using the fullname template + name: + +## Configure ingress resource that allow you to access the +## pushgateway installation. Set up the URL +## ref: http://kubernetes.io/docs/user-guide/ingress/ +## +ingress: + ## Enable Ingress. + ## + enabled: false + # AWS ALB requires path of /* + className: "" + path: / + pathType: ImplementationSpecific + + ## Extra paths to prepend to every host configuration. This is useful when working with annotation based services. + extraPaths: [] + # - path: /* + # backend: + # serviceName: ssl-redirect + # servicePort: use-annotation + + ## Annotations. + ## + # annotations: + # kubernetes.io/ingress.class: nginx + # kubernetes.io/tls-acme: 'true' + + ## Hostnames. + ## Must be provided if Ingress is enabled. + ## + # hosts: + # - pushgateway.domain.com + + ## TLS configuration. + ## Secrets must be manually created in the namespace. + ## + # tls: + # - secretName: pushgateway-tls + # hosts: + # - pushgateway.domain.com + +tolerations: [] + # - effect: NoSchedule + # operator: Exists + +## Node labels for pushgateway pod assignment +## Ref: https://kubernetes.io/docs/user-guide/node-selection/ +## +nodeSelector: {} + +replicaCount: 1 + +## When running more than one replica alongside with persistence, different volumes are needed +## per replica, since sharing a `persistence.file` across replicas does not keep metrics synced. +## For this purpose, you can enable the `runAsStatefulSet` to deploy the pushgateway as a +## StatefulSet instead of as a Deployment. +runAsStatefulSet: false + +## Security context to be added to push-gateway pods +## +securityContext: + fsGroup: 65534 + runAsUser: 65534 + runAsNonRoot: true + +## Security context to be added to push-gateway containers +## Having a separate variable as securityContext differs for pods and containers. +containerSecurityContext: {} +# allowPrivilegeEscalation: false +# readOnlyRootFilesystem: true +# runAsUser: 65534 +# runAsNonRoot: true + +## Affinity for pod assignment +## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity +affinity: {} + +## Topology spread constraints for pods +## Ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ +topologySpreadConstraints: [] + +# Enable this if you're using https://github.com/coreos/prometheus-operator +serviceMonitor: + enabled: false + namespace: monitoring + + # telemetryPath: HTTP resource path from which to fetch metrics. + # Telemetry path, default /metrics, has to be prefixed accordingly if pushgateway sets a route prefix at start-up. + # + telemetryPath: "/metrics" + + # Fallback to the prometheus default unless specified + # interval: 10s + + ## scheme: HTTP scheme to use for scraping. Can be used with `tlsConfig` for example if using istio mTLS. + # scheme: "" + + ## tlsConfig: TLS configuration to use when scraping the endpoint. For example if using istio mTLS. + ## Of type: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#tlsconfig + # tlsConfig: {} + + # bearerTokenFile: + # Fallback to the prometheus default unless specified + # scrapeTimeout: 30s + + ## Used to pass Labels that are used by the Prometheus installed in your cluster to select Service Monitors to work with + ## ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#prometheusspec + additionalLabels: {} + + # Retain the job and instance labels of the metrics pushed to the Pushgateway + # [Scraping Pushgateway](https://github.com/prometheus/pushgateway#configure-the-pushgateway-as-a-target-to-scrape) + honorLabels: true + + ## Metric relabel configs to apply to samples before ingestion. + ## [Metric Relabeling](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs) + metricRelabelings: [] + # - action: keep + # regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+' + # sourceLabels: [__name__] + + ## Relabel configs to apply to samples before ingestion. + ## [Relabeling](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config) + relabelings: [] + # - sourceLabels: [__meta_kubernetes_pod_node_name] + # separator: ; + # regex: ^(.*)$ + # targetLabel: nodename + # replacement: $1 + # action: replace + +# The values to set in the PodDisruptionBudget spec (minAvailable/maxUnavailable) +# If not set then a PodDisruptionBudget will not be created +podDisruptionBudget: {} + +priorityClassName: + +# Deployment Strategy type +strategy: + type: Recreate + +persistentVolume: + ## If true, pushgateway will create/use a Persistent Volume Claim + ## If false, use emptyDir + ## + enabled: false + + ## pushgateway data Persistent Volume access modes + ## Must match those of existing PV or dynamic provisioner + ## Ref: http://kubernetes.io/docs/user-guide/persistent-volumes/ + ## + accessModes: + - ReadWriteOnce + + ## pushgateway data Persistent Volume Claim annotations + ## + annotations: {} + + ## pushgateway data Persistent Volume existing claim name + ## Requires pushgateway.persistentVolume.enabled: true + ## If defined, PVC must be created manually before volume will be bound + existingClaim: "" + + ## pushgateway data Persistent Volume mount root path + ## + mountPath: /data + + ## pushgateway data Persistent Volume size + ## + size: 2Gi + + ## pushgateway data Persistent Volume Storage Class + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is + ## set, choosing the default provisioner. (gp2 on AWS, standard on + ## GKE, AWS & OpenStack) + ## + # storageClass: "-" + + ## Subdirectory of pushgateway data Persistent Volume to mount + ## Useful if the volume's root directory is not empty + ## + subPath: "" + +extraVolumes: [] + # - name: extra + # emptyDir: {} +extraVolumeMounts: [] + # - name: extra + # mountPath: /usr/share/extras + # readOnly: true + +# Configuration for clusters with restrictive network policies in place: +# - allowAll allows access to the PushGateway from any namespace +# - customSelector is a list of pod/namespaceSelectors to allow access from +# These options are mutually exclusive and the latter will take precedence. +networkPolicy: {} + # allowAll: true + # customSelectors: + # - namespaceSelector: + # matchLabels: + # type: admin + # - podSelector: + # matchLabels: + # app: myapp diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/NOTES.txt new file mode 100644 index 0000000..fc03c2a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/NOTES.txt @@ -0,0 +1,113 @@ +The Prometheus server can be accessed via port {{ .Values.server.service.servicePort }} on the following DNS name from within your cluster: +{{ template "prometheus.server.fullname" . }}.{{ .Release.Namespace }}.svc.cluster.local + +{{ if .Values.server.ingress.enabled -}} +From outside the cluster, the server URL(s) are: +{{- range .Values.server.ingress.hosts }} +http://{{ . }} +{{- end }} +{{- else }} +Get the Prometheus server URL by running these commands in the same shell: +{{- if contains "NodePort" .Values.server.service.type }} + export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ template "prometheus.server.fullname" . }}) + export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}") + echo http://$NODE_IP:$NODE_PORT +{{- else if contains "LoadBalancer" .Values.server.service.type }} + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + You can watch the status of by running 'kubectl get svc --namespace {{ .Release.Namespace }} -w {{ template "prometheus.server.fullname" . }}' + + export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ template "prometheus.server.fullname" . }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}') + echo http://$SERVICE_IP:{{ .Values.server.service.servicePort }} +{{- else if contains "ClusterIP" .Values.server.service.type }} + export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "prometheus.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") + kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 9090 +{{- end }} + + +{{- if .Values.server.persistentVolume.enabled }} +{{- else }} +################################################################################# +###### WARNING: Persistence is disabled!!! You will lose your data when ##### +###### the Server pod is terminated. ##### +################################################################################# +{{- end }} +{{- end }} + +{{ if .Values.alertmanager.enabled }} +The Prometheus alertmanager can be accessed via port {{ .Values.alertmanager.service.port }} on the following DNS name from within your cluster: +{{ template "prometheus.alertmanager.fullname" . }}.{{ .Release.Namespace }}.svc.cluster.local + +{{ if .Values.alertmanager.ingress.enabled -}} +From outside the cluster, the alertmanager URL(s) are: +{{- range .Values.alertmanager.ingress.hosts }} +http://{{ . }} +{{- end }} +{{- else }} +Get the Alertmanager URL by running these commands in the same shell: +{{- if contains "NodePort" .Values.alertmanager.service.type }} + export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ template "prometheus.alertmanager.fullname" . }}) + export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}") + echo http://$NODE_IP:$NODE_PORT +{{- else if contains "LoadBalancer" .Values.alertmanager.service.type }} + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + You can watch the status of by running 'kubectl get svc --namespace {{ .Release.Namespace }} -w {{ template "prometheus.alertmanager.fullname" . }}' + + export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ template "prometheus.alertmanager.fullname" . }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}') + echo http://$SERVICE_IP:{{ .Values.alertmanager.service.servicePort }} +{{- else if contains "ClusterIP" .Values.alertmanager.service.type }} + export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "alertmanager.name" .Subcharts.alertmanager }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") + kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 9093 +{{- end }} +{{- end }} + +{{- if .Values.alertmanager.persistence.enabled }} +{{- else }} +################################################################################# +###### WARNING: Persistence is disabled!!! You will lose your data when ##### +###### the AlertManager pod is terminated. ##### +################################################################################# +{{- end }} +{{- end }} + +{{- if (index .Values "prometheus-node-exporter" "enabled") }} +################################################################################# +###### WARNING: Pod Security Policy has been disabled by default since ##### +###### it deprecated after k8s 1.25+. use ##### +###### (index .Values "prometheus-node-exporter" "rbac" ##### +###### . "pspEnabled") with (index .Values ##### +###### "prometheus-node-exporter" "rbac" "pspAnnotations") ##### +###### in case you still need it. ##### +################################################################################# +{{- end }} + +{{ if (index .Values "prometheus-pushgateway" "enabled") }} +The Prometheus PushGateway can be accessed via port {{ index .Values "prometheus-pushgateway" "service" "port" }} on the following DNS name from within your cluster: +{{ include "prometheus-pushgateway.fullname" (index .Subcharts "prometheus-pushgateway") }}.{{ .Release.Namespace }}.svc.cluster.local + +{{ if (index .Values "prometheus-pushgateway" "ingress" "enabled") -}} +From outside the cluster, the pushgateway URL(s) are: +{{- range (index .Values "prometheus-pushgateway" "ingress" "hosts") }} +http://{{ . }} +{{- end }} +{{- else }} +Get the PushGateway URL by running these commands in the same shell: +{{- $pushgateway_svc_type := index .Values "prometheus-pushgateway" "service" "type" -}} +{{- if contains "NodePort" $pushgateway_svc_type }} + export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "prometheus-pushgateway.fullname" (index .Subcharts "prometheus-pushgateway") }}) + export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}") + echo http://$NODE_IP:$NODE_PORT +{{- else if contains "LoadBalancer" $pushgateway_svc_type }} + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + You can watch the status of by running 'kubectl get svc --namespace {{ .Release.Namespace }} -w {{ include "prometheus-pushgateway.fullname" (index .Subcharts "prometheus-pushgateway") }}' + + export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "prometheus-pushgateway.fullname" (index .Subcharts "prometheus-pushgateway") }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}') + echo http://$SERVICE_IP:{{ index .Values "prometheus-pushgateway" "service" "port" }} +{{- else if contains "ClusterIP" $pushgateway_svc_type }} + export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app={{ include "prometheus.name" (index .Subcharts "prometheus-pushgateway") }},component=pushgateway" -o jsonpath="{.items[0].metadata.name}") + kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 9091 +{{- end }} +{{- end }} +{{- end }} + +For more information on running Prometheus, visit: +https://prometheus.io/ diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/_helpers.tpl new file mode 100644 index 0000000..0810e3c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/_helpers.tpl @@ -0,0 +1,234 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "prometheus.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "prometheus.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create labels for prometheus +*/}} +{{- define "prometheus.common.matchLabels" -}} +app.kubernetes.io/name: {{ include "prometheus.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end -}} + +{{/* +Create unified labels for prometheus components +*/}} +{{- define "prometheus.common.metaLabels" -}} +app.kubernetes.io/version: {{ .Chart.AppVersion }} +helm.sh/chart: {{ include "prometheus.chart" . }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +app.kubernetes.io/part-of: {{ include "prometheus.name" . }} +{{- with .Values.commonMetaLabels}} +{{ toYaml . }} +{{- end }} +{{- end -}} + +{{- define "prometheus.server.labels" -}} +{{ include "prometheus.server.matchLabels" . }} +{{ include "prometheus.common.metaLabels" . }} +{{- end -}} + +{{- define "prometheus.server.matchLabels" -}} +app.kubernetes.io/component: {{ .Values.server.name }} +{{ include "prometheus.common.matchLabels" . }} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "prometheus.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Create a fully qualified ClusterRole name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "prometheus.clusterRoleName" -}} +{{- if .Values.server.clusterRoleNameOverride -}} +{{ .Values.server.clusterRoleNameOverride | trunc 63 | trimSuffix "-" }} +{{- else -}} +{{ include "prometheus.server.fullname" . }} +{{- end -}} +{{- end -}} + +{{/* +Create a fully qualified alertmanager name for communicating with the user via NOTES.txt +*/}} +{{- define "prometheus.alertmanager.fullname" -}} +{{- template "alertmanager.fullname" .Subcharts.alertmanager -}} +{{- end -}} + +{{/* +Create a fully qualified Prometheus server name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "prometheus.server.fullname" -}} +{{- if .Values.server.fullnameOverride -}} +{{- .Values.server.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- printf "%s-%s" .Release.Name .Values.server.name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s-%s" .Release.Name $name .Values.server.name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Get KubeVersion removing pre-release information. +*/}} +{{- define "prometheus.kubeVersion" -}} + {{- default .Capabilities.KubeVersion.Version (regexFind "v[0-9]+\\.[0-9]+\\.[0-9]+" .Capabilities.KubeVersion.Version) -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for deployment. +*/}} +{{- define "prometheus.deployment.apiVersion" -}} +{{- print "apps/v1" -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for networkpolicy. +*/}} +{{- define "prometheus.networkPolicy.apiVersion" -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for poddisruptionbudget. +*/}} +{{- define "prometheus.podDisruptionBudget.apiVersion" -}} +{{- if .Capabilities.APIVersions.Has "policy/v1" }} +{{- print "policy/v1" -}} +{{- else -}} +{{- print "policy/v1beta1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for rbac. +*/}} +{{- define "rbac.apiVersion" -}} +{{- if .Capabilities.APIVersions.Has "rbac.authorization.k8s.io/v1" }} +{{- print "rbac.authorization.k8s.io/v1" -}} +{{- else -}} +{{- print "rbac.authorization.k8s.io/v1beta1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "ingress.apiVersion" -}} + {{- if and (.Capabilities.APIVersions.Has "networking.k8s.io/v1") (semverCompare ">= 1.19.x" (include "prometheus.kubeVersion" .)) -}} + {{- print "networking.k8s.io/v1" -}} + {{- else if .Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" -}} + {{- print "networking.k8s.io/v1beta1" -}} + {{- else -}} + {{- print "extensions/v1beta1" -}} + {{- end -}} +{{- end -}} + +{{/* +Return if ingress is stable. +*/}} +{{- define "ingress.isStable" -}} + {{- eq (include "ingress.apiVersion" .) "networking.k8s.io/v1" -}} +{{- end -}} + +{{/* +Return if ingress supports ingressClassName. +*/}} +{{- define "ingress.supportsIngressClassName" -}} + {{- or (eq (include "ingress.isStable" .) "true") (and (eq (include "ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18.x" (include "prometheus.kubeVersion" .))) -}} +{{- end -}} + +{{/* +Return if ingress supports pathType. +*/}} +{{- define "ingress.supportsPathType" -}} + {{- or (eq (include "ingress.isStable" .) "true") (and (eq (include "ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18.x" (include "prometheus.kubeVersion" .))) -}} +{{- end -}} + +{{/* +Create the name of the service account to use for the server component +*/}} +{{- define "prometheus.serviceAccountName.server" -}} +{{- if .Values.serviceAccounts.server.create -}} + {{ default (include "prometheus.server.fullname" .) .Values.serviceAccounts.server.name }} +{{- else -}} + {{ default "default" .Values.serviceAccounts.server.name }} +{{- end -}} +{{- end -}} + +{{/* +Define the prometheus.namespace template if set with forceNamespace or .Release.Namespace is set +*/}} +{{- define "prometheus.namespace" -}} + {{- default .Release.Namespace .Values.forceNamespace -}} +{{- end }} + +{{/* +Define template prometheus.namespaces producing a list of namespaces to monitor +*/}} +{{- define "prometheus.namespaces" -}} +{{- $namespaces := list }} +{{- if and .Values.rbac.create .Values.server.useExistingClusterRoleName }} + {{- if .Values.server.namespaces -}} + {{- range $ns := join "," .Values.server.namespaces | split "," }} + {{- $namespaces = append $namespaces (tpl $ns $) }} + {{- end -}} + {{- end -}} + {{- if .Values.server.releaseNamespace -}} + {{- $namespaces = append $namespaces (include "prometheus.namespace" .) }} + {{- end -}} +{{- end -}} +{{ mustToJson $namespaces }} +{{- end -}} + +{{/* +Define prometheus.server.remoteWrite producing a list of remoteWrite configurations with URL templating +*/}} +{{- define "prometheus.server.remoteWrite" -}} +{{- $remoteWrites := list }} +{{- range $remoteWrite := .Values.server.remoteWrite }} + {{- $remoteWrites = tpl $remoteWrite.url $ | set $remoteWrite "url" | append $remoteWrites }} +{{- end -}} +{{ toYaml $remoteWrites }} +{{- end -}} + +{{/* +Define prometheus.server.remoteRead producing a list of remoteRead configurations with URL templating +*/}} +{{- define "prometheus.server.remoteRead" -}} +{{- $remoteReads := list }} +{{- range $remoteRead := .Values.server.remoteRead }} + {{- $remoteReads = tpl $remoteRead.url $ | set $remoteRead "url" | append $remoteReads }} +{{- end -}} +{{ toYaml $remoteReads }} +{{- end -}} + diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/clusterrole.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/clusterrole.yaml new file mode 100644 index 0000000..25e3cec --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/clusterrole.yaml @@ -0,0 +1,56 @@ +{{- if and .Values.rbac.create (empty .Values.server.useExistingClusterRoleName) -}} +apiVersion: {{ template "rbac.apiVersion" . }} +kind: ClusterRole +metadata: + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} + name: {{ include "prometheus.clusterRoleName" . }} +rules: +{{- if and .Values.podSecurityPolicy.enabled (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") }} + - apiGroups: + - extensions + resources: + - podsecuritypolicies + verbs: + - use + resourceNames: + - {{ template "prometheus.server.fullname" . }} +{{- end }} + - apiGroups: + - "" + resources: + - nodes + - nodes/proxy + - nodes/metrics + - services + - endpoints + - pods + - ingresses + - configmaps + verbs: + - get + - list + - watch + - apiGroups: + - "extensions" + - "networking.k8s.io" + resources: + - ingresses/status + - ingresses + verbs: + - get + - list + - watch + - apiGroups: + - "discovery.k8s.io" + resources: + - endpointslices + verbs: + - get + - list + - watch + - nonResourceURLs: + - "/metrics" + verbs: + - get +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/clusterrolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/clusterrolebinding.yaml new file mode 100644 index 0000000..28f4bda --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/clusterrolebinding.yaml @@ -0,0 +1,16 @@ +{{- if and .Values.rbac.create (empty .Values.server.namespaces) (empty .Values.server.useExistingClusterRoleName) -}} +apiVersion: {{ template "rbac.apiVersion" . }} +kind: ClusterRoleBinding +metadata: + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} + name: {{ include "prometheus.clusterRoleName" . }} +subjects: + - kind: ServiceAccount + name: {{ template "prometheus.serviceAccountName.server" . }} + namespace: {{ include "prometheus.namespace" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "prometheus.clusterRoleName" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/cm.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/cm.yaml new file mode 100644 index 0000000..c670666 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/cm.yaml @@ -0,0 +1,99 @@ +{{- if (empty .Values.server.configMapOverrideName) -}} +apiVersion: v1 +kind: ConfigMap +metadata: + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} + {{- with .Values.server.extraConfigmapLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ template "prometheus.server.fullname" . }} + namespace: {{ include "prometheus.namespace" . }} +data: + allow-snippet-annotations: "false" +{{- $root := . -}} +{{- range $key, $value := .Values.ruleFiles }} + {{ $key }}: {{- toYaml $value | indent 2 }} +{{- end }} +{{- range $key, $value := .Values.serverFiles }} + {{ $key }}: | +{{- if eq $key "prometheus.yml" }} + global: +{{ $root.Values.server.global | toYaml | trimSuffix "\n" | indent 6 }} +{{- if $root.Values.server.remoteWrite }} + remote_write: +{{- include "prometheus.server.remoteWrite" $root | nindent 4 }} +{{- end }} +{{- if $root.Values.server.remoteRead }} + remote_read: +{{- include "prometheus.server.remoteRead" $root | nindent 4 }} +{{- end }} +{{- if or $root.Values.server.tsdb $root.Values.server.exemplars }} + storage: +{{- if $root.Values.server.tsdb }} + tsdb: +{{ $root.Values.server.tsdb | toYaml | indent 8 }} +{{- end }} +{{- if $root.Values.server.exemplars }} + exemplars: +{{ $root.Values.server.exemplars | toYaml | indent 8 }} +{{- end }} +{{- end }} +{{- if $root.Values.scrapeConfigFiles }} + scrape_config_files: +{{ toYaml $root.Values.scrapeConfigFiles | indent 4 }} +{{- end }} +{{- end }} +{{- if eq $key "alerts" }} +{{- if and (not (empty $value)) (empty $value.groups) }} + groups: +{{- range $ruleKey, $ruleValue := $value }} + - name: {{ $ruleKey -}}.rules + rules: +{{ $ruleValue | toYaml | trimSuffix "\n" | indent 6 }} +{{- end }} +{{- else }} +{{ toYaml $value | indent 4 }} +{{- end }} +{{- else }} +{{ toYaml $value | default "{}" | indent 4 }} +{{- end }} +{{- if eq $key "prometheus.yml" -}} +{{- if $root.Values.extraScrapeConfigs }} +{{ tpl $root.Values.extraScrapeConfigs $root | indent 4 }} +{{- end -}} +{{- if or ($root.Values.alertmanager.enabled) ($root.Values.server.alertmanagers) }} + alerting: +{{- if $root.Values.alertRelabelConfigs }} +{{ $root.Values.alertRelabelConfigs | toYaml | trimSuffix "\n" | indent 6 }} +{{- end }} + alertmanagers: +{{- if $root.Values.server.alertmanagers }} +{{ toYaml $root.Values.server.alertmanagers | indent 8 }} +{{- else }} + - kubernetes_sd_configs: + - role: pod + tls_config: + ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token + {{- if $root.Values.alertmanager.prefixURL }} + path_prefix: {{ $root.Values.alertmanager.prefixURL }} + {{- end }} + relabel_configs: + - source_labels: [__meta_kubernetes_namespace] + regex: {{ $root.Release.Namespace }} + action: keep + - source_labels: [__meta_kubernetes_pod_label_app_kubernetes_io_instance] + regex: {{ $root.Release.Name }} + action: keep + - source_labels: [__meta_kubernetes_pod_label_app_kubernetes_io_name] + regex: {{ default "alertmanager" $root.Values.alertmanager.nameOverride | trunc 63 | trimSuffix "-" }} + action: keep + - source_labels: [__meta_kubernetes_pod_container_port_number] + regex: "9093" + action: keep +{{- end -}} +{{- end -}} +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/deploy.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/deploy.yaml new file mode 100644 index 0000000..93f93c4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/deploy.yaml @@ -0,0 +1,363 @@ +{{- if not .Values.server.statefulSet.enabled -}} +apiVersion: {{ template "prometheus.deployment.apiVersion" . }} +kind: Deployment +metadata: +{{- if .Values.server.deploymentAnnotations }} + annotations: + {{ toYaml .Values.server.deploymentAnnotations | nindent 4 }} +{{- end }} + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} + name: {{ template "prometheus.server.fullname" . }} + namespace: {{ include "prometheus.namespace" . }} +spec: + selector: + matchLabels: + {{- include "prometheus.server.matchLabels" . | nindent 6 }} + replicas: {{ .Values.server.replicaCount }} + revisionHistoryLimit: {{ .Values.server.revisionHistoryLimit }} + {{- if .Values.server.strategy }} + strategy: +{{ toYaml .Values.server.strategy | trim | indent 4 }} + {{ if eq .Values.server.strategy.type "Recreate" }}rollingUpdate: null{{ end }} +{{- end }} + template: + metadata: + {{- if .Values.server.podAnnotations }} + annotations: + {{ toYaml .Values.server.podAnnotations | nindent 8 }} + {{- end }} + labels: + {{- include "prometheus.server.labels" . | nindent 8 }} + {{- if .Values.server.podLabels}} + {{ toYaml .Values.server.podLabels | nindent 8 }} + {{- end}} + spec: +{{- if .Values.server.priorityClassName }} + priorityClassName: "{{ .Values.server.priorityClassName }}" +{{- end }} +{{- if .Values.server.schedulerName }} + schedulerName: "{{ .Values.server.schedulerName }}" +{{- end }} +{{- if semverCompare ">=1.13-0" .Capabilities.KubeVersion.GitVersion }} + {{- if or (.Values.server.enableServiceLinks) (eq (.Values.server.enableServiceLinks | toString) "") }} + enableServiceLinks: true + {{- else }} + enableServiceLinks: false + {{- end }} +{{- end }} + serviceAccountName: {{ template "prometheus.serviceAccountName.server" . }} +{{- if kindIs "bool" .Values.server.automountServiceAccountToken }} + automountServiceAccountToken: {{ .Values.server.automountServiceAccountToken }} +{{- end }} + {{- if .Values.server.extraInitContainers }} + initContainers: +{{ toYaml .Values.server.extraInitContainers | indent 8 }} + {{- end }} + containers: + {{- if .Values.configmapReload.prometheus.enabled }} + - name: {{ template "prometheus.name" . }}-{{ .Values.server.name }}-{{ .Values.configmapReload.prometheus.name }} + {{- if .Values.configmapReload.prometheus.image.digest }} + image: "{{ .Values.configmapReload.prometheus.image.repository }}@{{ .Values.configmapReload.prometheus.image.digest }}" + {{- else }} + image: "{{ .Values.configmapReload.prometheus.image.repository }}:{{ .Values.configmapReload.prometheus.image.tag }}" + {{- end }} + imagePullPolicy: "{{ .Values.configmapReload.prometheus.image.pullPolicy }}" + {{- with .Values.configmapReload.prometheus.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + args: + - --watched-dir=/etc/config + {{- $default_url := "http://127.0.0.1:9090/-/reload" }} + {{- with .Values.server.prefixURL }} + {{- $default_url = printf "http://127.0.0.1:9090%s/-/reload" . }} + {{- end }} + - --reload-url={{ default $default_url .Values.configmapReload.reloadUrl }} + {{- range $key, $value := .Values.configmapReload.prometheus.extraArgs }} + - --{{ $key }}={{ $value }} + {{- end }} + {{- range .Values.configmapReload.prometheus.extraVolumeDirs }} + - --watched-dir={{ . }} + {{- end }} + {{- with .Values.configmapReload.env }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.configmapReload.prometheus.containerPort }} + ports: + - containerPort: {{ .Values.configmapReload.prometheus.containerPort }} + {{- end }} + {{- with .Values.configmapReload.prometheus.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - name: config-volume + mountPath: /etc/config + readOnly: true + {{- range .Values.configmapReload.prometheus.extraConfigmapMounts }} + - name: {{ $.Values.configmapReload.prometheus.name }}-{{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath }} + readOnly: {{ .readOnly }} + {{- end }} + {{- with .Values.configmapReload.prometheus.extraVolumeMounts }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- end }} + + - name: {{ template "prometheus.name" . }}-{{ .Values.server.name }} + {{- if .Values.server.image.digest }} + image: "{{ .Values.server.image.repository }}@{{ .Values.server.image.digest }}" + {{- else }} + image: "{{ .Values.server.image.repository }}:{{ .Values.server.image.tag | default .Chart.AppVersion}}" + {{- end }} + imagePullPolicy: "{{ .Values.server.image.pullPolicy }}" + {{- with .Values.server.command }} + command: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.server.env }} + env: +{{ toYaml .Values.server.env | indent 12}} + {{- end }} + args: + {{- if .Values.server.defaultFlagsOverride }} + {{ toYaml .Values.server.defaultFlagsOverride | nindent 12}} + {{- else }} + {{- if .Values.server.retention }} + - --storage.tsdb.retention.time={{ .Values.server.retention }} + {{- end }} + {{- if .Values.server.retentionSize }} + - --storage.tsdb.retention.size={{ .Values.server.retentionSize }} + {{- end }} + - --config.file={{ .Values.server.configPath }} + {{- if .Values.server.storagePath }} + - --storage.tsdb.path={{ .Values.server.storagePath }} + {{- else }} + - --storage.tsdb.path={{ .Values.server.persistentVolume.mountPath }} + {{- end }} + - --web.console.libraries=/etc/prometheus/console_libraries + - --web.console.templates=/etc/prometheus/consoles + {{- range .Values.server.extraFlags }} + - --{{ . }} + {{- end }} + {{- range $key, $value := .Values.server.extraArgs }} + - --{{ $key }}={{ $value }} + {{- end }} + {{- if .Values.server.prefixURL }} + - --web.route-prefix={{ .Values.server.prefixURL }} + {{- end }} + {{- if .Values.server.baseURL }} + - --web.external-url={{ .Values.server.baseURL }} + {{- end }} + {{- end }} + ports: + - containerPort: 9090 + {{- if .Values.server.portName }} + name: {{ .Values.server.portName }} + {{- end }} + {{- if .Values.server.hostPort }} + hostPort: {{ .Values.server.hostPort }} + {{- end }} + readinessProbe: + {{- if not .Values.server.tcpSocketProbeEnabled }} + httpGet: + path: {{ .Values.server.prefixURL }}/-/ready + port: 9090 + scheme: {{ .Values.server.probeScheme }} + {{- with .Values.server.probeHeaders }} + httpHeaders: +{{- toYaml . | nindent 14 }} + {{- end }} + {{- else }} + tcpSocket: + port: 9090 + {{- end }} + initialDelaySeconds: {{ .Values.server.readinessProbeInitialDelay }} + periodSeconds: {{ .Values.server.readinessProbePeriodSeconds }} + timeoutSeconds: {{ .Values.server.readinessProbeTimeout }} + failureThreshold: {{ .Values.server.readinessProbeFailureThreshold }} + successThreshold: {{ .Values.server.readinessProbeSuccessThreshold }} + livenessProbe: + {{- if not .Values.server.tcpSocketProbeEnabled }} + httpGet: + path: {{ .Values.server.prefixURL }}/-/healthy + port: 9090 + scheme: {{ .Values.server.probeScheme }} + {{- with .Values.server.probeHeaders }} + httpHeaders: +{{- toYaml . | nindent 14 }} + {{- end }} + {{- else }} + tcpSocket: + port: 9090 + {{- end }} + initialDelaySeconds: {{ .Values.server.livenessProbeInitialDelay }} + periodSeconds: {{ .Values.server.livenessProbePeriodSeconds }} + timeoutSeconds: {{ .Values.server.livenessProbeTimeout }} + failureThreshold: {{ .Values.server.livenessProbeFailureThreshold }} + successThreshold: {{ .Values.server.livenessProbeSuccessThreshold }} + {{- if .Values.server.startupProbe.enabled }} + startupProbe: + {{- if not .Values.server.tcpSocketProbeEnabled }} + httpGet: + path: {{ .Values.server.prefixURL }}/-/healthy + port: 9090 + scheme: {{ .Values.server.probeScheme }} + {{- if .Values.server.probeHeaders }} + httpHeaders: + {{- range .Values.server.probeHeaders}} + - name: {{ .name }} + value: {{ .value }} + {{- end }} + {{- end }} + {{- else }} + tcpSocket: + port: 9090 + {{- end }} + failureThreshold: {{ .Values.server.startupProbe.failureThreshold }} + periodSeconds: {{ .Values.server.startupProbe.periodSeconds }} + timeoutSeconds: {{ .Values.server.startupProbe.timeoutSeconds }} + {{- end }} + {{- with .Values.server.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - name: config-volume + mountPath: /etc/config + - name: storage-volume + mountPath: {{ .Values.server.persistentVolume.mountPath }} + subPath: "{{ .Values.server.persistentVolume.subPath }}" + {{- range .Values.server.extraHostPathMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath }} + readOnly: {{ .readOnly }} + {{- end }} + {{- range .Values.server.extraConfigmapMounts }} + - name: {{ $.Values.server.name }}-{{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath }} + readOnly: {{ .readOnly }} + {{- end }} + {{- range .Values.server.extraSecretMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath }} + readOnly: {{ .readOnly }} + {{- end }} + {{- if .Values.server.extraVolumeMounts }} + {{ toYaml .Values.server.extraVolumeMounts | nindent 12 }} + {{- end }} + {{- with .Values.server.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.server.sidecarContainers }} + {{- range $name, $spec := .Values.server.sidecarContainers }} + - name: {{ $name }} + {{- if kindIs "string" $spec }} + {{- tpl $spec $ | nindent 10 }} + {{- else }} + {{- toYaml $spec | nindent 10 }} + {{- end }} + {{- end }} + {{- end }} + {{- if .Values.server.hostNetwork }} + hostNetwork: true + dnsPolicy: ClusterFirstWithHostNet + {{- else }} + dnsPolicy: {{ .Values.server.dnsPolicy }} + {{- end }} + {{- if .Values.imagePullSecrets }} + imagePullSecrets: +{{ toYaml .Values.imagePullSecrets | indent 8 }} + {{- end }} + {{- if .Values.server.nodeSelector }} + nodeSelector: +{{ toYaml .Values.server.nodeSelector | indent 8 }} + {{- end }} + {{- if .Values.server.hostAliases }} + hostAliases: +{{ toYaml .Values.server.hostAliases | indent 8 }} + {{- end }} + {{- if .Values.server.dnsConfig }} + dnsConfig: +{{ toYaml .Values.server.dnsConfig | indent 8 }} + {{- end }} + {{- with .Values.server.securityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.server.tolerations }} + tolerations: +{{ toYaml .Values.server.tolerations | indent 8 }} + {{- end }} + {{- if .Values.server.affinity }} + affinity: +{{ toYaml .Values.server.affinity | indent 8 }} + {{- end }} + {{- with .Values.server.topologySpreadConstraints }} + topologySpreadConstraints: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.server.terminationGracePeriodSeconds }} + volumes: + - name: config-volume + {{- if empty .Values.server.configFromSecret }} + configMap: + name: {{ if .Values.server.configMapOverrideName }}{{ .Release.Name }}-{{ .Values.server.configMapOverrideName }}{{- else }}{{ template "prometheus.server.fullname" . }}{{- end }} + {{- else }} + secret: + secretName: {{ .Values.server.configFromSecret }} + {{- end }} + {{- range .Values.server.extraHostPathMounts }} + - name: {{ .name }} + hostPath: + path: {{ .hostPath }} + {{- end }} + {{- range .Values.configmapReload.prometheus.extraConfigmapMounts }} + - name: {{ $.Values.configmapReload.prometheus.name }}-{{ .name }} + configMap: + name: {{ .configMap }} + {{- end }} + {{- range .Values.server.extraConfigmapMounts }} + - name: {{ $.Values.server.name }}-{{ .name }} + configMap: + name: {{ .configMap }} + {{- end }} + {{- range .Values.server.extraSecretMounts }} + - name: {{ .name }} + secret: + secretName: {{ .secretName }} + {{- with .optional }} + optional: {{ . }} + {{- end }} + {{- end }} + {{- range .Values.configmapReload.prometheus.extraConfigmapMounts }} + - name: {{ .name }} + configMap: + name: {{ .configMap }} + {{- with .optional }} + optional: {{ . }} + {{- end }} + {{- end }} +{{- if .Values.server.extraVolumes }} +{{ toYaml .Values.server.extraVolumes | indent 8}} +{{- end }} + - name: storage-volume + {{- if .Values.server.persistentVolume.enabled }} + persistentVolumeClaim: + claimName: {{ if .Values.server.persistentVolume.existingClaim }}{{ .Values.server.persistentVolume.existingClaim }}{{- else }}{{ template "prometheus.server.fullname" . }}{{- end }} + {{- else }} + emptyDir: + {{- if .Values.server.emptyDir.sizeLimit }} + sizeLimit: {{ .Values.server.emptyDir.sizeLimit }} + {{- else }} + {} + {{- end -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/extra-manifests.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/extra-manifests.yaml new file mode 100644 index 0000000..2b21b71 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/extra-manifests.yaml @@ -0,0 +1,4 @@ +{{ range .Values.extraManifests }} +--- +{{ tpl . $ }} +{{ end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/headless-svc.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/headless-svc.yaml new file mode 100644 index 0000000..df9db99 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/headless-svc.yaml @@ -0,0 +1,35 @@ +{{- if .Values.server.statefulSet.enabled -}} +apiVersion: v1 +kind: Service +metadata: +{{- if .Values.server.statefulSet.headless.annotations }} + annotations: +{{ toYaml .Values.server.statefulSet.headless.annotations | indent 4 }} +{{- end }} + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} +{{- if .Values.server.statefulSet.headless.labels }} +{{ toYaml .Values.server.statefulSet.headless.labels | indent 4 }} +{{- end }} + name: {{ template "prometheus.server.fullname" . }}-headless + namespace: {{ include "prometheus.namespace" . }} +spec: + clusterIP: None + ports: + - name: http + port: {{ .Values.server.statefulSet.headless.servicePort }} + protocol: TCP + targetPort: 9090 + {{- if .Values.server.statefulSet.headless.gRPC.enabled }} + - name: grpc + port: {{ .Values.server.statefulSet.headless.gRPC.servicePort }} + protocol: TCP + targetPort: 10901 + {{- if .Values.server.statefulSet.headless.gRPC.nodePort }} + nodePort: {{ .Values.server.statefulSet.headless.gRPC.nodePort }} + {{- end }} + {{- end }} + + selector: + {{- include "prometheus.server.matchLabels" . | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/ingress.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/ingress.yaml new file mode 100644 index 0000000..84341a9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/ingress.yaml @@ -0,0 +1,57 @@ +{{- if .Values.server.ingress.enabled -}} +{{- $ingressApiIsStable := eq (include "ingress.isStable" .) "true" -}} +{{- $ingressSupportsIngressClassName := eq (include "ingress.supportsIngressClassName" .) "true" -}} +{{- $ingressSupportsPathType := eq (include "ingress.supportsPathType" .) "true" -}} +{{- $releaseName := .Release.Name -}} +{{- $serviceName := include "prometheus.server.fullname" . }} +{{- $servicePort := .Values.server.ingress.servicePort | default .Values.server.service.servicePort -}} +{{- $ingressPath := .Values.server.ingress.path -}} +{{- $ingressPathType := .Values.server.ingress.pathType -}} +{{- $extraPaths := .Values.server.ingress.extraPaths -}} +apiVersion: {{ template "ingress.apiVersion" . }} +kind: Ingress +metadata: +{{- if .Values.server.ingress.annotations }} + annotations: +{{ toYaml .Values.server.ingress.annotations | indent 4 }} +{{- end }} + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} +{{- range $key, $value := .Values.server.ingress.extraLabels }} + {{ $key }}: {{ $value }} +{{- end }} + name: {{ template "prometheus.server.fullname" . }} + namespace: {{ include "prometheus.namespace" . }} +spec: + {{- if and $ingressSupportsIngressClassName .Values.server.ingress.ingressClassName }} + ingressClassName: {{ .Values.server.ingress.ingressClassName }} + {{- end }} + rules: + {{- range .Values.server.ingress.hosts }} + {{- $url := splitList "/" . }} + - host: {{ first $url }} + http: + paths: +{{ if $extraPaths }} +{{ toYaml $extraPaths | indent 10 }} +{{- end }} + - path: {{ $ingressPath }} + {{- if $ingressSupportsPathType }} + pathType: {{ $ingressPathType }} + {{- end }} + backend: + {{- if $ingressApiIsStable }} + service: + name: {{ $serviceName }} + port: + number: {{ $servicePort }} + {{- else }} + serviceName: {{ $serviceName }} + servicePort: {{ $servicePort }} + {{- end }} + {{- end -}} +{{- if .Values.server.ingress.tls }} + tls: +{{ toYaml .Values.server.ingress.tls | indent 4 }} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/network-policy.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/network-policy.yaml new file mode 100644 index 0000000..3254ffc --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/network-policy.yaml @@ -0,0 +1,16 @@ +{{- if .Values.networkPolicy.enabled }} +apiVersion: {{ template "prometheus.networkPolicy.apiVersion" . }} +kind: NetworkPolicy +metadata: + name: {{ template "prometheus.server.fullname" . }} + namespace: {{ include "prometheus.namespace" . }} + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} +spec: + podSelector: + matchLabels: + {{- include "prometheus.server.matchLabels" . | nindent 6 }} + ingress: + - ports: + - port: 9090 +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/pdb.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/pdb.yaml new file mode 100644 index 0000000..7ffe673 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/pdb.yaml @@ -0,0 +1,15 @@ +{{- if .Values.server.podDisruptionBudget.enabled }} +{{- $pdbSpec := omit .Values.server.podDisruptionBudget "enabled" }} +apiVersion: {{ template "prometheus.podDisruptionBudget.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ template "prometheus.server.fullname" . }} + namespace: {{ include "prometheus.namespace" . }} + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "prometheus.server.matchLabels" . | nindent 6 }} + {{- toYaml $pdbSpec | nindent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/psp.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/psp.yaml new file mode 100644 index 0000000..5776e25 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/psp.yaml @@ -0,0 +1,53 @@ +{{- if and .Values.rbac.create .Values.podSecurityPolicy.enabled }} +{{- if .Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy" }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ template "prometheus.server.fullname" . }} + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} + {{- with .Values.server.podSecurityPolicy.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + privileged: false + allowPrivilegeEscalation: false + allowedCapabilities: + - 'CHOWN' + volumes: + - 'configMap' + - 'persistentVolumeClaim' + - 'emptyDir' + - 'secret' + - 'hostPath' + allowedHostPaths: + - pathPrefix: /etc + readOnly: true + - pathPrefix: {{ .Values.server.persistentVolume.mountPath }} + {{- range .Values.server.extraHostPathMounts }} + - pathPrefix: {{ .hostPath }} + readOnly: {{ .readOnly }} + {{- end }} + hostNetwork: false + hostPID: false + hostIPC: false + runAsUser: + rule: 'RunAsAny' + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 1 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + # Forbid adding the root group. + - min: 1 + max: 65535 + readOnlyRootFilesystem: false +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/pvc.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/pvc.yaml new file mode 100644 index 0000000..a9dc4fc --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/pvc.yaml @@ -0,0 +1,43 @@ +{{- if not .Values.server.statefulSet.enabled -}} +{{- if .Values.server.persistentVolume.enabled -}} +{{- if not .Values.server.persistentVolume.existingClaim -}} +apiVersion: v1 +kind: PersistentVolumeClaim +metadata: + {{- if .Values.server.persistentVolume.annotations }} + annotations: +{{ toYaml .Values.server.persistentVolume.annotations | indent 4 }} + {{- end }} + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} + {{- with .Values.server.persistentVolume.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + name: {{ template "prometheus.server.fullname" . }} + namespace: {{ include "prometheus.namespace" . }} +spec: + accessModes: +{{ toYaml .Values.server.persistentVolume.accessModes | indent 4 }} +{{- if .Values.server.persistentVolume.storageClass }} +{{- if (eq "-" .Values.server.persistentVolume.storageClass) }} + storageClassName: "" +{{- else }} + storageClassName: "{{ .Values.server.persistentVolume.storageClass }}" +{{- end }} +{{- end }} +{{- if .Values.server.persistentVolume.volumeBindingMode }} + volumeBindingMode: "{{ .Values.server.persistentVolume.volumeBindingMode }}" +{{- end }} + resources: + requests: + storage: "{{ .Values.server.persistentVolume.size }}" +{{- if .Values.server.persistentVolume.selector }} + selector: + {{- toYaml .Values.server.persistentVolume.selector | nindent 4 }} +{{- end -}} +{{- if .Values.server.persistentVolume.volumeName }} + volumeName: "{{ .Values.server.persistentVolume.volumeName }}" +{{- end -}} +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/rolebinding.yaml new file mode 100644 index 0000000..721b388 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/rolebinding.yaml @@ -0,0 +1,18 @@ +{{- range include "prometheus.namespaces" . | fromJsonArray }} +--- +apiVersion: {{ template "rbac.apiVersion" $ }} +kind: RoleBinding +metadata: + labels: + {{- include "prometheus.server.labels" $ | nindent 4 }} + name: {{ template "prometheus.server.fullname" $ }} + namespace: {{ . }} +subjects: + - kind: ServiceAccount + name: {{ template "prometheus.serviceAccountName.server" $ }} + namespace: {{ include "prometheus.namespace" $ }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ $.Values.server.useExistingClusterRoleName }} +{{ end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/service.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/service.yaml new file mode 100644 index 0000000..069f327 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/service.yaml @@ -0,0 +1,63 @@ +{{- if .Values.server.service.enabled -}} +apiVersion: v1 +kind: Service +metadata: +{{- if .Values.server.service.annotations }} + annotations: +{{ toYaml .Values.server.service.annotations | indent 4 }} +{{- end }} + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} +{{- if .Values.server.service.labels }} +{{ toYaml .Values.server.service.labels | indent 4 }} +{{- end }} + name: {{ template "prometheus.server.fullname" . }} + namespace: {{ include "prometheus.namespace" . }} +spec: +{{- if .Values.server.service.clusterIP }} + clusterIP: {{ .Values.server.service.clusterIP }} +{{- end }} +{{- if .Values.server.service.externalIPs }} + externalIPs: +{{ toYaml .Values.server.service.externalIPs | indent 4 }} +{{- end }} +{{- if .Values.server.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.server.service.loadBalancerIP }} +{{- end }} +{{- if .Values.server.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- range $cidr := .Values.server.service.loadBalancerSourceRanges }} + - {{ $cidr }} + {{- end }} +{{- end }} + ports: + - name: http + port: {{ .Values.server.service.servicePort }} + protocol: TCP + targetPort: 9090 + {{- if .Values.server.service.nodePort }} + nodePort: {{ .Values.server.service.nodePort }} + {{- end }} + {{- if .Values.server.service.gRPC.enabled }} + - name: grpc + port: {{ .Values.server.service.gRPC.servicePort }} + protocol: TCP + targetPort: 10901 + {{- if .Values.server.service.gRPC.nodePort }} + nodePort: {{ .Values.server.service.gRPC.nodePort }} + {{- end }} + {{- end }} +{{- if .Values.server.service.additionalPorts }} +{{ toYaml .Values.server.service.additionalPorts | indent 4 }} +{{- end }} + selector: + {{- if and .Values.server.statefulSet.enabled .Values.server.service.statefulsetReplica.enabled }} + statefulset.kubernetes.io/pod-name: {{ template "prometheus.server.fullname" . }}-{{ .Values.server.service.statefulsetReplica.replica }} + {{- else -}} + {{- include "prometheus.server.matchLabels" . | nindent 4 }} +{{- if .Values.server.service.sessionAffinity }} + sessionAffinity: {{ .Values.server.service.sessionAffinity }} +{{- end }} + {{- end }} + type: "{{ .Values.server.service.type }}" +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/serviceaccount.yaml new file mode 100644 index 0000000..6d5ab0c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/serviceaccount.yaml @@ -0,0 +1,16 @@ +{{- if .Values.serviceAccounts.server.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} + name: {{ template "prometheus.serviceAccountName.server" . }} + namespace: {{ include "prometheus.namespace" . }} + annotations: +{{ toYaml .Values.serviceAccounts.server.annotations | indent 4 }} +{{- if kindIs "bool" .Values.server.automountServiceAccountToken }} +automountServiceAccountToken: {{ .Values.server.automountServiceAccountToken }} +{{- else if kindIs "bool" .Values.serviceAccounts.server.automountServiceAccountToken }} +automountServiceAccountToken: {{ .Values.serviceAccounts.server.automountServiceAccountToken }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/sts.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/sts.yaml new file mode 100644 index 0000000..63851c4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/sts.yaml @@ -0,0 +1,385 @@ +{{- if .Values.server.statefulSet.enabled -}} +apiVersion: apps/v1 +kind: StatefulSet +metadata: +{{- if .Values.server.statefulSet.annotations }} + annotations: + {{ toYaml .Values.server.statefulSet.annotations | nindent 4 }} +{{- end }} + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} + {{- if .Values.server.statefulSet.labels}} + {{ toYaml .Values.server.statefulSet.labels | nindent 4 }} + {{- end}} + name: {{ template "prometheus.server.fullname" . }} + namespace: {{ include "prometheus.namespace" . }} +spec: + {{- if semverCompare ">= 1.27.x" (include "prometheus.kubeVersion" .) }} + persistentVolumeClaimRetentionPolicy: + whenDeleted: {{ ternary "Delete" "Retain" .Values.server.statefulSet.pvcDeleteOnStsDelete }} + whenScaled: {{ ternary "Delete" "Retain" .Values.server.statefulSet.pvcDeleteOnStsScale }} + {{- end }} + serviceName: {{ template "prometheus.server.fullname" . }}-headless + selector: + matchLabels: + {{- include "prometheus.server.matchLabels" . | nindent 6 }} + replicas: {{ .Values.server.replicaCount }} + revisionHistoryLimit: {{ .Values.server.revisionHistoryLimit }} + podManagementPolicy: {{ .Values.server.statefulSet.podManagementPolicy }} + template: + metadata: + {{- if .Values.server.podAnnotations }} + annotations: + {{ toYaml .Values.server.podAnnotations | nindent 8 }} + {{- end }} + labels: + {{- include "prometheus.server.labels" . | nindent 8 }} + {{- if .Values.server.podLabels}} + {{ toYaml .Values.server.podLabels | nindent 8 }} + {{- end}} + spec: +{{- if .Values.server.priorityClassName }} + priorityClassName: "{{ .Values.server.priorityClassName }}" +{{- end }} +{{- if .Values.server.schedulerName }} + schedulerName: "{{ .Values.server.schedulerName }}" +{{- end }} +{{- if semverCompare ">=1.13-0" .Capabilities.KubeVersion.GitVersion }} + {{- if or (.Values.server.enableServiceLinks) (eq (.Values.server.enableServiceLinks | toString) "") }} + enableServiceLinks: true + {{- else }} + enableServiceLinks: false + {{- end }} +{{- end }} + serviceAccountName: {{ template "prometheus.serviceAccountName.server" . }} +{{- if kindIs "bool" .Values.server.automountServiceAccountToken }} + automountServiceAccountToken: {{ .Values.server.automountServiceAccountToken }} +{{- end }} + {{- if .Values.server.extraInitContainers }} + initContainers: +{{ toYaml .Values.server.extraInitContainers | indent 8 }} + {{- end }} + containers: + {{- if .Values.configmapReload.prometheus.enabled }} + - name: {{ template "prometheus.name" . }}-{{ .Values.server.name }}-{{ .Values.configmapReload.prometheus.name }} + {{- if .Values.configmapReload.prometheus.image.digest }} + image: "{{ .Values.configmapReload.prometheus.image.repository }}@{{ .Values.configmapReload.prometheus.image.digest }}" + {{- else }} + image: "{{ .Values.configmapReload.prometheus.image.repository }}:{{ .Values.configmapReload.prometheus.image.tag }}" + {{- end }} + imagePullPolicy: "{{ .Values.configmapReload.prometheus.image.pullPolicy }}" + {{- with .Values.configmapReload.prometheus.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + args: + - --watched-dir=/etc/config + {{- $default_url := "http://127.0.0.1:9090/-/reload" }} + {{- with .Values.server.prefixURL }} + {{- $default_url = printf "http://127.0.0.1:9090%s/-/reload" . }} + {{- end }} + - --reload-url={{ default $default_url .Values.configmapReload.reloadUrl }} + {{- range $key, $value := .Values.configmapReload.prometheus.extraArgs }} + - --{{ $key }}={{ $value }} + {{- end }} + {{- range .Values.configmapReload.prometheus.extraVolumeDirs }} + - --watched-dir={{ . }} + {{- end }} + {{- with .Values.configmapReload.env }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.configmapReload.prometheus.containerPort }} + ports: + - containerPort: {{ .Values.configmapReload.prometheus.containerPort }} + {{- end }} + {{- with .Values.configmapReload.prometheus.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - name: config-volume + mountPath: /etc/config + readOnly: true + {{- range .Values.configmapReload.prometheus.extraConfigmapMounts }} + - name: {{ $.Values.configmapReload.prometheus.name }}-{{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath }} + readOnly: {{ .readOnly }} + {{- end }} + {{- end }} + + - name: {{ template "prometheus.name" . }}-{{ .Values.server.name }} + {{- if .Values.server.image.digest }} + image: "{{ .Values.server.image.repository }}@{{ .Values.server.image.digest }}" + {{- else }} + image: "{{ .Values.server.image.repository }}:{{ .Values.server.image.tag | default .Chart.AppVersion }}" + {{- end }} + imagePullPolicy: "{{ .Values.server.image.pullPolicy }}" + {{- with .Values.server.command }} + command: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.server.env }} + env: +{{ toYaml .Values.server.env | indent 12}} + {{- end }} + args: + {{- if .Values.server.defaultFlagsOverride }} + {{ toYaml .Values.server.defaultFlagsOverride | nindent 12}} + {{- else }} + {{- if .Values.server.prefixURL }} + - --web.route-prefix={{ .Values.server.prefixURL }} + {{- end }} + {{- if .Values.server.retention }} + - --storage.tsdb.retention.time={{ .Values.server.retention }} + {{- end }} + {{- if .Values.server.retentionSize }} + - --storage.tsdb.retention.size={{ .Values.server.retentionSize }} + {{- end }} + - --config.file={{ .Values.server.configPath }} + {{- if .Values.server.storagePath }} + - --storage.tsdb.path={{ .Values.server.storagePath }} + {{- else }} + - --storage.tsdb.path={{ .Values.server.persistentVolume.mountPath }} + {{- end }} + - --web.console.libraries=/etc/prometheus/console_libraries + - --web.console.templates=/etc/prometheus/consoles + {{- range .Values.server.extraFlags }} + - --{{ . }} + {{- end }} + {{- range $key, $value := .Values.server.extraArgs }} + - --{{ $key }}={{ $value }} + {{- end }} + {{- if .Values.server.baseURL }} + - --web.external-url={{ .Values.server.baseURL }} + {{- end }} + {{- end }} + ports: + - containerPort: 9090 + {{- if .Values.server.portName }} + name: {{ .Values.server.portName }} + {{- end }} + {{- if .Values.server.hostPort }} + hostPort: {{ .Values.server.hostPort }} + {{- end }} + readinessProbe: + {{- if not .Values.server.tcpSocketProbeEnabled }} + httpGet: + path: {{ .Values.server.prefixURL }}/-/ready + port: 9090 + scheme: {{ .Values.server.probeScheme }} + {{- with .Values.server.probeHeaders }} + httpHeaders: +{{- toYaml . | nindent 14 }} + {{- end }} + {{- else }} + tcpSocket: + port: 9090 + {{- end }} + initialDelaySeconds: {{ .Values.server.readinessProbeInitialDelay }} + periodSeconds: {{ .Values.server.readinessProbePeriodSeconds }} + timeoutSeconds: {{ .Values.server.readinessProbeTimeout }} + failureThreshold: {{ .Values.server.readinessProbeFailureThreshold }} + successThreshold: {{ .Values.server.readinessProbeSuccessThreshold }} + livenessProbe: + {{- if not .Values.server.tcpSocketProbeEnabled }} + httpGet: + path: {{ .Values.server.prefixURL }}/-/healthy + port: 9090 + scheme: {{ .Values.server.probeScheme }} + {{- with .Values.server.probeHeaders }} + httpHeaders: +{{- toYaml . | nindent 14 }} + {{- end }} + {{- else }} + tcpSocket: + port: 9090 + {{- end }} + initialDelaySeconds: {{ .Values.server.livenessProbeInitialDelay }} + periodSeconds: {{ .Values.server.livenessProbePeriodSeconds }} + timeoutSeconds: {{ .Values.server.livenessProbeTimeout }} + failureThreshold: {{ .Values.server.livenessProbeFailureThreshold }} + successThreshold: {{ .Values.server.livenessProbeSuccessThreshold }} + {{- if .Values.server.startupProbe.enabled }} + startupProbe: + {{- if not .Values.server.tcpSocketProbeEnabled }} + httpGet: + path: {{ .Values.server.prefixURL }}/-/healthy + port: 9090 + scheme: {{ .Values.server.probeScheme }} + {{- if .Values.server.probeHeaders }} + httpHeaders: + {{- range .Values.server.probeHeaders}} + - name: {{ .name }} + value: {{ .value }} + {{- end }} + {{- end }} + {{- else }} + tcpSocket: + port: 9090 + {{- end }} + failureThreshold: {{ .Values.server.startupProbe.failureThreshold }} + periodSeconds: {{ .Values.server.startupProbe.periodSeconds }} + timeoutSeconds: {{ .Values.server.startupProbe.timeoutSeconds }} + {{- end }} + {{- with .Values.server.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - name: config-volume + mountPath: /etc/config + - name: {{ ternary .Values.server.persistentVolume.statefulSetNameOverride "storage-volume" (and .Values.server.persistentVolume.enabled (not (empty .Values.server.persistentVolume.statefulSetNameOverride))) }} + mountPath: {{ .Values.server.persistentVolume.mountPath }} + subPath: "{{ .Values.server.persistentVolume.subPath }}" + {{- range .Values.server.extraHostPathMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath }} + readOnly: {{ .readOnly }} + {{- end }} + {{- range .Values.server.extraConfigmapMounts }} + - name: {{ $.Values.server.name }}-{{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath }} + readOnly: {{ .readOnly }} + {{- end }} + {{- range .Values.server.extraSecretMounts }} + - name: {{ .name }} + mountPath: {{ .mountPath }} + subPath: {{ .subPath }} + readOnly: {{ .readOnly }} + {{- end }} + {{- if .Values.server.extraVolumeMounts }} + {{ toYaml .Values.server.extraVolumeMounts | nindent 12 }} + {{- end }} + {{- with .Values.server.containerSecurityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.server.sidecarContainers }} + {{- range $name, $spec := .Values.server.sidecarContainers }} + - name: {{ $name }} + {{- if kindIs "string" $spec }} + {{- tpl $spec $ | nindent 10 }} + {{- else }} + {{- toYaml $spec | nindent 10 }} + {{- end }} + {{- end }} + {{- end }} + hostNetwork: {{ .Values.server.hostNetwork }} + {{- if .Values.server.dnsPolicy }} + dnsPolicy: {{ .Values.server.dnsPolicy }} + {{- end }} + {{- if .Values.imagePullSecrets }} + imagePullSecrets: +{{ toYaml .Values.imagePullSecrets | indent 8 }} + {{- end }} + {{- if .Values.server.nodeSelector }} + nodeSelector: +{{ toYaml .Values.server.nodeSelector | indent 8 }} + {{- end }} + {{- if .Values.server.hostAliases }} + hostAliases: +{{ toYaml .Values.server.hostAliases | indent 8 }} + {{- end }} + {{- if .Values.server.dnsConfig }} + dnsConfig: +{{ toYaml .Values.server.dnsConfig | indent 8 }} + {{- end }} + {{- with .Values.server.securityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.server.tolerations }} + tolerations: +{{ toYaml .Values.server.tolerations | indent 8 }} + {{- end }} + {{- if .Values.server.affinity }} + affinity: +{{ toYaml .Values.server.affinity | indent 8 }} + {{- end }} + {{- with .Values.server.topologySpreadConstraints }} + topologySpreadConstraints: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.server.terminationGracePeriodSeconds }} + volumes: + - name: config-volume + {{- if empty .Values.server.configFromSecret }} + configMap: + name: {{ if .Values.server.configMapOverrideName }}{{ .Release.Name }}-{{ .Values.server.configMapOverrideName }}{{- else }}{{ template "prometheus.server.fullname" . }}{{- end }} + {{- else }} + secret: + secretName: {{ .Values.server.configFromSecret }} + {{- end }} + {{- range .Values.server.extraHostPathMounts }} + - name: {{ .name }} + hostPath: + path: {{ .hostPath }} + {{- end }} + {{- range .Values.configmapReload.prometheus.extraConfigmapMounts }} + - name: {{ $.Values.configmapReload.prometheus.name }}-{{ .name }} + configMap: + name: {{ .configMap }} + {{- end }} + {{- range .Values.server.extraConfigmapMounts }} + - name: {{ $.Values.server.name }}-{{ .name }} + configMap: + name: {{ .configMap }} + {{- end }} + {{- range .Values.server.extraSecretMounts }} + - name: {{ .name }} + secret: + secretName: {{ .secretName }} + {{- with .optional }} + optional: {{ . }} + {{- end }} + {{- end }} + {{- range .Values.configmapReload.prometheus.extraConfigmapMounts }} + - name: {{ .name }} + configMap: + name: {{ .configMap }} + {{- with .optional }} + optional: {{ . }} + {{- end }} + {{- end }} +{{- if .Values.server.extraVolumes }} +{{ toYaml .Values.server.extraVolumes | indent 8}} +{{- end }} +{{- if .Values.server.persistentVolume.enabled }} + volumeClaimTemplates: + - metadata: + name: {{ .Values.server.persistentVolume.statefulSetNameOverride | default "storage-volume" }} + {{- if .Values.server.persistentVolume.annotations }} + annotations: +{{ toYaml .Values.server.persistentVolume.annotations | indent 10 }} + {{- end }} + {{- if .Values.server.persistentVolume.labels }} + labels: +{{ toYaml .Values.server.persistentVolume.labels | indent 10 }} + {{- end }} + spec: + accessModes: +{{ toYaml .Values.server.persistentVolume.accessModes | indent 10 }} + resources: + requests: + storage: "{{ .Values.server.persistentVolume.size }}" + {{- if .Values.server.persistentVolume.storageClass }} + {{- if (eq "-" .Values.server.persistentVolume.storageClass) }} + storageClassName: "" + {{- else }} + storageClassName: "{{ .Values.server.persistentVolume.storageClass }}" + {{- end }} + {{- end }} +{{- else }} + - name: storage-volume + emptyDir: + {{- if .Values.server.emptyDir.sizeLimit }} + sizeLimit: {{ .Values.server.emptyDir.sizeLimit }} + {{- else }} + {} + {{- end -}} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/vpa.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/vpa.yaml new file mode 100644 index 0000000..cd07ad8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/templates/vpa.yaml @@ -0,0 +1,26 @@ +{{- if .Values.server.verticalAutoscaler.enabled -}} +{{- if .Capabilities.APIVersions.Has "autoscaling.k8s.io/v1/VerticalPodAutoscaler" }} +apiVersion: autoscaling.k8s.io/v1 +{{- else }} +apiVersion: autoscaling.k8s.io/v1beta2 +{{- end }} +kind: VerticalPodAutoscaler +metadata: + name: {{ template "prometheus.server.fullname" . }}-vpa + namespace: {{ include "prometheus.namespace" . }} + labels: + {{- include "prometheus.server.labels" . | nindent 4 }} +spec: + targetRef: + apiVersion: "apps/v1" +{{- if .Values.server.statefulSet.enabled }} + kind: StatefulSet +{{- else }} + kind: Deployment +{{- end }} + name: {{ template "prometheus.server.fullname" . }} + updatePolicy: + updateMode: {{ .Values.server.verticalAutoscaler.updateMode | default "Off" | quote }} + resourcePolicy: + containerPolicies: {{ .Values.server.verticalAutoscaler.containerPolicies | default list | toYaml | trim | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/values.schema.json b/observability/lgtm-distributed/charts/oncall/charts/prometheus/values.schema.json new file mode 100644 index 0000000..1828064 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/values.schema.json @@ -0,0 +1,738 @@ +{ + "$schema": "http://json-schema.org/schema#", + "type": "object", + "properties": { + "alertRelabelConfigs": { + "type": "object" + }, + "alertmanager": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + }, + "persistence": { + "type": "object", + "properties": { + "size": { + "type": "string" + } + } + }, + "podSecurityContext": { + "type": "object", + "properties": { + "fsGroup": { + "type": "integer" + }, + "runAsGroup": { + "type": "integer" + }, + "runAsNonRoot": { + "type": "boolean" + }, + "runAsUser": { + "type": "integer" + } + } + } + } + }, + "configmapReload": { + "type": "object", + "properties": { + "env": { + "type": "array" + }, + "prometheus": { + "type": "object", + "properties": { + "containerSecurityContext": { + "type": "object" + }, + "enabled": { + "type": "boolean" + }, + "extraArgs": { + "type": "object" + }, + "extraConfigmapMounts": { + "type": "array" + }, + "extraVolumeDirs": { + "type": "array" + }, + "extraVolumeMounts": { + "type": "array" + }, + "image": { + "type": "object", + "properties": { + "digest": { + "type": "string" + }, + "pullPolicy": { + "type": "string" + }, + "repository": { + "type": "string" + }, + "tag": { + "type": "string" + } + } + }, + "name": { + "type": "string" + }, + "resources": { + "type": "object" + } + } + }, + "reloadUrl": { + "type": "string" + } + } + }, + "extraManifests": { + "type": "array" + }, + "extraScrapeConfigs": { + "type": "string" + }, + "forceNamespace": { + "type": "string" + }, + "imagePullSecrets": { + "type": "array" + }, + "kube-state-metrics": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + } + } + }, + "networkPolicy": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + } + } + }, + "podSecurityPolicy": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + } + } + }, + "prometheus-node-exporter": { + "type": "object", + "properties": { + "containerSecurityContext": { + "type": "object", + "properties": { + "allowPrivilegeEscalation": { + "type": "boolean" + } + } + }, + "enabled": { + "type": "boolean" + }, + "rbac": { + "type": "object", + "properties": { + "pspEnabled": { + "type": "boolean" + } + } + } + } + }, + "prometheus-pushgateway": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + }, + "serviceAnnotations": { + "type": "object", + "properties": { + "prometheus.io/probe": { + "type": "string" + } + } + } + } + }, + "rbac": { + "type": "object", + "properties": { + "create": { + "type": "boolean" + } + } + }, + "ruleFiles": { + "type": "object" + }, + "server": { + "type": "object", + "properties": { + "affinity": { + "type": "object" + }, + "alertmanagers": { + "type": "array" + }, + "baseURL": { + "type": "string" + }, + "clusterRoleNameOverride": { + "type": "string" + }, + "command": { + "type": "array" + }, + "configMapOverrideName": { + "type": "string" + }, + "configPath": { + "type": "string" + }, + "containerSecurityContext": { + "type": "object" + }, + "defaultFlagsOverride": { + "type": "array" + }, + "deploymentAnnotations": { + "type": "object" + }, + "dnsConfig": { + "type": "object" + }, + "dnsPolicy": { + "type": "string" + }, + "emptyDir": { + "type": "object", + "properties": { + "sizeLimit": { + "type": "string" + } + } + }, + "enableServiceLinks": { + "type": "boolean" + }, + "env": { + "type": "array" + }, + "exemplars": { + "type": "object" + }, + "extraArgs": { + "type": "object" + }, + "extraConfigmapLabels": { + "type": "object" + }, + "extraConfigmapMounts": { + "type": "array" + }, + "extraFlags": { + "type": "array", + "items": { + "type": "string" + } + }, + "extraHostPathMounts": { + "type": "array" + }, + "extraInitContainers": { + "type": "array" + }, + "extraSecretMounts": { + "type": "array" + }, + "extraVolumeMounts": { + "type": "array" + }, + "extraVolumes": { + "type": "array" + }, + "global": { + "type": "object", + "properties": { + "evaluation_interval": { + "type": "string" + }, + "scrape_interval": { + "type": "string" + }, + "scrape_timeout": { + "type": "string" + } + } + }, + "hostAliases": { + "type": "array" + }, + "hostNetwork": { + "type": "boolean" + }, + "image": { + "type": "object", + "properties": { + "digest": { + "type": "string" + }, + "pullPolicy": { + "type": "string" + }, + "repository": { + "type": "string" + }, + "tag": { + "type": "string" + } + } + }, + "ingress": { + "type": "object", + "properties": { + "annotations": { + "type": "object" + }, + "enabled": { + "type": "boolean" + }, + "extraLabels": { + "type": "object" + }, + "extraPaths": { + "type": "array" + }, + "hosts": { + "type": "array" + }, + "path": { + "type": "string" + }, + "pathType": { + "type": "string" + }, + "tls": { + "type": "array" + } + } + }, + "livenessProbeFailureThreshold": { + "type": "integer" + }, + "livenessProbeInitialDelay": { + "type": "integer" + }, + "livenessProbePeriodSeconds": { + "type": "integer" + }, + "livenessProbeSuccessThreshold": { + "type": "integer" + }, + "livenessProbeTimeout": { + "type": "integer" + }, + "name": { + "type": "string" + }, + "nodeSelector": { + "type": "object" + }, + "persistentVolume": { + "type": "object", + "properties": { + "accessModes": { + "type": "array", + "items": { + "type": "string" + } + }, + "annotations": { + "type": "object" + }, + "enabled": { + "type": "boolean" + }, + "existingClaim": { + "type": "string" + }, + "labels": { + "type": "object" + }, + "mountPath": { + "type": "string" + }, + "size": { + "type": "string" + }, + "statefulSetNameOverride": { + "type": "string" + }, + "subPath": { + "type": "string" + } + } + }, + "podAnnotations": { + "type": "object" + }, + "podDisruptionBudget": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + }, + "maxUnavailable": { + "type": [ + "string", + "integer" + ] + } + } + }, + "podLabels": { + "type": "object" + }, + "podSecurityPolicy": { + "type": "object", + "properties": { + "annotations": { + "type": "object" + } + } + }, + "portName": { + "type": "string" + }, + "prefixURL": { + "type": "string" + }, + "priorityClassName": { + "type": "string" + }, + "probeHeaders": { + "type": "array" + }, + "probeScheme": { + "type": "string" + }, + "readinessProbeFailureThreshold": { + "type": "integer" + }, + "readinessProbeInitialDelay": { + "type": "integer" + }, + "readinessProbePeriodSeconds": { + "type": "integer" + }, + "readinessProbeSuccessThreshold": { + "type": "integer" + }, + "readinessProbeTimeout": { + "type": "integer" + }, + "releaseNamespace": { + "type": "boolean" + }, + "remoteRead": { + "type": "array" + }, + "remoteWrite": { + "type": "array" + }, + "replicaCount": { + "type": "integer" + }, + "resources": { + "type": "object" + }, + "retention": { + "type": "string" + }, + "retentionSize": { + "type": "string" + }, + "revisionHistoryLimit": { + "type": "integer" + }, + "securityContext": { + "type": "object", + "properties": { + "fsGroup": { + "type": "integer" + }, + "runAsGroup": { + "type": "integer" + }, + "runAsNonRoot": { + "type": "boolean" + }, + "runAsUser": { + "type": "integer" + } + } + }, + "service": { + "type": "object", + "properties": { + "additionalPorts": { + "type": "array" + }, + "annotations": { + "type": "object" + }, + "clusterIP": { + "type": "string" + }, + "enabled": { + "type": "boolean" + }, + "externalIPs": { + "type": "array" + }, + "gRPC": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + }, + "servicePort": { + "type": "integer" + } + } + }, + "labels": { + "type": "object" + }, + "loadBalancerIP": { + "type": "string" + }, + "loadBalancerSourceRanges": { + "type": "array" + }, + "servicePort": { + "type": "integer" + }, + "sessionAffinity": { + "type": "string" + }, + "statefulsetReplica": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + }, + "replica": { + "type": "integer" + } + } + }, + "type": { + "type": "string" + } + } + }, + "sidecarContainers": { + "type": "object" + }, + "sidecarTemplateValues": { + "type": "object" + }, + "startupProbe": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + }, + "failureThreshold": { + "type": "integer" + }, + "periodSeconds": { + "type": "integer" + }, + "timeoutSeconds": { + "type": "integer" + } + } + }, + "statefulSet": { + "type": "object", + "properties": { + "annotations": { + "type": "object" + }, + "enabled": { + "type": "boolean" + }, + "headless": { + "type": "object", + "properties": { + "annotations": { + "type": "object" + }, + "gRPC": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + }, + "servicePort": { + "type": "integer" + } + } + }, + "labels": { + "type": "object" + }, + "servicePort": { + "type": "integer" + } + } + }, + "labels": { + "type": "object" + }, + "podManagementPolicy": { + "type": "string" + }, + "pvcDeleteOnStsDelete": { + "type": "boolean" + }, + "pvcDeleteOnStsScale": { + "type": "boolean" + } + } + }, + "storagePath": { + "type": "string" + }, + "strategy": { + "type": "object", + "properties": { + "type": { + "type": "string" + } + } + }, + "tcpSocketProbeEnabled": { + "type": "boolean" + }, + "terminationGracePeriodSeconds": { + "type": "integer" + }, + "tolerations": { + "type": "array" + }, + "topologySpreadConstraints": { + "type": "array" + }, + "tsdb": { + "type": "object" + }, + "verticalAutoscaler": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean" + } + } + } + } + }, + "scrapeConfigFiles": { + "type": "array" + }, + "serverFiles": { + "type": "object", + "properties": { + "alerting_rules.yml": { + "type": "object" + }, + "alerts": { + "type": "object" + }, + "prometheus.yml": { + "type": "object", + "properties": { + "rule_files": { + "type": "array", + "items": { + "type": "string" + } + }, + "scrape_configs": { + "type": "array", + "items": { + "type": "object", + "properties": { + "job_name": { + "type": "string" + }, + "static_configs": { + "type": "array", + "items": { + "type": "object", + "properties": { + "targets": { + "type": "array", + "items": { + "type": "string" + } + } + } + } + } + } + } + } + } + }, + "recording_rules.yml": { + "type": "object" + }, + "rules": { + "type": "object" + } + } + }, + "serviceAccounts": { + "type": "object", + "properties": { + "server": { + "type": "object", + "properties": { + "annotations": { + "type": "object" + }, + "create": { + "type": "boolean" + }, + "name": { + "type": "string" + }, + "automountServiceAccountToken": { + "type": "boolean" + } + } + } + } + } + } +} diff --git a/observability/lgtm-distributed/charts/oncall/charts/prometheus/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/prometheus/values.yaml new file mode 100644 index 0000000..38ebf10 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/prometheus/values.yaml @@ -0,0 +1,1253 @@ +# yaml-language-server: $schema=values.schema.json +# Default values for prometheus. +# This is a YAML-formatted file. +# Declare variables to be passed into your templates. + +rbac: + create: true + +podSecurityPolicy: + enabled: false + +imagePullSecrets: [] +# - name: "image-pull-secret" + +## Define serviceAccount names for components. Defaults to component's fully qualified name. +## +serviceAccounts: + server: + create: true + name: "" + annotations: {} + + ## Opt out of automounting Kubernetes API credentials. + ## It will be overriden by server.automountServiceAccountToken value, if set. + # automountServiceAccountToken: false + +## Additional labels to attach to all resources +commonMetaLabels: {} + +## Monitors ConfigMap changes and POSTs to a URL +## Ref: https://github.com/prometheus-operator/prometheus-operator/tree/main/cmd/prometheus-config-reloader +## +configmapReload: + ## URL for configmap-reload to use for reloads + ## + reloadUrl: "" + + ## env sets environment variables to pass to the container. Can be set as name/value pairs, + ## read from secrets or configmaps. + env: [] + # - name: SOMEVAR + # value: somevalue + # - name: PASSWORD + # valueFrom: + # secretKeyRef: + # name: mysecret + # key: password + # optional: false + + prometheus: + ## If false, the configmap-reload container will not be deployed + ## + enabled: true + + ## configmap-reload container name + ## + name: configmap-reload + + ## configmap-reload container image + ## + image: + repository: quay.io/prometheus-operator/prometheus-config-reloader + tag: v0.70.0 + # When digest is set to a non-empty value, images will be pulled by digest (regardless of tag value). + digest: "" + pullPolicy: IfNotPresent + + # containerPort: 9533 + + ## Additional configmap-reload container arguments + ## + extraArgs: {} + + ## Additional configmap-reload volume directories + ## + extraVolumeDirs: [] + + ## Additional configmap-reload volume mounts + ## + extraVolumeMounts: [] + + ## Additional configmap-reload mounts + ## + extraConfigmapMounts: [] + # - name: prometheus-alerts + # mountPath: /etc/alerts.d + # subPath: "" + # configMap: prometheus-alerts + # readOnly: true + + ## Security context to be added to configmap-reload container + containerSecurityContext: {} + + ## configmap-reload resource requests and limits + ## Ref: http://kubernetes.io/docs/user-guide/compute-resources/ + ## + resources: {} + +server: + ## Prometheus server container name + ## + name: server + + ## Opt out of automounting Kubernetes API credentials. + ## If set it will override serviceAccounts.server.automountServiceAccountToken value for ServiceAccount. + # automountServiceAccountToken: false + + ## Use a ClusterRole (and ClusterRoleBinding) + ## - If set to false - we define a RoleBinding in the defined namespaces ONLY + ## + ## NB: because we need a Role with nonResourceURL's ("/metrics") - you must get someone with Cluster-admin privileges to define this role for you, before running with this setting enabled. + ## This makes prometheus work - for users who do not have ClusterAdmin privs, but wants prometheus to operate on their own namespaces, instead of clusterwide. + ## + ## You MUST also set namespaces to the ones you have access to and want monitored by Prometheus. + ## + # useExistingClusterRoleName: nameofclusterrole + + ## If set it will override prometheus.server.fullname value for ClusterRole and ClusterRoleBinding + ## + clusterRoleNameOverride: "" + + # Enable only the release namespace for monitoring. By default all namespaces are monitored. + # If releaseNamespace and namespaces are both set a merged list will be monitored. + releaseNamespace: false + + ## namespaces to monitor (instead of monitoring all - clusterwide). Needed if you want to run without Cluster-admin privileges. + # namespaces: + # - yournamespace + + # sidecarContainers - add more containers to prometheus server + # Key/Value where Key is the sidecar `- name: ` + # Example: + # sidecarContainers: + # webserver: + # image: nginx + # OR for adding OAuth authentication to Prometheus + # sidecarContainers: + # oauth-proxy: + # image: quay.io/oauth2-proxy/oauth2-proxy:v7.1.2 + # args: + # - --upstream=http://127.0.0.1:9090 + # - --http-address=0.0.0.0:8081 + # - ... + # ports: + # - containerPort: 8081 + # name: oauth-proxy + # protocol: TCP + # resources: {} + sidecarContainers: {} + + # sidecarTemplateValues - context to be used in template for sidecarContainers + # Example: + # sidecarTemplateValues: *your-custom-globals + # sidecarContainers: + # webserver: |- + # {{ include "webserver-container-template" . }} + # Template for `webserver-container-template` might looks like this: + # image: "{{ .Values.server.sidecarTemplateValues.repository }}:{{ .Values.server.sidecarTemplateValues.tag }}" + # ... + # + sidecarTemplateValues: {} + + ## Prometheus server container image + ## + image: + repository: quay.io/prometheus/prometheus + # if not set appVersion field from Chart.yaml is used + tag: "" + # When digest is set to a non-empty value, images will be pulled by digest (regardless of tag value). + digest: "" + pullPolicy: IfNotPresent + + ## Prometheus server command + ## + command: [] + + ## prometheus server priorityClassName + ## + priorityClassName: "" + + ## EnableServiceLinks indicates whether information about services should be injected + ## into pod's environment variables, matching the syntax of Docker links. + ## WARNING: the field is unsupported and will be skipped in K8s prior to v1.13.0. + ## + enableServiceLinks: true + + ## The URL prefix at which the container can be accessed. Useful in the case the '-web.external-url' includes a slug + ## so that the various internal URLs are still able to access as they are in the default case. + ## (Optional) + prefixURL: "" + + ## External URL which can access prometheus + ## Maybe same with Ingress host name + baseURL: "" + + ## Additional server container environment variables + ## + ## You specify this manually like you would a raw deployment manifest. + ## This means you can bind in environment variables from secrets. + ## + ## e.g. static environment variable: + ## - name: DEMO_GREETING + ## value: "Hello from the environment" + ## + ## e.g. secret environment variable: + ## - name: USERNAME + ## valueFrom: + ## secretKeyRef: + ## name: mysecret + ## key: username + env: [] + + # List of flags to override default parameters, e.g: + # - --enable-feature=agent + # - --storage.agent.retention.max-time=30m + # - --config.file=/etc/config/prometheus.yml + defaultFlagsOverride: [] + + extraFlags: + - web.enable-lifecycle + ## web.enable-admin-api flag controls access to the administrative HTTP API which includes functionality such as + ## deleting time series. This is disabled by default. + # - web.enable-admin-api + ## + ## storage.tsdb.no-lockfile flag controls BD locking + # - storage.tsdb.no-lockfile + ## + ## storage.tsdb.wal-compression flag enables compression of the write-ahead log (WAL) + # - storage.tsdb.wal-compression + + ## Path to a configuration file on prometheus server container FS + configPath: /etc/config/prometheus.yml + + ### The data directory used by prometheus to set --storage.tsdb.path + ### When empty server.persistentVolume.mountPath is used instead + storagePath: "" + + global: + ## How frequently to scrape targets by default + ## + scrape_interval: 1m + ## How long until a scrape request times out + ## + scrape_timeout: 10s + ## How frequently to evaluate rules + ## + evaluation_interval: 1m + ## https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_write + ## + remoteWrite: [] + ## https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_read + ## + remoteRead: [] + + ## https://prometheus.io/docs/prometheus/latest/configuration/configuration/#tsdb + ## + tsdb: {} + # out_of_order_time_window: 0s + + ## https://prometheus.io/docs/prometheus/latest/configuration/configuration/#exemplars + ## Must be enabled via --enable-feature=exemplar-storage + ## + exemplars: {} + # max_exemplars: 100000 + + ## Custom HTTP headers for Liveness/Readiness/Startup Probe + ## + ## Useful for providing HTTP Basic Auth to healthchecks + probeHeaders: [] + # - name: "Authorization" + # value: "Bearer ABCDEabcde12345" + + ## Additional Prometheus server container arguments + ## + extraArgs: {} + + ## Additional InitContainers to initialize the pod + ## + extraInitContainers: [] + + ## Additional Prometheus server Volume mounts + ## + extraVolumeMounts: [] + + ## Additional Prometheus server Volumes + ## + extraVolumes: [] + + ## Additional Prometheus server hostPath mounts + ## + extraHostPathMounts: [] + # - name: certs-dir + # mountPath: /etc/kubernetes/certs + # subPath: "" + # hostPath: /etc/kubernetes/certs + # readOnly: true + + extraConfigmapMounts: [] + # - name: certs-configmap + # mountPath: /prometheus + # subPath: "" + # configMap: certs-configmap + # readOnly: true + + ## Additional Prometheus server Secret mounts + # Defines additional mounts with secrets. Secrets must be manually created in the namespace. + extraSecretMounts: [] + # - name: secret-files + # mountPath: /etc/secrets + # subPath: "" + # secretName: prom-secret-files + # readOnly: true + + ## ConfigMap override where fullname is {{.Release.Name}}-{{.Values.server.configMapOverrideName}} + ## Defining configMapOverrideName will cause templates/server-configmap.yaml + ## to NOT generate a ConfigMap resource + ## + configMapOverrideName: "" + + ## Extra labels for Prometheus server ConfigMap (ConfigMap that holds serverFiles) + extraConfigmapLabels: {} + + ingress: + ## If true, Prometheus server Ingress will be created + ## + enabled: false + + # For Kubernetes >= 1.18 you should specify the ingress-controller via the field ingressClassName + # See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#specifying-the-class-of-an-ingress + # ingressClassName: nginx + + ## Prometheus server Ingress annotations + ## + annotations: {} + # kubernetes.io/ingress.class: nginx + # kubernetes.io/tls-acme: 'true' + + ## Prometheus server Ingress additional labels + ## + extraLabels: {} + + ## Redirect ingress to an additional defined port on the service + # servicePort: 8081 + + ## Prometheus server Ingress hostnames with optional path + ## Must be provided if Ingress is enabled + ## + hosts: [] + # - prometheus.domain.com + # - domain.com/prometheus + + path: / + + # pathType is only for k8s >= 1.18 + pathType: Prefix + + ## Extra paths to prepend to every host configuration. This is useful when working with annotation based services. + extraPaths: [] + # - path: /* + # backend: + # serviceName: ssl-redirect + # servicePort: use-annotation + + ## Prometheus server Ingress TLS configuration + ## Secrets must be manually created in the namespace + ## + tls: [] + # - secretName: prometheus-server-tls + # hosts: + # - prometheus.domain.com + + ## Server Deployment Strategy type + strategy: + type: Recreate + + ## hostAliases allows adding entries to /etc/hosts inside the containers + hostAliases: [] + # - ip: "127.0.0.1" + # hostnames: + # - "example.com" + + ## Node tolerations for server scheduling to nodes with taints + ## Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/taint-and-toleration/ + ## + tolerations: [] + # - key: "key" + # operator: "Equal|Exists" + # value: "value" + # effect: "NoSchedule|PreferNoSchedule|NoExecute(1.6 only)" + + ## Node labels for Prometheus server pod assignment + ## Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/ + ## + nodeSelector: {} + + ## Pod affinity + ## + affinity: {} + + ## Pod topology spread constraints + ## ref. https://kubernetes.io/docs/concepts/scheduling-eviction/topology-spread-constraints/ + topologySpreadConstraints: [] + + ## PodDisruptionBudget settings + ## ref: https://kubernetes.io/docs/concepts/workloads/pods/disruptions/ + ## + podDisruptionBudget: + enabled: false + maxUnavailable: 1 + # minAvailable: 1 + ## unhealthyPodEvictionPolicy is available since 1.27.0 (beta) + ## https://kubernetes.io/docs/tasks/run-application/configure-pdb/#unhealthy-pod-eviction-policy + # unhealthyPodEvictionPolicy: IfHealthyBudget + + ## Use an alternate scheduler, e.g. "stork". + ## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ + ## + # schedulerName: + + persistentVolume: + ## If true, Prometheus server will create/use a Persistent Volume Claim + ## If false, use emptyDir + ## + enabled: true + + ## If set it will override the name of the created persistent volume claim + ## generated by the stateful set. + ## + statefulSetNameOverride: "" + + ## Prometheus server data Persistent Volume access modes + ## Must match those of existing PV or dynamic provisioner + ## Ref: http://kubernetes.io/docs/user-guide/persistent-volumes/ + ## + accessModes: + - ReadWriteOnce + + ## Prometheus server data Persistent Volume labels + ## + labels: {} + + ## Prometheus server data Persistent Volume annotations + ## + annotations: {} + + ## Prometheus server data Persistent Volume existing claim name + ## Requires server.persistentVolume.enabled: true + ## If defined, PVC must be created manually before volume will be bound + existingClaim: "" + + ## Prometheus server data Persistent Volume mount root path + ## + mountPath: /data + + ## Prometheus server data Persistent Volume size + ## + size: 8Gi + + ## Prometheus server data Persistent Volume Storage Class + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is + ## set, choosing the default provisioner. (gp2 on AWS, standard on + ## GKE, AWS & OpenStack) + ## + # storageClass: "-" + + ## Prometheus server data Persistent Volume Binding Mode + ## If defined, volumeBindingMode: + ## If undefined (the default) or set to null, no volumeBindingMode spec is + ## set, choosing the default mode. + ## + # volumeBindingMode: "" + + ## Subdirectory of Prometheus server data Persistent Volume to mount + ## Useful if the volume's root directory is not empty + ## + subPath: "" + + ## Persistent Volume Claim Selector + ## Useful if Persistent Volumes have been provisioned in advance + ## Ref: https://kubernetes.io/docs/concepts/storage/persistent-volumes/#selector + ## + # selector: + # matchLabels: + # release: "stable" + # matchExpressions: + # - { key: environment, operator: In, values: [ dev ] } + + ## Persistent Volume Name + ## Useful if Persistent Volumes have been provisioned in advance and you want to use a specific one + ## + # volumeName: "" + + emptyDir: + ## Prometheus server emptyDir volume size limit + ## + sizeLimit: "" + + ## Annotations to be added to Prometheus server pods + ## + podAnnotations: {} + # iam.amazonaws.com/role: prometheus + + ## Labels to be added to Prometheus server pods + ## + podLabels: {} + + ## Prometheus AlertManager configuration + ## + alertmanagers: [] + + ## Specify if a Pod Security Policy for node-exporter must be created + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/ + ## + podSecurityPolicy: + annotations: {} + ## Specify pod annotations + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#apparmor + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#seccomp + ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/#sysctl + ## + # seccomp.security.alpha.kubernetes.io/allowedProfileNames: '*' + # seccomp.security.alpha.kubernetes.io/defaultProfileName: 'docker/default' + # apparmor.security.beta.kubernetes.io/defaultProfileName: 'runtime/default' + + ## Use a StatefulSet if replicaCount needs to be greater than 1 (see below) + ## + replicaCount: 1 + + ## Number of old history to retain to allow rollback + ## Default Kubernetes value is set to 10 + ## + revisionHistoryLimit: 10 + + ## Annotations to be added to deployment + ## + deploymentAnnotations: {} + + statefulSet: + ## If true, use a statefulset instead of a deployment for pod management. + ## This allows to scale replicas to more than 1 pod + ## + enabled: false + + annotations: {} + labels: {} + podManagementPolicy: OrderedReady + + ## Alertmanager headless service to use for the statefulset + ## + headless: + annotations: {} + labels: {} + servicePort: 80 + ## Enable gRPC port on service to allow auto discovery with thanos-querier + gRPC: + enabled: false + servicePort: 10901 + # nodePort: 10901 + + ## Statefulset's persistent volume claim retention policy + ## pvcDeleteOnStsDelete and pvcDeleteOnStsScale determine whether + ## statefulset's PVCs are deleted (true) or retained (false) on scaling down + ## and deleting statefulset, respectively. Requires 1.27.0+. + ## Ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#persistentvolumeclaim-retention + ## + pvcDeleteOnStsDelete: false + pvcDeleteOnStsScale: false + + ## Prometheus server readiness and liveness probe initial delay and timeout + ## Ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/ + ## + tcpSocketProbeEnabled: false + probeScheme: HTTP + readinessProbeInitialDelay: 30 + readinessProbePeriodSeconds: 5 + readinessProbeTimeout: 4 + readinessProbeFailureThreshold: 3 + readinessProbeSuccessThreshold: 1 + livenessProbeInitialDelay: 30 + livenessProbePeriodSeconds: 15 + livenessProbeTimeout: 10 + livenessProbeFailureThreshold: 3 + livenessProbeSuccessThreshold: 1 + startupProbe: + enabled: false + periodSeconds: 5 + failureThreshold: 30 + timeoutSeconds: 10 + + ## Prometheus server resource requests and limits + ## Ref: http://kubernetes.io/docs/user-guide/compute-resources/ + ## + resources: {} + # limits: + # cpu: 500m + # memory: 512Mi + # requests: + # cpu: 500m + # memory: 512Mi + + # Required for use in managed kubernetes clusters (such as AWS EKS) with custom CNI (such as calico), + # because control-plane managed by AWS cannot communicate with pods' IP CIDR and admission webhooks are not working + ## + hostNetwork: false + + # When hostNetwork is enabled, this will set to ClusterFirstWithHostNet automatically + dnsPolicy: ClusterFirst + + # Use hostPort + # hostPort: 9090 + + # Use portName + portName: "" + + ## Vertical Pod Autoscaler config + ## Ref: https://github.com/kubernetes/autoscaler/tree/master/vertical-pod-autoscaler + verticalAutoscaler: + ## If true a VPA object will be created for the controller (either StatefulSet or Deployemnt, based on above configs) + enabled: false + # updateMode: "Auto" + # containerPolicies: + # - containerName: 'prometheus-server' + + # Custom DNS configuration to be added to prometheus server pods + dnsConfig: {} + # nameservers: + # - 1.2.3.4 + # searches: + # - ns1.svc.cluster-domain.example + # - my.dns.search.suffix + # options: + # - name: ndots + # value: "2" + # - name: edns0 + + ## Security context to be added to server pods + ## + securityContext: + runAsUser: 65534 + runAsNonRoot: true + runAsGroup: 65534 + fsGroup: 65534 + + ## Security context to be added to server container + ## + containerSecurityContext: {} + + service: + ## If false, no Service will be created for the Prometheus server + ## + enabled: true + + annotations: {} + labels: {} + clusterIP: "" + + ## List of IP addresses at which the Prometheus server service is available + ## Ref: https://kubernetes.io/docs/concepts/services-networking/service/#external-ips + ## + externalIPs: [] + + loadBalancerIP: "" + loadBalancerSourceRanges: [] + servicePort: 80 + sessionAffinity: None + type: ClusterIP + + ## Enable gRPC port on service to allow auto discovery with thanos-querier + gRPC: + enabled: false + servicePort: 10901 + # nodePort: 10901 + + ## If using a statefulSet (statefulSet.enabled=true), configure the + ## service to connect to a specific replica to have a consistent view + ## of the data. + statefulsetReplica: + enabled: false + replica: 0 + + ## Additional port to define in the Service + additionalPorts: [] + # additionalPorts: + # - name: authenticated + # port: 8081 + # targetPort: 8081 + + ## Prometheus server pod termination grace period + ## + terminationGracePeriodSeconds: 300 + + ## Prometheus data retention period (default if not specified is 15 days) + ## + retention: "15d" + + ## Prometheus' data retention size. Supported units: B, KB, MB, GB, TB, PB, EB. + ## + retentionSize: "" + +## Prometheus server ConfigMap entries for rule files (allow prometheus labels interpolation) +ruleFiles: {} + +## Prometheus server ConfigMap entries for scrape_config_files +## (allows scrape configs defined in additional files) +## +scrapeConfigFiles: [] + +## Prometheus server ConfigMap entries +## +serverFiles: + ## Alerts configuration + ## Ref: https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/ + alerting_rules.yml: {} + # groups: + # - name: Instances + # rules: + # - alert: InstanceDown + # expr: up == 0 + # for: 5m + # labels: + # severity: page + # annotations: + # description: '{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes.' + # summary: 'Instance {{ $labels.instance }} down' + ## DEPRECATED DEFAULT VALUE, unless explicitly naming your files, please use alerting_rules.yml + alerts: {} + + ## Records configuration + ## Ref: https://prometheus.io/docs/prometheus/latest/configuration/recording_rules/ + recording_rules.yml: {} + ## DEPRECATED DEFAULT VALUE, unless explicitly naming your files, please use recording_rules.yml + rules: {} + + prometheus.yml: + rule_files: + - /etc/config/recording_rules.yml + - /etc/config/alerting_rules.yml + ## Below two files are DEPRECATED will be removed from this default values file + - /etc/config/rules + - /etc/config/alerts + + scrape_configs: + - job_name: prometheus + static_configs: + - targets: + - localhost:9090 + + # A scrape configuration for running Prometheus on a Kubernetes cluster. + # This uses separate scrape configs for cluster components (i.e. API server, node) + # and services to allow each to use different authentication configs. + # + # Kubernetes labels will be added as Prometheus labels on metrics via the + # `labelmap` relabeling action. + + # Scrape config for API servers. + # + # Kubernetes exposes API servers as endpoints to the default/kubernetes + # service so this uses `endpoints` role and uses relabelling to only keep + # the endpoints associated with the default/kubernetes service using the + # default named port `https`. This works for single API server deployments as + # well as HA API server deployments. + - job_name: 'kubernetes-apiservers' + + kubernetes_sd_configs: + - role: endpoints + + # Default to scraping over https. If required, just disable this or change to + # `http`. + scheme: https + + # This TLS & bearer token file config is used to connect to the actual scrape + # endpoints for cluster components. This is separate to discovery auth + # configuration because discovery & scraping are two separate concerns in + # Prometheus. The discovery auth config is automatic if Prometheus runs inside + # the cluster. Otherwise, more config options have to be provided within the + # . + tls_config: + ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + # If your node certificates are self-signed or use a different CA to the + # master CA, then disable certificate verification below. Note that + # certificate verification is an integral part of a secure infrastructure + # so this should only be disabled in a controlled environment. You can + # disable certificate verification by uncommenting the line below. + # + insecure_skip_verify: true + bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token + + # Keep only the default/kubernetes service endpoints for the https port. This + # will add targets for each API server which Kubernetes adds an endpoint to + # the default/kubernetes service. + relabel_configs: + - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name] + action: keep + regex: default;kubernetes;https + + - job_name: 'kubernetes-nodes' + + # Default to scraping over https. If required, just disable this or change to + # `http`. + scheme: https + + # This TLS & bearer token file config is used to connect to the actual scrape + # endpoints for cluster components. This is separate to discovery auth + # configuration because discovery & scraping are two separate concerns in + # Prometheus. The discovery auth config is automatic if Prometheus runs inside + # the cluster. Otherwise, more config options have to be provided within the + # . + tls_config: + ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + # If your node certificates are self-signed or use a different CA to the + # master CA, then disable certificate verification below. Note that + # certificate verification is an integral part of a secure infrastructure + # so this should only be disabled in a controlled environment. You can + # disable certificate verification by uncommenting the line below. + # + insecure_skip_verify: true + bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token + + kubernetes_sd_configs: + - role: node + + relabel_configs: + - action: labelmap + regex: __meta_kubernetes_node_label_(.+) + - target_label: __address__ + replacement: kubernetes.default.svc:443 + - source_labels: [__meta_kubernetes_node_name] + regex: (.+) + target_label: __metrics_path__ + replacement: /api/v1/nodes/$1/proxy/metrics + + + - job_name: 'kubernetes-nodes-cadvisor' + + # Default to scraping over https. If required, just disable this or change to + # `http`. + scheme: https + + # This TLS & bearer token file config is used to connect to the actual scrape + # endpoints for cluster components. This is separate to discovery auth + # configuration because discovery & scraping are two separate concerns in + # Prometheus. The discovery auth config is automatic if Prometheus runs inside + # the cluster. Otherwise, more config options have to be provided within the + # . + tls_config: + ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + # If your node certificates are self-signed or use a different CA to the + # master CA, then disable certificate verification below. Note that + # certificate verification is an integral part of a secure infrastructure + # so this should only be disabled in a controlled environment. You can + # disable certificate verification by uncommenting the line below. + # + insecure_skip_verify: true + bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token + + kubernetes_sd_configs: + - role: node + + # This configuration will work only on kubelet 1.7.3+ + # As the scrape endpoints for cAdvisor have changed + # if you are using older version you need to change the replacement to + # replacement: /api/v1/nodes/$1:4194/proxy/metrics + # more info here https://github.com/coreos/prometheus-operator/issues/633 + relabel_configs: + - action: labelmap + regex: __meta_kubernetes_node_label_(.+) + - target_label: __address__ + replacement: kubernetes.default.svc:443 + - source_labels: [__meta_kubernetes_node_name] + regex: (.+) + target_label: __metrics_path__ + replacement: /api/v1/nodes/$1/proxy/metrics/cadvisor + + # Metric relabel configs to apply to samples before ingestion. + # [Metric Relabeling](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs) + # metric_relabel_configs: + # - action: labeldrop + # regex: (kubernetes_io_hostname|failure_domain_beta_kubernetes_io_region|beta_kubernetes_io_os|beta_kubernetes_io_arch|beta_kubernetes_io_instance_type|failure_domain_beta_kubernetes_io_zone) + + # Scrape config for service endpoints. + # + # The relabeling allows the actual service scrape endpoint to be configured + # via the following annotations: + # + # * `prometheus.io/scrape`: Only scrape services that have a value of + # `true`, except if `prometheus.io/scrape-slow` is set to `true` as well. + # * `prometheus.io/scheme`: If the metrics endpoint is secured then you will need + # to set this to `https` & most likely set the `tls_config` of the scrape config. + # * `prometheus.io/path`: If the metrics path is not `/metrics` override this. + # * `prometheus.io/port`: If the metrics are exposed on a different port to the + # service then set this appropriately. + # * `prometheus.io/param_`: If the metrics endpoint uses parameters + # then you can set any parameter + - job_name: 'kubernetes-service-endpoints' + honor_labels: true + + kubernetes_sd_configs: + - role: endpoints + + relabel_configs: + - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape] + action: keep + regex: true + - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape_slow] + action: drop + regex: true + - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme] + action: replace + target_label: __scheme__ + regex: (https?) + - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path] + action: replace + target_label: __metrics_path__ + regex: (.+) + - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port] + action: replace + target_label: __address__ + regex: (.+?)(?::\d+)?;(\d+) + replacement: $1:$2 + - action: labelmap + regex: __meta_kubernetes_service_annotation_prometheus_io_param_(.+) + replacement: __param_$1 + - action: labelmap + regex: __meta_kubernetes_service_label_(.+) + - source_labels: [__meta_kubernetes_namespace] + action: replace + target_label: namespace + - source_labels: [__meta_kubernetes_service_name] + action: replace + target_label: service + - source_labels: [__meta_kubernetes_pod_node_name] + action: replace + target_label: node + + # Scrape config for slow service endpoints; same as above, but with a larger + # timeout and a larger interval + # + # The relabeling allows the actual service scrape endpoint to be configured + # via the following annotations: + # + # * `prometheus.io/scrape-slow`: Only scrape services that have a value of `true` + # * `prometheus.io/scheme`: If the metrics endpoint is secured then you will need + # to set this to `https` & most likely set the `tls_config` of the scrape config. + # * `prometheus.io/path`: If the metrics path is not `/metrics` override this. + # * `prometheus.io/port`: If the metrics are exposed on a different port to the + # service then set this appropriately. + # * `prometheus.io/param_`: If the metrics endpoint uses parameters + # then you can set any parameter + - job_name: 'kubernetes-service-endpoints-slow' + honor_labels: true + + scrape_interval: 5m + scrape_timeout: 30s + + kubernetes_sd_configs: + - role: endpoints + + relabel_configs: + - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape_slow] + action: keep + regex: true + - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme] + action: replace + target_label: __scheme__ + regex: (https?) + - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path] + action: replace + target_label: __metrics_path__ + regex: (.+) + - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port] + action: replace + target_label: __address__ + regex: (.+?)(?::\d+)?;(\d+) + replacement: $1:$2 + - action: labelmap + regex: __meta_kubernetes_service_annotation_prometheus_io_param_(.+) + replacement: __param_$1 + - action: labelmap + regex: __meta_kubernetes_service_label_(.+) + - source_labels: [__meta_kubernetes_namespace] + action: replace + target_label: namespace + - source_labels: [__meta_kubernetes_service_name] + action: replace + target_label: service + - source_labels: [__meta_kubernetes_pod_node_name] + action: replace + target_label: node + + - job_name: 'prometheus-pushgateway' + honor_labels: true + + kubernetes_sd_configs: + - role: service + + relabel_configs: + - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe] + action: keep + regex: pushgateway + + # Example scrape config for probing services via the Blackbox Exporter. + # + # The relabeling allows the actual service scrape endpoint to be configured + # via the following annotations: + # + # * `prometheus.io/probe`: Only probe services that have a value of `true` + - job_name: 'kubernetes-services' + honor_labels: true + + metrics_path: /probe + params: + module: [http_2xx] + + kubernetes_sd_configs: + - role: service + + relabel_configs: + - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe] + action: keep + regex: true + - source_labels: [__address__] + target_label: __param_target + - target_label: __address__ + replacement: blackbox + - source_labels: [__param_target] + target_label: instance + - action: labelmap + regex: __meta_kubernetes_service_label_(.+) + - source_labels: [__meta_kubernetes_namespace] + target_label: namespace + - source_labels: [__meta_kubernetes_service_name] + target_label: service + + # Example scrape config for pods + # + # The relabeling allows the actual pod scrape endpoint to be configured via the + # following annotations: + # + # * `prometheus.io/scrape`: Only scrape pods that have a value of `true`, + # except if `prometheus.io/scrape-slow` is set to `true` as well. + # * `prometheus.io/scheme`: If the metrics endpoint is secured then you will need + # to set this to `https` & most likely set the `tls_config` of the scrape config. + # * `prometheus.io/path`: If the metrics path is not `/metrics` override this. + # * `prometheus.io/port`: Scrape the pod on the indicated port instead of the default of `9102`. + - job_name: 'kubernetes-pods' + honor_labels: true + + kubernetes_sd_configs: + - role: pod + + relabel_configs: + - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape] + action: keep + regex: true + - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape_slow] + action: drop + regex: true + - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scheme] + action: replace + regex: (https?) + target_label: __scheme__ + - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path] + action: replace + target_label: __metrics_path__ + regex: (.+) + - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_port, __meta_kubernetes_pod_ip] + action: replace + regex: (\d+);(([A-Fa-f0-9]{1,4}::?){1,7}[A-Fa-f0-9]{1,4}) + replacement: '[$2]:$1' + target_label: __address__ + - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_port, __meta_kubernetes_pod_ip] + action: replace + regex: (\d+);((([0-9]+?)(\.|$)){4}) + replacement: $2:$1 + target_label: __address__ + - action: labelmap + regex: __meta_kubernetes_pod_annotation_prometheus_io_param_(.+) + replacement: __param_$1 + - action: labelmap + regex: __meta_kubernetes_pod_label_(.+) + - source_labels: [__meta_kubernetes_namespace] + action: replace + target_label: namespace + - source_labels: [__meta_kubernetes_pod_name] + action: replace + target_label: pod + - source_labels: [__meta_kubernetes_pod_phase] + regex: Pending|Succeeded|Failed|Completed + action: drop + - source_labels: [__meta_kubernetes_pod_node_name] + action: replace + target_label: node + + # Example Scrape config for pods which should be scraped slower. An useful example + # would be stackriver-exporter which queries an API on every scrape of the pod + # + # The relabeling allows the actual pod scrape endpoint to be configured via the + # following annotations: + # + # * `prometheus.io/scrape-slow`: Only scrape pods that have a value of `true` + # * `prometheus.io/scheme`: If the metrics endpoint is secured then you will need + # to set this to `https` & most likely set the `tls_config` of the scrape config. + # * `prometheus.io/path`: If the metrics path is not `/metrics` override this. + # * `prometheus.io/port`: Scrape the pod on the indicated port instead of the default of `9102`. + - job_name: 'kubernetes-pods-slow' + honor_labels: true + + scrape_interval: 5m + scrape_timeout: 30s + + kubernetes_sd_configs: + - role: pod + + relabel_configs: + - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape_slow] + action: keep + regex: true + - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scheme] + action: replace + regex: (https?) + target_label: __scheme__ + - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path] + action: replace + target_label: __metrics_path__ + regex: (.+) + - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_port, __meta_kubernetes_pod_ip] + action: replace + regex: (\d+);(([A-Fa-f0-9]{1,4}::?){1,7}[A-Fa-f0-9]{1,4}) + replacement: '[$2]:$1' + target_label: __address__ + - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_port, __meta_kubernetes_pod_ip] + action: replace + regex: (\d+);((([0-9]+?)(\.|$)){4}) + replacement: $2:$1 + target_label: __address__ + - action: labelmap + regex: __meta_kubernetes_pod_annotation_prometheus_io_param_(.+) + replacement: __param_$1 + - action: labelmap + regex: __meta_kubernetes_pod_label_(.+) + - source_labels: [__meta_kubernetes_namespace] + action: replace + target_label: namespace + - source_labels: [__meta_kubernetes_pod_name] + action: replace + target_label: pod + - source_labels: [__meta_kubernetes_pod_phase] + regex: Pending|Succeeded|Failed|Completed + action: drop + - source_labels: [__meta_kubernetes_pod_node_name] + action: replace + target_label: node + +# adds additional scrape configs to prometheus.yml +# must be a string so you have to add a | after extraScrapeConfigs: +# example adds prometheus-blackbox-exporter scrape config +extraScrapeConfigs: "" + # - job_name: 'prometheus-blackbox-exporter' + # metrics_path: /probe + # params: + # module: [http_2xx] + # static_configs: + # - targets: + # - https://example.com + # relabel_configs: + # - source_labels: [__address__] + # target_label: __param_target + # - source_labels: [__param_target] + # target_label: instance + # - target_label: __address__ + # replacement: prometheus-blackbox-exporter:9115 + +# Adds option to add alert_relabel_configs to avoid duplicate alerts in alertmanager +# useful in H/A prometheus with different external labels but the same alerts +alertRelabelConfigs: {} + # alert_relabel_configs: + # - source_labels: [dc] + # regex: (.+)\d+ + # target_label: dc + +networkPolicy: + ## Enable creation of NetworkPolicy resources. + ## + enabled: false + +# Force namespace of namespaced resources +forceNamespace: "" + +# Extra manifests to deploy as an array +extraManifests: [] + # - | + # apiVersion: v1 + # kind: ConfigMap + # metadata: + # labels: + # name: prometheus-extra + # data: + # extra-data: "value" + +# Configuration of subcharts defined in Chart.yaml + +## alertmanager sub-chart configurable values +## Please see https://github.com/prometheus-community/helm-charts/tree/main/charts/alertmanager +## +alertmanager: + ## If false, alertmanager will not be installed + ## + enabled: true + + persistence: + size: 2Gi + + podSecurityContext: + runAsUser: 65534 + runAsNonRoot: true + runAsGroup: 65534 + fsGroup: 65534 + +## kube-state-metrics sub-chart configurable values +## Please see https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-state-metrics +## +kube-state-metrics: + ## If false, kube-state-metrics sub-chart will not be installed + ## + enabled: true + +## prometheus-node-exporter sub-chart configurable values +## Please see https://github.com/prometheus-community/helm-charts/tree/main/charts/prometheus-node-exporter +## +prometheus-node-exporter: + ## If false, node-exporter will not be installed + ## + enabled: true + + rbac: + pspEnabled: false + + containerSecurityContext: + allowPrivilegeEscalation: false + +## prometheus-pushgateway sub-chart configurable values +## Please see https://github.com/prometheus-community/helm-charts/tree/main/charts/prometheus-pushgateway +## +prometheus-pushgateway: + ## If false, pushgateway will not be installed + ## + enabled: true + + # Optional service annotations + serviceAnnotations: + prometheus.io/probe: pushgateway diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/.helmignore new file mode 100644 index 0000000..f0c1319 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/.helmignore @@ -0,0 +1,21 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/Chart.lock b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/Chart.lock new file mode 100644 index 0000000..292abdd --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/Chart.lock @@ -0,0 +1,6 @@ +dependencies: +- name: common + repository: oci://registry-1.docker.io/bitnamicharts + version: 2.4.0 +digest: sha256:8c1a5dc923412d11d4d841420494b499cb707305c8b9f87f45ea1a8bf3172cb3 +generated: "2023-05-21T16:02:30.719339666Z" diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/Chart.yaml new file mode 100644 index 0000000..b845d05 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/Chart.yaml @@ -0,0 +1,26 @@ +annotations: + category: Infrastructure + licenses: Apache-2.0 +apiVersion: v2 +appVersion: 3.12.0 +dependencies: +- name: common + repository: oci://registry-1.docker.io/bitnamicharts + tags: + - bitnami-common + version: 2.x.x +description: RabbitMQ is an open source general-purpose message broker that is designed + for consistent, highly-available messaging scenarios (both synchronous and asynchronous). +home: https://bitnami.com +icon: https://bitnami.com/assets/stacks/rabbitmq/img/rabbitmq-stack-220x234.png +keywords: +- rabbitmq +- message queue +- AMQP +maintainers: +- name: VMware, Inc. + url: https://github.com/bitnami/charts +name: rabbitmq +sources: +- https://github.com/bitnami/charts/tree/main/bitnami/rabbitmq +version: 12.0.0 diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/README.md b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/README.md new file mode 100644 index 0000000..d3c1ee8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/README.md @@ -0,0 +1,728 @@ + + +# RabbitMQ packaged by Bitnami + +RabbitMQ is an open source general-purpose message broker that is designed for consistent, highly-available messaging scenarios (both synchronous and asynchronous). + +[Overview of RabbitMQ](https://www.rabbitmq.com) + +Trademarks: This software listing is packaged by Bitnami. The respective trademarks mentioned in the offering are owned by the respective companies, and use of them does not imply any affiliation or endorsement. + +## TL;DR + +```console +helm install my-release oci://registry-1.docker.io/bitnamicharts/rabbitmq +``` + +## Introduction + +This chart bootstraps a [RabbitMQ](https://github.com/bitnami/containers/tree/main/bitnami/rabbitmq) deployment on a [Kubernetes](https://kubernetes.io) cluster using the [Helm](https://helm.sh) package manager. + +Bitnami charts can be used with [Kubeapps](https://kubeapps.dev/) for deployment and management of Helm Charts in clusters. + +## Prerequisites + +- Kubernetes 1.19+ +- Helm 3.2.0+ +- PV provisioner support in the underlying infrastructure + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```console +helm install my-release oci://registry-1.docker.io/bitnamicharts/rabbitmq +``` + +The command deploys RabbitMQ on the Kubernetes cluster in the default configuration. The [Parameters](#parameters) section lists the parameters that can be configured during installation. + +> **Tip**: List all releases using `helm list` + +## Uninstalling the Chart + +To uninstall/delete the `my-release` deployment: + +```console +helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + +## Parameters + +### Global parameters + +| Name | Description | Value | +| ------------------------- | ----------------------------------------------- | ----- | +| `global.imageRegistry` | Global Docker image registry | `""` | +| `global.imagePullSecrets` | Global Docker registry secret names as an array | `[]` | +| `global.storageClass` | Global StorageClass for Persistent Volume(s) | `""` | + +### RabbitMQ Image parameters + +| Name | Description | Value | +| ------------------- | -------------------------------------------------------------------------------------------------------- | --------------------- | +| `image.registry` | RabbitMQ image registry | `docker.io` | +| `image.repository` | RabbitMQ image repository | `bitnami/rabbitmq` | +| `image.tag` | RabbitMQ image tag (immutable tags are recommended) | `3.12.0-debian-11-r0` | +| `image.digest` | RabbitMQ image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag | `""` | +| `image.pullPolicy` | RabbitMQ image pull policy | `IfNotPresent` | +| `image.pullSecrets` | Specify docker-registry secret names as an array | `[]` | +| `image.debug` | Set to true if you would like to see extra information on logs | `false` | + +### Common parameters + +| Name | Description | Value | +| -------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------- | +| `nameOverride` | String to partially override rabbitmq.fullname template (will maintain the release name) | `""` | +| `fullnameOverride` | String to fully override rabbitmq.fullname template | `""` | +| `namespaceOverride` | String to fully override common.names.namespace | `""` | +| `kubeVersion` | Force target Kubernetes version (using Helm capabilities if not set) | `""` | +| `clusterDomain` | Kubernetes Cluster Domain | `cluster.local` | +| `extraDeploy` | Array of extra objects to deploy with the release | `[]` | +| `commonAnnotations` | Annotations to add to all deployed objects | `{}` | +| `servicenameOverride` | String to partially override headless service name | `""` | +| `commonLabels` | Labels to add to all deployed objects | `{}` | +| `serviceBindings.enabled` | Create secret for service binding (Experimental) | `false` | +| `diagnosticMode.enabled` | Enable diagnostic mode (all probes will be disabled and the command will be overridden) | `false` | +| `diagnosticMode.command` | Command to override all containers in the deployment | `["sleep"]` | +| `diagnosticMode.args` | Args to override all containers in the deployment | `["infinity"]` | +| `hostAliases` | Deployment pod host aliases | `[]` | +| `dnsPolicy` | DNS Policy for pod | `""` | +| `dnsConfig` | DNS Configuration pod | `{}` | +| `auth.username` | RabbitMQ application username | `user` | +| `auth.password` | RabbitMQ application password | `""` | +| `auth.securePassword` | Whether to set the RabbitMQ password securely. This is incompatible with loading external RabbitMQ definitions and 'true' when not setting the auth.password parameter. | `true` | +| `auth.existingPasswordSecret` | Existing secret with RabbitMQ credentials (must contain a value for `rabbitmq-password` key) | `""` | +| `auth.enableLoopbackUser` | If enabled, the user `auth.username` can only connect from localhost | `false` | +| `auth.erlangCookie` | Erlang cookie to determine whether different nodes are allowed to communicate with each other | `""` | +| `auth.existingErlangSecret` | Existing secret with RabbitMQ Erlang cookie (must contain a value for `rabbitmq-erlang-cookie` key) | `""` | +| `auth.tls.enabled` | Enable TLS support on RabbitMQ | `false` | +| `auth.tls.autoGenerated` | Generate automatically self-signed TLS certificates | `false` | +| `auth.tls.failIfNoPeerCert` | When set to true, TLS connection will be rejected if client fails to provide a certificate | `true` | +| `auth.tls.sslOptionsVerify` | Should [peer verification](https://www.rabbitmq.com/ssl.html#peer-verification) be enabled? | `verify_peer` | +| `auth.tls.sslOptionsPassword.enabled` | Enable usage of password for private Key | `false` | +| `auth.tls.sslOptionsPassword.existingSecret` | Name of existing Secret containing the sslOptionsPassword | `""` | +| `auth.tls.sslOptionsPassword.key` | Enable Key referring to sslOptionsPassword in Secret specified in auth.tls.sslOptionsPassword.existingSecret | `""` | +| `auth.tls.sslOptionsPassword.password` | Use this string as Password. If set, auth.tls.sslOptionsPassword.existingSecret and auth.tls.sslOptionsPassword.key are ignored | `""` | +| `auth.tls.caCertificate` | Certificate Authority (CA) bundle content | `""` | +| `auth.tls.serverCertificate` | Server certificate content | `""` | +| `auth.tls.serverKey` | Server private key content | `""` | +| `auth.tls.existingSecret` | Existing secret with certificate content to RabbitMQ credentials | `""` | +| `auth.tls.existingSecretFullChain` | Whether or not the existing secret contains the full chain in the certificate (`tls.crt`). Will be used in place of `ca.cert` if `true`. | `false` | +| `auth.tls.overrideCaCertificate` | Existing secret with certificate content be mounted instead of the `ca.crt` coming from caCertificate or existingSecret/existingSecretFullChain. | `""` | +| `logs` | Path of the RabbitMQ server's Erlang log file. Value for the `RABBITMQ_LOGS` environment variable | `-` | +| `ulimitNofiles` | RabbitMQ Max File Descriptors | `65536` | +| `maxAvailableSchedulers` | RabbitMQ maximum available scheduler threads | `""` | +| `onlineSchedulers` | RabbitMQ online scheduler threads | `""` | +| `memoryHighWatermark.enabled` | Enable configuring Memory high watermark on RabbitMQ | `false` | +| `memoryHighWatermark.type` | Memory high watermark type. Either `absolute` or `relative` | `relative` | +| `memoryHighWatermark.value` | Memory high watermark value | `0.4` | +| `plugins` | List of default plugins to enable (should only be altered to remove defaults; for additional plugins use `extraPlugins`) | `rabbitmq_management rabbitmq_peer_discovery_k8s` | +| `communityPlugins` | List of Community plugins (URLs) to be downloaded during container initialization | `""` | +| `extraPlugins` | Extra plugins to enable (single string containing a space-separated list) | `rabbitmq_auth_backend_ldap` | +| `clustering.enabled` | Enable RabbitMQ clustering | `true` | +| `clustering.addressType` | Switch clustering mode. Either `ip` or `hostname` | `hostname` | +| `clustering.rebalance` | Rebalance master for queues in cluster when new replica is created | `false` | +| `clustering.forceBoot` | Force boot of an unexpectedly shut down cluster (in an unexpected order). | `false` | +| `clustering.partitionHandling` | Switch Partition Handling Strategy. Either `autoheal` or `pause-minority` or `pause-if-all-down` or `ignore` | `autoheal` | +| `loadDefinition.enabled` | Enable loading a RabbitMQ definitions file to configure RabbitMQ | `false` | +| `loadDefinition.file` | Name of the definitions file | `/app/load_definition.json` | +| `loadDefinition.existingSecret` | Existing secret with the load definitions file | `""` | +| `command` | Override default container command (useful when using custom images) | `[]` | +| `args` | Override default container args (useful when using custom images) | `[]` | +| `lifecycleHooks` | Overwrite livecycle for the RabbitMQ container(s) to automate configuration before or after startup | `{}` | +| `terminationGracePeriodSeconds` | Default duration in seconds k8s waits for container to exit before sending kill signal. | `120` | +| `extraEnvVars` | Extra environment variables to add to RabbitMQ pods | `[]` | +| `extraEnvVarsCM` | Name of existing ConfigMap containing extra environment variables | `""` | +| `extraEnvVarsSecret` | Name of existing Secret containing extra environment variables (in case of sensitive data) | `""` | +| `containerPorts.amqp` | | `5672` | +| `containerPorts.amqpTls` | | `5671` | +| `containerPorts.dist` | | `25672` | +| `containerPorts.manager` | | `15672` | +| `containerPorts.epmd` | | `4369` | +| `containerPorts.metrics` | | `9419` | +| `initScripts` | Dictionary of init scripts. Evaluated as a template. | `{}` | +| `initScriptsCM` | ConfigMap with the init scripts. Evaluated as a template. | `""` | +| `initScriptsSecret` | Secret containing `/docker-entrypoint-initdb.d` scripts to be executed at initialization time that contain sensitive data. Evaluated as a template. | `""` | +| `extraContainerPorts` | Extra ports to be included in container spec, primarily informational | `[]` | +| `configuration` | RabbitMQ Configuration file content: required cluster configuration | `""` | +| `tcpListenOptions.backlog` | Maximum size of the unaccepted TCP connections queue | `128` | +| `tcpListenOptions.nodelay` | When set to true, deactivates Nagle's algorithm. Default is true. Highly recommended for most users. | `true` | +| `tcpListenOptions.linger.lingerOn` | Enable Server socket lingering | `true` | +| `tcpListenOptions.linger.timeout` | Server Socket lingering timeout | `0` | +| `tcpListenOptions.keepalive` | When set to true, enables TCP keepalives | `false` | +| `configurationExistingSecret` | Existing secret with the configuration to use as rabbitmq.conf. | `""` | +| `extraConfiguration` | Configuration file content: extra configuration to be appended to RabbitMQ configuration | `""` | +| `extraConfigurationExistingSecret` | Existing secret with the extra configuration to append to `configuration`. | `""` | +| `advancedConfiguration` | Configuration file content: advanced configuration | `""` | +| `advancedConfigurationExistingSecret` | Existing secret with the advanced configuration file (must contain a key `advanced.config`). | `""` | +| `featureFlags` | that controls what features are considered to be enabled or available on all cluster nodes. | `""` | +| `ldap.enabled` | Enable LDAP support | `false` | +| `ldap.uri` | LDAP connection string. | `""` | +| `ldap.servers` | List of LDAP servers hostnames. This is valid only if ldap.uri is not set | `[]` | +| `ldap.port` | LDAP servers port. This is valid only if ldap.uri is not set | `""` | +| `ldap.userDnPattern` | Pattern used to translate the provided username into a value to be used for the LDAP bind. | `""` | +| `ldap.binddn` | DN of the account used to search in the LDAP server. | `""` | +| `ldap.bindpw` | Password for binddn account. | `""` | +| `ldap.basedn` | Base DN path where binddn account will search for the users. | `""` | +| `ldap.uidField` | Field used to match with the user name (uid, samAccountName, cn, etc). It matches with 'dn_lookup_attribute' in RabbitMQ configuration | `""` | +| `ldap.uidField` | Field used to match with the user name (uid, samAccountName, cn, etc). It matches with 'dn_lookup_attribute' in RabbitMQ configuration | `""` | +| `ldap.authorisationEnabled` | Enable LDAP authorisation. Please set 'advancedConfiguration' with tag, topic, resources and vhost mappings | `false` | +| `ldap.tls.enabled` | Enabled TLS configuration. | `false` | +| `ldap.tls.startTls` | Use STARTTLS instead of LDAPS. | `false` | +| `ldap.tls.skipVerify` | Skip any SSL verification (hostanames or certificates) | `false` | +| `ldap.tls.verify` | Verify connection. Valid values are 'verify_peer' or 'verify_none' | `verify_peer` | +| `ldap.tls.certificatesMountPath` | Where LDAP certifcates are mounted. | `/opt/bitnami/rabbitmq/ldap/certs` | +| `ldap.tls.certificatesSecret` | Secret with LDAP certificates. | `""` | +| `ldap.tls.CAFilename` | CA certificate filename. Should match with the CA entry key in the ldap.tls.certificatesSecret. | `""` | +| `ldap.tls.certFilename` | Client certificate filename to authenticate against the LDAP server. Should match with certificate the entry key in the ldap.tls.certificatesSecret. | `""` | +| `ldap.tls.certKeyFilename` | Client Key filename to authenticate against the LDAP server. Should match with certificate the entry key in the ldap.tls.certificatesSecret. | `""` | +| `extraVolumeMounts` | Optionally specify extra list of additional volumeMounts | `[]` | +| `extraVolumes` | Optionally specify extra list of additional volumes . | `[]` | +| `extraSecrets` | Optionally specify extra secrets to be created by the chart. | `{}` | +| `extraSecretsPrependReleaseName` | Set this flag to true if extraSecrets should be created with prepended. | `false` | + +### Statefulset parameters + +| Name | Description | Value | +| --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ | --------------- | +| `replicaCount` | Number of RabbitMQ replicas to deploy | `1` | +| `schedulerName` | Use an alternate scheduler, e.g. "stork". | `""` | +| `podManagementPolicy` | Pod management policy | `OrderedReady` | +| `podLabels` | RabbitMQ Pod labels. Evaluated as a template | `{}` | +| `podAnnotations` | RabbitMQ Pod annotations. Evaluated as a template | `{}` | +| `updateStrategy.type` | Update strategy type for RabbitMQ statefulset | `RollingUpdate` | +| `statefulsetLabels` | RabbitMQ statefulset labels. Evaluated as a template | `{}` | +| `statefulsetAnnotations` | RabbitMQ statefulset annotations. Evaluated as a template | `{}` | +| `priorityClassName` | Name of the priority class to be used by RabbitMQ pods, priority class needs to be created beforehand | `""` | +| `podAffinityPreset` | Pod affinity preset. Ignored if `affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `podAntiAffinityPreset` | Pod anti-affinity preset. Ignored if `affinity` is set. Allowed values: `soft` or `hard` | `soft` | +| `nodeAffinityPreset.type` | Node affinity preset type. Ignored if `affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `nodeAffinityPreset.key` | Node label key to match Ignored if `affinity` is set. | `""` | +| `nodeAffinityPreset.values` | Node label values to match. Ignored if `affinity` is set. | `[]` | +| `affinity` | Affinity for pod assignment. Evaluated as a template | `{}` | +| `nodeSelector` | Node labels for pod assignment. Evaluated as a template | `{}` | +| `tolerations` | Tolerations for pod assignment. Evaluated as a template | `[]` | +| `topologySpreadConstraints` | Topology Spread Constraints for pod assignment spread across your cluster among failure-domains. Evaluated as a template | `[]` | +| `podSecurityContext.enabled` | Enable RabbitMQ pods' Security Context | `true` | +| `podSecurityContext.fsGroup` | Set RabbitMQ pod's Security Context fsGroup | `1001` | +| `containerSecurityContext.enabled` | Enabled RabbitMQ containers' Security Context | `true` | +| `containerSecurityContext.runAsUser` | Set RabbitMQ containers' Security Context runAsUser | `1001` | +| `containerSecurityContext.runAsNonRoot` | Set RabbitMQ container's Security Context runAsNonRoot | `true` | +| `resources.limits` | The resources limits for RabbitMQ containers | `{}` | +| `resources.requests` | The requested resources for RabbitMQ containers | `{}` | +| `livenessProbe.enabled` | Enable livenessProbe | `true` | +| `livenessProbe.initialDelaySeconds` | Initial delay seconds for livenessProbe | `120` | +| `livenessProbe.periodSeconds` | Period seconds for livenessProbe | `30` | +| `livenessProbe.timeoutSeconds` | Timeout seconds for livenessProbe | `20` | +| `livenessProbe.failureThreshold` | Failure threshold for livenessProbe | `6` | +| `livenessProbe.successThreshold` | Success threshold for livenessProbe | `1` | +| `readinessProbe.enabled` | Enable readinessProbe | `true` | +| `readinessProbe.initialDelaySeconds` | Initial delay seconds for readinessProbe | `10` | +| `readinessProbe.periodSeconds` | Period seconds for readinessProbe | `30` | +| `readinessProbe.timeoutSeconds` | Timeout seconds for readinessProbe | `20` | +| `readinessProbe.failureThreshold` | Failure threshold for readinessProbe | `3` | +| `readinessProbe.successThreshold` | Success threshold for readinessProbe | `1` | +| `startupProbe.enabled` | Enable startupProbe | `false` | +| `startupProbe.initialDelaySeconds` | Initial delay seconds for startupProbe | `10` | +| `startupProbe.periodSeconds` | Period seconds for startupProbe | `30` | +| `startupProbe.timeoutSeconds` | Timeout seconds for startupProbe | `20` | +| `startupProbe.failureThreshold` | Failure threshold for startupProbe | `3` | +| `startupProbe.successThreshold` | Success threshold for startupProbe | `1` | +| `customLivenessProbe` | Override default liveness probe | `{}` | +| `customReadinessProbe` | Override default readiness probe | `{}` | +| `customStartupProbe` | Define a custom startup probe | `{}` | +| `initContainers` | Add init containers to the RabbitMQ pod | `[]` | +| `sidecars` | Add sidecar containers to the RabbitMQ pod | `[]` | +| `pdb.create` | Enable/disable a Pod Disruption Budget creation | `false` | +| `pdb.minAvailable` | Minimum number/percentage of pods that should remain scheduled | `1` | +| `pdb.maxUnavailable` | Maximum number/percentage of pods that may be made unavailable | `""` | + +### RBAC parameters + +| Name | Description | Value | +| --------------------------------------------- | ------------------------------------------------------------------------------------------ | ------ | +| `serviceAccount.create` | Enable creation of ServiceAccount for RabbitMQ pods | `true` | +| `serviceAccount.name` | Name of the created serviceAccount | `""` | +| `serviceAccount.automountServiceAccountToken` | Auto-mount the service account token in the pod | `true` | +| `serviceAccount.annotations` | Annotations for service account. Evaluated as a template. Only used if `create` is `true`. | `{}` | +| `rbac.create` | Whether RBAC rules should be created | `true` | + +### Persistence parameters + +| Name | Description | Value | +| --------------------------- | ------------------------------------------------ | -------------------------- | +| `persistence.enabled` | Enable RabbitMQ data persistence using PVC | `true` | +| `persistence.storageClass` | PVC Storage Class for RabbitMQ data volume | `""` | +| `persistence.selector` | Selector to match an existing Persistent Volume | `{}` | +| `persistence.accessModes` | PVC Access Modes for RabbitMQ data volume | `["ReadWriteOnce"]` | +| `persistence.existingClaim` | Provide an existing PersistentVolumeClaims | `""` | +| `persistence.mountPath` | The path the volume will be mounted at | `/bitnami/rabbitmq/mnesia` | +| `persistence.subPath` | The subdirectory of the volume to mount to | `""` | +| `persistence.size` | PVC Storage Request for RabbitMQ data volume | `8Gi` | +| `persistence.annotations` | Persistence annotations. Evaluated as a template | `{}` | +| `persistence.labels` | Persistence labels. Evaluated as a template | `{}` | + +### Exposure parameters + +| Name | Description | Value | +| ---------------------------------- | -------------------------------------------------------------------------------------------------------------------------------- | ------------------------ | +| `service.type` | Kubernetes Service type | `ClusterIP` | +| `service.portEnabled` | Amqp port. Cannot be disabled when `auth.tls.enabled` is `false`. Listener can be disabled with `listeners.tcp = none`. | `true` | +| `service.distPortEnabled` | Erlang distribution server port | `true` | +| `service.managerPortEnabled` | RabbitMQ Manager port | `true` | +| `service.epmdPortEnabled` | RabbitMQ EPMD Discovery service port | `true` | +| `service.ports.amqp` | Amqp service port | `5672` | +| `service.ports.amqpTls` | Amqp TLS service port | `5671` | +| `service.ports.dist` | Erlang distribution service port | `25672` | +| `service.ports.manager` | RabbitMQ Manager service port | `15672` | +| `service.ports.metrics` | RabbitMQ Prometheues metrics service port | `9419` | +| `service.ports.epmd` | EPMD Discovery service port | `4369` | +| `service.portNames.amqp` | Amqp service port name | `amqp` | +| `service.portNames.amqpTls` | Amqp TLS service port name | `amqp-tls` | +| `service.portNames.dist` | Erlang distribution service port name | `dist` | +| `service.portNames.manager` | RabbitMQ Manager service port name | `http-stats` | +| `service.portNames.metrics` | RabbitMQ Prometheues metrics service port name | `metrics` | +| `service.portNames.epmd` | EPMD Discovery service port name | `epmd` | +| `service.nodePorts.amqp` | Node port for Ampq | `""` | +| `service.nodePorts.amqpTls` | Node port for Ampq TLS | `""` | +| `service.nodePorts.dist` | Node port for Erlang distribution | `""` | +| `service.nodePorts.manager` | Node port for RabbitMQ Manager | `""` | +| `service.nodePorts.epmd` | Node port for EPMD Discovery | `""` | +| `service.nodePorts.metrics` | Node port for RabbitMQ Prometheues metrics | `""` | +| `service.extraPorts` | Extra ports to expose in the service | `[]` | +| `service.loadBalancerSourceRanges` | Address(es) that are allowed when service is `LoadBalancer` | `[]` | +| `service.externalIPs` | Set the ExternalIPs | `[]` | +| `service.externalTrafficPolicy` | Enable client source IP preservation | `Cluster` | +| `service.loadBalancerIP` | Set the LoadBalancerIP | `""` | +| `service.clusterIP` | Kubernetes service Cluster IP | `""` | +| `service.labels` | Service labels. Evaluated as a template | `{}` | +| `service.annotations` | Service annotations. Evaluated as a template | `{}` | +| `service.annotationsHeadless` | Headless Service annotations. Evaluated as a template | `{}` | +| `service.headless.annotations` | Annotations for the headless service. | `{}` | +| `service.sessionAffinity` | Session Affinity for Kubernetes service, can be "None" or "ClientIP" | `None` | +| `service.sessionAffinityConfig` | Additional settings for the sessionAffinity | `{}` | +| `ingress.enabled` | Enable ingress resource for Management console | `false` | +| `ingress.path` | Path for the default host. You may need to set this to '/*' in order to use this with ALB ingress controllers. | `/` | +| `ingress.pathType` | Ingress path type | `ImplementationSpecific` | +| `ingress.hostname` | Default host for the ingress resource | `rabbitmq.local` | +| `ingress.annotations` | Additional annotations for the Ingress resource. To enable certificate autogeneration, place here your cert-manager annotations. | `{}` | +| `ingress.tls` | Enable TLS configuration for the hostname defined at `ingress.hostname` parameter | `false` | +| `ingress.selfSigned` | Set this to true in order to create a TLS secret for this ingress record | `false` | +| `ingress.extraHosts` | The list of additional hostnames to be covered with this ingress record. | `[]` | +| `ingress.extraPaths` | An array with additional arbitrary paths that may need to be added to the ingress under the main host | `[]` | +| `ingress.extraRules` | The list of additional rules to be added to this ingress record. Evaluated as a template | `[]` | +| `ingress.extraTls` | The tls configuration for additional hostnames to be covered with this ingress record. | `[]` | +| `ingress.secrets` | Custom TLS certificates as secrets | `[]` | +| `ingress.ingressClassName` | IngressClass that will be be used to implement the Ingress (Kubernetes 1.18+) | `""` | +| `ingress.existingSecret` | It is you own the certificate as secret. | `""` | +| `networkPolicy.enabled` | Enable creation of NetworkPolicy resources | `false` | +| `networkPolicy.allowExternal` | Don't require client label for connections | `true` | +| `networkPolicy.additionalRules` | Additional NetworkPolicy Ingress "from" rules to set. Note that all rules are OR-ed. | `[]` | + +### Metrics Parameters + +| Name | Description | Value | +| ------------------------------------------ | -------------------------------------------------------------------------------------- | --------------------- | +| `metrics.enabled` | Enable exposing RabbitMQ metrics to be gathered by Prometheus | `false` | +| `metrics.plugins` | Plugins to enable Prometheus metrics in RabbitMQ | `rabbitmq_prometheus` | +| `metrics.podAnnotations` | Annotations for enabling prometheus to access the metrics endpoint | `{}` | +| `metrics.serviceMonitor.enabled` | Create ServiceMonitor Resource for scraping metrics using PrometheusOperator | `false` | +| `metrics.serviceMonitor.namespace` | Specify the namespace in which the serviceMonitor resource will be created | `""` | +| `metrics.serviceMonitor.interval` | Specify the interval at which metrics should be scraped | `30s` | +| `metrics.serviceMonitor.scrapeTimeout` | Specify the timeout after which the scrape is ended | `""` | +| `metrics.serviceMonitor.jobLabel` | The name of the label on the target service to use as the job name in prometheus. | `""` | +| `metrics.serviceMonitor.relabelings` | RelabelConfigs to apply to samples before scraping. | `[]` | +| `metrics.serviceMonitor.metricRelabelings` | MetricsRelabelConfigs to apply to samples before ingestion. | `[]` | +| `metrics.serviceMonitor.honorLabels` | honorLabels chooses the metric's labels on collisions with target labels | `false` | +| `metrics.serviceMonitor.targetLabels` | Used to keep given service's labels in target | `{}` | +| `metrics.serviceMonitor.podTargetLabels` | Used to keep given pod's labels in target | `{}` | +| `metrics.serviceMonitor.path` | Define the path used by ServiceMonitor to scrap metrics | `""` | +| `metrics.serviceMonitor.params` | Define the HTTP URL parameters used by ServiceMonitor | `{}` | +| `metrics.serviceMonitor.selector` | ServiceMonitor selector labels | `{}` | +| `metrics.serviceMonitor.labels` | Extra labels for the ServiceMonitor | `{}` | +| `metrics.serviceMonitor.annotations` | Extra annotations for the ServiceMonitor | `{}` | +| `metrics.prometheusRule.enabled` | Set this to true to create prometheusRules for Prometheus operator | `false` | +| `metrics.prometheusRule.additionalLabels` | Additional labels that can be used so prometheusRules will be discovered by Prometheus | `{}` | +| `metrics.prometheusRule.namespace` | namespace where prometheusRules resource should be created | `""` | +| `metrics.prometheusRule.rules` | List of rules, used as template by Helm. | `[]` | + +### Init Container Parameters + +| Name | Description | Value | +| ------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------- | ----------------------- | +| `volumePermissions.enabled` | Enable init container that changes the owner and group of the persistent volume(s) mountpoint to `runAsUser:fsGroup` | `false` | +| `volumePermissions.image.registry` | Init container volume-permissions image registry | `docker.io` | +| `volumePermissions.image.repository` | Init container volume-permissions image repository | `bitnami/bitnami-shell` | +| `volumePermissions.image.tag` | Init container volume-permissions image tag | `11-debian-11-r123` | +| `volumePermissions.image.digest` | Init container volume-permissions image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag | `""` | +| `volumePermissions.image.pullPolicy` | Init container volume-permissions image pull policy | `IfNotPresent` | +| `volumePermissions.image.pullSecrets` | Specify docker-registry secret names as an array | `[]` | +| `volumePermissions.resources.limits` | Init container volume-permissions resource limits | `{}` | +| `volumePermissions.resources.requests` | Init container volume-permissions resource requests | `{}` | +| `volumePermissions.containerSecurityContext.runAsUser` | User ID for the init container | `0` | + +The above parameters map to the env variables defined in [bitnami/rabbitmq](https://github.com/bitnami/containers/tree/main/bitnami/rabbitmq). For more information please refer to the [bitnami/rabbitmq](https://github.com/bitnami/containers/tree/main/bitnami/rabbitmq) image documentation. + +Specify each parameter using the `--set key=value[,key=value]` argument to `helm install`. For example, + +```console +helm install my-release \ + --set auth.username=admin,auth.password=secretpassword,auth.erlangCookie=secretcookie \ + oci://registry-1.docker.io/bitnamicharts/rabbitmq +``` + +The above command sets the RabbitMQ admin username and password to `admin` and `secretpassword` respectively. Additionally the secure erlang cookie is set to `secretcookie`. + +> NOTE: Once this chart is deployed, it is not possible to change the application's access credentials, such as usernames or passwords, using Helm. To change these application credentials after deployment, delete any persistent volumes (PVs) used by the chart and re-deploy it, or use the application's built-in administrative tools if available. + +Alternatively, a YAML file that specifies the values for the parameters can be provided while installing the chart. For example, + +```console +helm install my-release -f values.yaml oci://registry-1.docker.io/bitnamicharts/rabbitmq +``` + +> **Tip**: You can use the default [values.yaml](values.yaml) + +## Configuration and installation details + +### [Rolling vs Immutable tags](https://docs.bitnami.com/containers/how-to/understand-rolling-tags-containers/) + +It is strongly recommended to use immutable tags in a production environment. This ensures your deployment does not change automatically if the same tag is updated with a different image. + +Bitnami will release a new chart updating its containers if a new version of the main container, significant changes, or critical vulnerabilities exist. + +### Set pod affinity + +This chart allows you to set your custom affinity using the `affinity` parameter. Find more information about Pod's affinity in the [kubernetes documentation](https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity). + +As an alternative, you can use of the preset configurations for pod affinity, pod anti-affinity, and node affinity available at the [bitnami/common](https://github.com/bitnami/charts/tree/main/bitnami/common#affinities) chart. To do so, set the `podAffinityPreset`, `podAntiAffinityPreset`, or `nodeAffinityPreset` parameters. + +### Scale horizontally + +To horizontally scale this chart once it has been deployed, two options are available: + +- Use the `kubectl scale` command. +- Upgrade the chart modifying the `replicaCount` parameter. + +> NOTE: It is mandatory to specify the password and Erlang cookie that was set the first time the chart was installed when upgrading the chart. + +When scaling down the solution, unnecessary RabbitMQ nodes are automatically stopped, but they are not removed from the cluster. You need to manually remove them by running the `rabbitmqctl forget_cluster_node` command. + +Refer to the chart documentation for [more information on scaling the Rabbit cluster horizontally](https://docs.bitnami.com/kubernetes/infrastructure/rabbitmq/administration/scale-deployment/). + +### Enable TLS support + +To enable TLS support, first generate the certificates as described in the [RabbitMQ documentation for SSL certificate generation](https://www.rabbitmq.com/ssl.html#automated-certificate-generation). + +Once the certificates are generated, you have two alternatives: + +- Create a secret with the certificates and associate the secret when deploying the chart +- Include the certificates in the *values.yaml* file when deploying the chart + +Set the *auth.tls.failIfNoPeerCert* parameter to *false* to allow a TLS connection if the client fails to provide a certificate. + +Set the *auth.tls.sslOptionsVerify* to *verify_peer* to force a node to perform peer verification. When set to *verify_none*, peer verification will be disabled and certificate exchange won't be performed. + +Refer to the chart documentation for [more information and examples of enabling TLS and using Let's Encrypt certificates](https://docs.bitnami.com/kubernetes/infrastructure/rabbitmq/administration/enable-tls-ingress/). + +### Load custom definitions + +It is possible to [load a RabbitMQ definitions file to configure RabbitMQ](https://www.rabbitmq.com/management.html#load-definitions). + +Because definitions may contain RabbitMQ credentials, [store the JSON as a Kubernetes secret](https://kubernetes.io/docs/concepts/configuration/secret/#using-secrets-as-files-from-a-pod). Within the secret's data, choose a key name that corresponds with the desired load definitions filename (i.e. `load_definition.json`) and use the JSON object as the value. + +Next, specify the `load_definitions` property as an `extraConfiguration` pointing to the load definition file path within the container (i.e. `/app/load_definition.json`) and set `loadDefinition.enable` to `true`. Any load definitions specified will be available within in the container at `/app`. + +> NOTE: Loading a definition will take precedence over any configuration done through [Helm values](#parameters). + +If needed, you can use `extraSecrets` to let the chart create the secret for you. This way, you don't need to manually create it before deploying a release. These secrets can also be templated to use supplied chart values. + +Refer to the chart documentation for [more information and configuration examples of loading custom definitions](https://docs.bitnami.com/kubernetes/infrastructure/rabbitmq/configuration/load-files/). + +### Configure LDAP support + +LDAP support can be enabled in the chart by specifying the `ldap.*` parameters while creating a release. Refer to the chart documentation for [more information and a configuration example](https://docs.bitnami.com/kubernetes/infrastructure/rabbitmq/configuration/configure-ldap/). + +### Configure memory high watermark + +It is possible to configure a memory high watermark on RabbitMQ to define [memory thresholds](https://www.rabbitmq.com/memory.html#threshold) using the `memoryHighWatermark.*` parameters. To do so, you have two alternatives: + +- Set an absolute limit of RAM to be used on each RabbitMQ node, as shown in the configuration example below: + +```text +memoryHighWatermark.enabled="true" +memoryHighWatermark.type="absolute" +memoryHighWatermark.value="512MB" +``` + +- Set a relative limit of RAM to be used on each RabbitMQ node. To enable this feature, define the memory limits at pod level too. An example configuration is shown below: + +```text +memoryHighWatermark.enabled="true" +memoryHighWatermark.type="relative" +memoryHighWatermark.value="0.4" +resources.limits.memory="2Gi" +``` + +### Add extra environment variables + +In case you want to add extra environment variables (useful for advanced operations like custom init scripts), you can use the `extraEnvVars` property. + +```yaml +extraEnvVars: + - name: LOG_LEVEL + value: error +``` + +Alternatively, you can use a ConfigMap or a Secret with the environment variables. To do so, use the `.extraEnvVarsCM` or the `extraEnvVarsSecret` properties. + +### Use plugins + +The Bitnami Docker RabbitMQ image ships a set of plugins by default. By default, this chart enables `rabbitmq_management` and `rabbitmq_peer_discovery_k8s` since they are required for RabbitMQ to work on K8s. + +To enable extra plugins, set the `extraPlugins` parameter with the list of plugins you want to enable. In addition to this, the `communityPlugins` parameter can be used to specify a list of URLs (separated by spaces) for custom plugins for RabbitMQ. + +Refer to the chart documentation for [more information on using RabbitMQ plugins](https://docs.bitnami.com/kubernetes/infrastructure/rabbitmq/configuration/use-plugins/). + +### Advanced logging + +In case you want to configure RabbitMQ logging set `logs` value to false and set the log config in extraConfiguration following the [official documentation](https://www.rabbitmq.com/logging.html#log-file-location). + +An example: + +```yaml +logs: false # custom logging +extraConfiguration: | + log.default.level = warning + log.file = false + log.console = true + log.console.level = warning + log.console.formatter = json +``` + +### Recover the cluster from complete shutdown + +> IMPORTANT: Some of these procedures can lead to data loss. Always make a backup beforehand. + +The RabbitMQ cluster is able to support multiple node failures but, in a situation in which all the nodes are brought down at the same time, the cluster might not be able to self-recover. + +This happens if the pod management policy of the statefulset is not `Parallel` and the last pod to be running wasn't the first pod of the statefulset. If that happens, update the pod management policy to recover a healthy state: + +```console +$ kubectl delete statefulset STATEFULSET_NAME --cascade=false +helm upgrade RELEASE_NAME oci://registry-1.docker.io/bitnamicharts/rabbitmq \ + --set podManagementPolicy=Parallel \ + --set replicaCount=NUMBER_OF_REPLICAS \ + --set auth.password=PASSWORD \ + --set auth.erlangCookie=ERLANG_COOKIE +``` + +For a faster resyncronization of the nodes, you can temporarily disable the readiness probe by setting `readinessProbe.enabled=false`. Bear in mind that the pods will be exposed before they are actually ready to process requests. + +If the steps above don't bring the cluster to a healthy state, it could be possible that none of the RabbitMQ nodes think they were the last node to be up during the shutdown. In those cases, you can force the boot of the nodes by specifying the `clustering.forceBoot=true` parameter (which will execute [`rabbitmqctl force_boot`](https://www.rabbitmq.com/rabbitmqctl.8.html#force_boot) in each pod): + +```console +helm upgrade RELEASE_NAME oci://registry-1.docker.io/bitnamicharts/rabbitmq \ + --set podManagementPolicy=Parallel \ + --set clustering.forceBoot=true \ + --set replicaCount=NUMBER_OF_REPLICAS \ + --set auth.password=PASSWORD \ + --set auth.erlangCookie=ERLANG_COOKIE +``` + +More information: [Clustering Guide: Restarting](https://www.rabbitmq.com/clustering.html#restarting). + +### Known issues + +- Changing the password through RabbitMQ's UI can make the pod fail due to the default liveness probes. If you do so, remember to make the chart aware of the new password. Updating the default secret with the password you set through RabbitMQ's UI will automatically recreate the pods. If you are using your own secret, you may have to manually recreate the pods. + +## Persistence + +The [Bitnami RabbitMQ](https://github.com/bitnami/containers/tree/main/bitnami/rabbitmq) image stores the RabbitMQ data and configurations at the `/opt/bitnami/rabbitmq/var/lib/rabbitmq/` path of the container. + +The chart mounts a [Persistent Volume](https://kubernetes.io/docs/concepts/storage/persistent-volumes/) at this location. By default, the volume is created using dynamic volume provisioning. An existing PersistentVolumeClaim can also be defined. + +### Use existing PersistentVolumeClaims + +1. Create the PersistentVolume +2. Create the PersistentVolumeClaim +3. Install the chart + +```console +helm install my-release --set persistence.existingClaim=PVC_NAME oci://registry-1.docker.io/bitnamicharts/rabbitmq +``` + +### Adjust permissions of the persistence volume mountpoint + +As the image runs as non-root by default, it is necessary to adjust the ownership of the persistent volume so that the container can write data into it. + +By default, the chart is configured to use Kubernetes Security Context to automatically change the ownership of the volume. However, this feature does not work in all Kubernetes distributions. +As an alternative, this chart supports using an `initContainer` to change the ownership of the volume before mounting it in the final destination. + +You can enable this `initContainer` by setting `volumePermissions.enabled` to `true`. + +### Configure the default user/vhost + +If you want to create default user/vhost and set the default permission. you can use `extraConfiguration`: + +```yaml +auth: + username: default-user +extraConfiguration: |- + default_vhost = default-vhost + default_permissions.configure = .* + default_permissions.read = .* + default_permissions.write = .* +``` + +## Troubleshooting + +Find more information about how to deal with common errors related to Bitnami's Helm charts in [this troubleshooting guide](https://docs.bitnami.com/general/how-to/troubleshoot-helm-chart-issues). + +## Upgrading + +It's necessary to set the `auth.password` and `auth.erlangCookie` parameters when upgrading for readiness/liveness probes to work properly. When you install this chart for the first time, some notes will be displayed providing the credentials you must use under the 'Credentials' section. Please note down the password and the cookie, and run the command below to upgrade your chart: + +```console +helm upgrade my-release oci://registry-1.docker.io/bitnamicharts/rabbitmq --set auth.password=[PASSWORD] --set auth.erlangCookie=[RABBITMQ_ERLANG_COOKIE] +``` + +| Note: you need to substitute the placeholders [PASSWORD] and [RABBITMQ_ERLANG_COOKIE] with the values obtained in the installation notes. + +### To 11.0.0 + +This major version changes the default RabbitMQ image from 3.10.x to 3.11.x. Follow the [official instructions](https://www.rabbitmq.com/upgrade.html) to upgrade from 3.10 to 3.11. + +### To 10.0.0 + +This major version changes the default RabbitMQ image from 3.9.x to 3.10.x. Follow the [official instructions](https://www.rabbitmq.com/upgrade.html) to upgrade from 3.9 to 3.10. + +### To 9.0.0 + +This major release renames several values in this chart and adds missing features, in order to be aligned with the rest of the assets in the Bitnami charts repository. + + .dist + .manager + .metrics + .epmd + +- `service.port` has been renamed as `service.ports.amqp`. +- `service.portName` has been renamed as `service.portNames.amqp`. +- `service.nodePort`has been renamed as `service.nodePorts.amqp`. +- `service.tlsPort` has been renamed as `service.ports.amqpTls`. +- `service.tlsPortName` has been renamed as `service.portNames.amqpTls`. +- `service.tlsNodePort` has been renamed as `service.nodePorts.amqpTls`. +- `service.epmdPortName` has been renamed as `service.portNames.epmd`. +- `service.epmdNodePort` has been renamed as `service.nodePorts.epmd`. +- `service.distPort` has been renamed as `service.ports.dist`. +- `service.distPortName` has been renamed as `service.portNames.dist`. +- `service.distNodePort` has been renamed as `service.nodePorts.dist`. +- `service.managerPort` has been renamed as `service.ports.manager`. +- `service.managerPortName` has been renamed as `service.portNames.manager`. +- `service.managerNodePort` has been renamed as `service.nodePorts.manager`. +- `service.metricsPort` has been renamed as `service.ports.metrics`. +- `service.metricsPortName` has been renamed as `service.portNames.metrics`. +- `service.metricsNodePort` has been renamed as `service.nodePorts.metrics`. +- `persistence.volumes` has been removed, as it duplicates the parameter `extraVolumes`. +- `ingress.certManager` has been removed. +- `metrics.serviceMonitor.relabellings` has been replaced with `metrics.serviceMonitor.relabelings`, and it sets the field `relabelings` instead of `metricRelabelings`. +- `metrics.serviceMonitor.additionalLabels` has been renamed as `metrics.serviceMonitor.labels` +- `updateStrategyType` has been removed, use the field `updateStrategy` instead, which is interpreted as a template. +- The content of `podSecurityContext` and `containerSecurityContext` have been modified. +- The behavior of VolumePermissions has been modified to not change ownership of '.snapshot' and 'lost+found' +- Introduced the values `ContainerPorts.*`, separating the service and container ports configuration. + +### To 8.21.0 + +This new version of the chart bumps the RabbitMQ version to `3.9.1`. It is considered a minor release, and no breaking changes are expected. Additionally, RabbitMQ `3.9.X` nodes can run alongside `3.8.X` nodes. + +See the [Upgrading guide](https://www.rabbitmq.com/upgrade.html) and the [RabbitMQ change log](https://www.rabbitmq.com/changelog.html) for further documentation. + +### To 8.0.0 + +[On November 13, 2020, Helm v2 support was formally finished](https://github.com/helm/charts#status-of-the-project), this major version is the result of the required changes applied to the Helm Chart to be able to incorporate the different features added in Helm v3 and to be consistent with the Helm project itself regarding the Helm v2 EOL. + +[Learn more about this change and related upgrade considerations](https://docs.bitnami.com/kubernetes/infrastructure/rabbitmq/administration/upgrade-helm3/). + +### To 7.0.0 + +- Several parameters were renamed or disappeared in favor of new ones on this major version: + - `replicas` is renamed to `replicaCount`. + - `securityContext.*` is deprecated in favor of `podSecurityContext` and `containerSecurityContext`. + - Authentication parameters were reorganized under the `auth.*` parameter: + - `rabbitmq.username`, `rabbitmq.password`, and `rabbitmq.erlangCookie` are now `auth.username`, `auth.password`, and `auth.erlangCookie` respectively. + - `rabbitmq.tls.*` parameters are now under `auth.tls.*`. + - Parameters prefixed with `rabbitmq.` were renamed removing the prefix. E.g. `rabbitmq.configuration` -> renamed to `configuration`. + - `rabbitmq.rabbitmqClusterNodeName` is deprecated. + - `rabbitmq.setUlimitNofiles` is deprecated. + - `forceBoot.enabled` is renamed to `clustering.forceBoot`. + - `loadDefinition.secretName` is renamed to `loadDefinition.existingSecret`. + - `metics.port` is remamed to `service.metricsPort`. + - `service.extraContainerPorts` is renamed to `extraContainerPorts`. + - `service.nodeTlsPort` is renamed to `service.tlsNodePort`. + - `podDisruptionBudget` is deprecated in favor of `pdb.create`, `pdb.minAvailable`, and `pdb.maxUnavailable`. + - `rbacEnabled` -> deprecated in favor of `rbac.create`. + - New parameters: `serviceAccount.create`, and `serviceAccount.name`. + - New parameters: `memoryHighWatermark.enabled`, `memoryHighWatermark.type`, and `memoryHighWatermark.value`. +- Chart labels and Ingress configuration were adapted to follow the Helm charts best practices. +- Initialization logic now relies on the container. +- This version introduces `bitnami/common`, a [library chart](https://helm.sh/docs/topics/library_charts/#helm) as a dependency. More documentation about this new utility could be found [here](https://github.com/bitnami/charts/tree/main/bitnami/common#bitnami-common-library-chart). Please, make sure that you have updated the chart dependencies before executing any upgrade. +- The layout of the persistent volumes has changed (if using persistence). Action is required if preserving data through the upgrade is desired: + - The data has moved from `mnesia/` within the persistent volume to the root of the persistent volume + - The `config/` and `schema/` directories within the persistent volume are no longer used + - An init container can be used to move and clean up the peristent volumes. An example can be found [here](https://github.com/bitnami/charts/issues/10913#issuecomment-1169619513). + - Alternately the value `persistence.subPath` can be overridden to be `mnesia` so that the directory layout is consistent with what it was previously. + - Note however that this will leave the unused `config/` and `schema/` directories within the peristent volume forever. + +Consequences: + +- Backwards compatibility is not guaranteed. +- Compatibility with non Bitnami images is not guaranteed anymore. + +### To 6.0.0 + +This new version updates the RabbitMQ image to a [new version based on bash instead of node.js](https://github.com/bitnami/containers/tree/main/bitnami/rabbitmq#3715-r18-3715-ol-7-r19). However, since this Chart overwrites the container's command, the changes to the container shouldn't affect the Chart. To upgrade, it may be needed to enable the `fastBoot` option, as it is already the case from upgrading from 5.X to 5.Y. + +### To 5.0.0 + +This major release changes the clustering method from `ip` to `hostname`. +This change is needed to fix the persistence. The data dir will now depend on the hostname which is stable instead of the pod IP that might change. + +> IMPORTANT: Note that if you upgrade from a previous version you will lose your data. + +### To 3.0.0 + +Backwards compatibility is not guaranteed unless you modify the labels used on the chart's deployments. +Use the workaround below to upgrade from versions previous to 3.0.0. The following example assumes that the release name is rabbitmq: + +```console +kubectl delete statefulset rabbitmq --cascade=false +``` + +## Bitnami Kubernetes Documentation + +Bitnami Kubernetes documentation is available at [https://docs.bitnami.com/](https://docs.bitnami.com/). You can find there the following resources: + +- [Documentation for RabbitMQ Helm chart](https://docs.bitnami.com/kubernetes/infrastructure/rabbitmq/) +- [Get Started with Kubernetes guides](https://docs.bitnami.com/kubernetes/) +- [Bitnami Helm charts documentation](https://docs.bitnami.com/kubernetes/apps/) +- [Kubernetes FAQs](https://docs.bitnami.com/kubernetes/faq/) +- [Kubernetes Developer guides](https://docs.bitnami.com/tutorials/) + +## License + +Copyright © 2023 VMware, Inc. + +Licensed under the Apache License, Version 2.0 (the "License"); +you may not use this file except in compliance with the License. +You may obtain a copy of the License at + + + +Unless required by applicable law or agreed to in writing, software +distributed under the License is distributed on an "AS IS" BASIS, +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +See the License for the specific language governing permissions and +limitations under the License. \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/.helmignore new file mode 100644 index 0000000..50af031 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/.helmignore @@ -0,0 +1,22 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/Chart.yaml new file mode 100644 index 0000000..4fc56bb --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/Chart.yaml @@ -0,0 +1,23 @@ +annotations: + category: Infrastructure + licenses: Apache-2.0 +apiVersion: v2 +appVersion: 2.4.0 +description: A Library Helm Chart for grouping common logic between bitnami charts. + This chart is not deployable by itself. +home: https://bitnami.com +icon: https://bitnami.com/downloads/logos/bitnami-mark.png +keywords: +- common +- helper +- template +- function +- bitnami +maintainers: +- name: VMware, Inc. + url: https://github.com/bitnami/charts +name: common +sources: +- https://github.com/bitnami/charts +type: library +version: 2.4.0 diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/README.md b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/README.md new file mode 100644 index 0000000..72fca33 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/README.md @@ -0,0 +1,235 @@ +# Bitnami Common Library Chart + +A [Helm Library Chart](https://helm.sh/docs/topics/library_charts/#helm) for grouping common logic between Bitnami charts. + +Looking to use our applications in production? Try [VMware Application Catalog](https://bitnami.com/enterprise), the enterprise edition of Bitnami Application Catalog. + +## TL;DR + +```yaml +dependencies: + - name: common + version: 1.x.x + repository: oci://registry-1.docker.io/bitnamicharts +``` + +```console +helm dependency update +``` + +```yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "common.names.fullname" . }} +data: + myvalue: "Hello World" +``` + +## Introduction + +This chart provides a common template helpers which can be used to develop new charts using [Helm](https://helm.sh) package manager. + +Bitnami charts can be used with [Kubeapps](https://kubeapps.dev/) for deployment and management of Helm Charts in clusters. + +## Prerequisites + +- Kubernetes 1.19+ +- Helm 3.2.0+ + +## Parameters + +## Special input schemas + +### ImageRoot + +```yaml +registry: + type: string + description: Docker registry where the image is located + example: docker.io + +repository: + type: string + description: Repository and image name + example: bitnami/nginx + +tag: + type: string + description: image tag + example: 1.16.1-debian-10-r63 + +pullPolicy: + type: string + description: Specify a imagePullPolicy. Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + +pullSecrets: + type: array + items: + type: string + description: Optionally specify an array of imagePullSecrets (evaluated as templates). + +debug: + type: boolean + description: Set to true if you would like to see extra information on logs + example: false + +## An instance would be: +# registry: docker.io +# repository: bitnami/nginx +# tag: 1.16.1-debian-10-r63 +# pullPolicy: IfNotPresent +# debug: false +``` + +### Persistence + +```yaml +enabled: + type: boolean + description: Whether enable persistence. + example: true + +storageClass: + type: string + description: Ghost data Persistent Volume Storage Class, If set to "-", storageClassName: "" which disables dynamic provisioning. + example: "-" + +accessMode: + type: string + description: Access mode for the Persistent Volume Storage. + example: ReadWriteOnce + +size: + type: string + description: Size the Persistent Volume Storage. + example: 8Gi + +path: + type: string + description: Path to be persisted. + example: /bitnami + +## An instance would be: +# enabled: true +# storageClass: "-" +# accessMode: ReadWriteOnce +# size: 8Gi +# path: /bitnami +``` + +### ExistingSecret + +```yaml +name: + type: string + description: Name of the existing secret. + example: mySecret +keyMapping: + description: Mapping between the expected key name and the name of the key in the existing secret. + type: object + +## An instance would be: +# name: mySecret +# keyMapping: +# password: myPasswordKey +``` + +#### Example of use + +When we store sensitive data for a deployment in a secret, some times we want to give to users the possibility of using theirs existing secrets. + +```yaml +# templates/secret.yaml +--- +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "common.names.fullname" . }} + labels: + app: {{ include "common.names.fullname" . }} +type: Opaque +data: + password: {{ .Values.password | b64enc | quote }} + +# templates/dpl.yaml +--- +... + env: + - name: PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "common.secrets.name" (dict "existingSecret" .Values.existingSecret "context" $) }} + key: {{ include "common.secrets.key" (dict "existingSecret" .Values.existingSecret "key" "password") }} +... + +# values.yaml +--- +name: mySecret +keyMapping: + password: myPasswordKey +``` + +### ValidateValue + +#### NOTES.txt + +```console +{{- $validateValueConf00 := (dict "valueKey" "path.to.value00" "secret" "secretName" "field" "password-00") -}} +{{- $validateValueConf01 := (dict "valueKey" "path.to.value01" "secret" "secretName" "field" "password-01") -}} + +{{ include "common.validations.values.multiple.empty" (dict "required" (list $validateValueConf00 $validateValueConf01) "context" $) }} +``` + +If we force those values to be empty we will see some alerts + +```console +helm install test mychart --set path.to.value00="",path.to.value01="" + 'path.to.value00' must not be empty, please add '--set path.to.value00=$PASSWORD_00' to the command. To get the current value: + + export PASSWORD_00=$(kubectl get secret --namespace default secretName -o jsonpath="{.data.password-00}" | base64 -d) + + 'path.to.value01' must not be empty, please add '--set path.to.value01=$PASSWORD_01' to the command. To get the current value: + + export PASSWORD_01=$(kubectl get secret --namespace default secretName -o jsonpath="{.data.password-01}" | base64 -d) +``` + +## Upgrading + +### To 1.0.0 + +[On November 13, 2020, Helm v2 support was formally finished](https://github.com/helm/charts#status-of-the-project), this major version is the result of the required changes applied to the Helm Chart to be able to incorporate the different features added in Helm v3 and to be consistent with the Helm project itself regarding the Helm v2 EOL. + +#### What changes were introduced in this major version? + +- Previous versions of this Helm Chart use `apiVersion: v1` (installable by both Helm 2 and 3), this Helm Chart was updated to `apiVersion: v2` (installable by Helm 3 only). [Here](https://helm.sh/docs/topics/charts/#the-apiversion-field) you can find more information about the `apiVersion` field. +- Use `type: library`. [Here](https://v3.helm.sh/docs/faq/#library-chart-support) you can find more information. +- The different fields present in the *Chart.yaml* file has been ordered alphabetically in a homogeneous way for all the Bitnami Helm Charts + +#### Considerations when upgrading to this version + +- If you want to upgrade to this version from a previous one installed with Helm v3, you shouldn't face any issues +- If you want to upgrade to this version using Helm v2, this scenario is not supported as this version doesn't support Helm v2 anymore +- If you installed the previous version with Helm v2 and wants to upgrade to this version with Helm v3, please refer to the [official Helm documentation](https://helm.sh/docs/topics/v2_v3_migration/#migration-use-cases) about migrating from Helm v2 to v3 + +#### Useful links + +- +- +- + +## License + +Copyright © 2023 Bitnami + +Licensed under the Apache License, Version 2.0 (the "License"); +you may not use this file except in compliance with the License. +You may obtain a copy of the License at + + + +Unless required by applicable law or agreed to in writing, software +distributed under the License is distributed on an "AS IS" BASIS, +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +See the License for the specific language governing permissions and +limitations under the License. diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_affinities.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_affinities.tpl new file mode 100644 index 0000000..81902a6 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_affinities.tpl @@ -0,0 +1,106 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Return a soft nodeAffinity definition +{{ include "common.affinities.nodes.soft" (dict "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.nodes.soft" -}} +preferredDuringSchedulingIgnoredDuringExecution: + - preference: + matchExpressions: + - key: {{ .key }} + operator: In + values: + {{- range .values }} + - {{ . | quote }} + {{- end }} + weight: 1 +{{- end -}} + +{{/* +Return a hard nodeAffinity definition +{{ include "common.affinities.nodes.hard" (dict "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.nodes.hard" -}} +requiredDuringSchedulingIgnoredDuringExecution: + nodeSelectorTerms: + - matchExpressions: + - key: {{ .key }} + operator: In + values: + {{- range .values }} + - {{ . | quote }} + {{- end }} +{{- end -}} + +{{/* +Return a nodeAffinity definition +{{ include "common.affinities.nodes" (dict "type" "soft" "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.nodes" -}} + {{- if eq .type "soft" }} + {{- include "common.affinities.nodes.soft" . -}} + {{- else if eq .type "hard" }} + {{- include "common.affinities.nodes.hard" . -}} + {{- end -}} +{{- end -}} + +{{/* +Return a topologyKey definition +{{ include "common.affinities.topologyKey" (dict "topologyKey" "BAR") -}} +*/}} +{{- define "common.affinities.topologyKey" -}} +{{ .topologyKey | default "kubernetes.io/hostname" -}} +{{- end -}} + +{{/* +Return a soft podAffinity/podAntiAffinity definition +{{ include "common.affinities.pods.soft" (dict "component" "FOO" "extraMatchLabels" .Values.extraMatchLabels "topologyKey" "BAR" "context" $) -}} +*/}} +{{- define "common.affinities.pods.soft" -}} +{{- $component := default "" .component -}} +{{- $extraMatchLabels := default (dict) .extraMatchLabels -}} +preferredDuringSchedulingIgnoredDuringExecution: + - podAffinityTerm: + labelSelector: + matchLabels: {{- (include "common.labels.matchLabels" .context) | nindent 10 }} + {{- if not (empty $component) }} + {{ printf "app.kubernetes.io/component: %s" $component }} + {{- end }} + {{- range $key, $value := $extraMatchLabels }} + {{ $key }}: {{ $value | quote }} + {{- end }} + topologyKey: {{ include "common.affinities.topologyKey" (dict "topologyKey" .topologyKey) }} + weight: 1 +{{- end -}} + +{{/* +Return a hard podAffinity/podAntiAffinity definition +{{ include "common.affinities.pods.hard" (dict "component" "FOO" "extraMatchLabels" .Values.extraMatchLabels "topologyKey" "BAR" "context" $) -}} +*/}} +{{- define "common.affinities.pods.hard" -}} +{{- $component := default "" .component -}} +{{- $extraMatchLabels := default (dict) .extraMatchLabels -}} +requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: {{- (include "common.labels.matchLabels" .context) | nindent 8 }} + {{- if not (empty $component) }} + {{ printf "app.kubernetes.io/component: %s" $component }} + {{- end }} + {{- range $key, $value := $extraMatchLabels }} + {{ $key }}: {{ $value | quote }} + {{- end }} + topologyKey: {{ include "common.affinities.topologyKey" (dict "topologyKey" .topologyKey) }} +{{- end -}} + +{{/* +Return a podAffinity/podAntiAffinity definition +{{ include "common.affinities.pods" (dict "type" "soft" "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.pods" -}} + {{- if eq .type "soft" }} + {{- include "common.affinities.pods.soft" . -}} + {{- else if eq .type "hard" }} + {{- include "common.affinities.pods.hard" . -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_capabilities.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_capabilities.tpl new file mode 100644 index 0000000..697486a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_capabilities.tpl @@ -0,0 +1,180 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Return the target Kubernetes version +*/}} +{{- define "common.capabilities.kubeVersion" -}} +{{- if .Values.global }} + {{- if .Values.global.kubeVersion }} + {{- .Values.global.kubeVersion -}} + {{- else }} + {{- default .Capabilities.KubeVersion.Version .Values.kubeVersion -}} + {{- end -}} +{{- else }} +{{- default .Capabilities.KubeVersion.Version .Values.kubeVersion -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for poddisruptionbudget. +*/}} +{{- define "common.capabilities.policy.apiVersion" -}} +{{- if semverCompare "<1.21-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "policy/v1beta1" -}} +{{- else -}} +{{- print "policy/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for networkpolicy. +*/}} +{{- define "common.capabilities.networkPolicy.apiVersion" -}} +{{- if semverCompare "<1.7-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for cronjob. +*/}} +{{- define "common.capabilities.cronjob.apiVersion" -}} +{{- if semverCompare "<1.21-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "batch/v1beta1" -}} +{{- else -}} +{{- print "batch/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for daemonset. +*/}} +{{- define "common.capabilities.daemonset.apiVersion" -}} +{{- if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else -}} +{{- print "apps/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for deployment. +*/}} +{{- define "common.capabilities.deployment.apiVersion" -}} +{{- if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else -}} +{{- print "apps/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for statefulset. +*/}} +{{- define "common.capabilities.statefulset.apiVersion" -}} +{{- if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "apps/v1beta1" -}} +{{- else -}} +{{- print "apps/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "common.capabilities.ingress.apiVersion" -}} +{{- if .Values.ingress -}} +{{- if .Values.ingress.apiVersion -}} +{{- .Values.ingress.apiVersion -}} +{{- else if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else if semverCompare "<1.19-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "networking.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end }} +{{- else if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else if semverCompare "<1.19-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "networking.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for RBAC resources. +*/}} +{{- define "common.capabilities.rbac.apiVersion" -}} +{{- if semverCompare "<1.17-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "rbac.authorization.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "rbac.authorization.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for CRDs. +*/}} +{{- define "common.capabilities.crd.apiVersion" -}} +{{- if semverCompare "<1.19-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "apiextensions.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "apiextensions.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for APIService. +*/}} +{{- define "common.capabilities.apiService.apiVersion" -}} +{{- if semverCompare "<1.10-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "apiregistration.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "apiregistration.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for Horizontal Pod Autoscaler. +*/}} +{{- define "common.capabilities.hpa.apiVersion" -}} +{{- if semverCompare "<1.23-0" (include "common.capabilities.kubeVersion" .context) -}} +{{- if .beta2 -}} +{{- print "autoscaling/v2beta2" -}} +{{- else -}} +{{- print "autoscaling/v2beta1" -}} +{{- end -}} +{{- else -}} +{{- print "autoscaling/v2" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for Vertical Pod Autoscaler. +*/}} +{{- define "common.capabilities.vpa.apiVersion" -}} +{{- if semverCompare "<1.23-0" (include "common.capabilities.kubeVersion" .context) -}} +{{- if .beta2 -}} +{{- print "autoscaling/v2beta2" -}} +{{- else -}} +{{- print "autoscaling/v2beta1" -}} +{{- end -}} +{{- else -}} +{{- print "autoscaling/v2" -}} +{{- end -}} +{{- end -}} + +{{/* +Returns true if the used Helm version is 3.3+. +A way to check the used Helm version was not introduced until version 3.3.0 with .Capabilities.HelmVersion, which contains an additional "{}}" structure. +This check is introduced as a regexMatch instead of {{ if .Capabilities.HelmVersion }} because checking for the key HelmVersion in <3.3 results in a "interface not found" error. +**To be removed when the catalog's minimun Helm version is 3.3** +*/}} +{{- define "common.capabilities.supportsHelmVersion" -}} +{{- if regexMatch "{(v[0-9])*[^}]*}}$" (.Capabilities | toString ) }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_errors.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_errors.tpl new file mode 100644 index 0000000..a79cc2e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_errors.tpl @@ -0,0 +1,23 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Through error when upgrading using empty passwords values that must not be empty. + +Usage: +{{- $validationError00 := include "common.validations.values.single.empty" (dict "valueKey" "path.to.password00" "secret" "secretName" "field" "password-00") -}} +{{- $validationError01 := include "common.validations.values.single.empty" (dict "valueKey" "path.to.password01" "secret" "secretName" "field" "password-01") -}} +{{ include "common.errors.upgrade.passwords.empty" (dict "validationErrors" (list $validationError00 $validationError01) "context" $) }} + +Required password params: + - validationErrors - String - Required. List of validation strings to be return, if it is empty it won't throw error. + - context - Context - Required. Parent context. +*/}} +{{- define "common.errors.upgrade.passwords.empty" -}} + {{- $validationErrors := join "" .validationErrors -}} + {{- if and $validationErrors .context.Release.IsUpgrade -}} + {{- $errorString := "\nPASSWORDS ERROR: You must provide your current passwords when upgrading the release." -}} + {{- $errorString = print $errorString "\n Note that even after reinstallation, old credentials may be needed as they may be kept in persistent volume claims." -}} + {{- $errorString = print $errorString "\n Further information can be obtained at https://docs.bitnami.com/general/how-to/troubleshoot-helm-chart-issues/#credential-errors-while-upgrading-chart-releases" -}} + {{- $errorString = print $errorString "\n%s" -}} + {{- printf $errorString $validationErrors | fail -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_images.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_images.tpl new file mode 100644 index 0000000..d60c22e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_images.tpl @@ -0,0 +1,80 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Return the proper image name +{{ include "common.images.image" ( dict "imageRoot" .Values.path.to.the.image "global" .Values.global ) }} +*/}} +{{- define "common.images.image" -}} +{{- $registryName := .imageRoot.registry -}} +{{- $repositoryName := .imageRoot.repository -}} +{{- $separator := ":" -}} +{{- $termination := .imageRoot.tag | toString -}} +{{- if .global }} + {{- if .global.imageRegistry }} + {{- $registryName = .global.imageRegistry -}} + {{- end -}} +{{- end -}} +{{- if .imageRoot.digest }} + {{- $separator = "@" -}} + {{- $termination = .imageRoot.digest | toString -}} +{{- end -}} +{{- if $registryName }} + {{- printf "%s/%s%s%s" $registryName $repositoryName $separator $termination -}} +{{- else -}} + {{- printf "%s%s%s" $repositoryName $separator $termination -}} +{{- end -}} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names (deprecated: use common.images.renderPullSecrets instead) +{{ include "common.images.pullSecrets" ( dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "global" .Values.global) }} +*/}} +{{- define "common.images.pullSecrets" -}} + {{- $pullSecrets := list }} + + {{- if .global }} + {{- range .global.imagePullSecrets -}} + {{- $pullSecrets = append $pullSecrets . -}} + {{- end -}} + {{- end -}} + + {{- range .images -}} + {{- range .pullSecrets -}} + {{- $pullSecrets = append $pullSecrets . -}} + {{- end -}} + {{- end -}} + + {{- if (not (empty $pullSecrets)) }} +imagePullSecrets: + {{- range $pullSecrets | uniq }} + - name: {{ . }} + {{- end }} + {{- end }} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names evaluating values as templates +{{ include "common.images.renderPullSecrets" ( dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "context" $) }} +*/}} +{{- define "common.images.renderPullSecrets" -}} + {{- $pullSecrets := list }} + {{- $context := .context }} + + {{- if $context.Values.global }} + {{- range $context.Values.global.imagePullSecrets -}} + {{- $pullSecrets = append $pullSecrets (include "common.tplvalues.render" (dict "value" . "context" $context)) -}} + {{- end -}} + {{- end -}} + + {{- range .images -}} + {{- range .pullSecrets -}} + {{- $pullSecrets = append $pullSecrets (include "common.tplvalues.render" (dict "value" . "context" $context)) -}} + {{- end -}} + {{- end -}} + + {{- if (not (empty $pullSecrets)) }} +imagePullSecrets: + {{- range $pullSecrets | uniq }} + - name: {{ . }} + {{- end }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_ingress.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_ingress.tpl new file mode 100644 index 0000000..831da9c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_ingress.tpl @@ -0,0 +1,68 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Generate backend entry that is compatible with all Kubernetes API versions. + +Usage: +{{ include "common.ingress.backend" (dict "serviceName" "backendName" "servicePort" "backendPort" "context" $) }} + +Params: + - serviceName - String. Name of an existing service backend + - servicePort - String/Int. Port name (or number) of the service. It will be translated to different yaml depending if it is a string or an integer. + - context - Dict - Required. The context for the template evaluation. +*/}} +{{- define "common.ingress.backend" -}} +{{- $apiVersion := (include "common.capabilities.ingress.apiVersion" .context) -}} +{{- if or (eq $apiVersion "extensions/v1beta1") (eq $apiVersion "networking.k8s.io/v1beta1") -}} +serviceName: {{ .serviceName }} +servicePort: {{ .servicePort }} +{{- else -}} +service: + name: {{ .serviceName }} + port: + {{- if typeIs "string" .servicePort }} + name: {{ .servicePort }} + {{- else if or (typeIs "int" .servicePort) (typeIs "float64" .servicePort) }} + number: {{ .servicePort | int }} + {{- end }} +{{- end -}} +{{- end -}} + +{{/* +Print "true" if the API pathType field is supported +Usage: +{{ include "common.ingress.supportsPathType" . }} +*/}} +{{- define "common.ingress.supportsPathType" -}} +{{- if (semverCompare "<1.18-0" (include "common.capabilities.kubeVersion" .)) -}} +{{- print "false" -}} +{{- else -}} +{{- print "true" -}} +{{- end -}} +{{- end -}} + +{{/* +Returns true if the ingressClassname field is supported +Usage: +{{ include "common.ingress.supportsIngressClassname" . }} +*/}} +{{- define "common.ingress.supportsIngressClassname" -}} +{{- if semverCompare "<1.18-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "false" -}} +{{- else -}} +{{- print "true" -}} +{{- end -}} +{{- end -}} + +{{/* +Return true if cert-manager required annotations for TLS signed +certificates are set in the Ingress annotations +Ref: https://cert-manager.io/docs/usage/ingress/#supported-annotations +Usage: +{{ include "common.ingress.certManagerRequest" ( dict "annotations" .Values.path.to.the.ingress.annotations ) }} +*/}} +{{- define "common.ingress.certManagerRequest" -}} +{{ if or (hasKey .annotations "cert-manager.io/cluster-issuer") (hasKey .annotations "cert-manager.io/issuer") (hasKey .annotations "kubernetes.io/tls-acme") }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_labels.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_labels.tpl new file mode 100644 index 0000000..252066c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_labels.tpl @@ -0,0 +1,18 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Kubernetes standard labels +*/}} +{{- define "common.labels.standard" -}} +app.kubernetes.io/name: {{ include "common.names.name" . }} +helm.sh/chart: {{ include "common.names.chart" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end -}} + +{{/* +Labels to use on deploy.spec.selector.matchLabels and svc.spec.selector +*/}} +{{- define "common.labels.matchLabels" -}} +app.kubernetes.io/name: {{ include "common.names.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_names.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_names.tpl new file mode 100644 index 0000000..617a234 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_names.tpl @@ -0,0 +1,66 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "common.names.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "common.names.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "common.names.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Create a default fully qualified dependency name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +Usage: +{{ include "common.names.dependency.fullname" (dict "chartName" "dependency-chart-name" "chartValues" .Values.dependency-chart "context" $) }} +*/}} +{{- define "common.names.dependency.fullname" -}} +{{- if .chartValues.fullnameOverride -}} +{{- .chartValues.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .chartName .chartValues.nameOverride -}} +{{- if contains $name .context.Release.Name -}} +{{- .context.Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .context.Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts. +*/}} +{{- define "common.names.namespace" -}} +{{- default .Release.Namespace .Values.namespaceOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a fully qualified app name adding the installation's namespace. +*/}} +{{- define "common.names.fullname.namespace" -}} +{{- printf "%s-%s" (include "common.names.fullname" .) (include "common.names.namespace" .) | trunc 63 | trimSuffix "-" -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_secrets.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_secrets.tpl new file mode 100644 index 0000000..a1708b2 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_secrets.tpl @@ -0,0 +1,165 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Generate secret name. + +Usage: +{{ include "common.secrets.name" (dict "existingSecret" .Values.path.to.the.existingSecret "defaultNameSuffix" "mySuffix" "context" $) }} + +Params: + - existingSecret - ExistingSecret/String - Optional. The path to the existing secrets in the values.yaml given by the user + to be used instead of the default one. Allows for it to be of type String (just the secret name) for backwards compatibility. + +info: https://github.com/bitnami/charts/tree/main/bitnami/common#existingsecret + - defaultNameSuffix - String - Optional. It is used only if we have several secrets in the same deployment. + - context - Dict - Required. The context for the template evaluation. +*/}} +{{- define "common.secrets.name" -}} +{{- $name := (include "common.names.fullname" .context) -}} + +{{- if .defaultNameSuffix -}} +{{- $name = printf "%s-%s" $name .defaultNameSuffix | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{- with .existingSecret -}} +{{- if not (typeIs "string" .) -}} +{{- with .name -}} +{{- $name = . -}} +{{- end -}} +{{- else -}} +{{- $name = . -}} +{{- end -}} +{{- end -}} + +{{- printf "%s" $name -}} +{{- end -}} + +{{/* +Generate secret key. + +Usage: +{{ include "common.secrets.key" (dict "existingSecret" .Values.path.to.the.existingSecret "key" "keyName") }} + +Params: + - existingSecret - ExistingSecret/String - Optional. The path to the existing secrets in the values.yaml given by the user + to be used instead of the default one. Allows for it to be of type String (just the secret name) for backwards compatibility. + +info: https://github.com/bitnami/charts/tree/main/bitnami/common#existingsecret + - key - String - Required. Name of the key in the secret. +*/}} +{{- define "common.secrets.key" -}} +{{- $key := .key -}} + +{{- if .existingSecret -}} + {{- if not (typeIs "string" .existingSecret) -}} + {{- if .existingSecret.keyMapping -}} + {{- $key = index .existingSecret.keyMapping $.key -}} + {{- end -}} + {{- end }} +{{- end -}} + +{{- printf "%s" $key -}} +{{- end -}} + +{{/* +Generate secret password or retrieve one if already created. + +Usage: +{{ include "common.secrets.passwords.manage" (dict "secret" "secret-name" "key" "keyName" "providedValues" (list "path.to.password1" "path.to.password2") "length" 10 "strong" false "chartName" "chartName" "context" $) }} + +Params: + - secret - String - Required - Name of the 'Secret' resource where the password is stored. + - key - String - Required - Name of the key in the secret. + - providedValues - List - Required - The path to the validating value in the values.yaml, e.g: "mysql.password". Will pick first parameter with a defined value. + - length - int - Optional - Length of the generated random password. + - strong - Boolean - Optional - Whether to add symbols to the generated random password. + - chartName - String - Optional - Name of the chart used when said chart is deployed as a subchart. + - context - Context - Required - Parent context. + +The order in which this function returns a secret password: + 1. Already existing 'Secret' resource + (If a 'Secret' resource is found under the name provided to the 'secret' parameter to this function and that 'Secret' resource contains a key with the name passed as the 'key' parameter to this function then the value of this existing secret password will be returned) + 2. Password provided via the values.yaml + (If one of the keys passed to the 'providedValues' parameter to this function is a valid path to a key in the values.yaml and has a value, the value of the first key with a value will be returned) + 3. Randomly generated secret password + (A new random secret password with the length specified in the 'length' parameter will be generated and returned) + +*/}} +{{- define "common.secrets.passwords.manage" -}} + +{{- $password := "" }} +{{- $subchart := "" }} +{{- $chartName := default "" .chartName }} +{{- $passwordLength := default 10 .length }} +{{- $providedPasswordKey := include "common.utils.getKeyFromList" (dict "keys" .providedValues "context" $.context) }} +{{- $providedPasswordValue := include "common.utils.getValueFromKey" (dict "key" $providedPasswordKey "context" $.context) }} +{{- $secretData := (lookup "v1" "Secret" (include "common.names.namespace" .context) .secret).data }} +{{- if $secretData }} + {{- if hasKey $secretData .key }} + {{- $password = index $secretData .key | quote }} + {{- else }} + {{- printf "\nPASSWORDS ERROR: The secret \"%s\" does not contain the key \"%s\"\n" .secret .key | fail -}} + {{- end -}} +{{- else if $providedPasswordValue }} + {{- $password = $providedPasswordValue | toString | b64enc | quote }} +{{- else }} + + {{- if .context.Values.enabled }} + {{- $subchart = $chartName }} + {{- end -}} + + {{- $requiredPassword := dict "valueKey" $providedPasswordKey "secret" .secret "field" .key "subchart" $subchart "context" $.context -}} + {{- $requiredPasswordError := include "common.validations.values.single.empty" $requiredPassword -}} + {{- $passwordValidationErrors := list $requiredPasswordError -}} + {{- include "common.errors.upgrade.passwords.empty" (dict "validationErrors" $passwordValidationErrors "context" $.context) -}} + + {{- if .strong }} + {{- $subStr := list (lower (randAlpha 1)) (randNumeric 1) (upper (randAlpha 1)) | join "_" }} + {{- $password = randAscii $passwordLength }} + {{- $password = regexReplaceAllLiteral "\\W" $password "@" | substr 5 $passwordLength }} + {{- $password = printf "%s%s" $subStr $password | toString | shuffle | b64enc | quote }} + {{- else }} + {{- $password = randAlphaNum $passwordLength | b64enc | quote }} + {{- end }} +{{- end -}} +{{- printf "%s" $password -}} +{{- end -}} + +{{/* +Reuses the value from an existing secret, otherwise sets its value to a default value. + +Usage: +{{ include "common.secrets.lookup" (dict "secret" "secret-name" "key" "keyName" "defaultValue" .Values.myValue "context" $) }} + +Params: + - secret - String - Required - Name of the 'Secret' resource where the password is stored. + - key - String - Required - Name of the key in the secret. + - defaultValue - String - Required - The path to the validating value in the values.yaml, e.g: "mysql.password". Will pick first parameter with a defined value. + - context - Context - Required - Parent context. + +*/}} +{{- define "common.secrets.lookup" -}} +{{- $value := "" -}} +{{- $defaultValue := required "\n'common.secrets.lookup': Argument 'defaultValue' missing or empty" .defaultValue -}} +{{- $secretData := (lookup "v1" "Secret" (include "common.names.namespace" .context) .secret).data -}} +{{- if and $secretData (hasKey $secretData .key) -}} + {{- $value = index $secretData .key -}} +{{- else -}} + {{- $value = $defaultValue | toString | b64enc -}} +{{- end -}} +{{- printf "%s" $value -}} +{{- end -}} + +{{/* +Returns whether a previous generated secret already exists + +Usage: +{{ include "common.secrets.exists" (dict "secret" "secret-name" "context" $) }} + +Params: + - secret - String - Required - Name of the 'Secret' resource where the password is stored. + - context - Context - Required - Parent context. +*/}} +{{- define "common.secrets.exists" -}} +{{- $secret := (lookup "v1" "Secret" (include "common.names.namespace" .context) .secret) }} +{{- if $secret }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_storage.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_storage.tpl new file mode 100644 index 0000000..60e2a84 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_storage.tpl @@ -0,0 +1,23 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Return the proper Storage Class +{{ include "common.storage.class" ( dict "persistence" .Values.path.to.the.persistence "global" $) }} +*/}} +{{- define "common.storage.class" -}} + +{{- $storageClass := .persistence.storageClass -}} +{{- if .global -}} + {{- if .global.storageClass -}} + {{- $storageClass = .global.storageClass -}} + {{- end -}} +{{- end -}} + +{{- if $storageClass -}} + {{- if (eq "-" $storageClass) -}} + {{- printf "storageClassName: \"\"" -}} + {{- else }} + {{- printf "storageClassName: %s" $storageClass -}} + {{- end -}} +{{- end -}} + +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_tplvalues.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_tplvalues.tpl new file mode 100644 index 0000000..2db1668 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_tplvalues.tpl @@ -0,0 +1,13 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Renders a value that contains template. +Usage: +{{ include "common.tplvalues.render" ( dict "value" .Values.path.to.the.Value "context" $) }} +*/}} +{{- define "common.tplvalues.render" -}} + {{- if typeIs "string" .value }} + {{- tpl .value .context }} + {{- else }} + {{- tpl (.value | toYaml) .context }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_utils.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_utils.tpl new file mode 100644 index 0000000..b1ead50 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_utils.tpl @@ -0,0 +1,62 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Print instructions to get a secret value. +Usage: +{{ include "common.utils.secret.getvalue" (dict "secret" "secret-name" "field" "secret-value-field" "context" $) }} +*/}} +{{- define "common.utils.secret.getvalue" -}} +{{- $varname := include "common.utils.fieldToEnvVar" . -}} +export {{ $varname }}=$(kubectl get secret --namespace {{ include "common.names.namespace" .context | quote }} {{ .secret }} -o jsonpath="{.data.{{ .field }}}" | base64 -d) +{{- end -}} + +{{/* +Build env var name given a field +Usage: +{{ include "common.utils.fieldToEnvVar" dict "field" "my-password" }} +*/}} +{{- define "common.utils.fieldToEnvVar" -}} + {{- $fieldNameSplit := splitList "-" .field -}} + {{- $upperCaseFieldNameSplit := list -}} + + {{- range $fieldNameSplit -}} + {{- $upperCaseFieldNameSplit = append $upperCaseFieldNameSplit ( upper . ) -}} + {{- end -}} + + {{ join "_" $upperCaseFieldNameSplit }} +{{- end -}} + +{{/* +Gets a value from .Values given +Usage: +{{ include "common.utils.getValueFromKey" (dict "key" "path.to.key" "context" $) }} +*/}} +{{- define "common.utils.getValueFromKey" -}} +{{- $splitKey := splitList "." .key -}} +{{- $value := "" -}} +{{- $latestObj := $.context.Values -}} +{{- range $splitKey -}} + {{- if not $latestObj -}} + {{- printf "please review the entire path of '%s' exists in values" $.key | fail -}} + {{- end -}} + {{- $value = ( index $latestObj . ) -}} + {{- $latestObj = $value -}} +{{- end -}} +{{- printf "%v" (default "" $value) -}} +{{- end -}} + +{{/* +Returns first .Values key with a defined value or first of the list if all non-defined +Usage: +{{ include "common.utils.getKeyFromList" (dict "keys" (list "path.to.key1" "path.to.key2") "context" $) }} +*/}} +{{- define "common.utils.getKeyFromList" -}} +{{- $key := first .keys -}} +{{- $reverseKeys := reverse .keys }} +{{- range $reverseKeys }} + {{- $value := include "common.utils.getValueFromKey" (dict "key" . "context" $.context ) }} + {{- if $value -}} + {{- $key = . }} + {{- end -}} +{{- end -}} +{{- printf "%s" $key -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_warnings.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_warnings.tpl new file mode 100644 index 0000000..ae10fa4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/_warnings.tpl @@ -0,0 +1,14 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Warning about using rolling tag. +Usage: +{{ include "common.warnings.rollingTag" .Values.path.to.the.imageRoot }} +*/}} +{{- define "common.warnings.rollingTag" -}} + +{{- if and (contains "bitnami/" .repository) (not (.tag | toString | regexFind "-r\\d+$|sha256:")) }} +WARNING: Rolling tag detected ({{ .repository }}:{{ .tag }}), please note that it is strongly recommended to avoid using rolling tags in a production environment. ++info https://docs.bitnami.com/containers/how-to/understand-rolling-tags-containers/ +{{- end }} + +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_cassandra.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_cassandra.tpl new file mode 100644 index 0000000..ded1ae3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_cassandra.tpl @@ -0,0 +1,72 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate Cassandra required passwords are not empty. + +Usage: +{{ include "common.validations.values.cassandra.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where Cassandra values are stored, e.g: "cassandra-passwords-secret" + - subchart - Boolean - Optional. Whether Cassandra is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.cassandra.passwords" -}} + {{- $existingSecret := include "common.cassandra.values.existingSecret" . -}} + {{- $enabled := include "common.cassandra.values.enabled" . -}} + {{- $dbUserPrefix := include "common.cassandra.values.key.dbUser" . -}} + {{- $valueKeyPassword := printf "%s.password" $dbUserPrefix -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "cassandra-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.cassandra.values.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether Cassandra is used as subchart or not. Default: false +*/}} +{{- define "common.cassandra.values.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.cassandra.dbUser.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.dbUser.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled cassandra. + +Usage: +{{ include "common.cassandra.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.cassandra.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.cassandra.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key dbUser + +Usage: +{{ include "common.cassandra.values.key.dbUser" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether Cassandra is used as subchart or not. Default: false +*/}} +{{- define "common.cassandra.values.key.dbUser" -}} + {{- if .subchart -}} + cassandra.dbUser + {{- else -}} + dbUser + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_mariadb.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_mariadb.tpl new file mode 100644 index 0000000..b6906ff --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_mariadb.tpl @@ -0,0 +1,103 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate MariaDB required passwords are not empty. + +Usage: +{{ include "common.validations.values.mariadb.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where MariaDB values are stored, e.g: "mysql-passwords-secret" + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.mariadb.passwords" -}} + {{- $existingSecret := include "common.mariadb.values.auth.existingSecret" . -}} + {{- $enabled := include "common.mariadb.values.enabled" . -}} + {{- $architecture := include "common.mariadb.values.architecture" . -}} + {{- $authPrefix := include "common.mariadb.values.key.auth" . -}} + {{- $valueKeyRootPassword := printf "%s.rootPassword" $authPrefix -}} + {{- $valueKeyUsername := printf "%s.username" $authPrefix -}} + {{- $valueKeyPassword := printf "%s.password" $authPrefix -}} + {{- $valueKeyReplicationPassword := printf "%s.replicationPassword" $authPrefix -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredRootPassword := dict "valueKey" $valueKeyRootPassword "secret" .secret "field" "mariadb-root-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRootPassword -}} + + {{- $valueUsername := include "common.utils.getValueFromKey" (dict "key" $valueKeyUsername "context" .context) }} + {{- if not (empty $valueUsername) -}} + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "mariadb-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + {{- end -}} + + {{- if (eq $architecture "replication") -}} + {{- $requiredReplicationPassword := dict "valueKey" $valueKeyReplicationPassword "secret" .secret "field" "mariadb-replication-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredReplicationPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.mariadb.values.auth.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.mariadb.values.auth.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.mariadb.auth.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.auth.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled mariadb. + +Usage: +{{ include "common.mariadb.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.mariadb.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.mariadb.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for architecture + +Usage: +{{ include "common.mariadb.values.architecture" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.mariadb.values.architecture" -}} + {{- if .subchart -}} + {{- .context.Values.mariadb.architecture -}} + {{- else -}} + {{- .context.Values.architecture -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key auth + +Usage: +{{ include "common.mariadb.values.key.auth" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.mariadb.values.key.auth" -}} + {{- if .subchart -}} + mariadb.auth + {{- else -}} + auth + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_mongodb.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_mongodb.tpl new file mode 100644 index 0000000..f820ec1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_mongodb.tpl @@ -0,0 +1,108 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate MongoDB® required passwords are not empty. + +Usage: +{{ include "common.validations.values.mongodb.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where MongoDB® values are stored, e.g: "mongodb-passwords-secret" + - subchart - Boolean - Optional. Whether MongoDB® is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.mongodb.passwords" -}} + {{- $existingSecret := include "common.mongodb.values.auth.existingSecret" . -}} + {{- $enabled := include "common.mongodb.values.enabled" . -}} + {{- $authPrefix := include "common.mongodb.values.key.auth" . -}} + {{- $architecture := include "common.mongodb.values.architecture" . -}} + {{- $valueKeyRootPassword := printf "%s.rootPassword" $authPrefix -}} + {{- $valueKeyUsername := printf "%s.username" $authPrefix -}} + {{- $valueKeyDatabase := printf "%s.database" $authPrefix -}} + {{- $valueKeyPassword := printf "%s.password" $authPrefix -}} + {{- $valueKeyReplicaSetKey := printf "%s.replicaSetKey" $authPrefix -}} + {{- $valueKeyAuthEnabled := printf "%s.enabled" $authPrefix -}} + + {{- $authEnabled := include "common.utils.getValueFromKey" (dict "key" $valueKeyAuthEnabled "context" .context) -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") (eq $authEnabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredRootPassword := dict "valueKey" $valueKeyRootPassword "secret" .secret "field" "mongodb-root-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRootPassword -}} + + {{- $valueUsername := include "common.utils.getValueFromKey" (dict "key" $valueKeyUsername "context" .context) }} + {{- $valueDatabase := include "common.utils.getValueFromKey" (dict "key" $valueKeyDatabase "context" .context) }} + {{- if and $valueUsername $valueDatabase -}} + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "mongodb-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + {{- end -}} + + {{- if (eq $architecture "replicaset") -}} + {{- $requiredReplicaSetKey := dict "valueKey" $valueKeyReplicaSetKey "secret" .secret "field" "mongodb-replica-set-key" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredReplicaSetKey -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.mongodb.values.auth.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MongoDb is used as subchart or not. Default: false +*/}} +{{- define "common.mongodb.values.auth.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.mongodb.auth.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.auth.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled mongodb. + +Usage: +{{ include "common.mongodb.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.mongodb.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.mongodb.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key auth + +Usage: +{{ include "common.mongodb.values.key.auth" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MongoDB® is used as subchart or not. Default: false +*/}} +{{- define "common.mongodb.values.key.auth" -}} + {{- if .subchart -}} + mongodb.auth + {{- else -}} + auth + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for architecture + +Usage: +{{ include "common.mongodb.values.architecture" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MongoDB® is used as subchart or not. Default: false +*/}} +{{- define "common.mongodb.values.architecture" -}} + {{- if .subchart -}} + {{- .context.Values.mongodb.architecture -}} + {{- else -}} + {{- .context.Values.architecture -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_mysql.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_mysql.tpl new file mode 100644 index 0000000..74472a0 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_mysql.tpl @@ -0,0 +1,103 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate MySQL required passwords are not empty. + +Usage: +{{ include "common.validations.values.mysql.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where MySQL values are stored, e.g: "mysql-passwords-secret" + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.mysql.passwords" -}} + {{- $existingSecret := include "common.mysql.values.auth.existingSecret" . -}} + {{- $enabled := include "common.mysql.values.enabled" . -}} + {{- $architecture := include "common.mysql.values.architecture" . -}} + {{- $authPrefix := include "common.mysql.values.key.auth" . -}} + {{- $valueKeyRootPassword := printf "%s.rootPassword" $authPrefix -}} + {{- $valueKeyUsername := printf "%s.username" $authPrefix -}} + {{- $valueKeyPassword := printf "%s.password" $authPrefix -}} + {{- $valueKeyReplicationPassword := printf "%s.replicationPassword" $authPrefix -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredRootPassword := dict "valueKey" $valueKeyRootPassword "secret" .secret "field" "mysql-root-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRootPassword -}} + + {{- $valueUsername := include "common.utils.getValueFromKey" (dict "key" $valueKeyUsername "context" .context) }} + {{- if not (empty $valueUsername) -}} + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "mysql-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + {{- end -}} + + {{- if (eq $architecture "replication") -}} + {{- $requiredReplicationPassword := dict "valueKey" $valueKeyReplicationPassword "secret" .secret "field" "mysql-replication-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredReplicationPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.mysql.values.auth.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.mysql.values.auth.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.mysql.auth.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.auth.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled mysql. + +Usage: +{{ include "common.mysql.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.mysql.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.mysql.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for architecture + +Usage: +{{ include "common.mysql.values.architecture" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.mysql.values.architecture" -}} + {{- if .subchart -}} + {{- .context.Values.mysql.architecture -}} + {{- else -}} + {{- .context.Values.architecture -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key auth + +Usage: +{{ include "common.mysql.values.key.auth" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.mysql.values.key.auth" -}} + {{- if .subchart -}} + mysql.auth + {{- else -}} + auth + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_postgresql.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_postgresql.tpl new file mode 100644 index 0000000..164ec0d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_postgresql.tpl @@ -0,0 +1,129 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate PostgreSQL required passwords are not empty. + +Usage: +{{ include "common.validations.values.postgresql.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where postgresql values are stored, e.g: "postgresql-passwords-secret" + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.postgresql.passwords" -}} + {{- $existingSecret := include "common.postgresql.values.existingSecret" . -}} + {{- $enabled := include "common.postgresql.values.enabled" . -}} + {{- $valueKeyPostgresqlPassword := include "common.postgresql.values.key.postgressPassword" . -}} + {{- $valueKeyPostgresqlReplicationEnabled := include "common.postgresql.values.key.replicationPassword" . -}} + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + {{- $requiredPostgresqlPassword := dict "valueKey" $valueKeyPostgresqlPassword "secret" .secret "field" "postgresql-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPostgresqlPassword -}} + + {{- $enabledReplication := include "common.postgresql.values.enabled.replication" . -}} + {{- if (eq $enabledReplication "true") -}} + {{- $requiredPostgresqlReplicationPassword := dict "valueKey" $valueKeyPostgresqlReplicationEnabled "secret" .secret "field" "postgresql-replication-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPostgresqlReplicationPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to decide whether evaluate global values. + +Usage: +{{ include "common.postgresql.values.use.global" (dict "key" "key-of-global" "context" $) }} +Params: + - key - String - Required. Field to be evaluated within global, e.g: "existingSecret" +*/}} +{{- define "common.postgresql.values.use.global" -}} + {{- if .context.Values.global -}} + {{- if .context.Values.global.postgresql -}} + {{- index .context.Values.global.postgresql .key | quote -}} + {{- end -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.postgresql.values.existingSecret" (dict "context" $) }} +*/}} +{{- define "common.postgresql.values.existingSecret" -}} + {{- $globalValue := include "common.postgresql.values.use.global" (dict "key" "existingSecret" "context" .context) -}} + + {{- if .subchart -}} + {{- default (.context.Values.postgresql.existingSecret | quote) $globalValue -}} + {{- else -}} + {{- default (.context.Values.existingSecret | quote) $globalValue -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled postgresql. + +Usage: +{{ include "common.postgresql.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.postgresql.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.postgresql.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key postgressPassword. + +Usage: +{{ include "common.postgresql.values.key.postgressPassword" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.postgresql.values.key.postgressPassword" -}} + {{- $globalValue := include "common.postgresql.values.use.global" (dict "key" "postgresqlUsername" "context" .context) -}} + + {{- if not $globalValue -}} + {{- if .subchart -}} + postgresql.postgresqlPassword + {{- else -}} + postgresqlPassword + {{- end -}} + {{- else -}} + global.postgresql.postgresqlPassword + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled.replication. + +Usage: +{{ include "common.postgresql.values.enabled.replication" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.postgresql.values.enabled.replication" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.postgresql.replication.enabled -}} + {{- else -}} + {{- printf "%v" .context.Values.replication.enabled -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key replication.password. + +Usage: +{{ include "common.postgresql.values.key.replicationPassword" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.postgresql.values.key.replicationPassword" -}} + {{- if .subchart -}} + postgresql.replication.password + {{- else -}} + replication.password + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_redis.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_redis.tpl new file mode 100644 index 0000000..dcccfc1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_redis.tpl @@ -0,0 +1,76 @@ + +{{/* vim: set filetype=mustache: */}} +{{/* +Validate Redis® required passwords are not empty. + +Usage: +{{ include "common.validations.values.redis.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where redis values are stored, e.g: "redis-passwords-secret" + - subchart - Boolean - Optional. Whether redis is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.redis.passwords" -}} + {{- $enabled := include "common.redis.values.enabled" . -}} + {{- $valueKeyPrefix := include "common.redis.values.keys.prefix" . -}} + {{- $standarizedVersion := include "common.redis.values.standarized.version" . }} + + {{- $existingSecret := ternary (printf "%s%s" $valueKeyPrefix "auth.existingSecret") (printf "%s%s" $valueKeyPrefix "existingSecret") (eq $standarizedVersion "true") }} + {{- $existingSecretValue := include "common.utils.getValueFromKey" (dict "key" $existingSecret "context" .context) }} + + {{- $valueKeyRedisPassword := ternary (printf "%s%s" $valueKeyPrefix "auth.password") (printf "%s%s" $valueKeyPrefix "password") (eq $standarizedVersion "true") }} + {{- $valueKeyRedisUseAuth := ternary (printf "%s%s" $valueKeyPrefix "auth.enabled") (printf "%s%s" $valueKeyPrefix "usePassword") (eq $standarizedVersion "true") }} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $useAuth := include "common.utils.getValueFromKey" (dict "key" $valueKeyRedisUseAuth "context" .context) -}} + {{- if eq $useAuth "true" -}} + {{- $requiredRedisPassword := dict "valueKey" $valueKeyRedisPassword "secret" .secret "field" "redis-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRedisPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled redis. + +Usage: +{{ include "common.redis.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.redis.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.redis.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right prefix path for the values + +Usage: +{{ include "common.redis.values.key.prefix" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether redis is used as subchart or not. Default: false +*/}} +{{- define "common.redis.values.keys.prefix" -}} + {{- if .subchart -}}redis.{{- else -}}{{- end -}} +{{- end -}} + +{{/* +Checks whether the redis chart's includes the standarizations (version >= 14) + +Usage: +{{ include "common.redis.values.standarized.version" (dict "context" $) }} +*/}} +{{- define "common.redis.values.standarized.version" -}} + + {{- $standarizedAuth := printf "%s%s" (include "common.redis.values.keys.prefix" .) "auth" -}} + {{- $standarizedAuthValues := include "common.utils.getValueFromKey" (dict "key" $standarizedAuth "context" .context) }} + + {{- if $standarizedAuthValues -}} + {{- true -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_validations.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_validations.tpl new file mode 100644 index 0000000..9a814cf --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/templates/validations/_validations.tpl @@ -0,0 +1,46 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate values must not be empty. + +Usage: +{{- $validateValueConf00 := (dict "valueKey" "path.to.value" "secret" "secretName" "field" "password-00") -}} +{{- $validateValueConf01 := (dict "valueKey" "path.to.value" "secret" "secretName" "field" "password-01") -}} +{{ include "common.validations.values.empty" (dict "required" (list $validateValueConf00 $validateValueConf01) "context" $) }} + +Validate value params: + - valueKey - String - Required. The path to the validating value in the values.yaml, e.g: "mysql.password" + - secret - String - Optional. Name of the secret where the validating value is generated/stored, e.g: "mysql-passwords-secret" + - field - String - Optional. Name of the field in the secret data, e.g: "mysql-password" +*/}} +{{- define "common.validations.values.multiple.empty" -}} + {{- range .required -}} + {{- include "common.validations.values.single.empty" (dict "valueKey" .valueKey "secret" .secret "field" .field "context" $.context) -}} + {{- end -}} +{{- end -}} + +{{/* +Validate a value must not be empty. + +Usage: +{{ include "common.validations.value.empty" (dict "valueKey" "mariadb.password" "secret" "secretName" "field" "my-password" "subchart" "subchart" "context" $) }} + +Validate value params: + - valueKey - String - Required. The path to the validating value in the values.yaml, e.g: "mysql.password" + - secret - String - Optional. Name of the secret where the validating value is generated/stored, e.g: "mysql-passwords-secret" + - field - String - Optional. Name of the field in the secret data, e.g: "mysql-password" + - subchart - String - Optional - Name of the subchart that the validated password is part of. +*/}} +{{- define "common.validations.values.single.empty" -}} + {{- $value := include "common.utils.getValueFromKey" (dict "key" .valueKey "context" .context) }} + {{- $subchart := ternary "" (printf "%s." .subchart) (empty .subchart) }} + + {{- if not $value -}} + {{- $varname := "my-value" -}} + {{- $getCurrentValue := "" -}} + {{- if and .secret .field -}} + {{- $varname = include "common.utils.fieldToEnvVar" . -}} + {{- $getCurrentValue = printf " To get the current value:\n\n %s\n" (include "common.utils.secret.getvalue" .) -}} + {{- end -}} + {{- printf "\n '%s' must not be empty, please add '--set %s%s=$%s' to the command.%s" .valueKey $subchart .valueKey $varname $getCurrentValue -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/values.yaml new file mode 100644 index 0000000..f2df68e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/charts/common/values.yaml @@ -0,0 +1,5 @@ +## bitnami/common +## It is required by CI/CD tools and processes. +## @skip exampleValue +## +exampleValue: common-chart diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/NOTES.txt new file mode 100644 index 0000000..2d26bce --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/NOTES.txt @@ -0,0 +1,154 @@ +CHART NAME: {{ .Chart.Name }} +CHART VERSION: {{ .Chart.Version }} +APP VERSION: {{ .Chart.AppVersion }} + +{{- $servicePort := or (.Values.service.portEnabled) (not .Values.auth.tls.enabled) | ternary .Values.service.ports.amqp .Values.service.ports.amqpTls -}} + +** Please be patient while the chart is being deployed ** + +{{- if .Values.diagnosticMode.enabled }} +The chart has been deployed in diagnostic mode. All probes have been disabled and the command has been overwritten with: + + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 4 }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 4 }} + +Get the list of pods by executing: + + kubectl get pods --namespace {{ .Release.Namespace }} -l app.kubernetes.io/instance={{ .Release.Name }} + +Access the pod you want to debug by executing + + kubectl exec --namespace {{ .Release.Namespace }} -ti -- bash + +In order to replicate the container startup scripts execute this command: + + /opt/bitnami/scripts/rabbitmq/entrypoint.sh /opt/bitnami/scripts/rabbitmq/run.sh + +{{- else }} + +Credentials: + +{{- if not .Values.loadDefinition.enabled }} + echo "Username : {{ .Values.auth.username }}" + echo "Password : $(kubectl get secret --namespace {{ .Release.Namespace }} {{ include "rabbitmq.secretPasswordName" . }} -o jsonpath="{.data.rabbitmq-password}" | base64 -d)" +{{- end }} + echo "ErLang Cookie : $(kubectl get secret --namespace {{ .Release.Namespace }} {{ include "rabbitmq.secretErlangName" . }} -o jsonpath="{.data.rabbitmq-erlang-cookie}" | base64 -d)" + +Note that the credentials are saved in persistent volume claims and will not be changed upon upgrade or reinstallation unless the persistent volume claim has been deleted. If this is not the first installation of this chart, the credentials may not be valid. +This is applicable when no passwords are set and therefore the random password is autogenerated. In case of using a fixed password, you should specify it when upgrading. +More information about the credentials may be found at https://docs.bitnami.com/general/how-to/troubleshoot-helm-chart-issues/#credential-errors-while-upgrading-chart-releases. + +RabbitMQ can be accessed within the cluster on port {{ $servicePort }} at {{ include "common.names.fullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }} + +To access for outside the cluster, perform the following steps: + +{{- if .Values.ingress.enabled }} +{{- if contains "NodePort" .Values.service.type }} + +To Access the RabbitMQ AMQP port: + +1. Obtain the NodePort IP and ports: + + export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}") + export NODE_PORT_AMQP=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[?(@.name=='amqp')].nodePort}" services {{ include "common.names.fullname" . }}) + echo "URL : amqp://$NODE_IP:$NODE_PORT_AMQP/" + +{{- else if contains "LoadBalancer" .Values.service.type }} + +To Access the RabbitMQ AMQP port: + +1. Obtain the LoadBalancer IP: + +NOTE: It may take a few minutes for the LoadBalancer IP to be available. + Watch the status with: 'kubectl get svc --namespace {{ .Release.Namespace }} -w {{ include "common.names.fullname" . }}' + + export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "common.names.fullname" . }} --template "{{ "{{ range (index .status.loadBalancer.ingress 0) }}{{ . }}{{ end }}" }}") + echo "URL : amqp://$SERVICE_IP:{{ $servicePort }}/" + +{{- else if contains "ClusterIP" .Values.service.type }} + +To Access the RabbitMQ AMQP port: + +1. Create a port-forward to the AMQP port: + + kubectl port-forward --namespace {{ .Release.Namespace }} svc/{{ include "common.names.fullname" . }} {{ $servicePort }}:{{ $servicePort }} & + echo "URL : amqp://127.0.0.1:{{ $servicePort }}/" + +{{- end }} + +2. Access RabbitMQ using using the obtained URL. + +To Access the RabbitMQ Management interface: + +1. Get the RabbitMQ Management URL and associate its hostname to your cluster external IP: + + export CLUSTER_IP=$(minikube ip) # On Minikube. Use: `kubectl cluster-info` on others K8s clusters + echo "RabbitMQ Management: http{{ if .Values.ingress.tls }}s{{ end }}://{{ .Values.ingress.hostname }}/" + echo "$CLUSTER_IP {{ .Values.ingress.hostname }}" | sudo tee -a /etc/hosts + +2. Open a browser and access RabbitMQ Management using the obtained URL. + +{{- else }} +{{- if contains "NodePort" .Values.service.type }} + +Obtain the NodePort IP and ports: + + export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}") + export NODE_PORT_AMQP=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[?(@.name=='amqp')].nodePort}" services {{ include "common.names.fullname" . }}) + export NODE_PORT_STATS=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[?(@.name=='http-stats')].nodePort}" services {{ include "common.names.fullname" . }}) + +To Access the RabbitMQ AMQP port: + + echo "URL : amqp://$NODE_IP:$NODE_PORT_AMQP/" + +To Access the RabbitMQ Management interface: + + echo "URL : http://$NODE_IP:$NODE_PORT_STATS/" + +{{- else if contains "LoadBalancer" .Values.service.type }} + +Obtain the LoadBalancer IP: + +NOTE: It may take a few minutes for the LoadBalancer IP to be available. + Watch the status with: 'kubectl get svc --namespace {{ .Release.Namespace }} -w {{ include "common.names.fullname" . }}' + + export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "common.names.fullname" . }} --template "{{ "{{ range (index .status.loadBalancer.ingress 0) }}{{ . }}{{ end }}" }}") + +To Access the RabbitMQ AMQP port: + + echo "URL : amqp://$SERVICE_IP:{{ $servicePort }}/" + +To Access the RabbitMQ Management interface: + + echo "URL : http://$SERVICE_IP:{{ .Values.service.ports.manager }}/" + +{{- else if contains "ClusterIP" .Values.service.type }} + +To Access the RabbitMQ AMQP port: + + echo "URL : amqp://127.0.0.1:{{ $servicePort }}/" + kubectl port-forward --namespace {{ .Release.Namespace }} svc/{{ include "common.names.fullname" . }} {{ $servicePort }}:{{ $servicePort }} + +To Access the RabbitMQ Management interface: + + echo "URL : http://127.0.0.1:{{ .Values.service.ports.manager }}/" + kubectl port-forward --namespace {{ .Release.Namespace }} svc/{{ include "common.names.fullname" . }} {{ .Values.service.ports.manager }}:{{ .Values.service.ports.manager }} + +{{- end }} +{{- end }} + +{{- if .Values.metrics.enabled }} + +To access the RabbitMQ Prometheus metrics, get the RabbitMQ Prometheus URL by running: + + kubectl port-forward --namespace {{ .Release.Namespace }} svc/{{ include "common.names.fullname" . }} {{ .Values.service.ports.metrics }}:{{ .Values.service.ports.metrics }} & + echo "Prometheus Metrics URL: http://127.0.0.1:{{ .Values.service.ports.metrics }}/metrics" + +Then, open the obtained URL in a browser. + +{{- end }} + +{{- include "common.warnings.rollingTag" .Values.image }} +{{- include "common.warnings.rollingTag" .Values.volumePermissions.image }} + +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/_helpers.tpl new file mode 100644 index 0000000..b1fc4e7 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/_helpers.tpl @@ -0,0 +1,263 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Return the proper RabbitMQ image name +*/}} +{{- define "rabbitmq.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return the proper image name (for the init container volume-permissions image) +*/}} +{{- define "rabbitmq.volumePermissions.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.volumePermissions.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names +*/}} +{{- define "rabbitmq.imagePullSecrets" -}} +{{ include "common.images.pullSecrets" (dict "images" (list .Values.image .Values.volumePermissions.image) "global" .Values.global) }} +{{- end -}} + +{{/* + Create the name of the service account to use + */}} +{{- define "rabbitmq.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "common.names.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Get the password secret. +*/}} +{{- define "rabbitmq.secretPasswordName" -}} + {{- if .Values.auth.existingPasswordSecret -}} + {{- printf "%s" (tpl .Values.auth.existingPasswordSecret $) -}} + {{- else -}} + {{- printf "%s" (include "common.names.fullname" .) -}} + {{- end -}} +{{- end -}} + +{{/* +Get the erlang secret. +*/}} +{{- define "rabbitmq.secretErlangName" -}} + {{- if .Values.auth.existingErlangSecret -}} + {{- printf "%s" (tpl .Values.auth.existingErlangSecret $) -}} + {{- else -}} + {{- printf "%s" (include "common.names.fullname" .) -}} + {{- end -}} +{{- end -}} + +{{/* +Get the TLS secret. +*/}} +{{- define "rabbitmq.tlsSecretName" -}} + {{- if .Values.auth.tls.existingSecret -}} + {{- printf "%s" (tpl .Values.auth.tls.existingSecret $) -}} + {{- else -}} + {{- printf "%s-certs" (include "common.names.fullname" .) -}} + {{- end -}} +{{- end -}} + +{{/* +Return true if a TLS credentials secret object should be created +*/}} +{{- define "rabbitmq.createTlsSecret" -}} +{{- if and .Values.auth.tls.enabled (not .Values.auth.tls.existingSecret) }} + {{- true -}} +{{- end -}} +{{- end -}} + +{{/* +Return the proper RabbitMQ plugin list +*/}} +{{- define "rabbitmq.plugins" -}} +{{- $plugins := .Values.plugins -}} +{{- if .Values.extraPlugins -}} +{{- $plugins = printf "%s %s" $plugins .Values.extraPlugins -}} +{{- end -}} +{{- if .Values.metrics.enabled -}} +{{- $plugins = printf "%s %s" $plugins .Values.metrics.plugins -}} +{{- end -}} +{{- printf "%s" $plugins | replace " " ", " -}} +{{- end -}} + +{{/* +Return the number of bytes given a value +following a base 2 o base 10 number system. +Usage: +{{ include "rabbitmq.toBytes" .Values.path.to.the.Value }} +*/}} +{{- define "rabbitmq.toBytes" -}} +{{- $value := int (regexReplaceAll "([0-9]+).*" . "${1}") }} +{{- $unit := regexReplaceAll "[0-9]+(.*)" . "${1}" }} +{{- if eq $unit "Ki" }} + {{- mul $value 1024 }} +{{- else if eq $unit "Mi" }} + {{- mul $value 1024 1024 }} +{{- else if eq $unit "Gi" }} + {{- mul $value 1024 1024 1024 }} +{{- else if eq $unit "Ti" }} + {{- mul $value 1024 1024 1024 1024 }} +{{- else if eq $unit "Pi" }} + {{- mul $value 1024 1024 1024 1024 1024 }} +{{- else if eq $unit "Ei" }} + {{- mul $value 1024 1024 1024 1024 1024 1024 }} +{{- else if eq $unit "K" }} + {{- mul $value 1000 }} +{{- else if eq $unit "M" }} + {{- mul $value 1000 1000 }} +{{- else if eq $unit "G" }} + {{- mul $value 1000 1000 1000 }} +{{- else if eq $unit "T" }} + {{- mul $value 1000 1000 1000 1000 }} +{{- else if eq $unit "P" }} + {{- mul $value 1000 1000 1000 1000 1000 }} +{{- else if eq $unit "E" }} + {{- mul $value 1000 1000 1000 1000 1000 1000 }} +{{- end }} +{{- end -}} + +{{/* +Compile all warnings into a single message, and call fail. +*/}} +{{- define "rabbitmq.validateValues" -}} +{{- $messages := list -}} +{{- $messages := append $messages (include "rabbitmq.validateValues.ldap" .) -}} +{{- $messages := append $messages (include "rabbitmq.validateValues.memoryHighWatermark" .) -}} +{{- $messages := append $messages (include "rabbitmq.validateValues.ingress.tls" .) -}} +{{- $messages := append $messages (include "rabbitmq.validateValues.auth.tls" .) -}} +{{- $messages := without $messages "" -}} +{{- $message := join "\n" $messages -}} + +{{- if $message -}} +{{- printf "\nVALUES VALIDATION:\n%s" $message | fail -}} +{{- end -}} +{{- end -}} + +{{/* +Validate values of rabbitmq - LDAP support +*/}} +{{- define "rabbitmq.validateValues.ldap" -}} +{{- if .Values.ldap.enabled }} +{{- $serversListLength := len .Values.ldap.servers }} +{{- $userDnPattern := coalesce .Values.ldap.user_dn_pattern .Values.ldap.userDnPattern }} +{{- if or (and (not (gt $serversListLength 0)) (empty .Values.ldap.uri)) (and (not $userDnPattern) (not .Values.ldap.basedn)) }} +rabbitmq: LDAP + Invalid LDAP configuration. When enabling LDAP support, the parameters "ldap.servers" or "ldap.uri" are mandatory + to configure the connection and "ldap.userDnPattern" or "ldap.basedn" are necessary to lookup the users. Please provide them: + $ helm install {{ .Release.Name }} oci://registry-1.docker.io/bitnamicharts/rabbitmq \ + --set ldap.enabled=true \ + --set ldap.servers[0]=my-ldap-server" \ + --set ldap.port="389" \ + --set ldap.userDnPattern="cn=${username},dc=example,dc=org" +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Validate values of rabbitmq - Memory high watermark +*/}} +{{- define "rabbitmq.validateValues.memoryHighWatermark" -}} +{{- if and (not (eq .Values.memoryHighWatermark.type "absolute")) (not (eq .Values.memoryHighWatermark.type "relative")) }} +rabbitmq: memoryHighWatermark.type + Invalid Memory high watermark type. Valid values are "absolute" and + "relative". Please set a valid mode (--set memoryHighWatermark.type="xxxx") +{{- else if and .Values.memoryHighWatermark.enabled (not .Values.resources.limits.memory) (eq .Values.memoryHighWatermark.type "relative") }} +rabbitmq: memoryHighWatermark + You enabled configuring memory high watermark using a relative limit. However, + no memory limits were defined at POD level. Define your POD limits as shown below: + + $ helm install {{ .Release.Name }} oci://registry-1.docker.io/bitnamicharts/rabbitmq \ + --set memoryHighWatermark.enabled=true \ + --set memoryHighWatermark.type="relative" \ + --set memoryHighWatermark.value="0.4" \ + --set resources.limits.memory="2Gi" + + Altenatively, user an absolute value for the memory memory high watermark : + + $ helm install {{ .Release.Name }} oci://registry-1.docker.io/bitnamicharts/rabbitmq \ + --set memoryHighWatermark.enabled=true \ + --set memoryHighWatermark.type="absolute" \ + --set memoryHighWatermark.value="512MB" +{{- end -}} +{{- end -}} + +{{/* +Validate values of rabbitmq - TLS configuration for Ingress +*/}} +{{- define "rabbitmq.validateValues.ingress.tls" -}} +{{- if and .Values.ingress.enabled .Values.ingress.tls (not (include "common.ingress.certManagerRequest" ( dict "annotations" .Values.ingress.annotations ))) (not .Values.ingress.selfSigned) (empty .Values.ingress.extraTls) }} +rabbitmq: ingress.tls + You enabled the TLS configuration for the default ingress hostname but + you did not enable any of the available mechanisms to create the TLS secret + to be used by the Ingress Controller. + Please use any of these alternatives: + - Use the `ingress.extraTls` and `ingress.secrets` parameters to provide your custom TLS certificates. + - Rely on cert-manager to create it by setting the corresponding annotations + - Rely on Helm to create self-signed certificates by setting `ingress.selfSigned=true` +{{- end -}} +{{- end -}} + +{{/* +Validate values of RabbitMQ - Auth TLS enabled +*/}} +{{- define "rabbitmq.validateValues.auth.tls" -}} +{{- if and .Values.auth.tls.enabled (not .Values.auth.tls.autoGenerated) (not .Values.auth.tls.existingSecret) (not .Values.auth.tls.caCertificate) (not .Values.auth.tls.serverCertificate) (not .Values.auth.tls.serverKey) }} +rabbitmq: auth.tls + You enabled TLS for RabbitMQ but you did not enable any of the available mechanisms to create the TLS secret. + Please use any of these alternatives: + - Provide an existing secret containing the TLS certificates using `auth.tls.existingSecret` + - Provide the plain text certificates using `auth.tls.caCertificate`, `auth.tls.serverCertificate` and `auth.tls.serverKey`. + - Enable auto-generated certificates using `auth.tls.autoGenerated`. +{{- end -}} +{{- end -}} + +{{/* +Get the initialization scripts volume name. +*/}} +{{- define "rabbitmq.initScripts" -}} +{{- printf "%s-init-scripts" (include "common.names.fullname" .) -}} +{{- end -}} + +{{/* +Returns the available value for certain key in an existing secret (if it exists), +otherwise it generates a random value. +*/}} +{{- define "getValueFromSecret" }} + {{- $len := (default 16 .Length) | int -}} + {{- $obj := (lookup "v1" "Secret" .Namespace .Name).data -}} + {{- if $obj }} + {{- index $obj .Key | b64dec -}} + {{- else -}} + {{- randAlphaNum $len -}} + {{- end -}} +{{- end }} + +{{/* +Get the extraConfigurationExistingSecret secret. +*/}} +{{- define "rabbitmq.extraConfiguration" -}} +{{- if not (empty .Values.extraConfigurationExistingSecret) -}} + {{- include "getValueFromSecret" (dict "Namespace" .Release.Namespace "Name" .Values.extraConfigurationExistingSecret "Length" 10 "Key" "extraConfiguration") -}} +{{- else -}} + {{- tpl .Values.extraConfiguration . -}} +{{- end -}} +{{- end -}} + +{{/* +Get the TLS.sslOptions.Password secret. +*/}} +{{- define "rabbitmq.tlsSslOptionsPassword" -}} +{{- if not (empty .Values.auth.tls.sslOptionsPassword.password) -}} + {{- .Values.auth.tls.sslOptionsPassword.password -}} +{{- else -}} + {{- include "getValueFromSecret" (dict "Namespace" .Release.Namespace "Name" .Values.auth.tls.sslOptionsPassword.existingSecret "Length" 10 "Key" .Values.auth.tls.sslOptionsPassword.key) -}} +{{- end -}} +{{- end -}} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/config-secret.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/config-secret.yaml new file mode 100644 index 0000000..f8886ec --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/config-secret.yaml @@ -0,0 +1,24 @@ +{{- if or (empty .Values.configurationExistingSecret) .Values.advancedConfiguration }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ printf "%s-config" (include "common.names.fullname" .) }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: Opaque +data: + {{- if empty .Values.configurationExistingSecret }} + rabbitmq.conf: |- + {{- include "common.tplvalues.render" (dict "value" .Values.configuration "context" $) | b64enc | nindent 4 }} + {{- end }} + {{- if .Values.advancedConfiguration }} + advanced.config: |- + {{- include "common.tplvalues.render" (dict "value" .Values.advancedConfiguration "context" $) | b64enc | nindent 4 }} + {{- end }} +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/extra-list.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/extra-list.yaml new file mode 100644 index 0000000..9ac65f9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/extra-list.yaml @@ -0,0 +1,4 @@ +{{- range .Values.extraDeploy }} +--- +{{ include "common.tplvalues.render" (dict "value" . "context" $) }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/ingress.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/ingress.yaml new file mode 100644 index 0000000..a66b8b0 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/ingress.yaml @@ -0,0 +1,60 @@ +{{- if .Values.ingress.enabled }} +apiVersion: {{ include "common.capabilities.ingress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + annotations: + {{- if .Values.ingress.annotations }} + {{- include "common.tplvalues.render" (dict "value" .Values.ingress.annotations "context" $) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + {{- if and .Values.ingress.ingressClassName (eq "true" (include "common.ingress.supportsIngressClassname" .)) }} + ingressClassName: {{ .Values.ingress.ingressClassName | quote }} + {{- end }} + rules: + {{- if .Values.ingress.hostname }} + - host: {{ include "common.tplvalues.render" ( dict "value" .Values.ingress.hostname "context" $ ) }} + http: + paths: + {{- if .Values.ingress.extraPaths }} + {{- toYaml .Values.ingress.extraPaths | nindent 10 }} + {{- end }} + - path: {{ .Values.ingress.path }} + {{- if eq "true" (include "common.ingress.supportsPathType" .) }} + pathType: {{ .Values.ingress.pathType }} + {{- end }} + backend: {{- include "common.ingress.backend" (dict "serviceName" (include "common.names.fullname" .) "servicePort" .Values.service.portNames.manager "context" $) | nindent 14 }} + {{- end }} + {{- range .Values.ingress.extraHosts }} + - host: {{ include "common.tplvalues.render" ( dict "value" .name "context" $ ) }} + http: + paths: + - path: {{ default "/" .path }} + {{- if eq "true" (include "common.ingress.supportsPathType" $) }} + pathType: {{ default "ImplementationSpecific" .pathType }} + {{- end }} + backend: {{- include "common.ingress.backend" (dict "serviceName" (include "common.names.fullname" $) "servicePort" $.Values.service.portNames.manager "context" $) | nindent 14 }} + {{- end }} + {{- if .Values.ingress.extraRules }} + {{- include "common.tplvalues.render" (dict "value" .Values.ingress.extraRules "context" $) | nindent 4 }} + {{- end }} + {{- if or (and .Values.ingress.tls (or (include "common.ingress.certManagerRequest" ( dict "annotations" .Values.ingress.annotations )) .Values.ingress.selfSigned)) .Values.ingress.extraTls }} + tls: + {{- if and .Values.ingress.tls (or (include "common.ingress.certManagerRequest" ( dict "annotations" .Values.ingress.annotations )) .Values.ingress.selfSigned) }} + - hosts: + - {{ .Values.ingress.hostname | quote }} + secretName: {{ default (printf "%s-tls" .Values.ingress.hostname | trunc 63 | trimSuffix "-") .Values.ingress.existingSecret }} + {{- end }} + {{- if .Values.ingress.extraTls }} + {{- include "common.tplvalues.render" (dict "value" .Values.ingress.extraTls "context" $) | nindent 4 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/init-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/init-configmap.yaml new file mode 100644 index 0000000..d84a353 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/init-configmap.yaml @@ -0,0 +1,16 @@ +{{- if .Values.initScripts }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ printf "%s-init-scripts" (include "common.names.fullname" .) }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: +{{- include "common.tplvalues.render" ( dict "value" .Values.initScripts "context" $ ) | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/networkpolicy.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/networkpolicy.yaml new file mode 100644 index 0000000..a5affcd --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/networkpolicy.yaml @@ -0,0 +1,40 @@ +{{- if .Values.networkPolicy.enabled }} +kind: NetworkPolicy +apiVersion: {{ include "common.capabilities.networkPolicy.apiVersion" . }} +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + podSelector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + ingress: + # Allow inbound connections + - ports: + - port: {{ .Values.service.ports.epmd }} # EPMD + - port: {{ .Values.service.ports.amqp }} + - port: {{ .Values.service.ports.amqpTls }} + - port: {{ .Values.service.ports.dist }} + - port: {{ .Values.service.ports.manager }} + {{- if not .Values.networkPolicy.allowExternal }} + from: + - podSelector: + matchLabels: + {{ printf "%s-client" (include "common.names.fullname" .) }}: "true" + - podSelector: + matchLabels: + {{- include "common.labels.matchLabels" . | nindent 14 }} + {{- if .Values.networkPolicy.additionalRules }} + {{- include "common.tplvalues.render" (dict "value" .Values.networkPolicy.additionalRules "context" $) | nindent 8 }} + {{- end }} + {{- end }} + # Allow prometheus scrapes + - ports: + - port: {{ .Values.service.ports.metrics }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/pdb.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/pdb.yaml new file mode 100644 index 0000000..827b49b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/pdb.yaml @@ -0,0 +1,23 @@ +{{- if .Values.pdb.create }} +apiVersion: {{ include "common.capabilities.policy.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + {{- if .Values.pdb.minAvailable }} + minAvailable: {{ .Values.pdb.minAvailable }} + {{- end }} + {{- if .Values.pdb.maxUnavailable }} + maxUnavailable: {{ .Values.pdb.maxUnavailable }} + {{- end }} + selector: + matchLabels: {{ include "common.labels.matchLabels" . | nindent 6 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/prometheusrule.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/prometheusrule.yaml new file mode 100644 index 0000000..fd7208b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/prometheusrule.yaml @@ -0,0 +1,23 @@ +{{- if and .Values.metrics.enabled .Values.metrics.prometheusRule.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ default (include "common.names.namespace" .) .Values.metrics.prometheusRule.namespace | quote}} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.metrics.prometheusRule.additionalLabels }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.prometheusRule.additionalLabels "context" $) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + groups: + {{- with .Values.metrics.prometheusRule.rules }} + - name: {{ template "common.names.name" $ }} + rules: {{- include "common.tplvalues.render" (dict "value" . "context" $) | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/role.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/role.yaml new file mode 100644 index 0000000..ab8be2f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/role.yaml @@ -0,0 +1,21 @@ +{{- if .Values.rbac.create }} +kind: Role +apiVersion: {{ include "common.capabilities.rbac.apiVersion" . }} +metadata: + name: {{ printf "%s-endpoint-reader" (include "common.names.fullname" .) }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +rules: + - apiGroups: [""] + resources: ["endpoints"] + verbs: ["get"] + - apiGroups: [""] + resources: ["events"] + verbs: ["create"] +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/rolebinding.yaml new file mode 100644 index 0000000..b086f16 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/rolebinding.yaml @@ -0,0 +1,21 @@ +{{- if .Values.rbac.create }} +kind: RoleBinding +apiVersion: {{ include "common.capabilities.rbac.apiVersion" . }} +metadata: + name: {{ printf "%s-endpoint-reader" (include "common.names.fullname" .) }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +subjects: + - kind: ServiceAccount + name: {{ template "rabbitmq.serviceAccountName" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ printf "%s-endpoint-reader" (include "common.names.fullname" .) }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/secrets.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/secrets.yaml new file mode 100644 index 0000000..5dc93b4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/secrets.yaml @@ -0,0 +1,68 @@ +{{- $host := include "common.names.fullname" . }} +{{- $port := print .Values.service.ports.amqp }} +{{- $user := print .Values.auth.username }} +{{- $password := include "common.secrets.passwords.manage" (dict "secret" (include "rabbitmq.secretPasswordName" .) "key" "rabbitmq-password" "length" 16 "providedValues" (list "auth.password") "context" $) | trimAll "\"" | b64dec }} + +{{- if or (not .Values.auth.existingErlangSecret) (not .Values.auth.existingPasswordSecret) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: Opaque +data: + {{- if (not .Values.auth.existingPasswordSecret ) }} + rabbitmq-password: {{ print $password | b64enc | quote }} + {{ end }} + {{- if (not .Values.auth.existingErlangSecret ) }} + rabbitmq-erlang-cookie: {{ include "common.secrets.passwords.manage" (dict "secret" (include "common.names.fullname" .) "key" "rabbitmq-erlang-cookie" "length" 32 "providedValues" (list "auth.erlangCookie") "context" $) }} + {{ end }} +{{- end }} +{{- range $key, $value := .Values.extraSecrets }} +--- +apiVersion: v1 +kind: Secret +metadata: + name: {{ ternary (printf "%s-%s" $.Release.Name $key) $key $.Values.extraSecretsPrependReleaseName }} + namespace: {{ include "common.names.namespace" $ | quote }} + labels: {{- include "common.labels.standard" $ | nindent 4 }} + {{- if $.Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" $.Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if $.Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" $.Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: Opaque +stringData: {{- include "common.tplvalues.render" (dict "value" $value "context" $) | nindent 2 }} +{{- end }} +{{- if .Values.serviceBindings.enabled }} +--- +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "common.names.fullname" . }}-svcbind + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: servicebinding.io/rabbitmq +data: + provider: {{ print "bitnami" | b64enc | quote }} + type: {{ print "rabbitmq" | b64enc | quote }} + host: {{ print $host | b64enc | quote }} + port: {{ print $port | b64enc | quote }} + username: {{ print $user | b64enc | quote }} + password: {{ print $password | b64enc | quote }} + uri: {{ printf "amqp://%s:%s@%s:%s" $user $password $host $port | b64enc | quote }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/serviceaccount.yaml new file mode 100644 index 0000000..43c45d1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/serviceaccount.yaml @@ -0,0 +1,24 @@ +{{- if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "rabbitmq.serviceAccountName" . }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if or .Values.serviceAccount.annotations .Values.commonAnnotations }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.serviceAccount.annotations }} + {{- include "common.tplvalues.render" (dict "value" .Values.serviceAccount.annotations "context" $) | nindent 4 }} + {{- end }} + {{- end }} +automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }} +secrets: + - name: {{ include "common.names.fullname" . }} +{{- end }} + diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/servicemonitor.yaml new file mode 100644 index 0000000..9d4d26b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/servicemonitor.yaml @@ -0,0 +1,60 @@ +{{- if and .Values.metrics.enabled .Values.metrics.serviceMonitor.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ default (include "common.names.namespace" .) .Values.metrics.serviceMonitor.namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.metrics.serviceMonitor.labels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.labels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.annotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + jobLabel: {{ .Values.metrics.serviceMonitor.jobLabel | quote }} + endpoints: + - port: metrics + {{- if .Values.metrics.serviceMonitor.path }} + path: {{ .Values.metrics.serviceMonitor.path }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.params }} + params: {{ toYaml .Values.metrics.serviceMonitor.params | nindent 8 }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.interval }} + interval: {{ .Values.metrics.serviceMonitor.interval }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.metrics.serviceMonitor.scrapeTimeout }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.honorLabels }} + honorLabels: {{ .Values.metrics.serviceMonitor.honorLabels }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.relabelings }} + relabelings: {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.relabelings "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.metricRelabelings }} + metricRelabelings: {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.metricRelabelings "context" $) | nindent 8 }} + {{- end }} + namespaceSelector: + matchNames: + - {{ include "common.names.namespace" . | quote }} + {{- if .Values.metrics.serviceMonitor.podTargetLabels }} + podTargetLabels: {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.podTargetLabels "context" $) | nindent 4 }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.targetLabels }} + targetLabels: {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.serviceMonitor.targetLabels "context" $) | nindent 4 }} + {{- end }} + selector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + {{- if .Values.metrics.serviceMonitor.selector }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.serviceMonitor.selector "context" $) | nindent 6 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/statefulset.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/statefulset.yaml new file mode 100644 index 0000000..af4ca9e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/statefulset.yaml @@ -0,0 +1,466 @@ +apiVersion: {{ include "common.capabilities.statefulset.apiVersion" . }} +kind: StatefulSet +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.statefulsetLabels }} + {{- include "common.tplvalues.render" (dict "value" .Values.statefulsetLabels "context" $) | nindent 4 }} + {{- end }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if or .Values.commonAnnotations .Values.statefulsetAnnotations }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.statefulsetAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.statefulsetAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- end }} +spec: + serviceName: {{ printf "%s-%s" (include "common.names.fullname" .) (default "headless" .Values.servicenameOverride) }} + podManagementPolicy: {{ .Values.podManagementPolicy }} + replicas: {{ .Values.replicaCount }} + {{- if .Values.updateStrategy }} + updateStrategy: {{- toYaml .Values.updateStrategy | nindent 4 }} + {{- end }} + selector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + template: + metadata: + labels: {{- include "common.labels.standard" . | nindent 8 }} + {{- if .Values.podLabels }} + {{- include "common.tplvalues.render" (dict "value" .Values.podLabels "context" $) | nindent 8 }} + {{- end }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 8 }} + {{- end }} + checksum/config: {{ include (print $.Template.BasePath "/config-secret.yaml") . | sha256sum }} + {{- if or (not .Values.auth.existingErlangSecret) (not .Values.auth.existingPasswordSecret) .Values.extraSecrets }} + checksum/secret: {{ include (print $.Template.BasePath "/secrets.yaml") . | sha256sum }} + {{- end }} + {{- if .Values.podAnnotations }} + {{- include "common.tplvalues.render" (dict "value" .Values.podAnnotations "context" $) | nindent 8 }} + {{- end }} + {{- if and .Values.metrics.enabled .Values.metrics.podAnnotations }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.podAnnotations "context" $) | nindent 8 }} + {{- end }} + spec: + {{- include "rabbitmq.imagePullSecrets" . | nindent 6 }} + {{- if .Values.schedulerName }} + schedulerName: {{ .Values.schedulerName | quote }} + {{- end }} + serviceAccountName: {{ template "rabbitmq.serviceAccountName" . }} + {{- if .Values.affinity }} + affinity: {{- include "common.tplvalues.render" (dict "value" .Values.affinity "context" .) | nindent 8 }} + {{- else }} + affinity: + podAffinity: {{- include "common.affinities.pods" (dict "type" .Values.podAffinityPreset "context" $) | nindent 10 }} + podAntiAffinity: {{- include "common.affinities.pods" (dict "type" .Values.podAntiAffinityPreset "context" $) | nindent 10 }} + nodeAffinity: {{- include "common.affinities.nodes" (dict "type" .Values.nodeAffinityPreset.type "key" .Values.nodeAffinityPreset.key "values" .Values.nodeAffinityPreset.values) | nindent 10 }} + {{- end }} + {{- if .Values.hostAliases }} + hostAliases: {{- include "common.tplvalues.render" (dict "value" .Values.hostAliases "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.nodeSelector }} + nodeSelector: {{- include "common.tplvalues.render" (dict "value" .Values.nodeSelector "context" .) | nindent 8 }} + {{- end }} + {{- if .Values.tolerations }} + tolerations: {{- include "common.tplvalues.render" (dict "value" .Values.tolerations "context" .) | nindent 8 }} + {{- end }} + {{- if .Values.topologySpreadConstraints }} + topologySpreadConstraints: {{- include "common.tplvalues.render" (dict "value" .Values.topologySpreadConstraints "context" .) | nindent 8 }} + {{- end }} + {{- if .Values.priorityClassName }} + priorityClassName: {{ .Values.priorityClassName }} + {{- end }} + {{- if .Values.podSecurityContext.enabled }} + securityContext: {{- omit .Values.podSecurityContext "enabled" | toYaml | nindent 8 }} + {{- end }} + {{- if .Values.dnsPolicy }} + dnsPolicy: {{ .Values.dnsPolicy }} + {{- end }} + {{- if .Values.dnsConfig }} + dnsConfig: {{- include "common.tplvalues.render" (dict "value" .Values.dnsConfig "context" .) | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.terminationGracePeriodSeconds }} + initContainers: + {{- if and .Values.volumePermissions.enabled .Values.persistence.enabled }} + - name: volume-permissions + image: {{ include "rabbitmq.volumePermissions.image" . }} + imagePullPolicy: {{ .Values.volumePermissions.image.pullPolicy | quote }} + command: + - /bin/bash + args: + - -ec + - | + mkdir -p "{{ .Values.persistence.mountPath }}" + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + chown `id -u`:`id -G | cut -d " " -f2` {{ .Values.persistence.mountPath }} + {{- else }} + chown "{{ .Values.containerSecurityContext.runAsUser }}:{{ .Values.podSecurityContext.fsGroup }}" "{{ .Values.persistence.mountPath }}" + {{- end }} + find "{{ .Values.persistence.mountPath }}" -mindepth 1 -maxdepth 1 -not -name ".snapshot" -not -name "lost+found" | \ + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + xargs -r chown -R `id -u`:`id -G | cut -d " " -f2` + {{- else }} + xargs -r chown -R "{{ .Values.containerSecurityContext.runAsUser }}:{{ .Values.podSecurityContext.fsGroup }}" + {{- end }} + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + securityContext: {{- omit .Values.volumePermissions.containerSecurityContext "runAsUser" | toYaml | nindent 12 }} + {{- else }} + securityContext: {{- .Values.volumePermissions.containerSecurityContext | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.volumePermissions.resources }} + resources: {{- toYaml .Values.volumePermissions.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: data + mountPath: {{ .Values.persistence.mountPath }} + {{- if .Values.persistence.subPath }} + subPath: {{ .Values.persistence.subPath }} + {{- end }} + {{- end }} + {{- if .Values.initContainers }} + {{- include "common.tplvalues.render" (dict "value" .Values.initContainers "context" $) | nindent 8 }} + {{- end }} + containers: + - name: rabbitmq + image: {{ template "rabbitmq.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy | quote }} + {{- if .Values.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + {{- else if .Values.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.command "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else if .Values.args }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.args "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.lifecycleHooks }} + lifecycle: {{- include "common.tplvalues.render" (dict "value" .Values.lifecycleHooks "context" $) | nindent 12 }} + {{- else }} + lifecycle: + preStop: + exec: + command: + - /bin/bash + - -ec + - | + if [[ -f /opt/bitnami/scripts/rabbitmq/nodeshutdown.sh ]]; then + /opt/bitnami/scripts/rabbitmq/nodeshutdown.sh -t {{ .Values.terminationGracePeriodSeconds | quote }} -d {{ ternary "true" "false" .Values.image.debug | quote }} + else + rabbitmqctl stop_app + fi + {{- end }} + env: + - name: BITNAMI_DEBUG + value: {{ ternary "true" "false" (or .Values.image.debug .Values.diagnosticMode.enabled) | quote }} + - name: MY_POD_IP + valueFrom: + fieldRef: + fieldPath: status.podIP + - name: MY_POD_NAME + valueFrom: + fieldRef: + fieldPath: metadata.name + - name: MY_POD_NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + - name: K8S_SERVICE_NAME + value: {{ printf "%s-%s" (include "common.names.fullname" .) (default "headless" .Values.servicenameOverride) }} + - name: K8S_ADDRESS_TYPE + value: {{ .Values.clustering.addressType }} + {{- if .Values.featureFlags }} + - name: RABBITMQ_FEATURE_FLAGS + value: {{ .Values.featureFlags }} + {{- end }} + - name: RABBITMQ_FORCE_BOOT + value: {{ ternary "yes" "no" .Values.clustering.forceBoot | quote }} + {{- if (eq "hostname" .Values.clustering.addressType) }} + - name: RABBITMQ_NODE_NAME + value: "rabbit@$(MY_POD_NAME).$(K8S_SERVICE_NAME).$(MY_POD_NAMESPACE).svc.{{ .Values.clusterDomain }}" + - name: K8S_HOSTNAME_SUFFIX + value: ".$(K8S_SERVICE_NAME).$(MY_POD_NAMESPACE).svc.{{ .Values.clusterDomain }}" + {{- else }} + - name: RABBITMQ_NODE_NAME + value: "rabbit@$(MY_POD_NAME)" + {{- end }} + - name: RABBITMQ_MNESIA_DIR + value: "{{ .Values.persistence.mountPath }}/$(RABBITMQ_NODE_NAME)" + - name: RABBITMQ_LDAP_ENABLE + value: {{ ternary "yes" "no" .Values.ldap.enabled | quote }} + {{- if .Values.ldap.enabled }} + - name: RABBITMQ_LDAP_TLS + value: {{ ternary "yes" "no" .Values.ldap.tls.enabled | quote }} + - name: RABBITMQ_LDAP_SERVERS + value: {{ .Values.ldap.servers | join "," | quote }} + - name: RABBITMQ_LDAP_SERVERS_PORT + value: {{ .Values.ldap.port | quote }} + - name: RABBITMQ_LDAP_USER_DN_PATTERN + value: {{ .Values.ldap.user_dn_pattern }} + {{- end }} + {{- if .Values.logs }} + - name: RABBITMQ_LOGS + value: {{ .Values.logs | quote }} + {{- end }} + - name: RABBITMQ_ULIMIT_NOFILES + value: {{ .Values.ulimitNofiles | quote }} + {{- if and .Values.maxAvailableSchedulers }} + - name: RABBITMQ_SERVER_ADDITIONAL_ERL_ARGS + value: {{ printf "+S %s:%s" (toString .Values.maxAvailableSchedulers) (toString .Values.onlineSchedulers) -}} + {{- end }} + - name: RABBITMQ_USE_LONGNAME + value: "true" + - name: RABBITMQ_ERL_COOKIE + valueFrom: + secretKeyRef: + name: {{ template "rabbitmq.secretErlangName" . }} + key: rabbitmq-erlang-cookie + {{- if and .Values.clustering.rebalance (gt (.Values.replicaCount | int) 1) }} + - name: RABBITMQ_CLUSTER_REBALANCE + value: "true" + {{- end }} + - name: RABBITMQ_LOAD_DEFINITIONS + value: {{ ternary "yes" "no" .Values.loadDefinition.enabled | quote }} + - name: RABBITMQ_DEFINITIONS_FILE + value: {{ .Values.loadDefinition.file | quote }} + - name: RABBITMQ_SECURE_PASSWORD + value: {{ ternary "yes" "no" (or .Values.auth.securePassword (not .Values.auth.password)) | quote }} + - name: RABBITMQ_USERNAME + value: {{ .Values.auth.username | quote }} + - name: RABBITMQ_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "rabbitmq.secretPasswordName" . }} + key: rabbitmq-password + - name: RABBITMQ_PLUGINS + value: {{ include "rabbitmq.plugins" . | quote }} + {{- if .Values.communityPlugins }} + - name: RABBITMQ_COMMUNITY_PLUGINS + value: {{ .Values.communityPlugins | quote }} + {{- end }} + {{- if .Values.extraEnvVars }} + {{- include "common.tplvalues.render" (dict "value" .Values.extraEnvVars "context" $) | nindent 12 }} + {{- end }} + envFrom: + {{- if .Values.extraEnvVarsCM }} + - configMapRef: + name: {{ include "common.tplvalues.render" (dict "value" .Values.extraEnvVarsCM "context" $) }} + {{- end }} + {{- if .Values.extraEnvVarsSecret }} + - secretRef: + name: {{ include "common.tplvalues.render" (dict "value" .Values.extraEnvVarsSecret "context" $) }} + {{- end }} + ports: + - name: amqp + containerPort: {{ .Values.containerPorts.amqp }} + - name: dist + containerPort: {{ .Values.containerPorts.dist }} + - name: stats + containerPort: {{ .Values.containerPorts.manager }} + - name: epmd + containerPort: {{ .Values.containerPorts.epmd }} + {{- if .Values.metrics.enabled }} + - name: metrics + containerPort: {{ .Values.containerPorts.metrics }} + {{- end }} + {{- if .Values.auth.tls.enabled }} + - name: amqp-tls + containerPort: {{ .Values.containerPorts.amqpTls }} + {{- end }} + {{- if .Values.extraContainerPorts }} + {{- include "common.tplvalues.render" (dict "value" .Values.extraContainerPorts "context" $) | nindent 12 }} + {{- end }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.customLivenessProbe }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.customLivenessProbe "context" $) | nindent 12 }} + {{- else if .Values.livenessProbe.enabled }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.livenessProbe "enabled") "context" $) | nindent 12 }} + exec: + command: + - sh + - -ec + {{- if or (.Values.loadDefinition.enabled) (not (contains "rabbitmq_management" .Values.plugins )) }} + - rabbitmq-diagnostics -q ping + {{- else }} + - curl -f --user {{ .Values.auth.username }}:$RABBITMQ_PASSWORD 127.0.0.1:{{ .Values.containerPorts.manager }}/api/health/checks/virtual-hosts + {{- end }} + {{- end }} + {{- if .Values.customReadinessProbe }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.customReadinessProbe "context" $) | nindent 12 }} + {{- else if .Values.readinessProbe.enabled }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.readinessProbe "enabled") "context" $) | nindent 12 }} + exec: + command: + - sh + - -ec + {{- if or (.Values.loadDefinition.enabled) (not (contains "rabbitmq_management" .Values.plugins )) }} + - rabbitmq-diagnostics -q check_running && rabbitmq-diagnostics -q check_local_alarms + {{- else }} + - curl -f --user {{ .Values.auth.username }}:$RABBITMQ_PASSWORD 127.0.0.1:{{ .Values.containerPorts.manager }}/api/health/checks/local-alarms + {{- end }} + {{- end }} + {{- if .Values.customStartupProbe }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.customStartupProbe "context" $) | nindent 12 }} + {{- else if .Values.startupProbe.enabled }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.startupProbe "enabled") "context" $) | nindent 12 }} + tcpSocket: + port: {{ternary "amqp-tls" "amqp" .Values.auth.tls.enabled }} + {{- end }} + {{- end }} + {{- if .Values.resources }} + resources: {{- toYaml .Values.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: configuration + mountPath: /bitnami/rabbitmq/conf + - name: data + mountPath: {{ .Values.persistence.mountPath }} + {{- if .Values.persistence.subPath }} + subPath: {{ .Values.persistence.subPath }} + {{- end }} + {{- if .Values.auth.tls.enabled }} + - name: certs + mountPath: /opt/bitnami/rabbitmq/certs + {{- end }} + {{- if and .Values.ldap.tls.enabled .Values.ldap.tls.certificatesSecret }} + - name: ldap-certs + mountPath: {{ .Values.ldap.tls.certificatesMountPath }} + {{- end }} + {{- if .Values.loadDefinition.enabled }} + - name: load-definition-volume + mountPath: /app + readOnly: true + {{- end }} + {{- if .Values.extraVolumeMounts }} + {{- include "common.tplvalues.render" (dict "value" .Values.extraVolumeMounts "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.initScripts }} + - name: custom-init-scripts + mountPath: /docker-entrypoint-initdb.d/init-scripts + {{- end }} + {{- if .Values.initScriptsCM }} + - name: custom-init-scripts-cm + mountPath: /docker-entrypoint-initdb.d/init-scripts-cm + {{- end }} + {{- if .Values.initScriptsSecret }} + - name: custom-init-scripts-secret + mountPath: /docker-entrypoint-initdb.d/init-scripts-secret + {{- end }} + {{- if .Values.sidecars }} + {{- include "common.tplvalues.render" (dict "value" .Values.sidecars "context" $) | nindent 8 }} + {{- end }} + volumes: + {{- if .Values.auth.tls.enabled }} + - name: certs + projected: + sources: + - secret: + name: {{ template "rabbitmq.tlsSecretName" . }} + items: + {{- if not .Values.auth.tls.overrideCaCertificate }} + - key: {{ ternary "tls.crt" "ca.crt" .Values.auth.tls.existingSecretFullChain }} + path: ca_certificate.pem + {{- end }} + - key: tls.crt + path: server_certificate.pem + - key: tls.key + path: server_key.pem + {{- if .Values.auth.tls.overrideCaCertificate }} + - secret: + name: {{ .Values.auth.tls.overrideCaCertificate }} + items: + - key: ca.crt + path: ca_certificate.pem + {{- end }} + {{- end }} + {{- if and .Values.ldap.tls.enabled .Values.ldap.tls.certificatesSecret }} + - name: ldap-certs + secret: + secretName: {{ .Values.ldap.tls.certificatesSecret }} + {{- end }} + - name: configuration + projected: + sources: + {{- if or (and (empty .Values.configurationExistingSecret) .Values.configuration) (and (not .Values.advancedConfigurationExistingSecret) .Values.advancedConfiguration) }} + - secret: + name: {{ printf "%s-config" (include "common.names.fullname" .) }} + {{- end }} + {{- if and .Values.advancedConfigurationExistingSecret (not .Values.advancedConfiguration) }} + - secret: + name: {{ tpl .Values.advancedConfigurationExistingSecret . | quote }} + {{- end }} + {{- if not (empty .Values.configurationExistingSecret) }} + - secret: + name: {{ tpl .Values.configurationExistingSecret . | quote }} + {{- end }} + {{- if .Values.loadDefinition.enabled }} + - name: load-definition-volume + secret: + secretName: {{ tpl .Values.loadDefinition.existingSecret . | quote }} + {{- end }} + {{- if .Values.initScripts }} + - name: custom-init-scripts + configMap: + name: {{ template "rabbitmq.initScripts" . }} + {{- end }} + {{- if .Values.initScriptsCM }} + - name: custom-init-scripts-cm + configMap: + name: {{ tpl .Values.initScriptsCM . | quote }} + {{- end }} + {{- if .Values.initScriptsSecret }} + - name: custom-init-scripts-secret + secret: + secretName: {{ tpl .Values.initScriptsSecret . | quote }} + defaultMode: 0755 + {{- end }} + {{- if .Values.extraVolumes }} + {{- include "common.tplvalues.render" (dict "value" .Values.extraVolumes "context" $) | nindent 8 }} + {{- end }} + {{- if not .Values.persistence.enabled }} + - name: data + emptyDir: {} + {{- else if .Values.persistence.existingClaim }} + - name: data + persistentVolumeClaim: + {{- with .Values.persistence.existingClaim }} + claimName: {{ tpl . $ }} + {{- end }} + {{- else }} + volumeClaimTemplates: + - apiVersion: v1 + kind: PersistentVolumeClaim + metadata: + name: data + labels: + {{- include "common.labels.matchLabels" . | nindent 10 }} + {{- if .Values.persistence.labels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.persistence.labels "context" $) | nindent 10 }} + {{- end }} + {{- if .Values.persistence.annotations }} + annotations: + {{- include "common.tplvalues.render" ( dict "value" .Values.persistence.annotations "context" $) | nindent 10 }} + {{- end }} + spec: + accessModes: + {{- range .Values.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + resources: + requests: + storage: {{ .Values.persistence.size | quote }} + {{ include "common.storage.class" (dict "persistence" .Values.persistence "global" .Values.global) }} + {{- if .Values.persistence.selector }} + selector: {{- include "common.tplvalues.render" (dict "value" .Values.persistence.selector "context" $) | nindent 10 }} + {{- end -}} + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/svc-headless.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/svc-headless.yaml new file mode 100644 index 0000000..023194b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/svc-headless.yaml @@ -0,0 +1,47 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ printf "%s-%s" (include "common.names.fullname" .) (default "headless" .Values.servicenameOverride) }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if or .Values.service.annotationsHeadless .Values.commonAnnotations .Values.service.headless.annotations }} + annotations: + {{- if .Values.service.headless.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.service.headless.annotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.service.annotationsHeadless }} + {{- include "common.tplvalues.render" (dict "value" .Values.service.annotationsHeadless "context" $) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- end }} +spec: + clusterIP: None + ports: + - name: {{ .Values.service.portNames.epmd }} + port: {{ .Values.service.ports.epmd }} + targetPort: epmd + {{- if or (.Values.service.portEnabled) (not .Values.auth.tls.enabled) }} + - name: {{ .Values.service.portNames.amqp }} + port: {{ .Values.service.ports.amqp }} + targetPort: amqp + {{- end }} + {{- if .Values.auth.tls.enabled }} + - name: {{ .Values.service.portNames.amqpTls }} + port: {{ .Values.service.ports.amqpTls }} + targetPort: amqp-tls + {{- end }} + - name: {{ .Values.service.portNames.dist }} + port: {{ .Values.service.ports.dist }} + targetPort: dist + {{- if .Values.service.managerPortEnabled }} + - name: {{ .Values.service.portNames.manager }} + port: {{ .Values.service.ports.manager }} + targetPort: stats + {{- end }} + selector: {{ include "common.labels.matchLabels" . | nindent 4 }} + publishNotReadyAddresses: true diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/svc.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/svc.yaml new file mode 100644 index 0000000..3dde7a8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/svc.yaml @@ -0,0 +1,111 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "common.names.fullname" . }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.service.labels }} + {{- include "common.tplvalues.render" (dict "value" .Values.service.labels "context" $) | nindent 4 }} + {{- end }} + {{- if or (.Values.service.annotations) (.Values.commonAnnotations) }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" (dict "value" .Values.commonAnnotations "context" $) | nindent 4 }} + {{- end -}} + {{- if .Values.service.annotations }} + {{- include "common.tplvalues.render" (dict "value" .Values.service.annotations "context" $) | nindent 4 }} + {{- end -}} + {{- end }} +spec: + type: {{ .Values.service.type }} + {{- if not (empty .Values.service.clusterIP) }} + clusterIP: {{ .Values.service.clusterIP }} + {{- end }} + {{- if eq .Values.service.type "LoadBalancer" }} + {{- if not (empty .Values.service.loadBalancerIP) }} + loadBalancerIP: {{ .Values.service.loadBalancerIP }} + {{- end }} + {{- if .Values.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: {{- toYaml .Values.service.loadBalancerSourceRanges | nindent 4 }} + {{- end }} + {{- end }} + {{- if or (eq .Values.service.type "LoadBalancer") (eq .Values.service.type "NodePort") }} + externalTrafficPolicy: {{ .Values.service.externalTrafficPolicy | quote }} + {{- end }} + {{- if .Values.service.sessionAffinity }} + sessionAffinity: {{ .Values.service.sessionAffinity }} + {{- end }} + {{- if .Values.service.sessionAffinityConfig }} + sessionAffinityConfig: {{- include "common.tplvalues.render" (dict "value" .Values.service.sessionAffinityConfig "context" $) | nindent 4 }} + {{- end }} + {{- if .Values.service.externalIPs }} + externalIPs: {{- toYaml .Values.service.externalIPs | nindent 4 }} + {{- end }} + ports: + {{- if or (.Values.service.portEnabled) (not .Values.auth.tls.enabled) }} + - name: {{ .Values.service.portNames.amqp }} + port: {{ .Values.service.ports.amqp }} + targetPort: amqp + {{- if (eq .Values.service.type "ClusterIP") }} + nodePort: null + {{- else if and (or (eq .Values.service.type "NodePort") (eq .Values.service.type "LoadBalancer")) (not (empty .Values.service.nodePorts.amqp)) }} + nodePort: {{ .Values.service.nodePorts.amqp }} + {{- end }} + {{- end }} + {{- if .Values.auth.tls.enabled }} + - name: {{ .Values.service.portNames.amqpTls }} + port: {{ .Values.service.ports.amqpTls }} + targetPort: amqp-tls + {{- if (eq .Values.service.type "ClusterIP") }} + nodePort: null + {{- else if and (or (eq .Values.service.type "NodePort") (eq .Values.service.type "LoadBalancer")) (not (empty .Values.service.nodePorts.amqpTls)) }} + nodePort: {{ .Values.service.nodePorts.amqpTls }} + {{- end }} + {{- end }} + {{- if .Values.service.epmdPortEnabled }} + - name: {{ .Values.service.portNames.epmd }} + port: {{ .Values.service.ports.epmd }} + targetPort: epmd + {{- if (eq .Values.service.type "ClusterIP") }} + nodePort: null + {{- else if and (or (eq .Values.service.type "NodePort") (eq .Values.service.type "LoadBalancer")) (not (empty .Values.service.nodePorts.epmd)) }} + nodePort: {{ .Values.service.nodePorts.epmd }} + {{- end }} + {{- end }} + {{- if .Values.service.distPortEnabled }} + - name: {{ .Values.service.portNames.dist }} + port: {{ .Values.service.ports.dist }} + targetPort: dist + {{- if eq .Values.service.type "ClusterIP" }} + nodePort: null + {{- else if and (or (eq .Values.service.type "NodePort") (eq .Values.service.type "LoadBalancer")) (not (empty .Values.service.nodePorts.dist)) }} + nodePort: {{ .Values.service.nodePorts.dist }} + {{- end }} + {{- end }} + {{- if .Values.service.managerPortEnabled }} + - name: {{ .Values.service.portNames.manager }} + port: {{ .Values.service.ports.manager }} + targetPort: stats + {{- if eq .Values.service.type "ClusterIP" }} + nodePort: null + {{- else if and (or (eq .Values.service.type "NodePort") (eq .Values.service.type "LoadBalancer")) (not (empty .Values.service.nodePorts.manager)) }} + nodePort: {{ .Values.service.nodePorts.manager }} + {{- end }} + {{- end }} + {{- if .Values.metrics.enabled }} + - name: {{ .Values.service.portNames.metrics }} + port: {{ .Values.service.ports.metrics }} + targetPort: metrics + {{- if eq .Values.service.type "ClusterIP" }} + nodePort: null + {{- else if and (or (eq .Values.service.type "NodePort") (eq .Values.service.type "LoadBalancer")) (not (empty .Values.service.nodePorts.metrics)) }} + nodePort: {{ .Values.service.nodePorts.metrics }} + {{- end }} + {{- end }} + {{- if .Values.service.extraPorts }} + {{- include "common.tplvalues.render" (dict "value" .Values.service.extraPorts "context" $) | nindent 4 }} + {{- end }} + selector: {{ include "common.labels.matchLabels" . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/tls-secrets.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/tls-secrets.yaml new file mode 100644 index 0000000..ee8dc03 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/tls-secrets.yaml @@ -0,0 +1,79 @@ +{{- if .Values.ingress.enabled }} +{{- if .Values.ingress.secrets }} +{{- range .Values.ingress.secrets }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ .name }} + namespace: {{ include "common.names.namespace" $ | quote }} + labels: {{- include "common.labels.standard" $ | nindent 4 }} + {{- if $.Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if $.Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: kubernetes.io/tls +data: + tls.crt: {{ .certificate | b64enc }} + tls.key: {{ .key | b64enc }} +--- +{{- end }} +{{- end }} +{{- if and .Values.ingress.tls .Values.ingress.selfSigned (not .Values.ingress.existingSecret) }} +{{- $secretName := printf "%s-tls" .Values.ingress.hostname }} +{{- $ca := genCA "rabbitmq-ca" 365 }} +{{- $cert := genSignedCert .Values.ingress.hostname nil (list .Values.ingress.hostname) 365 $ca }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ $secretName }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: kubernetes.io/tls +data: + tls.crt: {{ include "common.secrets.lookup" (dict "secret" $secretName "key" "tls.crt" "defaultValue" $cert.Cert "context" $) }} + tls.key: {{ include "common.secrets.lookup" (dict "secret" $secretName "key" "tls.key" "defaultValue" $cert.Key "context" $) }} + ca.crt: {{ include "common.secrets.lookup" (dict "secret" $secretName "key" "ca.crt" "defaultValue" $ca.Cert "context" $) }} +{{- end }} +{{- end }} +{{- if (include "rabbitmq.createTlsSecret" . ) }} +{{- $secretName := printf "%s-certs" (include "common.names.fullname" .) }} +--- +apiVersion: v1 +kind: Secret +metadata: + name: {{ $secretName }} + namespace: {{ include "common.names.namespace" . | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: kubernetes.io/tls +data: + {{- if not .Values.auth.tls.autoGenerated }} + tls.crt: {{ required "A valid .Values.auth.tls.serverCertificate entry required!" .Values.auth.tls.serverCertificate | b64enc | quote }} + tls.key: {{ required "A valid .Values.auth.tls.serverKey entry required!" .Values.auth.tls.serverKey | b64enc | quote }} + ca.crt: {{ required "A valid .Values.auth.tls.caCertificate entry required!" .Values.auth.tls.caCertificate | b64enc | quote }} + {{- else }} + {{- $ca := genCA "rabbitmq-internal-ca" 365 }} + {{- $fullname := include "common.names.fullname" . }} + {{- $releaseNamespace := .Release.Namespace }} + {{- $clusterDomain := .Values.clusterDomain }} + {{- $serviceName := include "common.names.fullname" . }} + {{- $altNames := list (printf "*.%s.%s.svc.%s" $serviceName $releaseNamespace $clusterDomain) (printf "%s.%s.svc.%s" $serviceName $releaseNamespace $clusterDomain) $fullname }} + {{- $cert := genSignedCert $fullname nil $altNames 365 $ca }} + tls.crt: {{ include "common.secrets.lookup" (dict "secret" $secretName "key" "tls.crt" "defaultValue" $cert.Cert "context" $) }} + tls.key: {{ include "common.secrets.lookup" (dict "secret" $secretName "key" "tls.key" "defaultValue" $cert.Key "context" $) }} + ca.crt: {{ include "common.secrets.lookup" (dict "secret" $secretName "key" "ca.crt" "defaultValue" $ca.Cert "context" $) }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/validation.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/validation.yaml new file mode 100644 index 0000000..f72ef7f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/templates/validation.yaml @@ -0,0 +1,2 @@ +{{- include "rabbitmq.validateValues" . }} + diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/values.schema.json b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/values.schema.json new file mode 100644 index 0000000..8ef33ef --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/values.schema.json @@ -0,0 +1,100 @@ +{ + "$schema": "http://json-schema.org/schema#", + "type": "object", + "properties": { + "auth": { + "type": "object", + "properties": { + "username": { + "type": "string", + "title": "RabbitMQ user", + "form": true + }, + "password": { + "type": "string", + "title": "RabbitMQ password", + "form": true, + "description": "Defaults to a random 10-character alphanumeric string if not set" + } + } + }, + "extraConfiguration": { + "type": "string", + "title": "Extra RabbitMQ Configuration", + "form": true, + "render": "textArea", + "description": "Extra configuration to be appended to RabbitMQ Configuration" + }, + "replicaCount": { + "type": "integer", + "form": true, + "title": "Number of replicas", + "description": "Number of replicas to deploy" + }, + "persistence": { + "type": "object", + "title": "Persistence configuration", + "form": true, + "properties": { + "enabled": { + "type": "boolean", + "form": true, + "title": "Enable persistence", + "description": "Enable persistence using Persistent Volume Claims" + }, + "size": { + "type": "string", + "title": "Persistent Volume Size", + "form": true, + "render": "slider", + "sliderMin": 1, + "sliderMax": 100, + "sliderUnit": "Gi", + "hidden": { + "value": false, + "path": "persistence/enabled" + } + } + } + }, + "volumePermissions": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean", + "form": true, + "title": "Enable Init Containers", + "description": "Use an init container to set required folder permissions on the data volume before mounting it in the final destination" + } + } + }, + "metrics": { + "type": "object", + "form": true, + "title": "Prometheus metrics details", + "properties": { + "enabled": { + "type": "boolean", + "title": "Enable Prometheus metrics for RabbitMQ", + "description": "Install Prometheus plugin in the RabbitMQ container", + "form": true + }, + "serviceMonitor": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean", + "title": "Create Prometheus Operator ServiceMonitor", + "description": "Create a ServiceMonitor to track metrics using Prometheus Operator", + "form": true, + "hidden": { + "value": false, + "path": "metrics/enabled" + } + } + } + } + } + } + } +} diff --git a/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/values.yaml new file mode 100644 index 0000000..b418c21 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/rabbitmq/values.yaml @@ -0,0 +1,1429 @@ +## @section Global parameters +## Global Docker image parameters +## Please, note that this will override the image parameters, including dependencies, configured to use the global value +## Current available global Docker image parameters: imageRegistry, imagePullSecrets and storageClass +## + +## @param global.imageRegistry Global Docker image registry +## @param global.imagePullSecrets Global Docker registry secret names as an array +## @param global.storageClass Global StorageClass for Persistent Volume(s) +## +global: + imageRegistry: "" + ## E.g. + ## imagePullSecrets: + ## - myRegistryKeySecretName + ## + imagePullSecrets: [] + storageClass: "" + +## @section RabbitMQ Image parameters +## Bitnami RabbitMQ image version +## ref: https://hub.docker.com/r/bitnami/rabbitmq/tags/ +## @param image.registry RabbitMQ image registry +## @param image.repository RabbitMQ image repository +## @param image.tag RabbitMQ image tag (immutable tags are recommended) +## @param image.digest RabbitMQ image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag +## @param image.pullPolicy RabbitMQ image pull policy +## @param image.pullSecrets Specify docker-registry secret names as an array +## @param image.debug Set to true if you would like to see extra information on logs +## +image: + registry: docker.io + repository: bitnami/rabbitmq + tag: 3.12.0-debian-11-r0 + digest: "" + ## set to true if you would like to see extra information on logs + ## It turns BASH and/or NAMI debugging in the image + ## + debug: false + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + +## @section Common parameters +## + +## @param nameOverride String to partially override rabbitmq.fullname template (will maintain the release name) +## +nameOverride: "" +## @param fullnameOverride String to fully override rabbitmq.fullname template +## +fullnameOverride: "" +## @param namespaceOverride String to fully override common.names.namespace +## +namespaceOverride: "" +## @param kubeVersion Force target Kubernetes version (using Helm capabilities if not set) +## +kubeVersion: "" +## @param clusterDomain Kubernetes Cluster Domain +## +clusterDomain: cluster.local +## @param extraDeploy Array of extra objects to deploy with the release +## +extraDeploy: [] +## @param commonAnnotations Annotations to add to all deployed objects +## +commonAnnotations: {} +## @param servicenameOverride String to partially override headless service name +## +servicenameOverride: "" +## @param commonLabels Labels to add to all deployed objects +## +commonLabels: {} + +## @param serviceBindings.enabled Create secret for service binding (Experimental) +## Ref: https://servicebinding.io/service-provider/ +## +serviceBindings: + enabled: false + +## Enable diagnostic mode in the deployment +## +diagnosticMode: + ## @param diagnosticMode.enabled Enable diagnostic mode (all probes will be disabled and the command will be overridden) + ## + enabled: false + ## @param diagnosticMode.command Command to override all containers in the deployment + ## + command: + - sleep + ## @param diagnosticMode.args Args to override all containers in the deployment + ## + args: + - infinity + +## @param hostAliases Deployment pod host aliases +## https://kubernetes.io/docs/concepts/services-networking/add-entries-to-pod-etc-hosts-with-host-aliases/ +## +hostAliases: [] +## @param dnsPolicy DNS Policy for pod +## ref: https://kubernetes.io/docs/concepts/services-networking/dns-pod-service/ +## E.g. +## dnsPolicy: ClusterFirst +## +dnsPolicy: "" +## @param dnsConfig DNS Configuration pod +## ref: https://kubernetes.io/docs/concepts/services-networking/dns-pod-service/ +## E.g. +## dnsConfig: +## options: +## - name: ndots +## value: "4" +## +dnsConfig: {} +## RabbitMQ Authentication parameters +## +auth: + ## @param auth.username RabbitMQ application username + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/rabbitmq#environment-variables + ## + username: user + ## @param auth.password RabbitMQ application password + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/rabbitmq#environment-variables + ## + password: "" + ## @param auth.securePassword Whether to set the RabbitMQ password securely. This is incompatible with loading external RabbitMQ definitions and 'true' when not setting the auth.password parameter. + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/rabbitmq#environment-variables + ## + securePassword: true + ## @param auth.existingPasswordSecret Existing secret with RabbitMQ credentials (must contain a value for `rabbitmq-password` key) + ## e.g: + ## existingPasswordSecret: name-of-existing-secret + ## + existingPasswordSecret: "" + ## @param auth.enableLoopbackUser If enabled, the user `auth.username` can only connect from localhost + ## + enableLoopbackUser: false + ## @param auth.erlangCookie Erlang cookie to determine whether different nodes are allowed to communicate with each other + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/rabbitmq#environment-variables + ## + erlangCookie: "" + ## @param auth.existingErlangSecret Existing secret with RabbitMQ Erlang cookie (must contain a value for `rabbitmq-erlang-cookie` key) + ## e.g: + ## existingErlangSecret: name-of-existing-secret + ## + existingErlangSecret: "" + + ## Enable encryption to rabbitmq + ## ref: https://www.rabbitmq.com/ssl.html + ## @param auth.tls.enabled Enable TLS support on RabbitMQ + ## @param auth.tls.autoGenerated Generate automatically self-signed TLS certificates + ## @param auth.tls.failIfNoPeerCert When set to true, TLS connection will be rejected if client fails to provide a certificate + ## @param auth.tls.sslOptionsVerify Should [peer verification](https://www.rabbitmq.com/ssl.html#peer-verification) be enabled? + ## @param auth.tls.sslOptionsPassword.enabled Enable usage of password for private Key + ## @param auth.tls.sslOptionsPassword.existingSecret Name of existing Secret containing the sslOptionsPassword + ## @param auth.tls.sslOptionsPassword.key Enable Key referring to sslOptionsPassword in Secret specified in auth.tls.sslOptionsPassword.existingSecret + ## @param auth.tls.sslOptionsPassword.password Use this string as Password. If set, auth.tls.sslOptionsPassword.existingSecret and auth.tls.sslOptionsPassword.key are ignored + ## @param auth.tls.caCertificate Certificate Authority (CA) bundle content + ## @param auth.tls.serverCertificate Server certificate content + ## @param auth.tls.serverKey Server private key content + ## @param auth.tls.existingSecret Existing secret with certificate content to RabbitMQ credentials + ## @param auth.tls.existingSecretFullChain Whether or not the existing secret contains the full chain in the certificate (`tls.crt`). Will be used in place of `ca.cert` if `true`. + ## @param auth.tls.overrideCaCertificate Existing secret with certificate content be mounted instead of the `ca.crt` coming from caCertificate or existingSecret/existingSecretFullChain. + ## + tls: + enabled: false + autoGenerated: false + failIfNoPeerCert: true + sslOptionsVerify: verify_peer + sslOptionsPassword: + enabled: false + existingSecret: "" + key: "" + password: "" + caCertificate: "" + serverCertificate: "" + serverKey: "" + existingSecret: "" + existingSecretFullChain: false + overrideCaCertificate: "" + +## @param logs Path of the RabbitMQ server's Erlang log file. Value for the `RABBITMQ_LOGS` environment variable +## ref: https://www.rabbitmq.com/logging.html#log-file-location +## +logs: "-" +## @param ulimitNofiles RabbitMQ Max File Descriptors +## ref: https://github.com/bitnami/containers/tree/main/bitnami/rabbitmq#environment-variables +## ref: https://www.rabbitmq.com/install-debian.html#kernel-resource-limits +## +ulimitNofiles: "65536" +## RabbitMQ maximum available scheduler threads and online scheduler threads. By default it will create a thread per CPU detected, with the following parameters you can tune it manually. +## ref: https://hamidreza-s.github.io/erlang/scheduling/real-time/preemptive/migration/2016/02/09/erlang-scheduler-details.html#scheduler-threads +## ref: https://github.com/bitnami/charts/issues/2189 +## @param maxAvailableSchedulers RabbitMQ maximum available scheduler threads +## @param onlineSchedulers RabbitMQ online scheduler threads +## +maxAvailableSchedulers: "" +onlineSchedulers: "" + +## The memory threshold under which RabbitMQ will stop reading from client network sockets, in order to avoid being killed by the OS +## ref: https://www.rabbitmq.com/alarms.html +## ref: https://www.rabbitmq.com/memory.html#threshold +## +memoryHighWatermark: + ## @param memoryHighWatermark.enabled Enable configuring Memory high watermark on RabbitMQ + ## + enabled: false + ## @param memoryHighWatermark.type Memory high watermark type. Either `absolute` or `relative` + ## + type: "relative" + ## Memory high watermark value. + ## @param memoryHighWatermark.value Memory high watermark value + ## The default value of 0.4 stands for 40% of available RAM + ## Note: the memory relative limit is applied to the resource.limits.memory to calculate the memory threshold + ## You can also use an absolute value, e.g.: 256MB + ## + value: 0.4 + +## @param plugins List of default plugins to enable (should only be altered to remove defaults; for additional plugins use `extraPlugins`) +## +plugins: "rabbitmq_management rabbitmq_peer_discovery_k8s" +## @param communityPlugins List of Community plugins (URLs) to be downloaded during container initialization +## Combine it with extraPlugins to also enable them. +## +communityPlugins: "" +## @param extraPlugins Extra plugins to enable (single string containing a space-separated list) +## Use this instead of `plugins` to add new plugins +## +extraPlugins: "rabbitmq_auth_backend_ldap" + +## Clustering settings +## +clustering: + ## @param clustering.enabled Enable RabbitMQ clustering + ## + enabled: true + ## @param clustering.addressType Switch clustering mode. Either `ip` or `hostname` + ## + addressType: hostname + ## @param clustering.rebalance Rebalance master for queues in cluster when new replica is created + ## ref: https://www.rabbitmq.com/rabbitmq-queues.8.html#rebalance + ## + rebalance: false + ## @param clustering.forceBoot Force boot of an unexpectedly shut down cluster (in an unexpected order). + ## forceBoot executes 'rabbitmqctl force_boot' to force boot cluster shut down unexpectedly in an unknown order + ## ref: https://www.rabbitmq.com/rabbitmqctl.8.html#force_boot + ## + forceBoot: false + ## @param clustering.partitionHandling Switch Partition Handling Strategy. Either `autoheal` or `pause-minority` or `pause-if-all-down` or `ignore` + ## ref: https://www.rabbitmq.com/partitions.html#automatic-handling + ## + partitionHandling: autoheal + +## Loading a RabbitMQ definitions file to configure RabbitMQ +## +loadDefinition: + ## @param loadDefinition.enabled Enable loading a RabbitMQ definitions file to configure RabbitMQ + ## + enabled: false + ## @param loadDefinition.file Name of the definitions file + ## + file: "/app/load_definition.json" + ## @param loadDefinition.existingSecret Existing secret with the load definitions file + ## Can be templated if needed, e.g: + ## existingSecret: "{{ .Release.Name }}-load-definition" + ## + existingSecret: "" + +## @param command Override default container command (useful when using custom images) +## +command: [] +## @param args Override default container args (useful when using custom images) +## +args: [] +## @param lifecycleHooks Overwrite livecycle for the RabbitMQ container(s) to automate configuration before or after startup +## +lifecycleHooks: {} +## @param terminationGracePeriodSeconds Default duration in seconds k8s waits for container to exit before sending kill signal. +## Any time in excess of 10 seconds will be spent waiting for any synchronization necessary for cluster not to lose data. +## +terminationGracePeriodSeconds: 120 +## @param extraEnvVars Extra environment variables to add to RabbitMQ pods +## E.g: +## extraEnvVars: +## - name: FOO +## value: BAR +## +extraEnvVars: [] +## @param extraEnvVarsCM Name of existing ConfigMap containing extra environment variables +## +extraEnvVarsCM: "" +## @param extraEnvVarsSecret Name of existing Secret containing extra environment variables (in case of sensitive data) +## +extraEnvVarsSecret: "" + +## Container Ports +## @param containerPorts.amqp +## @param containerPorts.amqpTls +## @param containerPorts.dist +## @param containerPorts.manager +## @param containerPorts.epmd +## @param containerPorts.metrics +## +containerPorts: + amqp: 5672 + amqpTls: 5671 + dist: 25672 + manager: 15672 + epmd: 4369 + metrics: 9419 + +## @param initScripts Dictionary of init scripts. Evaluated as a template. +## Specify dictionary of scripts to be run at first boot +## Alternatively, you can put your scripts under the files/docker-entrypoint-initdb.d directory +## For example: +## initScripts: +## my_init_script.sh: | +## #!/bin/sh +## echo "Do something." +## +initScripts: {} +## @param initScriptsCM ConfigMap with the init scripts. Evaluated as a template. +## Note: This will override initScripts +## +initScriptsCM: "" +## @param initScriptsSecret Secret containing `/docker-entrypoint-initdb.d` scripts to be executed at initialization time that contain sensitive data. Evaluated as a template. +## +initScriptsSecret: "" +## @param extraContainerPorts Extra ports to be included in container spec, primarily informational +## E.g: +## extraContainerPorts: +## - name: new_port_name +## containerPort: 1234 +## +extraContainerPorts: [] +## @param configuration [string] RabbitMQ Configuration file content: required cluster configuration +## Do not override unless you know what you are doing. +## To add more configuration, use `extraConfiguration` of `advancedConfiguration` instead +## + +## RabbitMQ tcp_listen_options parameters +## See : https://www.rabbitmq.com/networking.html for additional information +## +tcpListenOptions: + ## @param tcpListenOptions.backlog Maximum size of the unaccepted TCP connections queue + ## + backlog: 128 + ## @param tcpListenOptions.nodelay When set to true, deactivates Nagle's algorithm. Default is true. Highly recommended for most users. + ## + nodelay: true + ## tcpListenOptions.linger + ## + linger: + ## @param tcpListenOptions.linger.lingerOn Enable Server socket lingering + ## + lingerOn: true + ## @param tcpListenOptions.linger.timeout Server Socket lingering timeout + ## + timeout: 0 + ## @param tcpListenOptions.keepalive When set to true, enables TCP keepalives + ## + keepalive: false + +configuration: |- + ## Username and password + ## + default_user = {{ .Values.auth.username }} + {{- if and (not .Values.auth.securePassword) .Values.auth.password }} + default_pass = {{ .Values.auth.password }} + {{- end }} + {{- if .Values.clustering.enabled }} + ## Clustering + ## + cluster_formation.peer_discovery_backend = rabbit_peer_discovery_k8s + cluster_formation.k8s.host = kubernetes.default + cluster_formation.node_cleanup.interval = 10 + cluster_formation.node_cleanup.only_log_warning = true + cluster_partition_handling = {{ .Values.clustering.partitionHandling }} + {{- end }} + {{ if and .Values.clustering.enabled .Values.loadDefinition.enabled }} + cluster_formation.target_cluster_size_hint = {{ .Values.replicaCount }} + {{ end }} + {{- if .Values.loadDefinition.enabled }} + load_definitions = {{ .Values.loadDefinition.file }} + {{- end }} + # queue master locator + queue_master_locator = min-masters + # enable loopback user + {{- if not (empty .Values.auth.username) }} + loopback_users.{{ .Values.auth.username }} = {{ .Values.auth.enableLoopbackUser }} + {{- else}} + loopback_users.guest = {{ .Values.auth.enableLoopbackUser }} + {{- end }} + {{ template "rabbitmq.extraConfiguration" . }} + {{- if .Values.auth.tls.enabled }} + ssl_options.verify = {{ .Values.auth.tls.sslOptionsVerify }} + listeners.ssl.default = {{ .Values.service.ports.amqpTls }} + ssl_options.fail_if_no_peer_cert = {{ .Values.auth.tls.failIfNoPeerCert }} + ssl_options.cacertfile = /opt/bitnami/rabbitmq/certs/ca_certificate.pem + ssl_options.certfile = /opt/bitnami/rabbitmq/certs/server_certificate.pem + ssl_options.keyfile = /opt/bitnami/rabbitmq/certs/server_key.pem + {{- if .Values.auth.tls.sslOptionsPassword.enabled }} + ssl_options.password = {{ template "rabbitmq.tlsSslOptionsPassword" . }} + {{- end }} + {{- end }} + {{- if .Values.ldap.enabled }} + auth_backends.1.authn = ldap + auth_backends.1.authz = {{ ternary "ldap" "internal" .Values.ldap.authorisationEnabled }} + auth_backends.2 = internal + {{- $host := list }} + {{- $port := ternary 636 389 .Values.ldap.tls.enabled }} + {{- if .Values.ldap.uri }} + {{- $hostPort := get (urlParse .Values.ldap.uri) "host" }} + {{- $host = list (index (splitList ":" $hostPort) 0) -}} + {{- if (contains ":" $hostPort) }} + {{- $port = index (splitList ":" $hostPort) 1 -}} + {{- end }} + {{- end }} + {{- range $index, $server := concat $host .Values.ldap.servers }} + auth_ldap.servers.{{ add $index 1 }} = {{ $server }} + {{- end }} + auth_ldap.port = {{ coalesce .Values.ldap.port $port }} + {{- if or .Values.ldap.user_dn_pattern .Values.ldap.userDnPattern }} + auth_ldap.user_dn_pattern = {{ coalesce .Values.ldap.user_dn_pattern .Values.ldap.userDnPattern }} + {{- end }} + {{- if .Values.ldap.basedn }} + auth_ldap.dn_lookup_base = {{ .Values.ldap.basedn }} + {{- end }} + {{- if .Values.ldap.uidField }} + auth_ldap.dn_lookup_attribute = {{ .Values.ldap.uidField }} + {{- end }} + {{- if .Values.ldap.binddn }} + auth_ldap.dn_lookup_bind.user_dn = {{ .Values.ldap.binddn }} + auth_ldap.dn_lookup_bind.password = {{ required "'ldap.bindpw' is required when 'ldap.binddn' is defined" .Values.ldap.bindpw }} + {{- end }} + {{- if .Values.ldap.tls.enabled }} + auth_ldap.use_ssl = {{ not .Values.ldap.tls.startTls }} + auth_ldap.use_starttls = {{ .Values.ldap.tls.startTls }} + {{- if .Values.ldap.tls.CAFilename }} + auth_ldap.ssl_options.cacertfile = {{ .Values.ldap.tls.certificatesMountPath }}/{{ .Values.ldap.tls.CAFilename }} + {{- end }} + {{- if .Values.ldap.tls.certFilename }} + auth_ldap.ssl_options.certfile = {{ .Values.ldap.tls.certificatesMountPath }}/{{ .Values.ldap.tls.certFilename }} + auth_ldap.ssl_options.keyfile = {{ .Values.ldap.tls.certificatesMountPath }}/{{ required "'ldap.tls.certKeyFilename' is required when 'ldap.tls.certFilename' is defined" .Values.ldap.tls.certKeyFilename }} + {{- end }} + {{- if .Values.ldap.tls.skipVerify }} + auth_ldap.ssl_options.verify = verify_none + auth_ldap.ssl_options.fail_if_no_peer_cert = false + {{- else if .Values.ldap.tls.verify }} + auth_ldap.ssl_options.verify = {{ .Values.ldap.tls.verify }} + {{- end }} + {{- end }} + {{- end }} + {{- if .Values.metrics.enabled }} + ## Prometheus metrics + ## + prometheus.tcp.port = {{ .Values.containerPorts.metrics }} + {{- end }} + {{- if .Values.memoryHighWatermark.enabled }} + ## Memory Threshold + ## + total_memory_available_override_value = {{ include "rabbitmq.toBytes" .Values.resources.limits.memory }} + vm_memory_high_watermark.{{ .Values.memoryHighWatermark.type }} = {{ .Values.memoryHighWatermark.value }} + ## TCP Listen Options + ## + tcp_listen_options.backlog = {{ .Values.tcpListenOptions.backlog }} + tcp_listen_options.nodelay = {{ .Values.tcpListenOptions.nodelay }} + tcp_listen_options.linger.on = {{ .Values.tcpListenOptions.linger.lingerOn }} + tcp_listen_options.linger.timeout = {{ .Values.tcpListenOptions.linger.timeout }} + tcp_listen_options.keepalive = {{ .Values.tcpListenOptions.keepalive }} + {{- end }} + +## @param configurationExistingSecret Existing secret with the configuration to use as rabbitmq.conf. +## Must contain the key "rabbitmq.conf" +## Takes precedence over `configuration`, so do not use both simultaneously +## With providing an existingSecret, extraConfiguration and extraConfigurationExistingSecret do not take any effect +## +configurationExistingSecret: "" + +## @param extraConfiguration [string] Configuration file content: extra configuration to be appended to RabbitMQ configuration +## Use this instead of `configuration` to add more configuration +## Do not use simultaneously with `extraConfigurationExistingSecret` +## +extraConfiguration: |- + #default_vhost = {{ .Release.Namespace }}-vhost + #disk_free_limit.absolute = 50MB + +## @param extraConfigurationExistingSecret Existing secret with the extra configuration to append to `configuration`. +## Must contain the key "extraConfiguration" +## Takes precedence over `extraConfiguration`, so do not use both simultaneously +## +extraConfigurationExistingSecret: "" + +## @param advancedConfiguration Configuration file content: advanced configuration +## Use this as additional configuration in classic config format (Erlang term configuration format) +## +## LDAP authorisation example: +## advancedConfiguration: |- +## [{rabbitmq_auth_backend_ldap,[ +## {tag_queries, [{administrator, {constant, true}}, +## {management, {constant, true}}]} +## ]}]. +## +## If both, advancedConfiguration and advancedConfigurationExistingSecret are set, then advancedConfiguration +## will be used instead of the secret. +# +advancedConfiguration: |- + +## @param advancedConfigurationExistingSecret Existing secret with the advanced configuration file (must contain a key `advanced.config`). +## Use this as additional configuration in classic config format (Erlang term configuration format) as in advancedConfiguration +## Do not use in combination with advancedConfiguration, will be ignored +## +advancedConfigurationExistingSecret: "" + +## This subsystem was introduced in RabbitMQ 3.8.0 to allow rolling upgrades of cluster members without shutting down the entire cluster. +## Feature flags are a mechanism that controls what features are considered to be enabled or available on all cluster nodes. If a feature flag is enabled, so is its associated feature (or behavior). If not then all nodes in the cluster will disable the feature (behavior). +## e.g, drop_unroutable_metric,empty_basic_get_metric,implicit_default_bindings,maintenance_mode_status,quorum_queue,virtual_host_metadata +## @param featureFlags that controls what features are considered to be enabled or available on all cluster nodes. +## +featureFlags: "" + +## LDAP configuration +## +ldap: + ## @param ldap.enabled Enable LDAP support + ## + enabled: false + ## @param ldap.uri LDAP connection string. + ## + uri: "" + ## @param ldap.servers List of LDAP servers hostnames. This is valid only if ldap.uri is not set + ## + servers: [] + ## @param ldap.port LDAP servers port. This is valid only if ldap.uri is not set + ## + port: "" + + ## DEPRECATED ldap.user_dn_pattern it will removed in a future, please use userDnPattern instead + ## Pattern used to translate the provided username into a value to be used for the LDAP bind + ## @param ldap.userDnPattern Pattern used to translate the provided username into a value to be used for the LDAP bind. + ## ref: https://www.rabbitmq.com/ldap.html#usernames-and-dns + ## + userDnPattern: "" + ## @param ldap.binddn DN of the account used to search in the LDAP server. + ## + binddn: "" + ## @param ldap.bindpw Password for binddn account. + ## + bindpw: "" + ## @param ldap.basedn Base DN path where binddn account will search for the users. + ## + basedn: "" + ## @param ldap.uidField Field used to match with the user name (uid, samAccountName, cn, etc). It matches with 'dn_lookup_attribute' in RabbitMQ configuration + ##��ref: https://www.rabbitmq.com/ldap.html#usernames-and-dns + ## + ## @param ldap.uidField Field used to match with the user name (uid, samAccountName, cn, etc). It matches with 'dn_lookup_attribute' in RabbitMQ configuration + ## + uidField: "" + ## @param ldap.authorisationEnabled Enable LDAP authorisation. Please set 'advancedConfiguration' with tag, topic, resources and vhost mappings + ## ref: https://www.rabbitmq.com/ldap.html#authorisation + ## + authorisationEnabled: false + ## @param ldap.tls.enabled Enabled TLS configuration. + ## @param ldap.tls.startTls Use STARTTLS instead of LDAPS. + ## @param ldap.tls.skipVerify Skip any SSL verification (hostanames or certificates) + ## @param ldap.tls.verify Verify connection. Valid values are 'verify_peer' or 'verify_none' + ## @param ldap.tls.certificatesMountPath Where LDAP certifcates are mounted. + ## @param ldap.tls.certificatesSecret Secret with LDAP certificates. + ## @param ldap.tls.CAFilename CA certificate filename. Should match with the CA entry key in the ldap.tls.certificatesSecret. + ## @param ldap.tls.certFilename Client certificate filename to authenticate against the LDAP server. Should match with certificate the entry key in the ldap.tls.certificatesSecret. + ## @param ldap.tls.certKeyFilename Client Key filename to authenticate against the LDAP server. Should match with certificate the entry key in the ldap.tls.certificatesSecret. + ## + tls: + enabled: false + startTls: false + skipVerify: false + verify: "verify_peer" + certificatesMountPath: /opt/bitnami/rabbitmq/ldap/certs + certificatesSecret: "" + CAFilename: "" + certFilename: "" + certKeyFilename: "" + +## @param extraVolumeMounts Optionally specify extra list of additional volumeMounts +## Examples: +## extraVolumeMounts: +## - name: extras +## mountPath: /usr/share/extras +## readOnly: true +## +extraVolumeMounts: [] +## @param extraVolumes Optionally specify extra list of additional volumes . +## Example: +## extraVolumes: +## - name: extras +## emptyDir: {} +## +extraVolumes: [] +## @param extraSecrets Optionally specify extra secrets to be created by the chart. +## This can be useful when combined with load_definitions to automatically create the secret containing the definitions to be loaded. +## Example: +## extraSecrets: +## load-definition: +## load_definition.json: | +## { +## ... +## } +## +extraSecrets: {} +## @param extraSecretsPrependReleaseName Set this flag to true if extraSecrets should be created with prepended. +## +extraSecretsPrependReleaseName: false + +## @section Statefulset parameters +## + +## @param replicaCount Number of RabbitMQ replicas to deploy +## +replicaCount: 1 +## @param schedulerName Use an alternate scheduler, e.g. "stork". +## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ +## +schedulerName: "" +## RabbitMQ should be initialized one by one when building cluster for the first time. +## Therefore, the default value of podManagementPolicy is 'OrderedReady' +## Once the RabbitMQ participates in the cluster, it waits for a response from another +## RabbitMQ in the same cluster at reboot, except the last RabbitMQ of the same cluster. +## If the cluster exits gracefully, you do not need to change the podManagementPolicy +## because the first RabbitMQ of the statefulset always will be last of the cluster. +## However if the last RabbitMQ of the cluster is not the first RabbitMQ due to a failure, +## you must change podManagementPolicy to 'Parallel'. +## ref : https://www.rabbitmq.com/clustering.html#restarting +## @param podManagementPolicy Pod management policy +## +podManagementPolicy: OrderedReady +## @param podLabels RabbitMQ Pod labels. Evaluated as a template +## Ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ +## +podLabels: {} +## @param podAnnotations RabbitMQ Pod annotations. Evaluated as a template +## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/ +## +podAnnotations: {} +## @param updateStrategy.type Update strategy type for RabbitMQ statefulset +## ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#update-strategies +## +updateStrategy: + ## StrategyType + ## Can be set to RollingUpdate or OnDelete + ## + type: RollingUpdate +## @param statefulsetLabels RabbitMQ statefulset labels. Evaluated as a template +## Ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ +## +statefulsetLabels: {} +## @param statefulsetAnnotations RabbitMQ statefulset annotations. Evaluated as a template +## Ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/ +## +statefulsetAnnotations: {} +## @param priorityClassName Name of the priority class to be used by RabbitMQ pods, priority class needs to be created beforehand +## Ref: https://kubernetes.io/docs/concepts/configuration/pod-priority-preemption/ +## +priorityClassName: "" +## @param podAffinityPreset Pod affinity preset. Ignored if `affinity` is set. Allowed values: `soft` or `hard` +## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity +## +podAffinityPreset: "" +## @param podAntiAffinityPreset Pod anti-affinity preset. Ignored if `affinity` is set. Allowed values: `soft` or `hard` +## Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity +## +podAntiAffinityPreset: soft + +## Node affinity preset +## Ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#node-affinity +## +nodeAffinityPreset: + ## @param nodeAffinityPreset.type Node affinity preset type. Ignored if `affinity` is set. Allowed values: `soft` or `hard` + ## + type: "" + ## @param nodeAffinityPreset.key Node label key to match Ignored if `affinity` is set. + ## E.g. + ## key: "kubernetes.io/e2e-az-name" + ## + key: "" + ## @param nodeAffinityPreset.values Node label values to match. Ignored if `affinity` is set. + ## E.g. + ## values: + ## - e2e-az1 + ## - e2e-az2 + ## + values: [] + +## @param affinity Affinity for pod assignment. Evaluated as a template +## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity +## Note: podAffinityPreset, podAntiAffinityPreset, and nodeAffinityPreset will be ignored when it's set +## +affinity: {} +## @param nodeSelector Node labels for pod assignment. Evaluated as a template +## ref: https://kubernetes.io/docs/user-guide/node-selection/ +## +nodeSelector: {} +## @param tolerations Tolerations for pod assignment. Evaluated as a template +## Ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ +## +tolerations: [] +## @param topologySpreadConstraints Topology Spread Constraints for pod assignment spread across your cluster among failure-domains. Evaluated as a template +## Ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/#spread-constraints-for-pods +## +topologySpreadConstraints: [] + +## RabbitMQ pods' Security Context +## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-pod +## @param podSecurityContext.enabled Enable RabbitMQ pods' Security Context +## @param podSecurityContext.fsGroup Set RabbitMQ pod's Security Context fsGroup +## +podSecurityContext: + enabled: true + fsGroup: 1001 + +## @param containerSecurityContext.enabled Enabled RabbitMQ containers' Security Context +## @param containerSecurityContext.runAsUser Set RabbitMQ containers' Security Context runAsUser +## @param containerSecurityContext.runAsNonRoot Set RabbitMQ container's Security Context runAsNonRoot +## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-container +## Example: +## containerSecurityContext: +## capabilities: +## drop: ["NET_RAW"] +## readOnlyRootFilesystem: true +## +containerSecurityContext: + enabled: true + runAsUser: 1001 + runAsNonRoot: true + +## RabbitMQ containers' resource requests and limits +## ref: https://kubernetes.io/docs/user-guide/compute-resources/ +## We usually recommend not to specify default resources and to leave this as a conscious +## choice for the user. This also increases chances charts run on environments with little +## resources, such as Minikube. If you do want to specify resources, uncomment the following +## lines, adjust them as necessary, and remove the curly braces after 'resources:'. +## @param resources.limits The resources limits for RabbitMQ containers +## @param resources.requests The requested resources for RabbitMQ containers +## +resources: + ## Example: + ## limits: + ## cpu: 1000m + ## memory: 2Gi + ## + limits: {} + ## Examples: + ## requests: + ## cpu: 1000m + ## memory: 2Gi + ## + requests: {} + +## Configure RabbitMQ containers' extra options for liveness probe +## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes +## @param livenessProbe.enabled Enable livenessProbe +## @param livenessProbe.initialDelaySeconds Initial delay seconds for livenessProbe +## @param livenessProbe.periodSeconds Period seconds for livenessProbe +## @param livenessProbe.timeoutSeconds Timeout seconds for livenessProbe +## @param livenessProbe.failureThreshold Failure threshold for livenessProbe +## @param livenessProbe.successThreshold Success threshold for livenessProbe +## +livenessProbe: + enabled: true + initialDelaySeconds: 120 + timeoutSeconds: 20 + periodSeconds: 30 + failureThreshold: 6 + successThreshold: 1 +## Configure RabbitMQ containers' extra options for readiness probe +## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes +## @param readinessProbe.enabled Enable readinessProbe +## @param readinessProbe.initialDelaySeconds Initial delay seconds for readinessProbe +## @param readinessProbe.periodSeconds Period seconds for readinessProbe +## @param readinessProbe.timeoutSeconds Timeout seconds for readinessProbe +## @param readinessProbe.failureThreshold Failure threshold for readinessProbe +## @param readinessProbe.successThreshold Success threshold for readinessProbe +## +readinessProbe: + enabled: true + initialDelaySeconds: 10 + timeoutSeconds: 20 + periodSeconds: 30 + failureThreshold: 3 + successThreshold: 1 + +## Configure RabbitMQ containers' extra options for startup probe +## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes +## @param startupProbe.enabled Enable startupProbe +## @param startupProbe.initialDelaySeconds Initial delay seconds for startupProbe +## @param startupProbe.periodSeconds Period seconds for startupProbe +## @param startupProbe.timeoutSeconds Timeout seconds for startupProbe +## @param startupProbe.failureThreshold Failure threshold for startupProbe +## @param startupProbe.successThreshold Success threshold for startupProbe +## +startupProbe: + enabled: false + initialDelaySeconds: 10 + timeoutSeconds: 20 + periodSeconds: 30 + failureThreshold: 3 + successThreshold: 1 + +## @param customLivenessProbe Override default liveness probe +## +customLivenessProbe: {} +## @param customReadinessProbe Override default readiness probe +## +customReadinessProbe: {} +## @param customStartupProbe Define a custom startup probe +## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/#define-startup-probes +## +customStartupProbe: {} +## @param initContainers Add init containers to the RabbitMQ pod +## Example: +## initContainers: +## - name: your-image-name +## image: your-image +## imagePullPolicy: Always +## ports: +## - name: portname +## containerPort: 1234 +## +initContainers: [] +## @param sidecars Add sidecar containers to the RabbitMQ pod +## Example: +## sidecars: +## - name: your-image-name +## image: your-image +## imagePullPolicy: Always +## ports: +## - name: portname +## containerPort: 1234 +## +sidecars: [] + +## Pod Disruption Budget configuration +## ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/ +## +pdb: + ## @param pdb.create Enable/disable a Pod Disruption Budget creation + ## + create: false + ## @param pdb.minAvailable Minimum number/percentage of pods that should remain scheduled + ## + minAvailable: 1 + ## @param pdb.maxUnavailable Maximum number/percentage of pods that may be made unavailable + ## + maxUnavailable: "" + +## @section RBAC parameters +## + +## RabbitMQ pods ServiceAccount +## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/ +## +serviceAccount: + ## @param serviceAccount.create Enable creation of ServiceAccount for RabbitMQ pods + ## + create: true + ## @param serviceAccount.name Name of the created serviceAccount + ## If not set and create is true, a name is generated using the rabbitmq.fullname template + ## + name: "" + ## @param serviceAccount.automountServiceAccountToken Auto-mount the service account token in the pod + ## + automountServiceAccountToken: true + ## @param serviceAccount.annotations Annotations for service account. Evaluated as a template. Only used if `create` is `true`. + ## + annotations: {} + +## Role Based Access +## ref: https://kubernetes.io/docs/admin/authorization/rbac/ +## +rbac: + ## @param rbac.create Whether RBAC rules should be created + ## binding RabbitMQ ServiceAccount to a role + ## that allows RabbitMQ pods querying the K8s API + ## + create: true + +## @section Persistence parameters +## + +persistence: + ## @param persistence.enabled Enable RabbitMQ data persistence using PVC + ## + enabled: true + ## @param persistence.storageClass PVC Storage Class for RabbitMQ data volume + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is + ## set, choosing the default provisioner. (gp2 on AWS, standard on + ## GKE, AWS & OpenStack) + ## + storageClass: "" + ## @param persistence.selector Selector to match an existing Persistent Volume + ## selector: + ## matchLabels: + ## app: my-app + ## + selector: {} + ## @param persistence.accessModes PVC Access Modes for RabbitMQ data volume + ## + accessModes: + - ReadWriteOnce + ## @param persistence.existingClaim Provide an existing PersistentVolumeClaims + ## The value is evaluated as a template + ## So, for example, the name can depend on .Release or .Chart + ## + existingClaim: "" + ## @param persistence.mountPath The path the volume will be mounted at + ## Note: useful when using custom RabbitMQ images + ## + mountPath: /bitnami/rabbitmq/mnesia + ## @param persistence.subPath The subdirectory of the volume to mount to + ## Useful in dev environments and one PV for multiple services + ## + subPath: "" + ## @param persistence.size PVC Storage Request for RabbitMQ data volume + ## If you change this value, you might have to adjust `rabbitmq.diskFreeLimit` as well + ## + size: 8Gi + ## @param persistence.annotations Persistence annotations. Evaluated as a template + ## Example: + ## annotations: + ## example.io/disk-volume-type: SSD + ## + annotations: {} + ## @param persistence.labels Persistence labels. Evaluated as a template + ## Example: + ## labels: + ## app: my-app + labels: {} + +## @section Exposure parameters +## + +## Kubernetes service type +## +service: + ## @param service.type Kubernetes Service type + ## + type: ClusterIP + + ## @param service.portEnabled Amqp port. Cannot be disabled when `auth.tls.enabled` is `false`. Listener can be disabled with `listeners.tcp = none`. + ## + portEnabled: true + ## @param service.distPortEnabled Erlang distribution server port + ## + distPortEnabled: true + ## @param service.managerPortEnabled RabbitMQ Manager port + ## ref: https://github.com/bitnami/containers/tree/main/bitnami/rabbitmq#environment-variables + ## + managerPortEnabled: true + ## @param service.epmdPortEnabled RabbitMQ EPMD Discovery service port + ## + epmdPortEnabled: true + ## Service ports + ## @param service.ports.amqp Amqp service port + ## @param service.ports.amqpTls Amqp TLS service port + ## @param service.ports.dist Erlang distribution service port + ## @param service.ports.manager RabbitMQ Manager service port + ## @param service.ports.metrics RabbitMQ Prometheues metrics service port + ## @param service.ports.epmd EPMD Discovery service port + ## + ports: + amqp: 5672 + amqpTls: 5671 + dist: 25672 + manager: 15672 + metrics: 9419 + epmd: 4369 + ## Service ports name + ## @param service.portNames.amqp Amqp service port name + ## @param service.portNames.amqpTls Amqp TLS service port name + ## @param service.portNames.dist Erlang distribution service port name + ## @param service.portNames.manager RabbitMQ Manager service port name + ## @param service.portNames.metrics RabbitMQ Prometheues metrics service port name + ## @param service.portNames.epmd EPMD Discovery service port name + ## + portNames: + amqp: "amqp" + amqpTls: "amqp-tls" + dist: "dist" + manager: "http-stats" + metrics: "metrics" + epmd: "epmd" + + ## Node ports to expose + ## @param service.nodePorts.amqp Node port for Ampq + ## @param service.nodePorts.amqpTls Node port for Ampq TLS + ## @param service.nodePorts.dist Node port for Erlang distribution + ## @param service.nodePorts.manager Node port for RabbitMQ Manager + ## @param service.nodePorts.epmd Node port for EPMD Discovery + ## @param service.nodePorts.metrics Node port for RabbitMQ Prometheues metrics + ## + nodePorts: + amqp: "" + amqpTls: "" + dist: "" + manager: "" + epmd: "" + metrics: "" + ## @param service.extraPorts Extra ports to expose in the service + ## E.g.: + ## extraPorts: + ## - name: new_svc_name + ## port: 1234 + ## targetPort: 1234 + ## + extraPorts: [] + ## @param service.loadBalancerSourceRanges Address(es) that are allowed when service is `LoadBalancer` + ## https://kubernetes.io/docs/tasks/access-application-cluster/configure-cloud-provider-firewall/#restrict-access-for-loadbalancer-service + ## e.g: + ## loadBalancerSourceRanges: + ## - 10.10.10.0/24 + ## + loadBalancerSourceRanges: [] + ## @param service.externalIPs Set the ExternalIPs + ## + externalIPs: [] + ## @param service.externalTrafficPolicy Enable client source IP preservation + ## ref https://kubernetes.io/docs/tasks/access-application-cluster/create-external-load-balancer/#preserving-the-client-source-ip + ## + externalTrafficPolicy: Cluster + ## @param service.loadBalancerIP Set the LoadBalancerIP + ## + loadBalancerIP: "" + ## @param service.clusterIP Kubernetes service Cluster IP + ## e.g.: + ## clusterIP: None + ## + clusterIP: "" + ## @param service.labels Service labels. Evaluated as a template + ## + labels: {} + ## @param service.annotations Service annotations. Evaluated as a template + ## Example: + ## annotations: + ## service.beta.kubernetes.io/aws-load-balancer-internal: 0.0.0.0/0 + ## + annotations: {} + ## DEPRECATED service.annotationsHeadless it will removed in a future release, please use service.headless.annotations instead + ## @param service.annotationsHeadless Headless Service annotations. Evaluated as a template + ## Example: + ## annotations: + ## external-dns.alpha.kubernetes.io/internal-hostname: rabbitmq.example.com + ## + annotationsHeadless: {} + ## Headless service properties + ## + headless: + ## @param service.headless.annotations Annotations for the headless service. + ## + annotations: {} + ## @param service.sessionAffinity Session Affinity for Kubernetes service, can be "None" or "ClientIP" + ## If "ClientIP", consecutive client requests will be directed to the same Pod + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#virtual-ips-and-service-proxies + ## + sessionAffinity: None + ## @param service.sessionAffinityConfig Additional settings for the sessionAffinity + ## sessionAffinityConfig: + ## clientIP: + ## timeoutSeconds: 300 + ## + sessionAffinityConfig: {} + +## Configure the ingress resource that allows you to access the +## RabbitMQ installation. Set up the URL +## ref: https://kubernetes.io/docs/user-guide/ingress/ +## +ingress: + ## @param ingress.enabled Enable ingress resource for Management console + ## + enabled: false + + ## @param ingress.path Path for the default host. You may need to set this to '/*' in order to use this with ALB ingress controllers. + ## + path: / + + ## @param ingress.pathType Ingress path type + ## + pathType: ImplementationSpecific + ## @param ingress.hostname Default host for the ingress resource + ## + hostname: rabbitmq.local + ## @param ingress.annotations Additional annotations for the Ingress resource. To enable certificate autogeneration, place here your cert-manager annotations. + ## For a full list of possible ingress annotations, please see + ## ref: https://github.com/kubernetes/ingress-nginx/blob/master/docs/user-guide/nginx-configuration/annotations.md + ## Use this parameter to set the required annotations for cert-manager, see + ## ref: https://cert-manager.io/docs/usage/ingress/#supported-annotations + ## + ## e.g: + ## annotations: + ## kubernetes.io/ingress.class: nginx + ## cert-manager.io/cluster-issuer: cluster-issuer-name + ## + annotations: {} + ## @param ingress.tls Enable TLS configuration for the hostname defined at `ingress.hostname` parameter + ## TLS certificates will be retrieved from a TLS secret with name: {{- printf "%s-tls" .Values.ingress.hostname }} + ## You can: + ## - Use the `ingress.secrets` parameter to create this TLS secret + ## - Rely on cert-manager to create it by setting the corresponding annotations + ## - Rely on Helm to create self-signed certificates by setting `ingress.selfSigned=true` + ## + tls: false + ## @param ingress.selfSigned Set this to true in order to create a TLS secret for this ingress record + ## using self-signed certificates generated by Helm + ## + selfSigned: false + ## @param ingress.extraHosts The list of additional hostnames to be covered with this ingress record. + ## Most likely the hostname above will be enough, but in the event more hosts are needed, this is an array + ## e.g: + ## extraHosts: + ## - name: rabbitmq.local + ## path: / + ## + extraHosts: [] + ## @param ingress.extraPaths An array with additional arbitrary paths that may need to be added to the ingress under the main host + ## e.g: + ## extraPaths: + ## - path: /* + ## backend: + ## serviceName: ssl-redirect + ## servicePort: use-annotation + ## + extraPaths: [] + ## @param ingress.extraRules The list of additional rules to be added to this ingress record. Evaluated as a template + ## Useful when looking for additional customization, such as using different backend + ## + extraRules: [] + ## @param ingress.extraTls The tls configuration for additional hostnames to be covered with this ingress record. + ## see: https://kubernetes.io/docs/concepts/services-networking/ingress/#tls + ## e.g: + ## extraTls: + ## - hosts: + ## - rabbitmq.local + ## secretName: rabbitmq.local-tls + ## + extraTls: [] + ## @param ingress.secrets Custom TLS certificates as secrets + ## NOTE: 'key' and 'certificate' are expected in PEM format + ## NOTE: 'name' should line up with a 'secretName' set further up + ## If it is not set and you're using cert-manager, this is unneeded, as it will create a secret for you with valid certificates + ## If it is not set and you're NOT using cert-manager either, self-signed certificates will be created valid for 365 days + ## It is also possible to create and manage the certificates outside of this helm chart + ## Please see README.md for more information + ## e.g: + ## secrets: + ## - name: rabbitmq.local-tls + ## key: |- + ## -----BEGIN RSA PRIVATE KEY----- + ## ... + ## -----END RSA PRIVATE KEY----- + ## certificate: |- + ## -----BEGIN CERTIFICATE----- + ## ... + ## -----END CERTIFICATE----- + ## + secrets: [] + ## @param ingress.ingressClassName IngressClass that will be be used to implement the Ingress (Kubernetes 1.18+) + ## This is supported in Kubernetes 1.18+ and required if you have more than one IngressClass marked as the default for your cluster . + ## ref: https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/ + ## + ingressClassName: "" + ## @param ingress.existingSecret It is you own the certificate as secret. + ## + existingSecret: "" + +## Network Policy configuration +## ref: https://kubernetes.io/docs/concepts/services-networking/network-policies/ +## +networkPolicy: + ## @param networkPolicy.enabled Enable creation of NetworkPolicy resources + ## + enabled: false + ## @param networkPolicy.allowExternal Don't require client label for connections + ## The Policy model to apply. When set to false, only pods with the correct + ## client label will have network access to the ports RabbitMQ is listening + ## on. When true, RabbitMQ will accept connections from any source + ## (with the correct destination port). + ## + allowExternal: true + ## @param networkPolicy.additionalRules Additional NetworkPolicy Ingress "from" rules to set. Note that all rules are OR-ed. + ## e.g: + ## additionalRules: + ## - matchLabels: + ## - role: frontend + ## - matchExpressions: + ## - key: role + ## operator: In + ## values: + ## - frontend + ## + additionalRules: [] + +## @section Metrics Parameters +## + +## Prometheus Metrics +## +metrics: + ## @param metrics.enabled Enable exposing RabbitMQ metrics to be gathered by Prometheus + ## + enabled: false + ## @param metrics.plugins Plugins to enable Prometheus metrics in RabbitMQ + ## + plugins: "rabbitmq_prometheus" + ## Prometheus pod annotations + ## @param metrics.podAnnotations [object] Annotations for enabling prometheus to access the metrics endpoint + ## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/ + ## + podAnnotations: + prometheus.io/scrape: "true" + prometheus.io/port: "{{ .Values.service.ports.metrics }}" + ## Prometheus Service Monitor + ## ref: https://github.com/coreos/prometheus-operator + ## + serviceMonitor: + ## @param metrics.serviceMonitor.enabled Create ServiceMonitor Resource for scraping metrics using PrometheusOperator + ## + enabled: false + ## @param metrics.serviceMonitor.namespace Specify the namespace in which the serviceMonitor resource will be created + ## + namespace: "" + ## @param metrics.serviceMonitor.interval Specify the interval at which metrics should be scraped + ## + interval: 30s + ## @param metrics.serviceMonitor.scrapeTimeout Specify the timeout after which the scrape is ended + ## e.g: + ## scrapeTimeout: 30s + ## + scrapeTimeout: "" + ## @param metrics.serviceMonitor.jobLabel The name of the label on the target service to use as the job name in prometheus. + ## + jobLabel: "" + ## @param metrics.serviceMonitor.relabelings RelabelConfigs to apply to samples before scraping. + ## + relabelings: [] + ## @param metrics.serviceMonitor.metricRelabelings MetricsRelabelConfigs to apply to samples before ingestion. + ## + metricRelabelings: [] + ## @param metrics.serviceMonitor.honorLabels honorLabels chooses the metric's labels on collisions with target labels + ## + honorLabels: false + ## @param metrics.serviceMonitor.targetLabels Used to keep given service's labels in target + ## e.g: + ## - app.kubernetes.io/name + ## + targetLabels: {} + ## @param metrics.serviceMonitor.podTargetLabels Used to keep given pod's labels in target + ## e.g: + ## - app.kubernetes.io/name + ## + podTargetLabels: {} + ## @param metrics.serviceMonitor.path Define the path used by ServiceMonitor to scrap metrics + ## Could be /metrics for aggregated metrics or /metrics/per-object for more details + ## + path: "" + ## @param metrics.serviceMonitor.params Define the HTTP URL parameters used by ServiceMonitor + ## + params: {} + ## @param metrics.serviceMonitor.selector ServiceMonitor selector labels + ## ref: https://github.com/bitnami/charts/tree/main/bitnami/prometheus-operator#prometheus-configuration + ## + ## selector: + ## prometheus: my-prometheus + ## + selector: {} + ## @param metrics.serviceMonitor.labels Extra labels for the ServiceMonitor + ## + labels: {} + ## @param metrics.serviceMonitor.annotations Extra annotations for the ServiceMonitor + ## + annotations: {} + + ## Custom PrometheusRule to be defined + ## The value is evaluated as a template, so, for example, the value can depend on .Release or .Chart + ## ref: https://github.com/coreos/prometheus-operator#customresourcedefinitions + ## + prometheusRule: + ## @param metrics.prometheusRule.enabled Set this to true to create prometheusRules for Prometheus operator + ## + enabled: false + ## @param metrics.prometheusRule.additionalLabels Additional labels that can be used so prometheusRules will be discovered by Prometheus + ## + additionalLabels: {} + ## @param metrics.prometheusRule.namespace namespace where prometheusRules resource should be created + ## + namespace: "" + ## List of rules, used as template by Helm. + ## @param metrics.prometheusRule.rules List of rules, used as template by Helm. + ## These are just examples rules inspired from https://awesome-prometheus-alerts.grep.to/rules.html + ## rules: + ## - alert: RabbitmqDown + ## expr: rabbitmq_up{service="{{ template "common.names.fullname" . }}"} == 0 + ## for: 5m + ## labels: + ## severity: error + ## annotations: + ## summary: Rabbitmq down (instance {{ "{{ $labels.instance }}" }}) + ## description: RabbitMQ node down + ## - alert: ClusterDown + ## expr: | + ## sum(rabbitmq_running{service="{{ template "common.names.fullname" . }}"}) + ## < {{ .Values.replicaCount }} + ## for: 5m + ## labels: + ## severity: error + ## annotations: + ## summary: Cluster down (instance {{ "{{ $labels.instance }}" }}) + ## description: | + ## Less than {{ .Values.replicaCount }} nodes running in RabbitMQ cluster + ## VALUE = {{ "{{ $value }}" }} + ## - alert: ClusterPartition + ## expr: rabbitmq_partitions{service="{{ template "common.names.fullname" . }}"} > 0 + ## for: 5m + ## labels: + ## severity: error + ## annotations: + ## summary: Cluster partition (instance {{ "{{ $labels.instance }}" }}) + ## description: | + ## Cluster partition + ## VALUE = {{ "{{ $value }}" }} + ## - alert: OutOfMemory + ## expr: | + ## rabbitmq_node_mem_used{service="{{ template "common.names.fullname" . }}"} + ## / rabbitmq_node_mem_limit{service="{{ template "common.names.fullname" . }}"} + ## * 100 > 90 + ## for: 5m + ## labels: + ## severity: warning + ## annotations: + ## summary: Out of memory (instance {{ "{{ $labels.instance }}" }}) + ## description: | + ## Memory available for RabbmitMQ is low (< 10%)\n VALUE = {{ "{{ $value }}" }} + ## LABELS: {{ "{{ $labels }}" }} + ## - alert: TooManyConnections + ## expr: rabbitmq_connectionsTotal{service="{{ template "common.names.fullname" . }}"} > 1000 + ## for: 5m + ## labels: + ## severity: warning + ## annotations: + ## summary: Too many connections (instance {{ "{{ $labels.instance }}" }}) + ## description: | + ## RabbitMQ instance has too many connections (> 1000) + ## VALUE = {{ "{{ $value }}" }}\n LABELS: {{ "{{ $labels }}" }} + ## + rules: [] + +## @section Init Container Parameters +## + +## Init Container parameters +## Change the owner and group of the persistent volume(s) mountpoint(s) to 'runAsUser:fsGroup' on each component +## values from the securityContext section of the component +## +volumePermissions: + ## @param volumePermissions.enabled Enable init container that changes the owner and group of the persistent volume(s) mountpoint to `runAsUser:fsGroup` + ## + enabled: false + ## @param volumePermissions.image.registry Init container volume-permissions image registry + ## @param volumePermissions.image.repository Init container volume-permissions image repository + ## @param volumePermissions.image.tag Init container volume-permissions image tag + ## @param volumePermissions.image.digest Init container volume-permissions image digest in the way sha256:aa.... Please note this parameter, if set, will override the tag + ## @param volumePermissions.image.pullPolicy Init container volume-permissions image pull policy + ## @param volumePermissions.image.pullSecrets Specify docker-registry secret names as an array + ## + image: + registry: docker.io + repository: bitnami/bitnami-shell + tag: 11-debian-11-r123 + digest: "" + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets (secrets must be manually created in the namespace) + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## Example: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## Init Container resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## We usually recommend not to specify default resources and to leave this as a conscious + ## choice for the user. This also increases chances charts run on environments with little + ## resources, such as Minikube. If you do want to specify resources, uncomment the following + ## lines, adjust them as necessary, and remove the curly braces after 'resources:'. + ## @param volumePermissions.resources.limits Init container volume-permissions resource limits + ## @param volumePermissions.resources.requests Init container volume-permissions resource requests + ## + resources: + ## Example: + ## limits: + ## cpu: 100m + ## memory: 128Mi + ## + limits: {} + ## Examples: + ## requests: + ## cpu: 100m + ## memory: 128Mi + ## + requests: {} + ## Init container' Security Context + ## Note: the chown of the data folder is done to containerSecurityContext.runAsUser + ## and not the below volumePermissions.containerSecurityContext.runAsUser + ## @param volumePermissions.containerSecurityContext.runAsUser User ID for the init container + ## + containerSecurityContext: + runAsUser: 0 diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/redis/.helmignore new file mode 100644 index 0000000..f0c1319 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/.helmignore @@ -0,0 +1,21 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/Chart.lock b/observability/lgtm-distributed/charts/oncall/charts/redis/Chart.lock new file mode 100644 index 0000000..ced3e29 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/Chart.lock @@ -0,0 +1,6 @@ +dependencies: +- name: common + repository: https://charts.bitnami.com/bitnami + version: 1.16.0 +digest: sha256:f41cb9ff725b7c9fa2725634196a6813566d630342f86a74903ed114b282c8c0 +generated: "2022-06-06T12:59:41.280407782Z" diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/Chart.yaml new file mode 100644 index 0000000..e89b016 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/Chart.yaml @@ -0,0 +1,28 @@ +annotations: + category: Database +apiVersion: v2 +appVersion: 6.2.7 +dependencies: +- name: common + repository: https://charts.bitnami.com/bitnami + tags: + - bitnami-common + version: 1.x.x +description: Redis(R) is an open source, advanced key-value store. It is often referred + to as a data structure server since keys can contain strings, hashes, lists, sets + and sorted sets. +home: https://github.com/bitnami/charts/tree/master/bitnami/redis +icon: https://bitnami.com/assets/stacks/redis/img/redis-stack-220x234.png +keywords: +- redis +- keyvalue +- database +maintainers: +- name: Bitnami + url: https://github.com/bitnami/charts +- email: cedric@desaintmartin.fr + name: desaintmartin +name: redis +sources: +- https://github.com/bitnami/bitnami-docker-redis +version: 16.13.2 diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/README.md b/observability/lgtm-distributed/charts/oncall/charts/redis/README.md new file mode 100644 index 0000000..5113c05 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/README.md @@ -0,0 +1,898 @@ + + +# Bitnami package for Redis(R) + +Redis(R) is an open source, advanced key-value store. It is often referred to as a data structure server since keys can contain strings, hashes, lists, sets and sorted sets. + +[Overview of Redis®](http://redis.io) + +Disclaimer: Redis is a registered trademark of Redis Ltd. Any rights therein are reserved to Redis Ltd. Any use by Bitnami is for referential purposes only and does not indicate any sponsorship, endorsement, or affiliation between Redis Ltd. + +## TL;DR + +```bash +$ helm repo add bitnami https://charts.bitnami.com/bitnami +$ helm install my-release bitnami/redis +``` + +## Introduction + +This chart bootstraps a [Redis®](https://github.com/bitnami/bitnami-docker-redis) deployment on a [Kubernetes](https://kubernetes.io) cluster using the [Helm](https://helm.sh) package manager. + +Bitnami charts can be used with [Kubeapps](https://kubeapps.dev/) for deployment and management of Helm Charts in clusters. + +### Choose between Redis® Helm Chart and Redis® Cluster Helm Chart + +You can choose any of the two Redis® Helm charts for deploying a Redis® cluster. + +1. [Redis® Helm Chart](https://github.com/bitnami/charts/tree/master/bitnami/redis) will deploy a master-replica cluster, with the [option](https://github.com/bitnami/charts/tree/master/bitnami/redis#redis-sentinel-configuration-parameters) of enabling using Redis® Sentinel. +2. [Redis® Cluster Helm Chart](https://github.com/bitnami/charts/tree/master/bitnami/redis-cluster) will deploy a Redis® Cluster topology with sharding. + +The main features of each chart are the following: + +| Redis® | Redis® Cluster | +|--------------------------------------------------------|------------------------------------------------------------------------| +| Supports multiple databases | Supports only one database. Better if you have a big dataset | +| Single write point (single master) | Multiple write points (multiple masters) | +| ![Redis® Topology](img/redis-topology.png) | ![Redis® Cluster Topology](img/redis-cluster-topology.png) | + +## Prerequisites + +- Kubernetes 1.19+ +- Helm 3.2.0+ +- PV provisioner support in the underlying infrastructure + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```bash +$ helm install my-release bitnami/redis +``` + +The command deploys Redis® on the Kubernetes cluster in the default configuration. The [Parameters](#parameters) section lists the parameters that can be configured during installation. + +> **Tip**: List all releases using `helm list` + +## Uninstalling the Chart + +To uninstall/delete the `my-release` deployment: + +```bash +$ helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + +## Parameters + +### Global parameters + +| Name | Description | Value | +| ------------------------- | ------------------------------------------------------ | ----- | +| `global.imageRegistry` | Global Docker image registry | `""` | +| `global.imagePullSecrets` | Global Docker registry secret names as an array | `[]` | +| `global.storageClass` | Global StorageClass for Persistent Volume(s) | `""` | +| `global.redis.password` | Global Redis® password (overrides `auth.password`) | `""` | + + +### Common parameters + +| Name | Description | Value | +| ------------------------ | --------------------------------------------------------------------------------------- | --------------- | +| `kubeVersion` | Override Kubernetes version | `""` | +| `nameOverride` | String to partially override common.names.fullname | `""` | +| `fullnameOverride` | String to fully override common.names.fullname | `""` | +| `commonLabels` | Labels to add to all deployed objects | `{}` | +| `commonAnnotations` | Annotations to add to all deployed objects | `{}` | +| `secretAnnotations` | Annotations to add to secret | `{}` | +| `clusterDomain` | Kubernetes cluster domain name | `cluster.local` | +| `extraDeploy` | Array of extra objects to deploy with the release | `[]` | +| `diagnosticMode.enabled` | Enable diagnostic mode (all probes will be disabled and the command will be overridden) | `false` | +| `diagnosticMode.command` | Command to override all containers in the deployment | `["sleep"]` | +| `diagnosticMode.args` | Args to override all containers in the deployment | `["infinity"]` | + + +### Redis® Image parameters + +| Name | Description | Value | +| ------------------- | ----------------------------------------------------- | --------------------- | +| `image.registry` | Redis® image registry | `docker.io` | +| `image.repository` | Redis® image repository | `bitnami/redis` | +| `image.tag` | Redis® image tag (immutable tags are recommended) | `6.2.7-debian-11-r11` | +| `image.pullPolicy` | Redis® image pull policy | `IfNotPresent` | +| `image.pullSecrets` | Redis® image pull secrets | `[]` | +| `image.debug` | Enable image debug mode | `false` | + + +### Redis® common configuration parameters + +| Name | Description | Value | +| -------------------------------- | ------------------------------------------------------------------------------------- | ------------- | +| `architecture` | Redis® architecture. Allowed values: `standalone` or `replication` | `replication` | +| `auth.enabled` | Enable password authentication | `true` | +| `auth.sentinel` | Enable password authentication on sentinels too | `true` | +| `auth.password` | Redis® password | `""` | +| `auth.existingSecret` | The name of an existing secret with Redis® credentials | `""` | +| `auth.existingSecretPasswordKey` | Password key to be retrieved from existing secret | `""` | +| `auth.usePasswordFiles` | Mount credentials as files instead of using an environment variable | `false` | +| `commonConfiguration` | Common configuration to be added into the ConfigMap | `""` | +| `existingConfigmap` | The name of an existing ConfigMap with your custom configuration for Redis® nodes | `""` | + + +### Redis® master configuration parameters + +| Name | Description | Value | +| ------------------------------------------- | ----------------------------------------------------------------------------------------------------- | ------------------------ | +| `master.count` | Number of Redis® master instances to deploy (experimental, requires additional configuration) | `1` | +| `master.configuration` | Configuration for Redis® master nodes | `""` | +| `master.disableCommands` | Array with Redis® commands to disable on master nodes | `["FLUSHDB","FLUSHALL"]` | +| `master.command` | Override default container command (useful when using custom images) | `[]` | +| `master.args` | Override default container args (useful when using custom images) | `[]` | +| `master.preExecCmds` | Additional commands to run prior to starting Redis® master | `[]` | +| `master.extraFlags` | Array with additional command line flags for Redis® master | `[]` | +| `master.extraEnvVars` | Array with extra environment variables to add to Redis® master nodes | `[]` | +| `master.extraEnvVarsCM` | Name of existing ConfigMap containing extra env vars for Redis® master nodes | `""` | +| `master.extraEnvVarsSecret` | Name of existing Secret containing extra env vars for Redis® master nodes | `""` | +| `master.containerPorts.redis` | Container port to open on Redis® master nodes | `6379` | +| `master.startupProbe.enabled` | Enable startupProbe on Redis® master nodes | `false` | +| `master.startupProbe.initialDelaySeconds` | Initial delay seconds for startupProbe | `20` | +| `master.startupProbe.periodSeconds` | Period seconds for startupProbe | `5` | +| `master.startupProbe.timeoutSeconds` | Timeout seconds for startupProbe | `5` | +| `master.startupProbe.failureThreshold` | Failure threshold for startupProbe | `5` | +| `master.startupProbe.successThreshold` | Success threshold for startupProbe | `1` | +| `master.livenessProbe.enabled` | Enable livenessProbe on Redis® master nodes | `true` | +| `master.livenessProbe.initialDelaySeconds` | Initial delay seconds for livenessProbe | `20` | +| `master.livenessProbe.periodSeconds` | Period seconds for livenessProbe | `5` | +| `master.livenessProbe.timeoutSeconds` | Timeout seconds for livenessProbe | `5` | +| `master.livenessProbe.failureThreshold` | Failure threshold for livenessProbe | `5` | +| `master.livenessProbe.successThreshold` | Success threshold for livenessProbe | `1` | +| `master.readinessProbe.enabled` | Enable readinessProbe on Redis® master nodes | `true` | +| `master.readinessProbe.initialDelaySeconds` | Initial delay seconds for readinessProbe | `20` | +| `master.readinessProbe.periodSeconds` | Period seconds for readinessProbe | `5` | +| `master.readinessProbe.timeoutSeconds` | Timeout seconds for readinessProbe | `1` | +| `master.readinessProbe.failureThreshold` | Failure threshold for readinessProbe | `5` | +| `master.readinessProbe.successThreshold` | Success threshold for readinessProbe | `1` | +| `master.customStartupProbe` | Custom startupProbe that overrides the default one | `{}` | +| `master.customLivenessProbe` | Custom livenessProbe that overrides the default one | `{}` | +| `master.customReadinessProbe` | Custom readinessProbe that overrides the default one | `{}` | +| `master.resources.limits` | The resources limits for the Redis® master containers | `{}` | +| `master.resources.requests` | The requested resources for the Redis® master containers | `{}` | +| `master.podSecurityContext.enabled` | Enabled Redis® master pods' Security Context | `true` | +| `master.podSecurityContext.fsGroup` | Set Redis® master pod's Security Context fsGroup | `1001` | +| `master.containerSecurityContext.enabled` | Enabled Redis® master containers' Security Context | `true` | +| `master.containerSecurityContext.runAsUser` | Set Redis® master containers' Security Context runAsUser | `1001` | +| `master.kind` | Use either Deployment or StatefulSet (default) | `StatefulSet` | +| `master.schedulerName` | Alternate scheduler for Redis® master pods | `""` | +| `master.updateStrategy.type` | Redis® master statefulset strategy type | `RollingUpdate` | +| `master.priorityClassName` | Redis® master pods' priorityClassName | `""` | +| `master.hostAliases` | Redis® master pods host aliases | `[]` | +| `master.podLabels` | Extra labels for Redis® master pods | `{}` | +| `master.podAnnotations` | Annotations for Redis® master pods | `{}` | +| `master.shareProcessNamespace` | Share a single process namespace between all of the containers in Redis® master pods | `false` | +| `master.podAffinityPreset` | Pod affinity preset. Ignored if `master.affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `master.podAntiAffinityPreset` | Pod anti-affinity preset. Ignored if `master.affinity` is set. Allowed values: `soft` or `hard` | `soft` | +| `master.nodeAffinityPreset.type` | Node affinity preset type. Ignored if `master.affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `master.nodeAffinityPreset.key` | Node label key to match. Ignored if `master.affinity` is set | `""` | +| `master.nodeAffinityPreset.values` | Node label values to match. Ignored if `master.affinity` is set | `[]` | +| `master.affinity` | Affinity for Redis® master pods assignment | `{}` | +| `master.nodeSelector` | Node labels for Redis® master pods assignment | `{}` | +| `master.tolerations` | Tolerations for Redis® master pods assignment | `[]` | +| `master.topologySpreadConstraints` | Spread Constraints for Redis® master pod assignment | `[]` | +| `master.dnsPolicy` | DNS Policy for Redis® master pod | `""` | +| `master.dnsConfig` | DNS Configuration for Redis® master pod | `{}` | +| `master.lifecycleHooks` | for the Redis® master container(s) to automate configuration before or after startup | `{}` | +| `master.extraVolumes` | Optionally specify extra list of additional volumes for the Redis® master pod(s) | `[]` | +| `master.extraVolumeMounts` | Optionally specify extra list of additional volumeMounts for the Redis® master container(s) | `[]` | +| `master.sidecars` | Add additional sidecar containers to the Redis® master pod(s) | `[]` | +| `master.initContainers` | Add additional init containers to the Redis® master pod(s) | `[]` | +| `master.persistence.enabled` | Enable persistence on Redis® master nodes using Persistent Volume Claims | `true` | +| `master.persistence.medium` | Provide a medium for `emptyDir` volumes. | `""` | +| `master.persistence.sizeLimit` | Set this to enable a size limit for `emptyDir` volumes. | `""` | +| `master.persistence.path` | The path the volume will be mounted at on Redis® master containers | `/data` | +| `master.persistence.subPath` | The subdirectory of the volume to mount on Redis® master containers | `""` | +| `master.persistence.storageClass` | Persistent Volume storage class | `""` | +| `master.persistence.accessModes` | Persistent Volume access modes | `["ReadWriteOnce"]` | +| `master.persistence.size` | Persistent Volume size | `8Gi` | +| `master.persistence.annotations` | Additional custom annotations for the PVC | `{}` | +| `master.persistence.selector` | Additional labels to match for the PVC | `{}` | +| `master.persistence.dataSource` | Custom PVC data source | `{}` | +| `master.persistence.existingClaim` | Use a existing PVC which must be created manually before bound | `""` | +| `master.service.type` | Redis® master service type | `ClusterIP` | +| `master.service.ports.redis` | Redis® master service port | `6379` | +| `master.service.nodePorts.redis` | Node port for Redis® master | `""` | +| `master.service.externalTrafficPolicy` | Redis® master service external traffic policy | `Cluster` | +| `master.service.extraPorts` | Extra ports to expose (normally used with the `sidecar` value) | `[]` | +| `master.service.internalTrafficPolicy` | Redis® master service internal traffic policy (requires Kubernetes v1.22 or greater to be usable) | `Cluster` | +| `master.service.clusterIP` | Redis® master service Cluster IP | `""` | +| `master.service.loadBalancerIP` | Redis® master service Load Balancer IP | `""` | +| `master.service.loadBalancerSourceRanges` | Redis® master service Load Balancer sources | `[]` | +| `master.service.annotations` | Additional custom annotations for Redis® master service | `{}` | +| `master.service.sessionAffinity` | Session Affinity for Kubernetes service, can be "None" or "ClientIP" | `None` | +| `master.service.sessionAffinityConfig` | Additional settings for the sessionAffinity | `{}` | +| `master.terminationGracePeriodSeconds` | Integer setting the termination grace period for the redis-master pods | `30` | + + +### Redis® replicas configuration parameters + +| Name | Description | Value | +| -------------------------------------------- | ------------------------------------------------------------------------------------------------------- | ------------------------ | +| `replica.replicaCount` | Number of Redis® replicas to deploy | `3` | +| `replica.configuration` | Configuration for Redis® replicas nodes | `""` | +| `replica.disableCommands` | Array with Redis® commands to disable on replicas nodes | `["FLUSHDB","FLUSHALL"]` | +| `replica.command` | Override default container command (useful when using custom images) | `[]` | +| `replica.args` | Override default container args (useful when using custom images) | `[]` | +| `replica.preExecCmds` | Additional commands to run prior to starting Redis® replicas | `[]` | +| `replica.extraFlags` | Array with additional command line flags for Redis® replicas | `[]` | +| `replica.extraEnvVars` | Array with extra environment variables to add to Redis® replicas nodes | `[]` | +| `replica.extraEnvVarsCM` | Name of existing ConfigMap containing extra env vars for Redis® replicas nodes | `""` | +| `replica.extraEnvVarsSecret` | Name of existing Secret containing extra env vars for Redis® replicas nodes | `""` | +| `replica.externalMaster.enabled` | Use external master for bootstrapping | `false` | +| `replica.externalMaster.host` | External master host to bootstrap from | `""` | +| `replica.externalMaster.port` | Port for Redis service external master host | `6379` | +| `replica.containerPorts.redis` | Container port to open on Redis® replicas nodes | `6379` | +| `replica.startupProbe.enabled` | Enable startupProbe on Redis® replicas nodes | `true` | +| `replica.startupProbe.initialDelaySeconds` | Initial delay seconds for startupProbe | `10` | +| `replica.startupProbe.periodSeconds` | Period seconds for startupProbe | `10` | +| `replica.startupProbe.timeoutSeconds` | Timeout seconds for startupProbe | `5` | +| `replica.startupProbe.failureThreshold` | Failure threshold for startupProbe | `22` | +| `replica.startupProbe.successThreshold` | Success threshold for startupProbe | `1` | +| `replica.livenessProbe.enabled` | Enable livenessProbe on Redis® replicas nodes | `true` | +| `replica.livenessProbe.initialDelaySeconds` | Initial delay seconds for livenessProbe | `20` | +| `replica.livenessProbe.periodSeconds` | Period seconds for livenessProbe | `5` | +| `replica.livenessProbe.timeoutSeconds` | Timeout seconds for livenessProbe | `5` | +| `replica.livenessProbe.failureThreshold` | Failure threshold for livenessProbe | `5` | +| `replica.livenessProbe.successThreshold` | Success threshold for livenessProbe | `1` | +| `replica.readinessProbe.enabled` | Enable readinessProbe on Redis® replicas nodes | `true` | +| `replica.readinessProbe.initialDelaySeconds` | Initial delay seconds for readinessProbe | `20` | +| `replica.readinessProbe.periodSeconds` | Period seconds for readinessProbe | `5` | +| `replica.readinessProbe.timeoutSeconds` | Timeout seconds for readinessProbe | `1` | +| `replica.readinessProbe.failureThreshold` | Failure threshold for readinessProbe | `5` | +| `replica.readinessProbe.successThreshold` | Success threshold for readinessProbe | `1` | +| `replica.customStartupProbe` | Custom startupProbe that overrides the default one | `{}` | +| `replica.customLivenessProbe` | Custom livenessProbe that overrides the default one | `{}` | +| `replica.customReadinessProbe` | Custom readinessProbe that overrides the default one | `{}` | +| `replica.resources.limits` | The resources limits for the Redis® replicas containers | `{}` | +| `replica.resources.requests` | The requested resources for the Redis® replicas containers | `{}` | +| `replica.podSecurityContext.enabled` | Enabled Redis® replicas pods' Security Context | `true` | +| `replica.podSecurityContext.fsGroup` | Set Redis® replicas pod's Security Context fsGroup | `1001` | +| `replica.containerSecurityContext.enabled` | Enabled Redis® replicas containers' Security Context | `true` | +| `replica.containerSecurityContext.runAsUser` | Set Redis® replicas containers' Security Context runAsUser | `1001` | +| `replica.schedulerName` | Alternate scheduler for Redis® replicas pods | `""` | +| `replica.updateStrategy.type` | Redis® replicas statefulset strategy type | `RollingUpdate` | +| `replica.priorityClassName` | Redis® replicas pods' priorityClassName | `""` | +| `replica.podManagementPolicy` | podManagementPolicy to manage scaling operation of %%MAIN_CONTAINER_NAME%% pods | `""` | +| `replica.hostAliases` | Redis® replicas pods host aliases | `[]` | +| `replica.podLabels` | Extra labels for Redis® replicas pods | `{}` | +| `replica.podAnnotations` | Annotations for Redis® replicas pods | `{}` | +| `replica.shareProcessNamespace` | Share a single process namespace between all of the containers in Redis® replicas pods | `false` | +| `replica.podAffinityPreset` | Pod affinity preset. Ignored if `replica.affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `replica.podAntiAffinityPreset` | Pod anti-affinity preset. Ignored if `replica.affinity` is set. Allowed values: `soft` or `hard` | `soft` | +| `replica.nodeAffinityPreset.type` | Node affinity preset type. Ignored if `replica.affinity` is set. Allowed values: `soft` or `hard` | `""` | +| `replica.nodeAffinityPreset.key` | Node label key to match. Ignored if `replica.affinity` is set | `""` | +| `replica.nodeAffinityPreset.values` | Node label values to match. Ignored if `replica.affinity` is set | `[]` | +| `replica.affinity` | Affinity for Redis® replicas pods assignment | `{}` | +| `replica.nodeSelector` | Node labels for Redis® replicas pods assignment | `{}` | +| `replica.tolerations` | Tolerations for Redis® replicas pods assignment | `[]` | +| `replica.topologySpreadConstraints` | Spread Constraints for Redis® replicas pod assignment | `[]` | +| `replica.dnsPolicy` | DNS Policy for Redis® replica pods | `""` | +| `replica.dnsConfig` | DNS Configuration for Redis® replica pods | `{}` | +| `replica.lifecycleHooks` | for the Redis® replica container(s) to automate configuration before or after startup | `{}` | +| `replica.extraVolumes` | Optionally specify extra list of additional volumes for the Redis® replicas pod(s) | `[]` | +| `replica.extraVolumeMounts` | Optionally specify extra list of additional volumeMounts for the Redis® replicas container(s) | `[]` | +| `replica.sidecars` | Add additional sidecar containers to the Redis® replicas pod(s) | `[]` | +| `replica.initContainers` | Add additional init containers to the Redis® replicas pod(s) | `[]` | +| `replica.persistence.enabled` | Enable persistence on Redis® replicas nodes using Persistent Volume Claims | `true` | +| `replica.persistence.medium` | Provide a medium for `emptyDir` volumes. | `""` | +| `replica.persistence.sizeLimit` | Set this to enable a size limit for `emptyDir` volumes. | `""` | +| `replica.persistence.path` | The path the volume will be mounted at on Redis® replicas containers | `/data` | +| `replica.persistence.subPath` | The subdirectory of the volume to mount on Redis® replicas containers | `""` | +| `replica.persistence.storageClass` | Persistent Volume storage class | `""` | +| `replica.persistence.accessModes` | Persistent Volume access modes | `["ReadWriteOnce"]` | +| `replica.persistence.size` | Persistent Volume size | `8Gi` | +| `replica.persistence.annotations` | Additional custom annotations for the PVC | `{}` | +| `replica.persistence.selector` | Additional labels to match for the PVC | `{}` | +| `replica.persistence.dataSource` | Custom PVC data source | `{}` | +| `replica.persistence.existingClaim` | Use a existing PVC which must be created manually before bound | `""` | +| `replica.service.type` | Redis® replicas service type | `ClusterIP` | +| `replica.service.ports.redis` | Redis® replicas service port | `6379` | +| `replica.service.nodePorts.redis` | Node port for Redis® replicas | `""` | +| `replica.service.externalTrafficPolicy` | Redis® replicas service external traffic policy | `Cluster` | +| `replica.service.internalTrafficPolicy` | Redis® replicas service internal traffic policy (requires Kubernetes v1.22 or greater to be usable) | `Cluster` | +| `replica.service.extraPorts` | Extra ports to expose (normally used with the `sidecar` value) | `[]` | +| `replica.service.clusterIP` | Redis® replicas service Cluster IP | `""` | +| `replica.service.loadBalancerIP` | Redis® replicas service Load Balancer IP | `""` | +| `replica.service.loadBalancerSourceRanges` | Redis® replicas service Load Balancer sources | `[]` | +| `replica.service.annotations` | Additional custom annotations for Redis® replicas service | `{}` | +| `replica.service.sessionAffinity` | Session Affinity for Kubernetes service, can be "None" or "ClientIP" | `None` | +| `replica.service.sessionAffinityConfig` | Additional settings for the sessionAffinity | `{}` | +| `replica.terminationGracePeriodSeconds` | Integer setting the termination grace period for the redis-replicas pods | `30` | +| `replica.autoscaling.enabled` | Enable replica autoscaling settings | `false` | +| `replica.autoscaling.minReplicas` | Minimum replicas for the pod autoscaling | `1` | +| `replica.autoscaling.maxReplicas` | Maximum replicas for the pod autoscaling | `11` | +| `replica.autoscaling.targetCPU` | Percentage of CPU to consider when autoscaling | `""` | +| `replica.autoscaling.targetMemory` | Percentage of Memory to consider when autoscaling | `""` | + + +### Redis® Sentinel configuration parameters + +| Name | Description | Value | +| --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------ | +| `sentinel.enabled` | Use Redis® Sentinel on Redis® pods. | `false` | +| `sentinel.image.registry` | Redis® Sentinel image registry | `docker.io` | +| `sentinel.image.repository` | Redis® Sentinel image repository | `bitnami/redis-sentinel` | +| `sentinel.image.tag` | Redis® Sentinel image tag (immutable tags are recommended) | `6.2.7-debian-11-r12` | +| `sentinel.image.pullPolicy` | Redis® Sentinel image pull policy | `IfNotPresent` | +| `sentinel.image.pullSecrets` | Redis® Sentinel image pull secrets | `[]` | +| `sentinel.image.debug` | Enable image debug mode | `false` | +| `sentinel.masterSet` | Master set name | `mymaster` | +| `sentinel.quorum` | Sentinel Quorum | `2` | +| `sentinel.getMasterTimeout` | Amount of time to allow before get_sentinel_master_info() times out. | `220` | +| `sentinel.automateClusterRecovery` | Automate cluster recovery in cases where the last replica is not considered a good replica and Sentinel won't automatically failover to it. | `false` | +| `sentinel.downAfterMilliseconds` | Timeout for detecting a Redis® node is down | `60000` | +| `sentinel.failoverTimeout` | Timeout for performing a election failover | `18000` | +| `sentinel.parallelSyncs` | Number of replicas that can be reconfigured in parallel to use the new master after a failover | `1` | +| `sentinel.configuration` | Configuration for Redis® Sentinel nodes | `""` | +| `sentinel.command` | Override default container command (useful when using custom images) | `[]` | +| `sentinel.args` | Override default container args (useful when using custom images) | `[]` | +| `sentinel.preExecCmds` | Additional commands to run prior to starting Redis® Sentinel | `[]` | +| `sentinel.extraEnvVars` | Array with extra environment variables to add to Redis® Sentinel nodes | `[]` | +| `sentinel.extraEnvVarsCM` | Name of existing ConfigMap containing extra env vars for Redis® Sentinel nodes | `""` | +| `sentinel.extraEnvVarsSecret` | Name of existing Secret containing extra env vars for Redis® Sentinel nodes | `""` | +| `sentinel.externalMaster.enabled` | Use external master for bootstrapping | `false` | +| `sentinel.externalMaster.host` | External master host to bootstrap from | `""` | +| `sentinel.externalMaster.port` | Port for Redis service external master host | `6379` | +| `sentinel.containerPorts.sentinel` | Container port to open on Redis® Sentinel nodes | `26379` | +| `sentinel.startupProbe.enabled` | Enable startupProbe on Redis® Sentinel nodes | `true` | +| `sentinel.startupProbe.initialDelaySeconds` | Initial delay seconds for startupProbe | `10` | +| `sentinel.startupProbe.periodSeconds` | Period seconds for startupProbe | `10` | +| `sentinel.startupProbe.timeoutSeconds` | Timeout seconds for startupProbe | `5` | +| `sentinel.startupProbe.failureThreshold` | Failure threshold for startupProbe | `22` | +| `sentinel.startupProbe.successThreshold` | Success threshold for startupProbe | `1` | +| `sentinel.livenessProbe.enabled` | Enable livenessProbe on Redis® Sentinel nodes | `true` | +| `sentinel.livenessProbe.initialDelaySeconds` | Initial delay seconds for livenessProbe | `20` | +| `sentinel.livenessProbe.periodSeconds` | Period seconds for livenessProbe | `5` | +| `sentinel.livenessProbe.timeoutSeconds` | Timeout seconds for livenessProbe | `5` | +| `sentinel.livenessProbe.failureThreshold` | Failure threshold for livenessProbe | `5` | +| `sentinel.livenessProbe.successThreshold` | Success threshold for livenessProbe | `1` | +| `sentinel.readinessProbe.enabled` | Enable readinessProbe on Redis® Sentinel nodes | `true` | +| `sentinel.readinessProbe.initialDelaySeconds` | Initial delay seconds for readinessProbe | `20` | +| `sentinel.readinessProbe.periodSeconds` | Period seconds for readinessProbe | `5` | +| `sentinel.readinessProbe.timeoutSeconds` | Timeout seconds for readinessProbe | `1` | +| `sentinel.readinessProbe.failureThreshold` | Failure threshold for readinessProbe | `5` | +| `sentinel.readinessProbe.successThreshold` | Success threshold for readinessProbe | `1` | +| `sentinel.customStartupProbe` | Custom startupProbe that overrides the default one | `{}` | +| `sentinel.customLivenessProbe` | Custom livenessProbe that overrides the default one | `{}` | +| `sentinel.customReadinessProbe` | Custom readinessProbe that overrides the default one | `{}` | +| `sentinel.persistence.enabled` | Enable persistence on Redis® sentinel nodes using Persistent Volume Claims (Experimental) | `false` | +| `sentinel.persistence.storageClass` | Persistent Volume storage class | `""` | +| `sentinel.persistence.accessModes` | Persistent Volume access modes | `["ReadWriteOnce"]` | +| `sentinel.persistence.size` | Persistent Volume size | `100Mi` | +| `sentinel.persistence.annotations` | Additional custom annotations for the PVC | `{}` | +| `sentinel.persistence.selector` | Additional labels to match for the PVC | `{}` | +| `sentinel.persistence.dataSource` | Custom PVC data source | `{}` | +| `sentinel.persistence.medium` | Provide a medium for `emptyDir` volumes. | `""` | +| `sentinel.resources.limits` | The resources limits for the Redis® Sentinel containers | `{}` | +| `sentinel.resources.requests` | The requested resources for the Redis® Sentinel containers | `{}` | +| `sentinel.containerSecurityContext.enabled` | Enabled Redis® Sentinel containers' Security Context | `true` | +| `sentinel.containerSecurityContext.runAsUser` | Set Redis® Sentinel containers' Security Context runAsUser | `1001` | +| `sentinel.lifecycleHooks` | for the Redis® sentinel container(s) to automate configuration before or after startup | `{}` | +| `sentinel.extraVolumes` | Optionally specify extra list of additional volumes for the Redis® Sentinel | `[]` | +| `sentinel.extraVolumeMounts` | Optionally specify extra list of additional volumeMounts for the Redis® Sentinel container(s) | `[]` | +| `sentinel.service.type` | Redis® Sentinel service type | `ClusterIP` | +| `sentinel.service.ports.redis` | Redis® service port for Redis® | `6379` | +| `sentinel.service.ports.sentinel` | Redis® service port for Redis® Sentinel | `26379` | +| `sentinel.service.nodePorts.redis` | Node port for Redis® | `""` | +| `sentinel.service.nodePorts.sentinel` | Node port for Sentinel | `""` | +| `sentinel.service.externalTrafficPolicy` | Redis® Sentinel service external traffic policy | `Cluster` | +| `sentinel.service.extraPorts` | Extra ports to expose (normally used with the `sidecar` value) | `[]` | +| `sentinel.service.clusterIP` | Redis® Sentinel service Cluster IP | `""` | +| `sentinel.service.loadBalancerIP` | Redis® Sentinel service Load Balancer IP | `""` | +| `sentinel.service.loadBalancerSourceRanges` | Redis® Sentinel service Load Balancer sources | `[]` | +| `sentinel.service.annotations` | Additional custom annotations for Redis® Sentinel service | `{}` | +| `sentinel.service.sessionAffinity` | Session Affinity for Kubernetes service, can be "None" or "ClientIP" | `None` | +| `sentinel.service.sessionAffinityConfig` | Additional settings for the sessionAffinity | `{}` | +| `sentinel.terminationGracePeriodSeconds` | Integer setting the termination grace period for the redis-node pods | `30` | + + +### Other Parameters + +| Name | Description | Value | +| --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- | ------- | +| `networkPolicy.enabled` | Enable creation of NetworkPolicy resources | `false` | +| `networkPolicy.allowExternal` | Don't require client label for connections | `true` | +| `networkPolicy.extraIngress` | Add extra ingress rules to the NetworkPolicy | `[]` | +| `networkPolicy.extraEgress` | Add extra egress rules to the NetworkPolicy | `[]` | +| `networkPolicy.ingressNSMatchLabels` | Labels to match to allow traffic from other namespaces | `{}` | +| `networkPolicy.ingressNSPodMatchLabels` | Pod labels to match to allow traffic from other namespaces | `{}` | +| `podSecurityPolicy.create` | Whether to create a PodSecurityPolicy. WARNING: PodSecurityPolicy is deprecated in Kubernetes v1.21 or later, unavailable in v1.25 or later | `false` | +| `podSecurityPolicy.enabled` | Enable PodSecurityPolicy's RBAC rules | `false` | +| `rbac.create` | Specifies whether RBAC resources should be created | `false` | +| `rbac.rules` | Custom RBAC rules to set | `[]` | +| `serviceAccount.create` | Specifies whether a ServiceAccount should be created | `true` | +| `serviceAccount.name` | The name of the ServiceAccount to use. | `""` | +| `serviceAccount.automountServiceAccountToken` | Whether to auto mount the service account token | `true` | +| `serviceAccount.annotations` | Additional custom annotations for the ServiceAccount | `{}` | +| `pdb.create` | Specifies whether a PodDisruptionBudget should be created | `false` | +| `pdb.minAvailable` | Min number of pods that must still be available after the eviction | `1` | +| `pdb.maxUnavailable` | Max number of pods that can be unavailable after the eviction | `""` | +| `tls.enabled` | Enable TLS traffic | `false` | +| `tls.authClients` | Require clients to authenticate | `true` | +| `tls.autoGenerated` | Enable autogenerated certificates | `false` | +| `tls.existingSecret` | The name of the existing secret that contains the TLS certificates | `""` | +| `tls.certificatesSecret` | DEPRECATED. Use existingSecret instead. | `""` | +| `tls.certFilename` | Certificate filename | `""` | +| `tls.certKeyFilename` | Certificate Key filename | `""` | +| `tls.certCAFilename` | CA Certificate filename | `""` | +| `tls.dhParamsFilename` | File containing DH params (in order to support DH based ciphers) | `""` | + + +### Metrics Parameters + +| Name | Description | Value | +| -------------------------------------------- | ------------------------------------------------------------------------------------------------ | ------------------------ | +| `metrics.enabled` | Start a sidecar prometheus exporter to expose Redis® metrics | `false` | +| `metrics.image.registry` | Redis® Exporter image registry | `docker.io` | +| `metrics.image.repository` | Redis® Exporter image repository | `bitnami/redis-exporter` | +| `metrics.image.tag` | Redis® Redis® Exporter image tag (immutable tags are recommended) | `1.43.0-debian-11-r4` | +| `metrics.image.pullPolicy` | Redis® Exporter image pull policy | `IfNotPresent` | +| `metrics.image.pullSecrets` | Redis® Exporter image pull secrets | `[]` | +| `metrics.command` | Override default metrics container init command (useful when using custom images) | `[]` | +| `metrics.redisTargetHost` | A way to specify an alternative Redis® hostname | `localhost` | +| `metrics.extraArgs` | Extra arguments for Redis® exporter, for example: | `{}` | +| `metrics.extraEnvVars` | Array with extra environment variables to add to Redis® exporter | `[]` | +| `metrics.containerSecurityContext.enabled` | Enabled Redis® exporter containers' Security Context | `true` | +| `metrics.containerSecurityContext.runAsUser` | Set Redis® exporter containers' Security Context runAsUser | `1001` | +| `metrics.extraVolumes` | Optionally specify extra list of additional volumes for the Redis® metrics sidecar | `[]` | +| `metrics.extraVolumeMounts` | Optionally specify extra list of additional volumeMounts for the Redis® metrics sidecar | `[]` | +| `metrics.resources.limits` | The resources limits for the Redis® exporter container | `{}` | +| `metrics.resources.requests` | The requested resources for the Redis® exporter container | `{}` | +| `metrics.podLabels` | Extra labels for Redis® exporter pods | `{}` | +| `metrics.podAnnotations` | Annotations for Redis® exporter pods | `{}` | +| `metrics.service.type` | Redis® exporter service type | `ClusterIP` | +| `metrics.service.port` | Redis® exporter service port | `9121` | +| `metrics.service.externalTrafficPolicy` | Redis® exporter service external traffic policy | `Cluster` | +| `metrics.service.extraPorts` | Extra ports to expose (normally used with the `sidecar` value) | `[]` | +| `metrics.service.loadBalancerIP` | Redis® exporter service Load Balancer IP | `""` | +| `metrics.service.loadBalancerSourceRanges` | Redis® exporter service Load Balancer sources | `[]` | +| `metrics.service.annotations` | Additional custom annotations for Redis® exporter service | `{}` | +| `metrics.serviceMonitor.enabled` | Create ServiceMonitor resource(s) for scraping metrics using PrometheusOperator | `false` | +| `metrics.serviceMonitor.namespace` | The namespace in which the ServiceMonitor will be created | `""` | +| `metrics.serviceMonitor.interval` | The interval at which metrics should be scraped | `30s` | +| `metrics.serviceMonitor.scrapeTimeout` | The timeout after which the scrape is ended | `""` | +| `metrics.serviceMonitor.relabellings` | Metrics RelabelConfigs to apply to samples before scraping. | `[]` | +| `metrics.serviceMonitor.metricRelabelings` | Metrics RelabelConfigs to apply to samples before ingestion. | `[]` | +| `metrics.serviceMonitor.honorLabels` | Specify honorLabels parameter to add the scrape endpoint | `false` | +| `metrics.serviceMonitor.additionalLabels` | Additional labels that can be used so ServiceMonitor resource(s) can be discovered by Prometheus | `{}` | +| `metrics.prometheusRule.enabled` | Create a custom prometheusRule Resource for scraping metrics using PrometheusOperator | `false` | +| `metrics.prometheusRule.namespace` | The namespace in which the prometheusRule will be created | `""` | +| `metrics.prometheusRule.additionalLabels` | Additional labels for the prometheusRule | `{}` | +| `metrics.prometheusRule.rules` | Custom Prometheus rules | `[]` | + + +### Init Container Parameters + +| Name | Description | Value | +| ------------------------------------------------------ | ----------------------------------------------------------------------------------------------- | ----------------------- | +| `volumePermissions.enabled` | Enable init container that changes the owner/group of the PV mount point to `runAsUser:fsGroup` | `false` | +| `volumePermissions.image.registry` | Bitnami Shell image registry | `docker.io` | +| `volumePermissions.image.repository` | Bitnami Shell image repository | `bitnami/bitnami-shell` | +| `volumePermissions.image.tag` | Bitnami Shell image tag (immutable tags are recommended) | `11-debian-11-r11` | +| `volumePermissions.image.pullPolicy` | Bitnami Shell image pull policy | `IfNotPresent` | +| `volumePermissions.image.pullSecrets` | Bitnami Shell image pull secrets | `[]` | +| `volumePermissions.resources.limits` | The resources limits for the init container | `{}` | +| `volumePermissions.resources.requests` | The requested resources for the init container | `{}` | +| `volumePermissions.containerSecurityContext.runAsUser` | Set init container's Security Context runAsUser | `0` | +| `sysctl.enabled` | Enable init container to modify Kernel settings | `false` | +| `sysctl.image.registry` | Bitnami Shell image registry | `docker.io` | +| `sysctl.image.repository` | Bitnami Shell image repository | `bitnami/bitnami-shell` | +| `sysctl.image.tag` | Bitnami Shell image tag (immutable tags are recommended) | `11-debian-11-r11` | +| `sysctl.image.pullPolicy` | Bitnami Shell image pull policy | `IfNotPresent` | +| `sysctl.image.pullSecrets` | Bitnami Shell image pull secrets | `[]` | +| `sysctl.command` | Override default init-sysctl container command (useful when using custom images) | `[]` | +| `sysctl.mountHostSys` | Mount the host `/sys` folder to `/host-sys` | `false` | +| `sysctl.resources.limits` | The resources limits for the init container | `{}` | +| `sysctl.resources.requests` | The requested resources for the init container | `{}` | + + +### useExternalDNS Parameters + +| Name | Description | Value | +| -------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------- | +| `useExternalDNS.enabled` | Enable various syntax that would enable external-dns to work. Note this requires a working installation of `external-dns` to be usable. | `false` | +| `useExternalDNS.additionalAnnotations` | Extra annotations to be utilized when `external-dns` is enabled. | `{}` | +| `useExternalDNS.annotationKey` | The annotation key utilized when `external-dns` is enabled. | `external-dns.alpha.kubernetes.io/` | +| `useExternalDNS.suffix` | The DNS suffix utilized when `external-dns` is enabled. Note that we prepend the suffix with the full name of the release. | `""` | + + +Specify each parameter using the `--set key=value[,key=value]` argument to `helm install`. For example, + +```bash +$ helm install my-release \ + --set auth.password=secretpassword \ + bitnami/redis +``` + +The above command sets the Redis® server password to `secretpassword`. + +> NOTE: Once this chart is deployed, it is not possible to change the application's access credentials, such as usernames or passwords, using Helm. To change these application credentials after deployment, delete any persistent volumes (PVs) used by the chart and re-deploy it, or use the application's built-in administrative tools if available. + +Alternatively, a YAML file that specifies the values for the parameters can be provided while installing the chart. For example, + +```bash +$ helm install my-release -f values.yaml bitnami/redis +``` + +> **Tip**: You can use the default [values.yaml](values.yaml) + +## Configuration and installation details + +### [Rolling VS Immutable tags](https://docs.bitnami.com/containers/how-to/understand-rolling-tags-containers/) + +It is strongly recommended to use immutable tags in a production environment. This ensures your deployment does not change automatically if the same tag is updated with a different image. + +Bitnami will release a new chart updating its containers if a new version of the main container, significant changes, or critical vulnerabilities exist. + +### Use a different Redis® version + +To modify the application version used in this chart, specify a different version of the image using the `image.tag` parameter and/or a different repository using the `image.repository` parameter. Refer to the [chart documentation for more information on these parameters and how to use them with images from a private registry](https://docs.bitnami.com/kubernetes/infrastructure/redis/configuration/change-image-version/). + +### Bootstrapping with an External Cluster + +This chart is equipped with the ability to bring online a set of Pods that connect to an existing Redis deployment that lies outside of Kubernetes. This effectively creates a hybrid Redis Deployment where both Pods in Kubernetes and Instances such as Virtual Machines can partake in a single Redis Deployment. This is helpful in situations where one may be migrating Redis from Virtual Machines into Kubernetes, for example. To take advantage of this, use the following as an example configuration: + +```yaml +replica: + externalMaster: + enabled: true + host: external-redis-0.internal +sentinel: + externalMaster: + enabled: true + host: external-redis-0.internal +``` + +:warning: This is currently limited to clusters in which Sentinel and Redis run on the same node! :warning: + +Please also note that the external sentinel must be listening on port `26379`, and this is currently not configurable. + +Once the Kubernetes Redis Deployment is online and confirmed to be working with the existing cluster, the configuration can then be removed and the cluster will remain connected. + +### External DNS + +This chart is equipped to allow leveraging the ExternalDNS project. Doing so will enable ExternalDNS to publish the FQDN for each instance, in the format of `..`. +Example, when using the following configuration: + +```yaml +useExternalDNS: + enabled: true + suffix: prod.example.org + additionalAnnotations: + ttl: 10 +``` + +On a cluster where the name of the Helm release is `a`, the hostname of a Pod is generated as: `a-redis-node-0.a-redis.prod.example.org`. The IP of that FQDN will match that of the associated Pod. This modifies the following parameters of the Redis/Sentinel configuration using this new FQDN: + +* `replica-announce-ip` +* `known-sentinel` +* `known-replica` +* `announce-ip` + +:warning: This requires a working installation of `external-dns` to be fully functional. :warning: + +See the [official ExternalDNS documentation](https://github.com/kubernetes-sigs/external-dns) for additional configuration options. + +### Cluster topologies + +#### Default: Master-Replicas + +When installing the chart with `architecture=replication`, it will deploy a Redis® master StatefulSet and a Redis® replicas StatefulSet. The replicas will be read-replicas of the master. Two services will be exposed: + +- Redis® Master service: Points to the master, where read-write operations can be performed +- Redis® Replicas service: Points to the replicas, where only read operations are allowed by default. + +In case the master crashes, the replicas will wait until the master node is respawned again by the Kubernetes Controller Manager. + +#### Standalone + +When installing the chart with `architecture=standalone`, it will deploy a standalone Redis® StatefulSet. A single service will be exposed: + +- Redis® Master service: Points to the master, where read-write operations can be performed + +#### Master-Replicas with Sentinel + +When installing the chart with `architecture=replication` and `sentinel.enabled=true`, it will deploy a Redis® master StatefulSet (only one master allowed) and a Redis® replicas StatefulSet. In this case, the pods will contain an extra container with Redis® Sentinel. This container will form a cluster of Redis® Sentinel nodes, which will promote a new master in case the actual one fails. In addition to this, only one service is exposed: + +- Redis® service: Exposes port 6379 for Redis® read-only operations and port 26379 for accessing Redis® Sentinel. + +For read-only operations, access the service using port 6379. For write operations, it's necessary to access the Redis® Sentinel cluster and query the current master using the command below (using redis-cli or similar): + +``` +SENTINEL get-master-addr-by-name +``` + +This command will return the address of the current master, which can be accessed from inside the cluster. + +In case the current master crashes, the Sentinel containers will elect a new master node. + +`master.count` greater than `1` is not designed for use when `sentinel.enabled=true`. + +### Multiple masters (experimental) + +When `master.count` is greater than `1`, special care must be taken to create a consistent setup. + +An example of use case is the creation of a redundant set of standalone masters or master-replicas per Kubernetes node where you must ensure: +- No more than `1` master can be deployed per Kubernetes node +- Replicas and writers can only see the single master of their own Kubernetes node + +One way of achieving this is by setting `master.service.internalTrafficPolicy=Local` in combination with a `master.affinity.podAntiAffinity` spec to never schedule more than one master per Kubernetes node. + +It's recommended to only change `master.count` if you know what you are doing. +`master.count` greater than `1` is not designed for use when `sentinel.enabled=true`. + +### Using a password file + +To use a password file for Redis® you need to create a secret containing the password and then deploy the chart using that secret. + +Refer to the chart documentation for more information on [using a password file for Redis®](https://docs.bitnami.com/kubernetes/infrastructure/redis/administration/use-password-file/). + +### Securing traffic using TLS + +TLS support can be enabled in the chart by specifying the `tls.` parameters while creating a release. The following parameters should be configured to properly enable the TLS support in the chart: + +- `tls.enabled`: Enable TLS support. Defaults to `false` +- `tls.existingSecret`: Name of the secret that contains the certificates. No defaults. +- `tls.certFilename`: Certificate filename. No defaults. +- `tls.certKeyFilename`: Certificate key filename. No defaults. +- `tls.certCAFilename`: CA Certificate filename. No defaults. + +Refer to the chart documentation for more information on [creating the secret and a TLS deployment example](https://docs.bitnami.com/kubernetes/infrastructure/redis/administration/enable-tls/). + +### Metrics + +The chart optionally can start a metrics exporter for [prometheus](https://prometheus.io). The metrics endpoint (port 9121) is exposed in the service. Metrics can be scraped from within the cluster using something similar as the described in the [example Prometheus scrape configuration](https://github.com/prometheus/prometheus/blob/master/documentation/examples/prometheus-kubernetes.yml). If metrics are to be scraped from outside the cluster, the Kubernetes API proxy can be utilized to access the endpoint. + +If you have enabled TLS by specifying `tls.enabled=true` you also need to specify TLS option to the metrics exporter. You can do that via `metrics.extraArgs`. You can find the metrics exporter CLI flags for TLS [here](https://github.com/oliver006/redis_exporter#command-line-flags). For example: + +You can either specify `metrics.extraArgs.skip-tls-verification=true` to skip TLS verification or providing the following values under `metrics.extraArgs` for TLS client authentication: + +```console +tls-client-key-file +tls-client-cert-file +tls-ca-cert-file +``` + +### Host Kernel Settings + +Redis® may require some changes in the kernel of the host machine to work as expected, in particular increasing the `somaxconn` value and disabling transparent huge pages. + +Refer to the chart documentation for more information on [configuring host kernel settings with an example](https://docs.bitnami.com/kubernetes/infrastructure/redis/administration/configure-kernel-settings/). + +## Persistence + +By default, the chart mounts a [Persistent Volume](https://kubernetes.io/docs/concepts/storage/persistent-volumes/) at the `/data` path. The volume is created using dynamic volume provisioning. If a Persistent Volume Claim already exists, specify it during installation. + +### Existing PersistentVolumeClaim + +1. Create the PersistentVolume +2. Create the PersistentVolumeClaim +3. Install the chart + +```bash +$ helm install my-release --set master.persistence.existingClaim=PVC_NAME bitnami/redis +``` + +## Backup and restore + +Refer to the chart documentation for more information on [backing up and restoring Redis® deployments](https://docs.bitnami.com/kubernetes/infrastructure/redis/administration/backup-restore/). + +## NetworkPolicy + +To enable network policy for Redis®, install [a networking plugin that implements the Kubernetes NetworkPolicy spec](https://kubernetes.io/docs/tasks/administer-cluster/declare-network-policy#before-you-begin), and set `networkPolicy.enabled` to `true`. + +Refer to the chart documenation for more information on [enabling the network policy in Redis® deployments](https://docs.bitnami.com/kubernetes/infrastructure/redis/administration/enable-network-policy/). + +### Setting Pod's affinity + +This chart allows you to set your custom affinity using the `XXX.affinity` parameter(s). Find more information about Pod's affinity in the [Kubernetes documentation](https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity). + +As an alternative, you can use of the preset configurations for pod affinity, pod anti-affinity, and node affinity available at the [bitnami/common](https://github.com/bitnami/charts/tree/master/bitnami/common#affinities) chart. To do so, set the `XXX.podAffinityPreset`, `XXX.podAntiAffinityPreset`, or `XXX.nodeAffinityPreset` parameters. + +## Troubleshooting + +Find more information about how to deal with common errors related to Bitnami's Helm charts in [this troubleshooting guide](https://docs.bitnami.com/general/how-to/troubleshoot-helm-chart-issues). + +## Upgrading + +A major chart version change (like v1.2.3 -> v2.0.0) indicates that there is an incompatible breaking change needing manual actions. + +### To 16.0.0 + +This major release renames several values in this chart and adds missing features, in order to be inline with the rest of assets in the Bitnami charts repository. + +Affected values: +- `master.service.port` renamed as `master.service.ports.redis`. +- `master.service.nodePort` renamed as `master.service.nodePorts.redis`. +- `replica.service.port` renamed as `replica.service.ports.redis`. +- `replica.service.nodePort` renamed as `replica.service.nodePorts.redis`. +- `sentinel.service.port` renamed as `sentinel.service.ports.redis`. +- `sentinel.service.sentinelPort` renamed as `sentinel.service.ports.sentinel`. +- `master.containerPort` renamed as `master.containerPorts.redis`. +- `replica.containerPort` renamed as `replica.containerPorts.redis`. +- `sentinel.containerPort` renamed as `sentinel.containerPorts.sentinel`. +- `master.spreadConstraints` renamed as `master.topologySpreadConstraints` +- `replica.spreadConstraints` renamed as `replica.topologySpreadConstraints` + +### To 15.0.0 + +The parameter to enable the usage of StaticIDs was removed. The behavior is to [always use StaticIDs](https://github.com/bitnami/charts/pull/7278). + +### To 14.8.0 + +The Redis® sentinel exporter was removed in this version because the upstream project was deprecated. The regular Redis® exporter is included in the sentinel scenario as usual. + +### To 14.0.0 + +- Several parameters were renamed or disappeared in favor of new ones on this major version: + - The term *slave* has been replaced by the term *replica*. Therefore, parameters prefixed with `slave` are now prefixed with `replicas`. + - Credentials parameter are reorganized under the `auth` parameter. + - `cluster.enabled` parameter is deprecated in favor of `architecture` parameter that accepts two values: `standalone` and `replication`. + - `securityContext.*` is deprecated in favor of `XXX.podSecurityContext` and `XXX.containerSecurityContext`. + - `sentinel.metrics.*` parameters are deprecated in favor of `metrics.sentinel.*` ones. +- New parameters to add custom command, environment variables, sidecars, init containers, etc. were added. +- Chart labels were adapted to follow the [Helm charts standard labels](https://helm.sh/docs/chart_best_practices/labels/#standard-labels). +- values.yaml metadata was adapted to follow the format supported by [Readme Generator for Helm](https://github.com/bitnami-labs/readme-generator-for-helm). + +Consequences: + +Backwards compatibility is not guaranteed. To upgrade to `14.0.0`, install a new release of the Redis® chart, and migrate the data from your previous release. You have 2 alternatives to do so: + +- Create a backup of the database, and restore it on the new release as explained in the [Backup and restore](#backup-and-restore) section. +- Reuse the PVC used to hold the master data on your previous release. To do so, use the `master.persistence.existingClaim` parameter. The following example assumes that the release name is `redis`: + +```bash +$ helm install redis bitnami/redis --set auth.password=[PASSWORD] --set master.persistence.existingClaim=[EXISTING_PVC] +``` + +| Note: you need to substitute the placeholder _[EXISTING_PVC]_ with the name of the PVC used on your previous release, and _[PASSWORD]_ with the password used in your previous release. + +### To 13.0.0 + +This major version updates the Redis® docker image version used from `6.0` to `6.2`, the new stable version. There are no major changes in the chart and there shouldn't be any breaking changes in it as `6.2` is basically a stricter superset of `6.0`. For more information, please refer to [Redis® 6.2 release notes](https://raw.githubusercontent.com/redis/redis/6.2/00-RELEASENOTES). + +### To 12.3.0 + +This version also introduces `bitnami/common`, a [library chart](https://helm.sh/docs/topics/library_charts/#helm) as a dependency. More documentation about this new utility could be found [here](https://github.com/bitnami/charts/tree/master/bitnami/common#bitnami-common-library-chart). Please, make sure that you have updated the chart dependencies before executing any upgrade. + +### To 12.0.0 + +[On November 13, 2020, Helm v2 support was formally finished](https://github.com/helm/charts#status-of-the-project), this major version is the result of the required changes applied to the Helm Chart to be able to incorporate the different features added in Helm v3 and to be consistent with the Helm project itself regarding the Helm v2 EOL. + +**What changes were introduced in this major version?** + +- Previous versions of this Helm Chart use `apiVersion: v1` (installable by both Helm 2 and 3), this Helm Chart was updated to `apiVersion: v2` (installable by Helm 3 only). [Here](https://helm.sh/docs/topics/charts/#the-apiversion-field) you can find more information about the `apiVersion` field. +- The different fields present in the *Chart.yaml* file has been ordered alphabetically in a homogeneous way for all the Bitnami Helm Charts + +**Considerations when upgrading to this version** + +- If you want to upgrade to this version from a previous one installed with Helm v3, you shouldn't face any issues +- If you want to upgrade to this version using Helm v2, this scenario is not supported as this version doesn't support Helm v2 anymore +- If you installed the previous version with Helm v2 and wants to upgrade to this version with Helm v3, please refer to the [official Helm documentation](https://helm.sh/docs/topics/v2_v3_migration/#migration-use-cases) about migrating from Helm v2 to v3 + +**Useful links** + +- https://docs.bitnami.com/tutorials/resolve-helm2-helm3-post-migration-issues/ +- https://helm.sh/docs/topics/v2_v3_migration/ +- https://helm.sh/blog/migrate-from-helm-v2-to-helm-v3/ + +### To 11.0.0 + +When deployed with sentinel enabled, only a group of nodes is deployed and the master/slave role is handled in the group. To avoid breaking the compatibility, the settings for this nodes are given through the `slave.xxxx` parameters in `values.yaml` + +### To 9.0.0 + +The metrics exporter has been changed from a separate deployment to a sidecar container, due to the latest changes in the Redis® exporter code. Check the [official page](https://github.com/oliver006/redis_exporter/) for more information. The metrics container image was changed from oliver006/redis_exporter to bitnami/redis-exporter (Bitnami's maintained package of oliver006/redis_exporter). + +### To 7.0.0 + +In order to improve the performance in case of slave failure, we added persistence to the read-only slaves. That means that we moved from Deployment to StatefulSets. This should not affect upgrades from previous versions of the chart, as the deployments did not contain any persistence at all. + +This version also allows enabling Redis® Sentinel containers inside of the Redis® Pods (feature disabled by default). In case the master crashes, a new Redis® node will be elected as master. In order to query the current master (no redis master service is exposed), you need to query first the Sentinel cluster. Find more information [in this section](#master-slave-with-sentinel). + +### To 11.0.0 + +When using sentinel, a new statefulset called `-node` was introduced. This will break upgrading from a previous version where the statefulsets are called master and slave. Hence the PVC will not match the new naming and won't be reused. If you want to keep your data, you will need to perform a backup and then a restore the data in this new version. + +### To 10.0.0 + +For releases with `usePassword: true`, the value `sentinel.usePassword` controls whether the password authentication also applies to the sentinel port. This defaults to `true` for a secure configuration, however it is possible to disable to account for the following cases: + +- Using a version of redis-sentinel prior to `5.0.1` where the authentication feature was introduced. +- Where redis clients need to be updated to support sentinel authentication. + +If using a master/slave topology, or with `usePassword: false`, no action is required. + +### To 8.0.18 + +For releases with `metrics.enabled: true` the default tag for the exporter image is now `v1.x.x`. This introduces many changes including metrics names. You'll want to use [this dashboard](https://github.com/oliver006/redis_exporter/blob/master/contrib/grafana_prometheus_redis_dashboard.json) now. Please see the [redis_exporter github page](https://github.com/oliver006/redis_exporter#upgrading-from-0x-to-1x) for more details. + +### To 7.0.0 + +This version causes a change in the Redis® Master StatefulSet definition, so the command helm upgrade would not work out of the box. As an alternative, one of the following could be done: + +- Recommended: Create a clone of the Redis® Master PVC (for example, using projects like [this one](https://github.com/edseymour/pvc-transfer)). Then launch a fresh release reusing this cloned PVC. + + ``` + helm install my-release bitnami/redis --set persistence.existingClaim= + ``` + +- Alternative (not recommended, do at your own risk): `helm delete --purge` does not remove the PVC assigned to the Redis® Master StatefulSet. As a consequence, the following commands can be done to upgrade the release + + ``` + helm delete --purge + helm install bitnami/redis + ``` + +Previous versions of the chart were not using persistence in the slaves, so this upgrade would add it to them. Another important change is that no values are inherited from master to slaves. For example, in 6.0.0 `slaves.readinessProbe.periodSeconds`, if empty, would be set to `master.readinessProbe.periodSeconds`. This approach lacked transparency and was difficult to maintain. From now on, all the slave parameters must be configured just as it is done with the masters. + +Some values have changed as well: + +- `master.port` and `slave.port` have been changed to `redisPort` (same value for both master and slaves) +- `master.securityContext` and `slave.securityContext` have been changed to `securityContext`(same values for both master and slaves) + +By default, the upgrade will not change the cluster topology. In case you want to use Redis® Sentinel, you must explicitly set `sentinel.enabled` to `true`. + +### To 6.0.0 + +Previous versions of the chart were using an init-container to change the permissions of the volumes. This was done in case the `securityContext` directive in the template was not enough for that (for example, with cephFS). In this new version of the chart, this container is disabled by default (which should not affect most of the deployments). If your installation still requires that init container, execute `helm upgrade` with the `--set volumePermissions.enabled=true`. + +### To 5.0.0 + +The default image in this release may be switched out for any image containing the `redis-server` +and `redis-cli` binaries. If `redis-server` is not the default image ENTRYPOINT, `master.command` +must be specified. + +#### Breaking changes + +- `master.args` and `slave.args` are removed. Use `master.command` or `slave.command` instead in order to override the image entrypoint, or `master.extraFlags` to pass additional flags to `redis-server`. +- `disableCommands` is now interpreted as an array of strings instead of a string of comma separated values. +- `master.persistence.path` now defaults to `/data`. + +### To 4.0.0 + +This version removes the `chart` label from the `spec.selector.matchLabels` +which is immutable since `StatefulSet apps/v1beta2`. It has been inadvertently +added, causing any subsequent upgrade to fail. See https://github.com/helm/charts/issues/7726. + +It also fixes https://github.com/helm/charts/issues/7726 where a deployment `extensions/v1beta1` can not be upgraded if `spec.selector` is not explicitly set. + +Finally, it fixes https://github.com/helm/charts/issues/7803 by removing mutable labels in `spec.VolumeClaimTemplate.metadata.labels` so that it is upgradable. + +In order to upgrade, delete the Redis® StatefulSet before upgrading: + +```bash +kubectl delete statefulsets.apps --cascade=false my-release-redis-master +``` + +And edit the Redis® slave (and metrics if enabled) deployment: + +```bash +kubectl patch deployments my-release-redis-slave --type=json -p='[{"op": "remove", "path": "/spec/selector/matchLabels/chart"}]' +kubectl patch deployments my-release-redis-metrics --type=json -p='[{"op": "remove", "path": "/spec/selector/matchLabels/chart"}]' +``` + +## License + +Copyright © 2022 Bitnami + +Licensed under the Apache License, Version 2.0 (the "License"); +you may not use this file except in compliance with the License. +You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + +Unless required by applicable law or agreed to in writing, software +distributed under the License is distributed on an "AS IS" BASIS, +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +See the License for the specific language governing permissions and +limitations under the License. \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/.helmignore b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/.helmignore new file mode 100644 index 0000000..50af031 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/.helmignore @@ -0,0 +1,22 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/Chart.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/Chart.yaml new file mode 100644 index 0000000..bd152e3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/Chart.yaml @@ -0,0 +1,23 @@ +annotations: + category: Infrastructure +apiVersion: v2 +appVersion: 1.16.0 +description: A Library Helm Chart for grouping common logic between bitnami charts. + This chart is not deployable by itself. +home: https://github.com/bitnami/charts/tree/master/bitnami/common +icon: https://bitnami.com/downloads/logos/bitnami-mark.png +keywords: +- common +- helper +- template +- function +- bitnami +maintainers: +- name: Bitnami + url: https://github.com/bitnami/charts +name: common +sources: +- https://github.com/bitnami/charts +- https://www.bitnami.com/ +type: library +version: 1.16.0 diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/README.md b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/README.md new file mode 100644 index 0000000..3b5e09c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/README.md @@ -0,0 +1,350 @@ +# Bitnami Common Library Chart + +A [Helm Library Chart](https://helm.sh/docs/topics/library_charts/#helm) for grouping common logic between bitnami charts. + +## TL;DR + +```yaml +dependencies: + - name: common + version: 1.x.x + repository: https://charts.bitnami.com/bitnami +``` + +```bash +$ helm dependency update +``` + +```yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "common.names.fullname" . }} +data: + myvalue: "Hello World" +``` + +## Introduction + +This chart provides a common template helpers which can be used to develop new charts using [Helm](https://helm.sh) package manager. + +Bitnami charts can be used with [Kubeapps](https://kubeapps.com/) for deployment and management of Helm Charts in clusters. This Helm chart has been tested on top of [Bitnami Kubernetes Production Runtime](https://kubeprod.io/) (BKPR). Deploy BKPR to get automated TLS certificates, logging and monitoring for your applications. + +## Prerequisites + +- Kubernetes 1.19+ +- Helm 3.2.0+ + +## Parameters + +The following table lists the helpers available in the library which are scoped in different sections. + +### Affinities + +| Helper identifier | Description | Expected Input | +|-------------------------------|------------------------------------------------------|------------------------------------------------| +| `common.affinities.nodes.soft` | Return a soft nodeAffinity definition | `dict "key" "FOO" "values" (list "BAR" "BAZ")` | +| `common.affinities.nodes.hard` | Return a hard nodeAffinity definition | `dict "key" "FOO" "values" (list "BAR" "BAZ")` | +| `common.affinities.pods.soft` | Return a soft podAffinity/podAntiAffinity definition | `dict "component" "FOO" "context" $` | +| `common.affinities.pods.hard` | Return a hard podAffinity/podAntiAffinity definition | `dict "component" "FOO" "context" $` | + +### Capabilities + +| Helper identifier | Description | Expected Input | +|------------------------------------------------|------------------------------------------------------------------------------------------------|-------------------| +| `common.capabilities.kubeVersion` | Return the target Kubernetes version (using client default if .Values.kubeVersion is not set). | `.` Chart context | +| `common.capabilities.cronjob.apiVersion` | Return the appropriate apiVersion for cronjob. | `.` Chart context | +| `common.capabilities.deployment.apiVersion` | Return the appropriate apiVersion for deployment. | `.` Chart context | +| `common.capabilities.statefulset.apiVersion` | Return the appropriate apiVersion for statefulset. | `.` Chart context | +| `common.capabilities.ingress.apiVersion` | Return the appropriate apiVersion for ingress. | `.` Chart context | +| `common.capabilities.rbac.apiVersion` | Return the appropriate apiVersion for RBAC resources. | `.` Chart context | +| `common.capabilities.crd.apiVersion` | Return the appropriate apiVersion for CRDs. | `.` Chart context | +| `common.capabilities.policy.apiVersion` | Return the appropriate apiVersion for podsecuritypolicy. | `.` Chart context | +| `common.capabilities.networkPolicy.apiVersion` | Return the appropriate apiVersion for networkpolicy. | `.` Chart context | +| `common.capabilities.apiService.apiVersion` | Return the appropriate apiVersion for APIService. | `.` Chart context | +| `common.capabilities.hpa.apiVersion` | Return the appropriate apiVersion for Horizontal Pod Autoscaler | `.` Chart context | +| `common.capabilities.supportsHelmVersion` | Returns true if the used Helm version is 3.3+ | `.` Chart context | + +### Errors + +| Helper identifier | Description | Expected Input | +|-----------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------| +| `common.errors.upgrade.passwords.empty` | It will ensure required passwords are given when we are upgrading a chart. If `validationErrors` is not empty it will throw an error and will stop the upgrade action. | `dict "validationErrors" (list $validationError00 $validationError01) "context" $` | + +### Images + +| Helper identifier | Description | Expected Input | +|-----------------------------|------------------------------------------------------|---------------------------------------------------------------------------------------------------------| +| `common.images.image` | Return the proper and full image name | `dict "imageRoot" .Values.path.to.the.image "global" $`, see [ImageRoot](#imageroot) for the structure. | +| `common.images.pullSecrets` | Return the proper Docker Image Registry Secret Names (deprecated: use common.images.renderPullSecrets instead) | `dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "global" .Values.global` | +| `common.images.renderPullSecrets` | Return the proper Docker Image Registry Secret Names (evaluates values as templates) | `dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "context" $` | + +### Ingress + +| Helper identifier | Description | Expected Input | +|-------------------------------------------|-------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| `common.ingress.backend` | Generate a proper Ingress backend entry depending on the API version | `dict "serviceName" "foo" "servicePort" "bar"`, see the [Ingress deprecation notice](https://kubernetes.io/blog/2019/07/18/api-deprecations-in-1-16/) for the syntax differences | +| `common.ingress.supportsPathType` | Prints "true" if the pathType field is supported | `.` Chart context | +| `common.ingress.supportsIngressClassname` | Prints "true" if the ingressClassname field is supported | `.` Chart context | +| `common.ingress.certManagerRequest` | Prints "true" if required cert-manager annotations for TLS signed certificates are set in the Ingress annotations | `dict "annotations" .Values.path.to.the.ingress.annotations` | + +### Labels + +| Helper identifier | Description | Expected Input | +|-----------------------------|-----------------------------------------------------------------------------|-------------------| +| `common.labels.standard` | Return Kubernetes standard labels | `.` Chart context | +| `common.labels.matchLabels` | Labels to use on `deploy.spec.selector.matchLabels` and `svc.spec.selector` | `.` Chart context | + +### Names + +| Helper identifier | Description | Expected Input | +|-----------------------------------|-----------------------------------------------------------------------|-------------------| +| `common.names.name` | Expand the name of the chart or use `.Values.nameOverride` | `.` Chart context | +| `common.names.fullname` | Create a default fully qualified app name. | `.` Chart context | +| `common.names.namespace` | Allow the release namespace to be overridden | `.` Chart context | +| `common.names.fullname.namespace` | Create a fully qualified app name adding the installation's namespace | `.` Chart context | +| `common.names.chart` | Chart name plus version | `.` Chart context | + +### Secrets + +| Helper identifier | Description | Expected Input | +|---------------------------|--------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| `common.secrets.name` | Generate the name of the secret. | `dict "existingSecret" .Values.path.to.the.existingSecret "defaultNameSuffix" "mySuffix" "context" $` see [ExistingSecret](#existingsecret) for the structure. | +| `common.secrets.key` | Generate secret key. | `dict "existingSecret" .Values.path.to.the.existingSecret "key" "keyName"` see [ExistingSecret](#existingsecret) for the structure. | +| `common.passwords.manage` | Generate secret password or retrieve one if already created. | `dict "secret" "secret-name" "key" "keyName" "providedValues" (list "path.to.password1" "path.to.password2") "length" 10 "strong" false "chartName" "chartName" "context" $`, length, strong and chartNAme fields are optional. | +| `common.secrets.exists` | Returns whether a previous generated secret already exists. | `dict "secret" "secret-name" "context" $` | + +### Storage + +| Helper identifier | Description | Expected Input | +|-------------------------------|---------------------------------------|---------------------------------------------------------------------------------------------------------------------| +| `common.storage.class` | Return the proper Storage Class | `dict "persistence" .Values.path.to.the.persistence "global" $`, see [Persistence](#persistence) for the structure. | + +### TplValues + +| Helper identifier | Description | Expected Input | +|---------------------------|----------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------| +| `common.tplvalues.render` | Renders a value that contains template | `dict "value" .Values.path.to.the.Value "context" $`, value is the value should rendered as template, context frequently is the chart context `$` or `.` | + +### Utils + +| Helper identifier | Description | Expected Input | +|--------------------------------|------------------------------------------------------------------------------------------|------------------------------------------------------------------------| +| `common.utils.fieldToEnvVar` | Build environment variable name given a field. | `dict "field" "my-password"` | +| `common.utils.secret.getvalue` | Print instructions to get a secret value. | `dict "secret" "secret-name" "field" "secret-value-field" "context" $` | +| `common.utils.getValueFromKey` | Gets a value from `.Values` object given its key path | `dict "key" "path.to.key" "context" $` | +| `common.utils.getKeyFromList` | Returns first `.Values` key with a defined value or first of the list if all non-defined | `dict "keys" (list "path.to.key1" "path.to.key2") "context" $` | + +### Validations + +| Helper identifier | Description | Expected Input | +|--------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| `common.validations.values.single.empty` | Validate a value must not be empty. | `dict "valueKey" "path.to.value" "secret" "secret.name" "field" "my-password" "subchart" "subchart" "context" $` secret, field and subchart are optional. In case they are given, the helper will generate a how to get instruction. See [ValidateValue](#validatevalue) | +| `common.validations.values.multiple.empty` | Validate a multiple values must not be empty. It returns a shared error for all the values. | `dict "required" (list $validateValueConf00 $validateValueConf01) "context" $`. See [ValidateValue](#validatevalue) | +| `common.validations.values.mariadb.passwords` | This helper will ensure required password for MariaDB are not empty. It returns a shared error for all the values. | `dict "secret" "mariadb-secret" "subchart" "true" "context" $` subchart field is optional and could be true or false it depends on where you will use mariadb chart and the helper. | +| `common.validations.values.mysql.passwords` | This helper will ensure required password for MySQL are not empty. It returns a shared error for all the values. | `dict "secret" "mysql-secret" "subchart" "true" "context" $` subchart field is optional and could be true or false it depends on where you will use mysql chart and the helper. | +| `common.validations.values.postgresql.passwords` | This helper will ensure required password for PostgreSQL are not empty. It returns a shared error for all the values. | `dict "secret" "postgresql-secret" "subchart" "true" "context" $` subchart field is optional and could be true or false it depends on where you will use postgresql chart and the helper. | +| `common.validations.values.redis.passwords` | This helper will ensure required password for Redis® are not empty. It returns a shared error for all the values. | `dict "secret" "redis-secret" "subchart" "true" "context" $` subchart field is optional and could be true or false it depends on where you will use redis chart and the helper. | +| `common.validations.values.cassandra.passwords` | This helper will ensure required password for Cassandra are not empty. It returns a shared error for all the values. | `dict "secret" "cassandra-secret" "subchart" "true" "context" $` subchart field is optional and could be true or false it depends on where you will use cassandra chart and the helper. | +| `common.validations.values.mongodb.passwords` | This helper will ensure required password for MongoDB® are not empty. It returns a shared error for all the values. | `dict "secret" "mongodb-secret" "subchart" "true" "context" $` subchart field is optional and could be true or false it depends on where you will use mongodb chart and the helper. | + +### Warnings + +| Helper identifier | Description | Expected Input | +|------------------------------|----------------------------------|------------------------------------------------------------| +| `common.warnings.rollingTag` | Warning about using rolling tag. | `ImageRoot` see [ImageRoot](#imageroot) for the structure. | + +## Special input schemas + +### ImageRoot + +```yaml +registry: + type: string + description: Docker registry where the image is located + example: docker.io + +repository: + type: string + description: Repository and image name + example: bitnami/nginx + +tag: + type: string + description: image tag + example: 1.16.1-debian-10-r63 + +pullPolicy: + type: string + description: Specify a imagePullPolicy. Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + +pullSecrets: + type: array + items: + type: string + description: Optionally specify an array of imagePullSecrets (evaluated as templates). + +debug: + type: boolean + description: Set to true if you would like to see extra information on logs + example: false + +## An instance would be: +# registry: docker.io +# repository: bitnami/nginx +# tag: 1.16.1-debian-10-r63 +# pullPolicy: IfNotPresent +# debug: false +``` + +### Persistence + +```yaml +enabled: + type: boolean + description: Whether enable persistence. + example: true + +storageClass: + type: string + description: Ghost data Persistent Volume Storage Class, If set to "-", storageClassName: "" which disables dynamic provisioning. + example: "-" + +accessMode: + type: string + description: Access mode for the Persistent Volume Storage. + example: ReadWriteOnce + +size: + type: string + description: Size the Persistent Volume Storage. + example: 8Gi + +path: + type: string + description: Path to be persisted. + example: /bitnami + +## An instance would be: +# enabled: true +# storageClass: "-" +# accessMode: ReadWriteOnce +# size: 8Gi +# path: /bitnami +``` + +### ExistingSecret + +```yaml +name: + type: string + description: Name of the existing secret. + example: mySecret +keyMapping: + description: Mapping between the expected key name and the name of the key in the existing secret. + type: object + +## An instance would be: +# name: mySecret +# keyMapping: +# password: myPasswordKey +``` + +#### Example of use + +When we store sensitive data for a deployment in a secret, some times we want to give to users the possibility of using theirs existing secrets. + +```yaml +# templates/secret.yaml +--- +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "common.names.fullname" . }} + labels: + app: {{ include "common.names.fullname" . }} +type: Opaque +data: + password: {{ .Values.password | b64enc | quote }} + +# templates/dpl.yaml +--- +... + env: + - name: PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "common.secrets.name" (dict "existingSecret" .Values.existingSecret "context" $) }} + key: {{ include "common.secrets.key" (dict "existingSecret" .Values.existingSecret "key" "password") }} +... + +# values.yaml +--- +name: mySecret +keyMapping: + password: myPasswordKey +``` + +### ValidateValue + +#### NOTES.txt + +```console +{{- $validateValueConf00 := (dict "valueKey" "path.to.value00" "secret" "secretName" "field" "password-00") -}} +{{- $validateValueConf01 := (dict "valueKey" "path.to.value01" "secret" "secretName" "field" "password-01") -}} + +{{ include "common.validations.values.multiple.empty" (dict "required" (list $validateValueConf00 $validateValueConf01) "context" $) }} +``` + +If we force those values to be empty we will see some alerts + +```console +$ helm install test mychart --set path.to.value00="",path.to.value01="" + 'path.to.value00' must not be empty, please add '--set path.to.value00=$PASSWORD_00' to the command. To get the current value: + + export PASSWORD_00=$(kubectl get secret --namespace default secretName -o jsonpath="{.data.password-00}" | base64 -d) + + 'path.to.value01' must not be empty, please add '--set path.to.value01=$PASSWORD_01' to the command. To get the current value: + + export PASSWORD_01=$(kubectl get secret --namespace default secretName -o jsonpath="{.data.password-01}" | base64 -d) +``` + +## Upgrading + +### To 1.0.0 + +[On November 13, 2020, Helm v2 support was formally finished](https://github.com/helm/charts#status-of-the-project), this major version is the result of the required changes applied to the Helm Chart to be able to incorporate the different features added in Helm v3 and to be consistent with the Helm project itself regarding the Helm v2 EOL. + +**What changes were introduced in this major version?** + +- Previous versions of this Helm Chart use `apiVersion: v1` (installable by both Helm 2 and 3), this Helm Chart was updated to `apiVersion: v2` (installable by Helm 3 only). [Here](https://helm.sh/docs/topics/charts/#the-apiversion-field) you can find more information about the `apiVersion` field. +- Use `type: library`. [Here](https://v3.helm.sh/docs/faq/#library-chart-support) you can find more information. +- The different fields present in the *Chart.yaml* file has been ordered alphabetically in a homogeneous way for all the Bitnami Helm Charts + +**Considerations when upgrading to this version** + +- If you want to upgrade to this version from a previous one installed with Helm v3, you shouldn't face any issues +- If you want to upgrade to this version using Helm v2, this scenario is not supported as this version doesn't support Helm v2 anymore +- If you installed the previous version with Helm v2 and wants to upgrade to this version with Helm v3, please refer to the [official Helm documentation](https://helm.sh/docs/topics/v2_v3_migration/#migration-use-cases) about migrating from Helm v2 to v3 + +**Useful links** + +- https://docs.bitnami.com/tutorials/resolve-helm2-helm3-post-migration-issues/ +- https://helm.sh/docs/topics/v2_v3_migration/ +- https://helm.sh/blog/migrate-from-helm-v2-to-helm-v3/ + +## License + +Copyright © 2022 Bitnami + +Licensed under the Apache License, Version 2.0 (the "License"); +you may not use this file except in compliance with the License. +You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + +Unless required by applicable law or agreed to in writing, software +distributed under the License is distributed on an "AS IS" BASIS, +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +See the License for the specific language governing permissions and +limitations under the License. diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_affinities.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_affinities.tpl new file mode 100644 index 0000000..189ea40 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_affinities.tpl @@ -0,0 +1,102 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Return a soft nodeAffinity definition +{{ include "common.affinities.nodes.soft" (dict "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.nodes.soft" -}} +preferredDuringSchedulingIgnoredDuringExecution: + - preference: + matchExpressions: + - key: {{ .key }} + operator: In + values: + {{- range .values }} + - {{ . | quote }} + {{- end }} + weight: 1 +{{- end -}} + +{{/* +Return a hard nodeAffinity definition +{{ include "common.affinities.nodes.hard" (dict "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.nodes.hard" -}} +requiredDuringSchedulingIgnoredDuringExecution: + nodeSelectorTerms: + - matchExpressions: + - key: {{ .key }} + operator: In + values: + {{- range .values }} + - {{ . | quote }} + {{- end }} +{{- end -}} + +{{/* +Return a nodeAffinity definition +{{ include "common.affinities.nodes" (dict "type" "soft" "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.nodes" -}} + {{- if eq .type "soft" }} + {{- include "common.affinities.nodes.soft" . -}} + {{- else if eq .type "hard" }} + {{- include "common.affinities.nodes.hard" . -}} + {{- end -}} +{{- end -}} + +{{/* +Return a soft podAffinity/podAntiAffinity definition +{{ include "common.affinities.pods.soft" (dict "component" "FOO" "extraMatchLabels" .Values.extraMatchLabels "context" $) -}} +*/}} +{{- define "common.affinities.pods.soft" -}} +{{- $component := default "" .component -}} +{{- $extraMatchLabels := default (dict) .extraMatchLabels -}} +preferredDuringSchedulingIgnoredDuringExecution: + - podAffinityTerm: + labelSelector: + matchLabels: {{- (include "common.labels.matchLabels" .context) | nindent 10 }} + {{- if not (empty $component) }} + {{ printf "app.kubernetes.io/component: %s" $component }} + {{- end }} + {{- range $key, $value := $extraMatchLabels }} + {{ $key }}: {{ $value | quote }} + {{- end }} + namespaces: + - {{ .context.Release.Namespace | quote }} + topologyKey: kubernetes.io/hostname + weight: 1 +{{- end -}} + +{{/* +Return a hard podAffinity/podAntiAffinity definition +{{ include "common.affinities.pods.hard" (dict "component" "FOO" "extraMatchLabels" .Values.extraMatchLabels "context" $) -}} +*/}} +{{- define "common.affinities.pods.hard" -}} +{{- $component := default "" .component -}} +{{- $extraMatchLabels := default (dict) .extraMatchLabels -}} +requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: {{- (include "common.labels.matchLabels" .context) | nindent 8 }} + {{- if not (empty $component) }} + {{ printf "app.kubernetes.io/component: %s" $component }} + {{- end }} + {{- range $key, $value := $extraMatchLabels }} + {{ $key }}: {{ $value | quote }} + {{- end }} + namespaces: + - {{ .context.Release.Namespace | quote }} + topologyKey: kubernetes.io/hostname +{{- end -}} + +{{/* +Return a podAffinity/podAntiAffinity definition +{{ include "common.affinities.pods" (dict "type" "soft" "key" "FOO" "values" (list "BAR" "BAZ")) -}} +*/}} +{{- define "common.affinities.pods" -}} + {{- if eq .type "soft" }} + {{- include "common.affinities.pods.soft" . -}} + {{- else if eq .type "hard" }} + {{- include "common.affinities.pods.hard" . -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_capabilities.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_capabilities.tpl new file mode 100644 index 0000000..9d9b760 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_capabilities.tpl @@ -0,0 +1,154 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Return the target Kubernetes version +*/}} +{{- define "common.capabilities.kubeVersion" -}} +{{- if .Values.global }} + {{- if .Values.global.kubeVersion }} + {{- .Values.global.kubeVersion -}} + {{- else }} + {{- default .Capabilities.KubeVersion.Version .Values.kubeVersion -}} + {{- end -}} +{{- else }} +{{- default .Capabilities.KubeVersion.Version .Values.kubeVersion -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for poddisruptionbudget. +*/}} +{{- define "common.capabilities.policy.apiVersion" -}} +{{- if semverCompare "<1.21-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "policy/v1beta1" -}} +{{- else -}} +{{- print "policy/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for networkpolicy. +*/}} +{{- define "common.capabilities.networkPolicy.apiVersion" -}} +{{- if semverCompare "<1.7-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for cronjob. +*/}} +{{- define "common.capabilities.cronjob.apiVersion" -}} +{{- if semverCompare "<1.21-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "batch/v1beta1" -}} +{{- else -}} +{{- print "batch/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for deployment. +*/}} +{{- define "common.capabilities.deployment.apiVersion" -}} +{{- if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else -}} +{{- print "apps/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for statefulset. +*/}} +{{- define "common.capabilities.statefulset.apiVersion" -}} +{{- if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "apps/v1beta1" -}} +{{- else -}} +{{- print "apps/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "common.capabilities.ingress.apiVersion" -}} +{{- if .Values.ingress -}} +{{- if .Values.ingress.apiVersion -}} +{{- .Values.ingress.apiVersion -}} +{{- else if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else if semverCompare "<1.19-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "networking.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end }} +{{- else if semverCompare "<1.14-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "extensions/v1beta1" -}} +{{- else if semverCompare "<1.19-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "networking.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for RBAC resources. +*/}} +{{- define "common.capabilities.rbac.apiVersion" -}} +{{- if semverCompare "<1.17-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "rbac.authorization.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "rbac.authorization.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for CRDs. +*/}} +{{- define "common.capabilities.crd.apiVersion" -}} +{{- if semverCompare "<1.19-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "apiextensions.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "apiextensions.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for APIService. +*/}} +{{- define "common.capabilities.apiService.apiVersion" -}} +{{- if semverCompare "<1.10-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "apiregistration.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "apiregistration.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for Horizontal Pod Autoscaler. +*/}} +{{- define "common.capabilities.hpa.apiVersion" -}} +{{- if semverCompare "<1.23-0" (include "common.capabilities.kubeVersion" .context) -}} +{{- if .beta2 -}} +{{- print "autoscaling/v2beta2" -}} +{{- else -}} +{{- print "autoscaling/v2beta1" -}} +{{- end -}} +{{- else -}} +{{- print "autoscaling/v2" -}} +{{- end -}} +{{- end -}} + +{{/* +Returns true if the used Helm version is 3.3+. +A way to check the used Helm version was not introduced until version 3.3.0 with .Capabilities.HelmVersion, which contains an additional "{}}" structure. +This check is introduced as a regexMatch instead of {{ if .Capabilities.HelmVersion }} because checking for the key HelmVersion in <3.3 results in a "interface not found" error. +**To be removed when the catalog's minimun Helm version is 3.3** +*/}} +{{- define "common.capabilities.supportsHelmVersion" -}} +{{- if regexMatch "{(v[0-9])*[^}]*}}$" (.Capabilities | toString ) }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_errors.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_errors.tpl new file mode 100644 index 0000000..a79cc2e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_errors.tpl @@ -0,0 +1,23 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Through error when upgrading using empty passwords values that must not be empty. + +Usage: +{{- $validationError00 := include "common.validations.values.single.empty" (dict "valueKey" "path.to.password00" "secret" "secretName" "field" "password-00") -}} +{{- $validationError01 := include "common.validations.values.single.empty" (dict "valueKey" "path.to.password01" "secret" "secretName" "field" "password-01") -}} +{{ include "common.errors.upgrade.passwords.empty" (dict "validationErrors" (list $validationError00 $validationError01) "context" $) }} + +Required password params: + - validationErrors - String - Required. List of validation strings to be return, if it is empty it won't throw error. + - context - Context - Required. Parent context. +*/}} +{{- define "common.errors.upgrade.passwords.empty" -}} + {{- $validationErrors := join "" .validationErrors -}} + {{- if and $validationErrors .context.Release.IsUpgrade -}} + {{- $errorString := "\nPASSWORDS ERROR: You must provide your current passwords when upgrading the release." -}} + {{- $errorString = print $errorString "\n Note that even after reinstallation, old credentials may be needed as they may be kept in persistent volume claims." -}} + {{- $errorString = print $errorString "\n Further information can be obtained at https://docs.bitnami.com/general/how-to/troubleshoot-helm-chart-issues/#credential-errors-while-upgrading-chart-releases" -}} + {{- $errorString = print $errorString "\n%s" -}} + {{- printf $errorString $validationErrors | fail -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_images.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_images.tpl new file mode 100644 index 0000000..42ffbc7 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_images.tpl @@ -0,0 +1,75 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Return the proper image name +{{ include "common.images.image" ( dict "imageRoot" .Values.path.to.the.image "global" $) }} +*/}} +{{- define "common.images.image" -}} +{{- $registryName := .imageRoot.registry -}} +{{- $repositoryName := .imageRoot.repository -}} +{{- $tag := .imageRoot.tag | toString -}} +{{- if .global }} + {{- if .global.imageRegistry }} + {{- $registryName = .global.imageRegistry -}} + {{- end -}} +{{- end -}} +{{- if $registryName }} +{{- printf "%s/%s:%s" $registryName $repositoryName $tag -}} +{{- else -}} +{{- printf "%s:%s" $repositoryName $tag -}} +{{- end -}} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names (deprecated: use common.images.renderPullSecrets instead) +{{ include "common.images.pullSecrets" ( dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "global" .Values.global) }} +*/}} +{{- define "common.images.pullSecrets" -}} + {{- $pullSecrets := list }} + + {{- if .global }} + {{- range .global.imagePullSecrets -}} + {{- $pullSecrets = append $pullSecrets . -}} + {{- end -}} + {{- end -}} + + {{- range .images -}} + {{- range .pullSecrets -}} + {{- $pullSecrets = append $pullSecrets . -}} + {{- end -}} + {{- end -}} + + {{- if (not (empty $pullSecrets)) }} +imagePullSecrets: + {{- range $pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names evaluating values as templates +{{ include "common.images.renderPullSecrets" ( dict "images" (list .Values.path.to.the.image1, .Values.path.to.the.image2) "context" $) }} +*/}} +{{- define "common.images.renderPullSecrets" -}} + {{- $pullSecrets := list }} + {{- $context := .context }} + + {{- if $context.Values.global }} + {{- range $context.Values.global.imagePullSecrets -}} + {{- $pullSecrets = append $pullSecrets (include "common.tplvalues.render" (dict "value" . "context" $context)) -}} + {{- end -}} + {{- end -}} + + {{- range .images -}} + {{- range .pullSecrets -}} + {{- $pullSecrets = append $pullSecrets (include "common.tplvalues.render" (dict "value" . "context" $context)) -}} + {{- end -}} + {{- end -}} + + {{- if (not (empty $pullSecrets)) }} +imagePullSecrets: + {{- range $pullSecrets }} + - name: {{ . }} + {{- end }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_ingress.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_ingress.tpl new file mode 100644 index 0000000..8caf73a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_ingress.tpl @@ -0,0 +1,68 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Generate backend entry that is compatible with all Kubernetes API versions. + +Usage: +{{ include "common.ingress.backend" (dict "serviceName" "backendName" "servicePort" "backendPort" "context" $) }} + +Params: + - serviceName - String. Name of an existing service backend + - servicePort - String/Int. Port name (or number) of the service. It will be translated to different yaml depending if it is a string or an integer. + - context - Dict - Required. The context for the template evaluation. +*/}} +{{- define "common.ingress.backend" -}} +{{- $apiVersion := (include "common.capabilities.ingress.apiVersion" .context) -}} +{{- if or (eq $apiVersion "extensions/v1beta1") (eq $apiVersion "networking.k8s.io/v1beta1") -}} +serviceName: {{ .serviceName }} +servicePort: {{ .servicePort }} +{{- else -}} +service: + name: {{ .serviceName }} + port: + {{- if typeIs "string" .servicePort }} + name: {{ .servicePort }} + {{- else if or (typeIs "int" .servicePort) (typeIs "float64" .servicePort) }} + number: {{ .servicePort | int }} + {{- end }} +{{- end -}} +{{- end -}} + +{{/* +Print "true" if the API pathType field is supported +Usage: +{{ include "common.ingress.supportsPathType" . }} +*/}} +{{- define "common.ingress.supportsPathType" -}} +{{- if (semverCompare "<1.18-0" (include "common.capabilities.kubeVersion" .)) -}} +{{- print "false" -}} +{{- else -}} +{{- print "true" -}} +{{- end -}} +{{- end -}} + +{{/* +Returns true if the ingressClassname field is supported +Usage: +{{ include "common.ingress.supportsIngressClassname" . }} +*/}} +{{- define "common.ingress.supportsIngressClassname" -}} +{{- if semverCompare "<1.18-0" (include "common.capabilities.kubeVersion" .) -}} +{{- print "false" -}} +{{- else -}} +{{- print "true" -}} +{{- end -}} +{{- end -}} + +{{/* +Return true if cert-manager required annotations for TLS signed +certificates are set in the Ingress annotations +Ref: https://cert-manager.io/docs/usage/ingress/#supported-annotations +Usage: +{{ include "common.ingress.certManagerRequest" ( dict "annotations" .Values.path.to.the.ingress.annotations ) }} +*/}} +{{- define "common.ingress.certManagerRequest" -}} +{{ if or (hasKey .annotations "cert-manager.io/cluster-issuer") (hasKey .annotations "cert-manager.io/issuer") }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_labels.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_labels.tpl new file mode 100644 index 0000000..252066c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_labels.tpl @@ -0,0 +1,18 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Kubernetes standard labels +*/}} +{{- define "common.labels.standard" -}} +app.kubernetes.io/name: {{ include "common.names.name" . }} +helm.sh/chart: {{ include "common.names.chart" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end -}} + +{{/* +Labels to use on deploy.spec.selector.matchLabels and svc.spec.selector +*/}} +{{- define "common.labels.matchLabels" -}} +app.kubernetes.io/name: {{ include "common.names.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_names.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_names.tpl new file mode 100644 index 0000000..1bdac8b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_names.tpl @@ -0,0 +1,70 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "common.names.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "common.names.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "common.names.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Create a default fully qualified dependency name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +Usage: +{{ include "common.names.dependency.fullname" (dict "chartName" "dependency-chart-name" "chartValues" .Values.dependency-chart "context" $) }} +*/}} +{{- define "common.names.dependency.fullname" -}} +{{- if .chartValues.fullnameOverride -}} +{{- .chartValues.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .chartName .chartValues.nameOverride -}} +{{- if contains $name .context.Release.Name -}} +{{- .context.Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .context.Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Allow the release namespace to be overridden for multi-namespace deployments in combined charts. +*/}} +{{- define "common.names.namespace" -}} +{{- if .Values.namespaceOverride -}} +{{- .Values.namespaceOverride -}} +{{- else -}} +{{- .Release.Namespace -}} +{{- end -}} +{{- end -}} + +{{/* +Create a fully qualified app name adding the installation's namespace. +*/}} +{{- define "common.names.fullname.namespace" -}} +{{- printf "%s-%s" (include "common.names.fullname" .) (include "common.names.namespace" .) | trunc 63 | trimSuffix "-" -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_secrets.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_secrets.tpl new file mode 100644 index 0000000..a53fb44 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_secrets.tpl @@ -0,0 +1,140 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Generate secret name. + +Usage: +{{ include "common.secrets.name" (dict "existingSecret" .Values.path.to.the.existingSecret "defaultNameSuffix" "mySuffix" "context" $) }} + +Params: + - existingSecret - ExistingSecret/String - Optional. The path to the existing secrets in the values.yaml given by the user + to be used instead of the default one. Allows for it to be of type String (just the secret name) for backwards compatibility. + +info: https://github.com/bitnami/charts/tree/master/bitnami/common#existingsecret + - defaultNameSuffix - String - Optional. It is used only if we have several secrets in the same deployment. + - context - Dict - Required. The context for the template evaluation. +*/}} +{{- define "common.secrets.name" -}} +{{- $name := (include "common.names.fullname" .context) -}} + +{{- if .defaultNameSuffix -}} +{{- $name = printf "%s-%s" $name .defaultNameSuffix | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{- with .existingSecret -}} +{{- if not (typeIs "string" .) -}} +{{- with .name -}} +{{- $name = . -}} +{{- end -}} +{{- else -}} +{{- $name = . -}} +{{- end -}} +{{- end -}} + +{{- printf "%s" $name -}} +{{- end -}} + +{{/* +Generate secret key. + +Usage: +{{ include "common.secrets.key" (dict "existingSecret" .Values.path.to.the.existingSecret "key" "keyName") }} + +Params: + - existingSecret - ExistingSecret/String - Optional. The path to the existing secrets in the values.yaml given by the user + to be used instead of the default one. Allows for it to be of type String (just the secret name) for backwards compatibility. + +info: https://github.com/bitnami/charts/tree/master/bitnami/common#existingsecret + - key - String - Required. Name of the key in the secret. +*/}} +{{- define "common.secrets.key" -}} +{{- $key := .key -}} + +{{- if .existingSecret -}} + {{- if not (typeIs "string" .existingSecret) -}} + {{- if .existingSecret.keyMapping -}} + {{- $key = index .existingSecret.keyMapping $.key -}} + {{- end -}} + {{- end }} +{{- end -}} + +{{- printf "%s" $key -}} +{{- end -}} + +{{/* +Generate secret password or retrieve one if already created. + +Usage: +{{ include "common.secrets.passwords.manage" (dict "secret" "secret-name" "key" "keyName" "providedValues" (list "path.to.password1" "path.to.password2") "length" 10 "strong" false "chartName" "chartName" "context" $) }} + +Params: + - secret - String - Required - Name of the 'Secret' resource where the password is stored. + - key - String - Required - Name of the key in the secret. + - providedValues - List - Required - The path to the validating value in the values.yaml, e.g: "mysql.password". Will pick first parameter with a defined value. + - length - int - Optional - Length of the generated random password. + - strong - Boolean - Optional - Whether to add symbols to the generated random password. + - chartName - String - Optional - Name of the chart used when said chart is deployed as a subchart. + - context - Context - Required - Parent context. + +The order in which this function returns a secret password: + 1. Already existing 'Secret' resource + (If a 'Secret' resource is found under the name provided to the 'secret' parameter to this function and that 'Secret' resource contains a key with the name passed as the 'key' parameter to this function then the value of this existing secret password will be returned) + 2. Password provided via the values.yaml + (If one of the keys passed to the 'providedValues' parameter to this function is a valid path to a key in the values.yaml and has a value, the value of the first key with a value will be returned) + 3. Randomly generated secret password + (A new random secret password with the length specified in the 'length' parameter will be generated and returned) + +*/}} +{{- define "common.secrets.passwords.manage" -}} + +{{- $password := "" }} +{{- $subchart := "" }} +{{- $chartName := default "" .chartName }} +{{- $passwordLength := default 10 .length }} +{{- $providedPasswordKey := include "common.utils.getKeyFromList" (dict "keys" .providedValues "context" $.context) }} +{{- $providedPasswordValue := include "common.utils.getValueFromKey" (dict "key" $providedPasswordKey "context" $.context) }} +{{- $secretData := (lookup "v1" "Secret" $.context.Release.Namespace .secret).data }} +{{- if $secretData }} + {{- if hasKey $secretData .key }} + {{- $password = index $secretData .key }} + {{- else }} + {{- printf "\nPASSWORDS ERROR: The secret \"%s\" does not contain the key \"%s\"\n" .secret .key | fail -}} + {{- end -}} +{{- else if $providedPasswordValue }} + {{- $password = $providedPasswordValue | toString | b64enc | quote }} +{{- else }} + + {{- if .context.Values.enabled }} + {{- $subchart = $chartName }} + {{- end -}} + + {{- $requiredPassword := dict "valueKey" $providedPasswordKey "secret" .secret "field" .key "subchart" $subchart "context" $.context -}} + {{- $requiredPasswordError := include "common.validations.values.single.empty" $requiredPassword -}} + {{- $passwordValidationErrors := list $requiredPasswordError -}} + {{- include "common.errors.upgrade.passwords.empty" (dict "validationErrors" $passwordValidationErrors "context" $.context) -}} + + {{- if .strong }} + {{- $subStr := list (lower (randAlpha 1)) (randNumeric 1) (upper (randAlpha 1)) | join "_" }} + {{- $password = randAscii $passwordLength }} + {{- $password = regexReplaceAllLiteral "\\W" $password "@" | substr 5 $passwordLength }} + {{- $password = printf "%s%s" $subStr $password | toString | shuffle | b64enc | quote }} + {{- else }} + {{- $password = randAlphaNum $passwordLength | b64enc | quote }} + {{- end }} +{{- end -}} +{{- printf "%s" $password -}} +{{- end -}} + +{{/* +Returns whether a previous generated secret already exists + +Usage: +{{ include "common.secrets.exists" (dict "secret" "secret-name" "context" $) }} + +Params: + - secret - String - Required - Name of the 'Secret' resource where the password is stored. + - context - Context - Required - Parent context. +*/}} +{{- define "common.secrets.exists" -}} +{{- $secret := (lookup "v1" "Secret" $.context.Release.Namespace .secret) }} +{{- if $secret }} + {{- true -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_storage.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_storage.tpl new file mode 100644 index 0000000..60e2a84 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_storage.tpl @@ -0,0 +1,23 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Return the proper Storage Class +{{ include "common.storage.class" ( dict "persistence" .Values.path.to.the.persistence "global" $) }} +*/}} +{{- define "common.storage.class" -}} + +{{- $storageClass := .persistence.storageClass -}} +{{- if .global -}} + {{- if .global.storageClass -}} + {{- $storageClass = .global.storageClass -}} + {{- end -}} +{{- end -}} + +{{- if $storageClass -}} + {{- if (eq "-" $storageClass) -}} + {{- printf "storageClassName: \"\"" -}} + {{- else }} + {{- printf "storageClassName: %s" $storageClass -}} + {{- end -}} +{{- end -}} + +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_tplvalues.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_tplvalues.tpl new file mode 100644 index 0000000..2db1668 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_tplvalues.tpl @@ -0,0 +1,13 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Renders a value that contains template. +Usage: +{{ include "common.tplvalues.render" ( dict "value" .Values.path.to.the.Value "context" $) }} +*/}} +{{- define "common.tplvalues.render" -}} + {{- if typeIs "string" .value }} + {{- tpl .value .context }} + {{- else }} + {{- tpl (.value | toYaml) .context }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_utils.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_utils.tpl new file mode 100644 index 0000000..8c22b2a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_utils.tpl @@ -0,0 +1,62 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Print instructions to get a secret value. +Usage: +{{ include "common.utils.secret.getvalue" (dict "secret" "secret-name" "field" "secret-value-field" "context" $) }} +*/}} +{{- define "common.utils.secret.getvalue" -}} +{{- $varname := include "common.utils.fieldToEnvVar" . -}} +export {{ $varname }}=$(kubectl get secret --namespace {{ .context.Release.Namespace | quote }} {{ .secret }} -o jsonpath="{.data.{{ .field }}}" | base64 -d) +{{- end -}} + +{{/* +Build env var name given a field +Usage: +{{ include "common.utils.fieldToEnvVar" dict "field" "my-password" }} +*/}} +{{- define "common.utils.fieldToEnvVar" -}} + {{- $fieldNameSplit := splitList "-" .field -}} + {{- $upperCaseFieldNameSplit := list -}} + + {{- range $fieldNameSplit -}} + {{- $upperCaseFieldNameSplit = append $upperCaseFieldNameSplit ( upper . ) -}} + {{- end -}} + + {{ join "_" $upperCaseFieldNameSplit }} +{{- end -}} + +{{/* +Gets a value from .Values given +Usage: +{{ include "common.utils.getValueFromKey" (dict "key" "path.to.key" "context" $) }} +*/}} +{{- define "common.utils.getValueFromKey" -}} +{{- $splitKey := splitList "." .key -}} +{{- $value := "" -}} +{{- $latestObj := $.context.Values -}} +{{- range $splitKey -}} + {{- if not $latestObj -}} + {{- printf "please review the entire path of '%s' exists in values" $.key | fail -}} + {{- end -}} + {{- $value = ( index $latestObj . ) -}} + {{- $latestObj = $value -}} +{{- end -}} +{{- printf "%v" (default "" $value) -}} +{{- end -}} + +{{/* +Returns first .Values key with a defined value or first of the list if all non-defined +Usage: +{{ include "common.utils.getKeyFromList" (dict "keys" (list "path.to.key1" "path.to.key2") "context" $) }} +*/}} +{{- define "common.utils.getKeyFromList" -}} +{{- $key := first .keys -}} +{{- $reverseKeys := reverse .keys }} +{{- range $reverseKeys }} + {{- $value := include "common.utils.getValueFromKey" (dict "key" . "context" $.context ) }} + {{- if $value -}} + {{- $key = . }} + {{- end -}} +{{- end -}} +{{- printf "%s" $key -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_warnings.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_warnings.tpl new file mode 100644 index 0000000..ae10fa4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/_warnings.tpl @@ -0,0 +1,14 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Warning about using rolling tag. +Usage: +{{ include "common.warnings.rollingTag" .Values.path.to.the.imageRoot }} +*/}} +{{- define "common.warnings.rollingTag" -}} + +{{- if and (contains "bitnami/" .repository) (not (.tag | toString | regexFind "-r\\d+$|sha256:")) }} +WARNING: Rolling tag detected ({{ .repository }}:{{ .tag }}), please note that it is strongly recommended to avoid using rolling tags in a production environment. ++info https://docs.bitnami.com/containers/how-to/understand-rolling-tags-containers/ +{{- end }} + +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_cassandra.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_cassandra.tpl new file mode 100644 index 0000000..ded1ae3 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_cassandra.tpl @@ -0,0 +1,72 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate Cassandra required passwords are not empty. + +Usage: +{{ include "common.validations.values.cassandra.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where Cassandra values are stored, e.g: "cassandra-passwords-secret" + - subchart - Boolean - Optional. Whether Cassandra is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.cassandra.passwords" -}} + {{- $existingSecret := include "common.cassandra.values.existingSecret" . -}} + {{- $enabled := include "common.cassandra.values.enabled" . -}} + {{- $dbUserPrefix := include "common.cassandra.values.key.dbUser" . -}} + {{- $valueKeyPassword := printf "%s.password" $dbUserPrefix -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "cassandra-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.cassandra.values.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether Cassandra is used as subchart or not. Default: false +*/}} +{{- define "common.cassandra.values.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.cassandra.dbUser.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.dbUser.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled cassandra. + +Usage: +{{ include "common.cassandra.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.cassandra.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.cassandra.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key dbUser + +Usage: +{{ include "common.cassandra.values.key.dbUser" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether Cassandra is used as subchart or not. Default: false +*/}} +{{- define "common.cassandra.values.key.dbUser" -}} + {{- if .subchart -}} + cassandra.dbUser + {{- else -}} + dbUser + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_mariadb.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_mariadb.tpl new file mode 100644 index 0000000..b6906ff --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_mariadb.tpl @@ -0,0 +1,103 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate MariaDB required passwords are not empty. + +Usage: +{{ include "common.validations.values.mariadb.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where MariaDB values are stored, e.g: "mysql-passwords-secret" + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.mariadb.passwords" -}} + {{- $existingSecret := include "common.mariadb.values.auth.existingSecret" . -}} + {{- $enabled := include "common.mariadb.values.enabled" . -}} + {{- $architecture := include "common.mariadb.values.architecture" . -}} + {{- $authPrefix := include "common.mariadb.values.key.auth" . -}} + {{- $valueKeyRootPassword := printf "%s.rootPassword" $authPrefix -}} + {{- $valueKeyUsername := printf "%s.username" $authPrefix -}} + {{- $valueKeyPassword := printf "%s.password" $authPrefix -}} + {{- $valueKeyReplicationPassword := printf "%s.replicationPassword" $authPrefix -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredRootPassword := dict "valueKey" $valueKeyRootPassword "secret" .secret "field" "mariadb-root-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRootPassword -}} + + {{- $valueUsername := include "common.utils.getValueFromKey" (dict "key" $valueKeyUsername "context" .context) }} + {{- if not (empty $valueUsername) -}} + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "mariadb-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + {{- end -}} + + {{- if (eq $architecture "replication") -}} + {{- $requiredReplicationPassword := dict "valueKey" $valueKeyReplicationPassword "secret" .secret "field" "mariadb-replication-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredReplicationPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.mariadb.values.auth.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.mariadb.values.auth.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.mariadb.auth.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.auth.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled mariadb. + +Usage: +{{ include "common.mariadb.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.mariadb.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.mariadb.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for architecture + +Usage: +{{ include "common.mariadb.values.architecture" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.mariadb.values.architecture" -}} + {{- if .subchart -}} + {{- .context.Values.mariadb.architecture -}} + {{- else -}} + {{- .context.Values.architecture -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key auth + +Usage: +{{ include "common.mariadb.values.key.auth" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MariaDB is used as subchart or not. Default: false +*/}} +{{- define "common.mariadb.values.key.auth" -}} + {{- if .subchart -}} + mariadb.auth + {{- else -}} + auth + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_mongodb.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_mongodb.tpl new file mode 100644 index 0000000..f820ec1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_mongodb.tpl @@ -0,0 +1,108 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate MongoDB® required passwords are not empty. + +Usage: +{{ include "common.validations.values.mongodb.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where MongoDB® values are stored, e.g: "mongodb-passwords-secret" + - subchart - Boolean - Optional. Whether MongoDB® is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.mongodb.passwords" -}} + {{- $existingSecret := include "common.mongodb.values.auth.existingSecret" . -}} + {{- $enabled := include "common.mongodb.values.enabled" . -}} + {{- $authPrefix := include "common.mongodb.values.key.auth" . -}} + {{- $architecture := include "common.mongodb.values.architecture" . -}} + {{- $valueKeyRootPassword := printf "%s.rootPassword" $authPrefix -}} + {{- $valueKeyUsername := printf "%s.username" $authPrefix -}} + {{- $valueKeyDatabase := printf "%s.database" $authPrefix -}} + {{- $valueKeyPassword := printf "%s.password" $authPrefix -}} + {{- $valueKeyReplicaSetKey := printf "%s.replicaSetKey" $authPrefix -}} + {{- $valueKeyAuthEnabled := printf "%s.enabled" $authPrefix -}} + + {{- $authEnabled := include "common.utils.getValueFromKey" (dict "key" $valueKeyAuthEnabled "context" .context) -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") (eq $authEnabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredRootPassword := dict "valueKey" $valueKeyRootPassword "secret" .secret "field" "mongodb-root-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRootPassword -}} + + {{- $valueUsername := include "common.utils.getValueFromKey" (dict "key" $valueKeyUsername "context" .context) }} + {{- $valueDatabase := include "common.utils.getValueFromKey" (dict "key" $valueKeyDatabase "context" .context) }} + {{- if and $valueUsername $valueDatabase -}} + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "mongodb-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + {{- end -}} + + {{- if (eq $architecture "replicaset") -}} + {{- $requiredReplicaSetKey := dict "valueKey" $valueKeyReplicaSetKey "secret" .secret "field" "mongodb-replica-set-key" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredReplicaSetKey -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.mongodb.values.auth.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MongoDb is used as subchart or not. Default: false +*/}} +{{- define "common.mongodb.values.auth.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.mongodb.auth.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.auth.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled mongodb. + +Usage: +{{ include "common.mongodb.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.mongodb.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.mongodb.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key auth + +Usage: +{{ include "common.mongodb.values.key.auth" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MongoDB® is used as subchart or not. Default: false +*/}} +{{- define "common.mongodb.values.key.auth" -}} + {{- if .subchart -}} + mongodb.auth + {{- else -}} + auth + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for architecture + +Usage: +{{ include "common.mongodb.values.architecture" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MongoDB® is used as subchart or not. Default: false +*/}} +{{- define "common.mongodb.values.architecture" -}} + {{- if .subchart -}} + {{- .context.Values.mongodb.architecture -}} + {{- else -}} + {{- .context.Values.architecture -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_mysql.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_mysql.tpl new file mode 100644 index 0000000..74472a0 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_mysql.tpl @@ -0,0 +1,103 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate MySQL required passwords are not empty. + +Usage: +{{ include "common.validations.values.mysql.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where MySQL values are stored, e.g: "mysql-passwords-secret" + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.mysql.passwords" -}} + {{- $existingSecret := include "common.mysql.values.auth.existingSecret" . -}} + {{- $enabled := include "common.mysql.values.enabled" . -}} + {{- $architecture := include "common.mysql.values.architecture" . -}} + {{- $authPrefix := include "common.mysql.values.key.auth" . -}} + {{- $valueKeyRootPassword := printf "%s.rootPassword" $authPrefix -}} + {{- $valueKeyUsername := printf "%s.username" $authPrefix -}} + {{- $valueKeyPassword := printf "%s.password" $authPrefix -}} + {{- $valueKeyReplicationPassword := printf "%s.replicationPassword" $authPrefix -}} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $requiredRootPassword := dict "valueKey" $valueKeyRootPassword "secret" .secret "field" "mysql-root-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRootPassword -}} + + {{- $valueUsername := include "common.utils.getValueFromKey" (dict "key" $valueKeyUsername "context" .context) }} + {{- if not (empty $valueUsername) -}} + {{- $requiredPassword := dict "valueKey" $valueKeyPassword "secret" .secret "field" "mysql-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPassword -}} + {{- end -}} + + {{- if (eq $architecture "replication") -}} + {{- $requiredReplicationPassword := dict "valueKey" $valueKeyReplicationPassword "secret" .secret "field" "mysql-replication-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredReplicationPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.mysql.values.auth.existingSecret" (dict "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.mysql.values.auth.existingSecret" -}} + {{- if .subchart -}} + {{- .context.Values.mysql.auth.existingSecret | quote -}} + {{- else -}} + {{- .context.Values.auth.existingSecret | quote -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled mysql. + +Usage: +{{ include "common.mysql.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.mysql.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.mysql.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for architecture + +Usage: +{{ include "common.mysql.values.architecture" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.mysql.values.architecture" -}} + {{- if .subchart -}} + {{- .context.Values.mysql.architecture -}} + {{- else -}} + {{- .context.Values.architecture -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key auth + +Usage: +{{ include "common.mysql.values.key.auth" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether MySQL is used as subchart or not. Default: false +*/}} +{{- define "common.mysql.values.key.auth" -}} + {{- if .subchart -}} + mysql.auth + {{- else -}} + auth + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_postgresql.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_postgresql.tpl new file mode 100644 index 0000000..164ec0d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_postgresql.tpl @@ -0,0 +1,129 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate PostgreSQL required passwords are not empty. + +Usage: +{{ include "common.validations.values.postgresql.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where postgresql values are stored, e.g: "postgresql-passwords-secret" + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.postgresql.passwords" -}} + {{- $existingSecret := include "common.postgresql.values.existingSecret" . -}} + {{- $enabled := include "common.postgresql.values.enabled" . -}} + {{- $valueKeyPostgresqlPassword := include "common.postgresql.values.key.postgressPassword" . -}} + {{- $valueKeyPostgresqlReplicationEnabled := include "common.postgresql.values.key.replicationPassword" . -}} + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + {{- $requiredPostgresqlPassword := dict "valueKey" $valueKeyPostgresqlPassword "secret" .secret "field" "postgresql-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPostgresqlPassword -}} + + {{- $enabledReplication := include "common.postgresql.values.enabled.replication" . -}} + {{- if (eq $enabledReplication "true") -}} + {{- $requiredPostgresqlReplicationPassword := dict "valueKey" $valueKeyPostgresqlReplicationEnabled "secret" .secret "field" "postgresql-replication-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredPostgresqlReplicationPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to decide whether evaluate global values. + +Usage: +{{ include "common.postgresql.values.use.global" (dict "key" "key-of-global" "context" $) }} +Params: + - key - String - Required. Field to be evaluated within global, e.g: "existingSecret" +*/}} +{{- define "common.postgresql.values.use.global" -}} + {{- if .context.Values.global -}} + {{- if .context.Values.global.postgresql -}} + {{- index .context.Values.global.postgresql .key | quote -}} + {{- end -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for existingSecret. + +Usage: +{{ include "common.postgresql.values.existingSecret" (dict "context" $) }} +*/}} +{{- define "common.postgresql.values.existingSecret" -}} + {{- $globalValue := include "common.postgresql.values.use.global" (dict "key" "existingSecret" "context" .context) -}} + + {{- if .subchart -}} + {{- default (.context.Values.postgresql.existingSecret | quote) $globalValue -}} + {{- else -}} + {{- default (.context.Values.existingSecret | quote) $globalValue -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled postgresql. + +Usage: +{{ include "common.postgresql.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.postgresql.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.postgresql.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key postgressPassword. + +Usage: +{{ include "common.postgresql.values.key.postgressPassword" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.postgresql.values.key.postgressPassword" -}} + {{- $globalValue := include "common.postgresql.values.use.global" (dict "key" "postgresqlUsername" "context" .context) -}} + + {{- if not $globalValue -}} + {{- if .subchart -}} + postgresql.postgresqlPassword + {{- else -}} + postgresqlPassword + {{- end -}} + {{- else -}} + global.postgresql.postgresqlPassword + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled.replication. + +Usage: +{{ include "common.postgresql.values.enabled.replication" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.postgresql.values.enabled.replication" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.postgresql.replication.enabled -}} + {{- else -}} + {{- printf "%v" .context.Values.replication.enabled -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for the key replication.password. + +Usage: +{{ include "common.postgresql.values.key.replicationPassword" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether postgresql is used as subchart or not. Default: false +*/}} +{{- define "common.postgresql.values.key.replicationPassword" -}} + {{- if .subchart -}} + postgresql.replication.password + {{- else -}} + replication.password + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_redis.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_redis.tpl new file mode 100644 index 0000000..dcccfc1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_redis.tpl @@ -0,0 +1,76 @@ + +{{/* vim: set filetype=mustache: */}} +{{/* +Validate Redis® required passwords are not empty. + +Usage: +{{ include "common.validations.values.redis.passwords" (dict "secret" "secretName" "subchart" false "context" $) }} +Params: + - secret - String - Required. Name of the secret where redis values are stored, e.g: "redis-passwords-secret" + - subchart - Boolean - Optional. Whether redis is used as subchart or not. Default: false +*/}} +{{- define "common.validations.values.redis.passwords" -}} + {{- $enabled := include "common.redis.values.enabled" . -}} + {{- $valueKeyPrefix := include "common.redis.values.keys.prefix" . -}} + {{- $standarizedVersion := include "common.redis.values.standarized.version" . }} + + {{- $existingSecret := ternary (printf "%s%s" $valueKeyPrefix "auth.existingSecret") (printf "%s%s" $valueKeyPrefix "existingSecret") (eq $standarizedVersion "true") }} + {{- $existingSecretValue := include "common.utils.getValueFromKey" (dict "key" $existingSecret "context" .context) }} + + {{- $valueKeyRedisPassword := ternary (printf "%s%s" $valueKeyPrefix "auth.password") (printf "%s%s" $valueKeyPrefix "password") (eq $standarizedVersion "true") }} + {{- $valueKeyRedisUseAuth := ternary (printf "%s%s" $valueKeyPrefix "auth.enabled") (printf "%s%s" $valueKeyPrefix "usePassword") (eq $standarizedVersion "true") }} + + {{- if and (or (not $existingSecret) (eq $existingSecret "\"\"")) (eq $enabled "true") -}} + {{- $requiredPasswords := list -}} + + {{- $useAuth := include "common.utils.getValueFromKey" (dict "key" $valueKeyRedisUseAuth "context" .context) -}} + {{- if eq $useAuth "true" -}} + {{- $requiredRedisPassword := dict "valueKey" $valueKeyRedisPassword "secret" .secret "field" "redis-password" -}} + {{- $requiredPasswords = append $requiredPasswords $requiredRedisPassword -}} + {{- end -}} + + {{- include "common.validations.values.multiple.empty" (dict "required" $requiredPasswords "context" .context) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right value for enabled redis. + +Usage: +{{ include "common.redis.values.enabled" (dict "context" $) }} +*/}} +{{- define "common.redis.values.enabled" -}} + {{- if .subchart -}} + {{- printf "%v" .context.Values.redis.enabled -}} + {{- else -}} + {{- printf "%v" (not .context.Values.enabled) -}} + {{- end -}} +{{- end -}} + +{{/* +Auxiliary function to get the right prefix path for the values + +Usage: +{{ include "common.redis.values.key.prefix" (dict "subchart" "true" "context" $) }} +Params: + - subchart - Boolean - Optional. Whether redis is used as subchart or not. Default: false +*/}} +{{- define "common.redis.values.keys.prefix" -}} + {{- if .subchart -}}redis.{{- else -}}{{- end -}} +{{- end -}} + +{{/* +Checks whether the redis chart's includes the standarizations (version >= 14) + +Usage: +{{ include "common.redis.values.standarized.version" (dict "context" $) }} +*/}} +{{- define "common.redis.values.standarized.version" -}} + + {{- $standarizedAuth := printf "%s%s" (include "common.redis.values.keys.prefix" .) "auth" -}} + {{- $standarizedAuthValues := include "common.utils.getValueFromKey" (dict "key" $standarizedAuth "context" .context) }} + + {{- if $standarizedAuthValues -}} + {{- true -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_validations.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_validations.tpl new file mode 100644 index 0000000..9a814cf --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/templates/validations/_validations.tpl @@ -0,0 +1,46 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Validate values must not be empty. + +Usage: +{{- $validateValueConf00 := (dict "valueKey" "path.to.value" "secret" "secretName" "field" "password-00") -}} +{{- $validateValueConf01 := (dict "valueKey" "path.to.value" "secret" "secretName" "field" "password-01") -}} +{{ include "common.validations.values.empty" (dict "required" (list $validateValueConf00 $validateValueConf01) "context" $) }} + +Validate value params: + - valueKey - String - Required. The path to the validating value in the values.yaml, e.g: "mysql.password" + - secret - String - Optional. Name of the secret where the validating value is generated/stored, e.g: "mysql-passwords-secret" + - field - String - Optional. Name of the field in the secret data, e.g: "mysql-password" +*/}} +{{- define "common.validations.values.multiple.empty" -}} + {{- range .required -}} + {{- include "common.validations.values.single.empty" (dict "valueKey" .valueKey "secret" .secret "field" .field "context" $.context) -}} + {{- end -}} +{{- end -}} + +{{/* +Validate a value must not be empty. + +Usage: +{{ include "common.validations.value.empty" (dict "valueKey" "mariadb.password" "secret" "secretName" "field" "my-password" "subchart" "subchart" "context" $) }} + +Validate value params: + - valueKey - String - Required. The path to the validating value in the values.yaml, e.g: "mysql.password" + - secret - String - Optional. Name of the secret where the validating value is generated/stored, e.g: "mysql-passwords-secret" + - field - String - Optional. Name of the field in the secret data, e.g: "mysql-password" + - subchart - String - Optional - Name of the subchart that the validated password is part of. +*/}} +{{- define "common.validations.values.single.empty" -}} + {{- $value := include "common.utils.getValueFromKey" (dict "key" .valueKey "context" .context) }} + {{- $subchart := ternary "" (printf "%s." .subchart) (empty .subchart) }} + + {{- if not $value -}} + {{- $varname := "my-value" -}} + {{- $getCurrentValue := "" -}} + {{- if and .secret .field -}} + {{- $varname = include "common.utils.fieldToEnvVar" . -}} + {{- $getCurrentValue = printf " To get the current value:\n\n %s\n" (include "common.utils.secret.getvalue" .) -}} + {{- end -}} + {{- printf "\n '%s' must not be empty, please add '--set %s%s=$%s' to the command.%s" .valueKey $subchart .valueKey $varname $getCurrentValue -}} + {{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/values.yaml new file mode 100644 index 0000000..f2df68e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/charts/common/values.yaml @@ -0,0 +1,5 @@ +## bitnami/common +## It is required by CI/CD tools and processes. +## @skip exampleValue +## +exampleValue: common-chart diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/img/redis-cluster-topology.png b/observability/lgtm-distributed/charts/oncall/charts/redis/img/redis-cluster-topology.png new file mode 100644 index 0000000..f0a02a9 Binary files /dev/null and b/observability/lgtm-distributed/charts/oncall/charts/redis/img/redis-cluster-topology.png differ diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/img/redis-topology.png b/observability/lgtm-distributed/charts/oncall/charts/redis/img/redis-topology.png new file mode 100644 index 0000000..3f5280f Binary files /dev/null and b/observability/lgtm-distributed/charts/oncall/charts/redis/img/redis-topology.png differ diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/NOTES.txt new file mode 100644 index 0000000..2623ade --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/NOTES.txt @@ -0,0 +1,191 @@ +CHART NAME: {{ .Chart.Name }} +CHART VERSION: {{ .Chart.Version }} +APP VERSION: {{ .Chart.AppVersion }} + +** Please be patient while the chart is being deployed ** + +{{- if .Values.diagnosticMode.enabled }} +The chart has been deployed in diagnostic mode. All probes have been disabled and the command has been overwritten with: + + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 4 }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 4 }} + +Get the list of pods by executing: + + kubectl get pods --namespace {{ .Release.Namespace }} -l app.kubernetes.io/instance={{ .Release.Name }} + +Access the pod you want to debug by executing + + kubectl exec --namespace {{ .Release.Namespace }} -ti -- bash + +In order to replicate the container startup scripts execute this command: + +For Redis: + + /opt/bitnami/scripts/redis/entrypoint.sh /opt/bitnami/scripts/redis/run.sh + +{{- if .Values.sentinel.enabled }} + +For Redis Sentinel: + + /opt/bitnami/scripts/redis-sentinel/entrypoint.sh /opt/bitnami/scripts/redis-sentinel/run.sh + +{{- end }} +{{- else }} + +{{- if contains .Values.master.service.type "LoadBalancer" }} +{{- if not .Values.auth.enabled }} +{{ if and (not .Values.networkPolicy.enabled) (.Values.networkPolicy.allowExternal) }} + +------------------------------------------------------------------------------- + WARNING + + By specifying "master.service.type=LoadBalancer" and "auth.enabled=false" you have + most likely exposed the Redis® service externally without any authentication + mechanism. + + For security reasons, we strongly suggest that you switch to "ClusterIP" or + "NodePort". As alternative, you can also switch to "auth.enabled=true" + providing a valid password on "password" parameter. + +------------------------------------------------------------------------------- +{{- end }} +{{- end }} +{{- end }} + +{{- if eq .Values.architecture "replication" }} +{{- if .Values.sentinel.enabled }} + +Redis® can be accessed via port {{ .Values.sentinel.service.ports.redis }} on the following DNS name from within your cluster: + + {{ template "common.names.fullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }} for read only operations + +For read/write operations, first access the Redis® Sentinel cluster, which is available in port {{ .Values.sentinel.service.ports.sentinel }} using the same domain name above. + +{{- else }} + +Redis® can be accessed on the following DNS names from within your cluster: + + {{ printf "%s-master.%s.svc.%s" (include "common.names.fullname" .) .Release.Namespace .Values.clusterDomain }} for read/write operations (port {{ .Values.master.service.ports.redis }}) + {{ printf "%s-replicas.%s.svc.%s" (include "common.names.fullname" .) .Release.Namespace .Values.clusterDomain }} for read-only operations (port {{ .Values.replica.service.ports.redis }}) + +{{- end }} +{{- else }} + +Redis® can be accessed via port {{ .Values.master.service.ports.redis }} on the following DNS name from within your cluster: + + {{ template "common.names.fullname" . }}-master.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }} + +{{- end }} + +{{ if .Values.auth.enabled }} + +To get your password run: + + export REDIS_PASSWORD=$(kubectl get secret --namespace {{ .Release.Namespace }} {{ template "redis.secretName" . }} -o jsonpath="{.data.redis-password}" | base64 -d) + +{{- end }} + +To connect to your Redis® server: + +1. Run a Redis® pod that you can use as a client: + + kubectl run --namespace {{ .Release.Namespace }} redis-client --restart='Never' {{ if .Values.auth.enabled }} --env REDIS_PASSWORD=$REDIS_PASSWORD {{ end }} --image {{ template "redis.image" . }} --command -- sleep infinity + +{{- if .Values.tls.enabled }} + + Copy your TLS certificates to the pod: + + kubectl cp --namespace {{ .Release.Namespace }} /path/to/client.cert redis-client:/tmp/client.cert + kubectl cp --namespace {{ .Release.Namespace }} /path/to/client.key redis-client:/tmp/client.key + kubectl cp --namespace {{ .Release.Namespace }} /path/to/CA.cert redis-client:/tmp/CA.cert + +{{- end }} + + Use the following command to attach to the pod: + + kubectl exec --tty -i redis-client \ + {{- if and (.Values.networkPolicy.enabled) (not .Values.networkPolicy.allowExternal) }}--labels="{{ template "common.names.fullname" . }}-client=true" \{{- end }} + --namespace {{ .Release.Namespace }} -- bash + +2. Connect using the Redis® CLI: + +{{- if eq .Values.architecture "replication" }} + {{- if .Values.sentinel.enabled }} + {{ if .Values.auth.enabled }}REDISCLI_AUTH="$REDIS_PASSWORD" {{ end }}redis-cli -h {{ template "common.names.fullname" . }} -p {{ .Values.sentinel.service.ports.redis }}{{ if .Values.tls.enabled }} --tls --cert /tmp/client.cert --key /tmp/client.key --cacert /tmp/CA.cert{{ end }} # Read only operations + {{ if .Values.auth.enabled }}REDISCLI_AUTH="$REDIS_PASSWORD" {{ end }}redis-cli -h {{ template "common.names.fullname" . }} -p {{ .Values.sentinel.service.ports.sentinel }}{{ if .Values.tls.enabled }} --tls --cert /tmp/client.cert --key /tmp/client.key --cacert /tmp/CA.cert{{ end }} # Sentinel access + {{- else }} + {{ if .Values.auth.enabled }}REDISCLI_AUTH="$REDIS_PASSWORD" {{ end }}redis-cli -h {{ printf "%s-master" (include "common.names.fullname" .) }}{{ if .Values.tls.enabled }} --tls --cert /tmp/client.cert --key /tmp/client.key --cacert /tmp/CA.cert{{ end }} + {{ if .Values.auth.enabled }}REDISCLI_AUTH="$REDIS_PASSWORD" {{ end }}redis-cli -h {{ printf "%s-replicas" (include "common.names.fullname" .) }}{{ if .Values.tls.enabled }} --tls --cert /tmp/client.cert --key /tmp/client.key --cacert /tmp/CA.cert{{ end }} + {{- end }} +{{- else }} + {{ if .Values.auth.enabled }}REDISCLI_AUTH="$REDIS_PASSWORD" {{ end }}redis-cli -h {{ template "common.names.fullname" . }}-master{{ if .Values.tls.enabled }} --tls --cert /tmp/client.cert --key /tmp/client.key --cacert /tmp/CA.cert{{ end }} +{{- end }} + +{{- if and (.Values.networkPolicy.enabled) (not .Values.networkPolicy.allowExternal) }} + +Note: Since NetworkPolicy is enabled, only pods with label {{ template "common.names.fullname" . }}-client=true" will be able to connect to redis. + +{{- else }} + +To connect to your database from outside the cluster execute the following commands: + +{{- if and (eq .Values.architecture "replication") .Values.sentinel.enabled }} +{{- if contains "NodePort" .Values.sentinel.service.type }} + + export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}") + export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ template "common.names.fullname" . }}) + {{ if .Values.auth.enabled }}REDISCLI_AUTH="$REDIS_PASSWORD" {{ end }}redis-cli -h $NODE_IP -p $NODE_PORT {{- if .Values.tls.enabled }} --tls --cert /tmp/client.cert --key /tmp/client.key --cacert /tmp/CA.cert{{ end }} + +{{- else if contains "LoadBalancer" .Values.sentinel.service.type }} + + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + Watch the status with: 'kubectl get svc --namespace {{ .Release.Namespace }} -w {{ template "common.names.fullname" . }}' + + export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ template "common.names.fullname" . }} --template "{{ "{{ range (index .status.loadBalancer.ingress 0) }}{{ . }}{{ end }}" }}") + {{ if .Values.auth.enabled }}REDISCLI_AUTH="$REDIS_PASSWORD" {{ end }}redis-cli -h $SERVICE_IP -p {{ .Values.sentinel.service.ports.redis }} {{- if .Values.tls.enabled }} --tls --cert /tmp/client.cert --key /tmp/client.key --cacert /tmp/CA.cert{{ end }} + +{{- else if contains "ClusterIP" .Values.sentinel.service.type }} + + kubectl port-forward --namespace {{ .Release.Namespace }} svc/{{ template "common.names.fullname" . }} {{ .Values.sentinel.service.ports.redis }}:{{ .Values.sentinel.service.ports.redis }} & + {{ if .Values.auth.enabled }}REDISCLI_AUTH="$REDIS_PASSWORD" {{ end }}redis-cli -h 127.0.0.1 -p {{ .Values.sentinel.service.ports.redis }} {{- if .Values.tls.enabled }} --tls --cert /tmp/client.cert --key /tmp/client.key --cacert /tmp/CA.cert{{ end }} + +{{- end }} +{{- else }} +{{- if contains "NodePort" .Values.master.service.type }} + + export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}") + export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ printf "%s-master" (include "common.names.fullname" .) }}) + {{ if .Values.auth.enabled }}REDISCLI_AUTH="$REDIS_PASSWORD" {{ end }}redis-cli -h $NODE_IP -p $NODE_PORT {{- if .Values.tls.enabled }} --tls --cert /tmp/client.cert --key /tmp/client.key --cacert /tmp/CA.cert{{ end }} + +{{- else if contains "LoadBalancer" .Values.master.service.type }} + + NOTE: It may take a few minutes for the LoadBalancer IP to be available. + Watch the status with: 'kubectl get svc --namespace {{ .Release.Namespace }} -w {{ template "common.names.fullname" . }}' + + export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ printf "%s-master" (include "common.names.fullname" .) }} --template "{{ "{{ range (index .status.loadBalancer.ingress 0) }}{{ . }}{{ end }}" }}") + {{ if .Values.auth.enabled }}REDISCLI_AUTH="$REDIS_PASSWORD" {{ end }}redis-cli -h $SERVICE_IP -p {{ .Values.master.service.ports.redis }} {{- if .Values.tls.enabled }} --tls --cert /tmp/client.cert --key /tmp/client.key --cacert /tmp/CA.cert{{ end }} + +{{- else if contains "ClusterIP" .Values.master.service.type }} + + kubectl port-forward --namespace {{ .Release.Namespace }} svc/{{ printf "%s-master" (include "common.names.fullname" .) }} {{ .Values.master.service.ports.redis }}:{{ .Values.master.service.ports.redis }} & + {{ if .Values.auth.enabled }}REDISCLI_AUTH="$REDIS_PASSWORD" {{ end }}redis-cli -h 127.0.0.1 -p {{ .Values.master.service.ports.redis }} {{- if .Values.tls.enabled }} --tls --cert /tmp/client.cert --key /tmp/client.key --cacert /tmp/CA.cert{{ end }} + +{{- end }} +{{- end }} + +{{- end }} +{{- end }} +{{- include "redis.checkRollingTags" . }} +{{- include "common.warnings.rollingTag" .Values.volumePermissions.image }} +{{- include "common.warnings.rollingTag" .Values.sysctl.image }} +{{- include "redis.validateValues" . }} + +{{- if and (eq .Values.architecture "replication") .Values.sentinel.enabled (eq .Values.sentinel.service.type "NodePort") (not .Release.IsUpgrade ) }} +{{- if $.Values.sentinel.service.nodePorts.sentinel }} +No need to upgrade, ports and nodeports have been set from values +{{- else }} +#!#!#!#!#!#!#!# IMPORTANT #!#!#!#!#!#!#!# +YOU NEED TO PERFORM AN UPGRADE FOR THE SERVICES AND WORKLOAD TO BE CREATED +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/_helpers.tpl new file mode 100644 index 0000000..f6f47d9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/_helpers.tpl @@ -0,0 +1,291 @@ +{{/* vim: set filetype=mustache: */}} + +{{/* +Return the proper Redis image name +*/}} +{{- define "redis.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return the proper Redis Sentinel image name +*/}} +{{- define "redis.sentinel.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.sentinel.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return the proper image name (for the metrics image) +*/}} +{{- define "redis.metrics.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.metrics.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return the proper image name (for the init container volume-permissions image) +*/}} +{{- define "redis.volumePermissions.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.volumePermissions.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return sysctl image +*/}} +{{- define "redis.sysctl.image" -}} +{{ include "common.images.image" (dict "imageRoot" .Values.sysctl.image "global" .Values.global) }} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names +*/}} +{{- define "redis.imagePullSecrets" -}} +{{- include "common.images.pullSecrets" (dict "images" (list .Values.image .Values.sentinel.image .Values.metrics.image .Values.volumePermissions.image .Values.sysctl.image) "global" .Values.global) -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for networkpolicy. +*/}} +{{- define "networkPolicy.apiVersion" -}} +{{- if semverCompare ">=1.4-0, <1.7-0" .Capabilities.KubeVersion.GitVersion -}} +{{- print "extensions/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiGroup for PodSecurityPolicy. +*/}} +{{- define "podSecurityPolicy.apiGroup" -}} +{{- if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}} +{{- print "policy" -}} +{{- else -}} +{{- print "extensions" -}} +{{- end -}} +{{- end -}} + +{{/* +Return true if a TLS secret object should be created +*/}} +{{- define "redis.createTlsSecret" -}} +{{- if and .Values.tls.enabled .Values.tls.autoGenerated (and (not .Values.tls.existingSecret) (not .Values.tls.certificatesSecret)) }} + {{- true -}} +{{- end -}} +{{- end -}} + +{{/* +Return the secret containing Redis TLS certificates +*/}} +{{- define "redis.tlsSecretName" -}} +{{- $secretName := coalesce .Values.tls.existingSecret .Values.tls.certificatesSecret -}} +{{- if $secretName -}} + {{- printf "%s" (tpl $secretName $) -}} +{{- else -}} + {{- printf "%s-crt" (include "common.names.fullname" .) -}} +{{- end -}} +{{- end -}} + +{{/* +Return the path to the cert file. +*/}} +{{- define "redis.tlsCert" -}} +{{- if (include "redis.createTlsSecret" . ) -}} + {{- printf "/opt/bitnami/redis/certs/%s" "tls.crt" -}} +{{- else -}} + {{- required "Certificate filename is required when TLS in enabled" .Values.tls.certFilename | printf "/opt/bitnami/redis/certs/%s" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the path to the cert key file. +*/}} +{{- define "redis.tlsCertKey" -}} +{{- if (include "redis.createTlsSecret" . ) -}} + {{- printf "/opt/bitnami/redis/certs/%s" "tls.key" -}} +{{- else -}} + {{- required "Certificate Key filename is required when TLS in enabled" .Values.tls.certKeyFilename | printf "/opt/bitnami/redis/certs/%s" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the path to the CA cert file. +*/}} +{{- define "redis.tlsCACert" -}} +{{- if (include "redis.createTlsSecret" . ) -}} + {{- printf "/opt/bitnami/redis/certs/%s" "ca.crt" -}} +{{- else -}} + {{- required "Certificate CA filename is required when TLS in enabled" .Values.tls.certCAFilename | printf "/opt/bitnami/redis/certs/%s" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the path to the DH params file. +*/}} +{{- define "redis.tlsDHParams" -}} +{{- if .Values.tls.dhParamsFilename -}} +{{- printf "/opt/bitnami/redis/certs/%s" .Values.tls.dhParamsFilename -}} +{{- end -}} +{{- end -}} + +{{/* +Create the name of the service account to use +*/}} +{{- define "redis.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "common.names.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Return the configuration configmap name +*/}} +{{- define "redis.configmapName" -}} +{{- if .Values.existingConfigmap -}} + {{- printf "%s" (tpl .Values.existingConfigmap $) -}} +{{- else -}} + {{- printf "%s-configuration" (include "common.names.fullname" .) -}} +{{- end -}} +{{- end -}} + +{{/* +Return true if a configmap object should be created +*/}} +{{- define "redis.createConfigmap" -}} +{{- if empty .Values.existingConfigmap }} + {{- true -}} +{{- end -}} +{{- end -}} + +{{/* +Get the password secret. +*/}} +{{- define "redis.secretName" -}} +{{- if .Values.auth.existingSecret -}} +{{- printf "%s" .Values.auth.existingSecret -}} +{{- else -}} +{{- printf "%s" (include "common.names.fullname" .) -}} +{{- end -}} +{{- end -}} + +{{/* +Get the password key to be retrieved from Redis® secret. +*/}} +{{- define "redis.secretPasswordKey" -}} +{{- if and .Values.auth.existingSecret .Values.auth.existingSecretPasswordKey -}} +{{- printf "%s" .Values.auth.existingSecretPasswordKey -}} +{{- else -}} +{{- printf "redis-password" -}} +{{- end -}} +{{- end -}} + + +{{/* +Returns the available value for certain key in an existing secret (if it exists), +otherwise it generates a random value. +*/}} +{{- define "getValueFromSecret" }} + {{- $len := (default 16 .Length) | int -}} + {{- $obj := (lookup "v1" "Secret" .Namespace .Name).data -}} + {{- if $obj }} + {{- index $obj .Key | b64dec -}} + {{- else -}} + {{- randAlphaNum $len -}} + {{- end -}} +{{- end }} + +{{/* +Return Redis® password +*/}} +{{- define "redis.password" -}} +{{- if not (empty .Values.global.redis.password) }} + {{- .Values.global.redis.password -}} +{{- else if not (empty .Values.auth.password) -}} + {{- .Values.auth.password -}} +{{- else -}} + {{- include "getValueFromSecret" (dict "Namespace" .Release.Namespace "Name" (include "common.names.fullname" .) "Length" 10 "Key" "redis-password") -}} +{{- end -}} +{{- end -}} + +{{/* Check if there are rolling tags in the images */}} +{{- define "redis.checkRollingTags" -}} +{{- include "common.warnings.rollingTag" .Values.image }} +{{- include "common.warnings.rollingTag" .Values.sentinel.image }} +{{- include "common.warnings.rollingTag" .Values.metrics.image }} +{{- end -}} + +{{/* +Compile all warnings into a single message, and call fail. +*/}} +{{- define "redis.validateValues" -}} +{{- $messages := list -}} +{{- $messages := append $messages (include "redis.validateValues.topologySpreadConstraints" .) -}} +{{- $messages := append $messages (include "redis.validateValues.architecture" .) -}} +{{- $messages := append $messages (include "redis.validateValues.podSecurityPolicy.create" .) -}} +{{- $messages := append $messages (include "redis.validateValues.tls" .) -}} +{{- $messages := without $messages "" -}} +{{- $message := join "\n" $messages -}} + +{{- if $message -}} +{{- printf "\nVALUES VALIDATION:\n%s" $message | fail -}} +{{- end -}} +{{- end -}} + +{{/* Validate values of Redis® - spreadConstrainsts K8s version */}} +{{- define "redis.validateValues.topologySpreadConstraints" -}} +{{- if and (semverCompare "<1.16-0" .Capabilities.KubeVersion.GitVersion) .Values.replica.topologySpreadConstraints -}} +redis: topologySpreadConstraints + Pod Topology Spread Constraints are only available on K8s >= 1.16 + Find more information at https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ +{{- end -}} +{{- end -}} + +{{/* Validate values of Redis® - must provide a valid architecture */}} +{{- define "redis.validateValues.architecture" -}} +{{- if and (ne .Values.architecture "standalone") (ne .Values.architecture "replication") -}} +redis: architecture + Invalid architecture selected. Valid values are "standalone" and + "replication". Please set a valid architecture (--set architecture="xxxx") +{{- end -}} +{{- if and .Values.sentinel.enabled (not (eq .Values.architecture "replication")) }} +redis: architecture + Using redis sentinel on standalone mode is not supported. + To deploy redis sentinel, please select the "replication" mode + (--set "architecture=replication,sentinel.enabled=true") +{{- end -}} +{{- end -}} + +{{/* Validate values of Redis® - PodSecurityPolicy create */}} +{{- define "redis.validateValues.podSecurityPolicy.create" -}} +{{- if and .Values.podSecurityPolicy.create (not .Values.podSecurityPolicy.enabled) }} +redis: podSecurityPolicy.create + In order to create PodSecurityPolicy, you also need to enable + podSecurityPolicy.enabled field +{{- end -}} +{{- end -}} + +{{/* Validate values of Redis® - TLS enabled */}} +{{- define "redis.validateValues.tls" -}} +{{- if and .Values.tls.enabled (not .Values.tls.autoGenerated) (not .Values.tls.existingSecret) (not .Values.tls.certificatesSecret) }} +redis: tls.enabled + In order to enable TLS, you also need to provide + an existing secret containing the TLS certificates or + enable auto-generated certificates. +{{- end -}} +{{- end -}} + +{{/* Define the suffix utilized for external-dns */}} +{{- define "redis.externalDNS.suffix" -}} +{{ printf "%s.%s" (include "common.names.fullname" .) .Values.useExternalDNS.suffix }} +{{- end -}} + +{{/* Compile all annotations utilized for external-dns */}} +{{- define "redis.externalDNS.annotations" -}} +{{- if .Values.useExternalDNS.enabled }} +{{ .Values.useExternalDNS.annotationKey }}hostname: {{ include "redis.externalDNS.suffix" . }} +{{- range $key, $val := .Values.useExternalDNS.additionalAnnotations }} +{{ $.Values.useExternalDNS.annotationKey }}{{ $key }}: {{ $val | quote }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/configmap.yaml new file mode 100644 index 0000000..9e70a38 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/configmap.yaml @@ -0,0 +1,59 @@ +{{- if (include "redis.createConfigmap" .) }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ printf "%s-configuration" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: + redis.conf: |- + # User-supplied common configuration: + {{- if .Values.commonConfiguration }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonConfiguration "context" $ ) | nindent 4 }} + {{- end }} + # End of common configuration + master.conf: |- + dir {{ .Values.master.persistence.path }} + # User-supplied master configuration: + {{- if .Values.master.configuration }} + {{- include "common.tplvalues.render" ( dict "value" .Values.master.configuration "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.master.disableCommands }} + {{- range .Values.master.disableCommands }} + rename-command {{ . }} "" + {{- end }} + {{- end }} + # End of master configuration + replica.conf: |- + dir {{ .Values.replica.persistence.path }} + # User-supplied replica configuration: + {{- if .Values.replica.configuration }} + {{- include "common.tplvalues.render" ( dict "value" .Values.replica.configuration "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.replica.disableCommands }} + {{- range .Values.replica.disableCommands }} + rename-command {{ . }} "" + {{- end }} + {{- end }} + # End of replica configuration + {{- if .Values.sentinel.enabled }} + sentinel.conf: |- + dir "/tmp" + port {{ .Values.sentinel.containerPorts.sentinel }} + sentinel monitor {{ .Values.sentinel.masterSet }} {{ template "common.names.fullname" . }}-node-0.{{ template "common.names.fullname" . }}-headless.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }} {{ .Values.sentinel.service.ports.redis }} {{ .Values.sentinel.quorum }} + sentinel down-after-milliseconds {{ .Values.sentinel.masterSet }} {{ .Values.sentinel.downAfterMilliseconds }} + sentinel failover-timeout {{ .Values.sentinel.masterSet }} {{ .Values.sentinel.failoverTimeout }} + sentinel parallel-syncs {{ .Values.sentinel.masterSet }} {{ .Values.sentinel.parallelSyncs }} + # User-supplied sentinel configuration: + {{- if .Values.sentinel.configuration }} + {{- include "common.tplvalues.render" ( dict "value" .Values.sentinel.configuration "context" $ ) | nindent 4 }} + {{- end }} + # End of sentinel configuration + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/extra-list.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/extra-list.yaml new file mode 100644 index 0000000..9ac65f9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/extra-list.yaml @@ -0,0 +1,4 @@ +{{- range .Values.extraDeploy }} +--- +{{ include "common.tplvalues.render" (dict "value" . "context" $) }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/headless-svc.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/headless-svc.yaml new file mode 100644 index 0000000..d798a0b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/headless-svc.yaml @@ -0,0 +1,30 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ printf "%s-headless" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + annotations: + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- include "redis.externalDNS.annotations" . | nindent 4 }} +spec: + type: ClusterIP + clusterIP: None + {{- if .Values.sentinel.enabled }} + publishNotReadyAddresses: true + {{- end }} + ports: + - name: tcp-redis + port: {{ if .Values.sentinel.enabled }}{{ .Values.sentinel.service.ports.redis }}{{ else }}{{ .Values.master.service.ports.redis }}{{ end }} + targetPort: redis + {{- if .Values.sentinel.enabled }} + - name: tcp-sentinel + port: {{ .Values.sentinel.service.ports.sentinel }} + targetPort: redis-sentinel + {{- end }} + selector: {{- include "common.labels.matchLabels" . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/health-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/health-configmap.yaml new file mode 100644 index 0000000..41f3145 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/health-configmap.yaml @@ -0,0 +1,192 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ printf "%s-health" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: + ping_readiness_local.sh: |- + #!/bin/bash + + [[ -f $REDIS_PASSWORD_FILE ]] && export REDIS_PASSWORD="$(< "${REDIS_PASSWORD_FILE}")" + [[ -n "$REDIS_PASSWORD" ]] && export REDISCLI_AUTH="$REDIS_PASSWORD" + response=$( + timeout -s 3 $1 \ + redis-cli \ + -h localhost \ +{{- if .Values.tls.enabled }} + -p $REDIS_TLS_PORT \ + --tls \ + --cacert {{ template "redis.tlsCACert" . }} \ + {{- if .Values.tls.authClients }} + --cert {{ template "redis.tlsCert" . }} \ + --key {{ template "redis.tlsCertKey" . }} \ + {{- end }} +{{- else }} + -p $REDIS_PORT \ +{{- end }} + ping + ) + if [ "$?" -eq "124" ]; then + echo "Timed out" + exit 1 + fi + if [ "$response" != "PONG" ]; then + echo "$response" + exit 1 + fi + ping_liveness_local.sh: |- + #!/bin/bash + + [[ -f $REDIS_PASSWORD_FILE ]] && export REDIS_PASSWORD="$(< "${REDIS_PASSWORD_FILE}")" + [[ -n "$REDIS_PASSWORD" ]] && export REDISCLI_AUTH="$REDIS_PASSWORD" + response=$( + timeout -s 3 $1 \ + redis-cli \ + -h localhost \ +{{- if .Values.tls.enabled }} + -p $REDIS_TLS_PORT \ + --tls \ + --cacert {{ template "redis.tlsCACert" . }} \ + {{- if .Values.tls.authClients }} + --cert {{ template "redis.tlsCert" . }} \ + --key {{ template "redis.tlsCertKey" . }} \ + {{- end }} +{{- else }} + -p $REDIS_PORT \ +{{- end }} + ping + ) + if [ "$?" -eq "124" ]; then + echo "Timed out" + exit 1 + fi + responseFirstWord=$(echo $response | head -n1 | awk '{print $1;}') + if [ "$response" != "PONG" ] && [ "$responseFirstWord" != "LOADING" ] && [ "$responseFirstWord" != "MASTERDOWN" ]; then + echo "$response" + exit 1 + fi +{{- if .Values.sentinel.enabled }} + ping_sentinel.sh: |- + #!/bin/bash + +{{- if .Values.auth.sentinel }} + [[ -f $REDIS_PASSWORD_FILE ]] && export REDIS_PASSWORD="$(< "${REDIS_PASSWORD_FILE}")" + [[ -n "$REDIS_PASSWORD" ]] && export REDISCLI_AUTH="$REDIS_PASSWORD" +{{- end }} + response=$( + timeout -s 3 $1 \ + redis-cli \ + -h localhost \ +{{- if .Values.tls.enabled }} + -p $REDIS_SENTINEL_TLS_PORT_NUMBER \ + --tls \ + --cacert "$REDIS_SENTINEL_TLS_CA_FILE" \ + {{- if .Values.tls.authClients }} + --cert "$REDIS_SENTINEL_TLS_CERT_FILE" \ + --key "$REDIS_SENTINEL_TLS_KEY_FILE" \ + {{- end }} +{{- else }} + -p $REDIS_SENTINEL_PORT \ +{{- end }} + ping + ) + if [ "$?" -eq "124" ]; then + echo "Timed out" + exit 1 + fi + if [ "$response" != "PONG" ]; then + echo "$response" + exit 1 + fi + parse_sentinels.awk: |- + /ip/ {FOUND_IP=1} + /port/ {FOUND_PORT=1} + /runid/ {FOUND_RUNID=1} + !/ip|port|runid/ { + if (FOUND_IP==1) { + IP=$1; FOUND_IP=0; + } + else if (FOUND_PORT==1) { + PORT=$1; + FOUND_PORT=0; + } else if (FOUND_RUNID==1) { + printf "\nsentinel known-sentinel {{ .Values.sentinel.masterSet }} %s %s %s", IP, PORT, $0; FOUND_RUNID=0; + } + } +{{- end }} + ping_readiness_master.sh: |- + #!/bin/bash + + [[ -f $REDIS_MASTER_PASSWORD_FILE ]] && export REDIS_MASTER_PASSWORD="$(< "${REDIS_MASTER_PASSWORD_FILE}")" + [[ -n "$REDIS_MASTER_PASSWORD" ]] && export REDISCLI_AUTH="$REDIS_MASTER_PASSWORD" + response=$( + timeout -s 3 $1 \ + redis-cli \ + -h $REDIS_MASTER_HOST \ + -p $REDIS_MASTER_PORT_NUMBER \ +{{- if .Values.tls.enabled }} + --tls \ + --cacert {{ template "redis.tlsCACert" . }} \ + {{- if .Values.tls.authClients }} + --cert {{ template "redis.tlsCert" . }} \ + --key {{ template "redis.tlsCertKey" . }} \ + {{- end }} +{{- end }} + ping + ) + if [ "$?" -eq "124" ]; then + echo "Timed out" + exit 1 + fi + if [ "$response" != "PONG" ]; then + echo "$response" + exit 1 + fi + ping_liveness_master.sh: |- + #!/bin/bash + + [[ -f $REDIS_MASTER_PASSWORD_FILE ]] && export REDIS_MASTER_PASSWORD="$(< "${REDIS_MASTER_PASSWORD_FILE}")" + [[ -n "$REDIS_MASTER_PASSWORD" ]] && export REDISCLI_AUTH="$REDIS_MASTER_PASSWORD" + response=$( + timeout -s 3 $1 \ + redis-cli \ + -h $REDIS_MASTER_HOST \ + -p $REDIS_MASTER_PORT_NUMBER \ +{{- if .Values.tls.enabled }} + --tls \ + --cacert {{ template "redis.tlsCACert" . }} \ + {{- if .Values.tls.authClients }} + --cert {{ template "redis.tlsCert" . }} \ + --key {{ template "redis.tlsCertKey" . }} \ + {{- end }} +{{- end }} + ping + ) + if [ "$?" -eq "124" ]; then + echo "Timed out" + exit 1 + fi + responseFirstWord=$(echo $response | head -n1 | awk '{print $1;}') + if [ "$response" != "PONG" ] && [ "$responseFirstWord" != "LOADING" ]; then + echo "$response" + exit 1 + fi + ping_readiness_local_and_master.sh: |- + script_dir="$(dirname "$0")" + exit_status=0 + "$script_dir/ping_readiness_local.sh" $1 || exit_status=$? + "$script_dir/ping_readiness_master.sh" $1 || exit_status=$? + exit $exit_status + ping_liveness_local_and_master.sh: |- + script_dir="$(dirname "$0")" + exit_status=0 + "$script_dir/ping_liveness_local.sh" $1 || exit_status=$? + "$script_dir/ping_liveness_master.sh" $1 || exit_status=$? + exit $exit_status diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/master/application.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/master/application.yaml new file mode 100644 index 0000000..85d5847 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/master/application.yaml @@ -0,0 +1,473 @@ +{{- if or (not (eq .Values.architecture "replication")) (not .Values.sentinel.enabled) }} +apiVersion: {{ include "common.capabilities.statefulset.apiVersion" . }} +kind: {{ .Values.master.kind }} +metadata: + name: {{ printf "%s-master" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: master + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.master.count }} + selector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + app.kubernetes.io/component: master + {{- if (eq .Values.master.kind "StatefulSet") }} + serviceName: {{ printf "%s-headless" (include "common.names.fullname" .) }} + {{- end }} + {{- if .Values.master.updateStrategy }} + {{- if (eq .Values.master.kind "Deployment") }} + strategy: {{- toYaml .Values.master.updateStrategy | nindent 4 }} + {{- else }} + updateStrategy: {{- toYaml .Values.master.updateStrategy | nindent 4 }} + {{- end }} + {{- end }} + template: + metadata: + labels: {{- include "common.labels.standard" . | nindent 8 }} + app.kubernetes.io/component: master + {{- if .Values.master.podLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.master.podLabels "context" $ ) | nindent 8 }} + {{- end }} + {{- if and .Values.metrics.enabled .Values.metrics.podLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.podLabels "context" $ ) | nindent 8 }} + {{- end }} + annotations: + {{- if (include "redis.createConfigmap" .) }} + checksum/configmap: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + {{- end }} + checksum/health: {{ include (print $.Template.BasePath "/health-configmap.yaml") . | sha256sum }} + checksum/scripts: {{ include (print $.Template.BasePath "/scripts-configmap.yaml") . | sha256sum }} + checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }} + {{- if .Values.master.podAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.master.podAnnotations "context" $ ) | nindent 8 }} + {{- end }} + {{- if and .Values.metrics.enabled .Values.metrics.podAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.podAnnotations "context" $ ) | nindent 8 }} + {{- end }} + spec: + {{- include "redis.imagePullSecrets" . | nindent 6 }} + {{- if .Values.master.hostAliases }} + hostAliases: {{- include "common.tplvalues.render" (dict "value" .Values.master.hostAliases "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.master.podSecurityContext.enabled }} + securityContext: {{- omit .Values.master.podSecurityContext "enabled" | toYaml | nindent 8 }} + {{- end }} + serviceAccountName: {{ template "redis.serviceAccountName" . }} + {{- if .Values.master.priorityClassName }} + priorityClassName: {{ .Values.master.priorityClassName | quote }} + {{- end }} + {{- if .Values.master.affinity }} + affinity: {{- include "common.tplvalues.render" (dict "value" .Values.master.affinity "context" $) | nindent 8 }} + {{- else }} + affinity: + podAffinity: {{- include "common.affinities.pods" (dict "type" .Values.master.podAffinityPreset "component" "master" "context" $) | nindent 10 }} + podAntiAffinity: {{- include "common.affinities.pods" (dict "type" .Values.master.podAntiAffinityPreset "component" "master" "context" $) | nindent 10 }} + nodeAffinity: {{- include "common.affinities.nodes" (dict "type" .Values.master.nodeAffinityPreset.type "key" .Values.master.nodeAffinityPreset.key "values" .Values.master.nodeAffinityPreset.values) | nindent 10 }} + {{- end }} + {{- if .Values.master.nodeSelector }} + nodeSelector: {{- include "common.tplvalues.render" (dict "value" .Values.master.nodeSelector "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.master.tolerations }} + tolerations: {{- include "common.tplvalues.render" (dict "value" .Values.master.tolerations "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.master.topologySpreadConstraints }} + topologySpreadConstraints: {{- include "common.tplvalues.render" (dict "value" .Values.master.topologySpreadConstraints "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.master.shareProcessNamespace }} + shareProcessNamespace: {{ .Values.master.shareProcessNamespace }} + {{- end }} + {{- if .Values.master.schedulerName }} + schedulerName: {{ .Values.master.schedulerName | quote }} + {{- end }} + {{- if .Values.master.dnsPolicy }} + dnsPolicy: {{ .Values.master.dnsPolicy }} + {{- end }} + {{- if .Values.master.dnsConfig }} + dnsConfig: {{- include "common.tplvalues.render" (dict "value" .Values.master.dnsConfig "context" $) | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.master.terminationGracePeriodSeconds }} + containers: + - name: redis + image: {{ template "redis.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy | quote }} + {{- if .Values.master.lifecycleHooks }} + lifecycle: {{- include "common.tplvalues.render" (dict "value" .Values.master.lifecycleHooks "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.master.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.master.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + {{- else if .Values.master.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.master.command "context" $) | nindent 12 }} + {{- else }} + command: + - /bin/bash + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else if .Values.master.args }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.master.args "context" $) | nindent 12 }} + {{- else }} + args: + - -c + - /opt/bitnami/scripts/start-scripts/start-master.sh + {{- end }} + env: + - name: BITNAMI_DEBUG + value: {{ ternary "true" "false" (or .Values.image.debug .Values.diagnosticMode.enabled) | quote }} + - name: REDIS_REPLICATION_MODE + value: master + - name: ALLOW_EMPTY_PASSWORD + value: {{ ternary "no" "yes" .Values.auth.enabled | quote }} + {{- if .Values.auth.enabled }} + {{- if .Values.auth.usePasswordFiles }} + - name: REDIS_PASSWORD_FILE + value: "/opt/bitnami/redis/secrets/redis-password" + {{- else }} + - name: REDIS_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "redis.secretName" . }} + key: {{ template "redis.secretPasswordKey" . }} + {{- end }} + {{- end }} + - name: REDIS_TLS_ENABLED + value: {{ ternary "yes" "no" .Values.tls.enabled | quote }} + {{- if .Values.tls.enabled }} + - name: REDIS_TLS_PORT + value: {{ .Values.master.containerPorts.redis | quote }} + - name: REDIS_TLS_AUTH_CLIENTS + value: {{ ternary "yes" "no" .Values.tls.authClients | quote }} + - name: REDIS_TLS_CERT_FILE + value: {{ template "redis.tlsCert" . }} + - name: REDIS_TLS_KEY_FILE + value: {{ template "redis.tlsCertKey" . }} + - name: REDIS_TLS_CA_FILE + value: {{ template "redis.tlsCACert" . }} + {{- if .Values.tls.dhParamsFilename }} + - name: REDIS_TLS_DH_PARAMS_FILE + value: {{ template "redis.tlsDHParams" . }} + {{- end }} + {{- else }} + - name: REDIS_PORT + value: {{ .Values.master.containerPorts.redis | quote }} + {{- end }} + {{- if .Values.master.extraEnvVars }} + {{- include "common.tplvalues.render" (dict "value" .Values.master.extraEnvVars "context" $) | nindent 12 }} + {{- end }} + {{- if or .Values.master.extraEnvVarsCM .Values.master.extraEnvVarsSecret }} + envFrom: + {{- if .Values.master.extraEnvVarsCM }} + - configMapRef: + name: {{ .Values.master.extraEnvVarsCM }} + {{- end }} + {{- if .Values.master.extraEnvVarsSecret }} + - secretRef: + name: {{ .Values.master.extraEnvVarsSecret }} + {{- end }} + {{- end }} + ports: + - name: redis + containerPort: {{ .Values.master.containerPorts.redis }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.master.startupProbe.enabled }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.master.startupProbe "enabled") "context" $) | nindent 12 }} + tcpSocket: + port: redis + {{- else if .Values.master.customStartupProbe }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.master.customStartupProbe "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.master.livenessProbe.enabled }} + livenessProbe: + initialDelaySeconds: {{ .Values.master.livenessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.master.livenessProbe.periodSeconds }} + # One second longer than command timeout should prevent generation of zombie processes. + timeoutSeconds: {{ add1 .Values.master.livenessProbe.timeoutSeconds }} + successThreshold: {{ .Values.master.livenessProbe.successThreshold }} + failureThreshold: {{ .Values.master.livenessProbe.failureThreshold }} + exec: + command: + - sh + - -c + - /health/ping_liveness_local.sh {{ .Values.master.livenessProbe.timeoutSeconds }} + {{- else if .Values.master.customLivenessProbe }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.master.customLivenessProbe "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.master.readinessProbe.enabled }} + readinessProbe: + initialDelaySeconds: {{ .Values.master.readinessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.master.readinessProbe.periodSeconds }} + timeoutSeconds: {{ add1 .Values.master.readinessProbe.timeoutSeconds }} + successThreshold: {{ .Values.master.readinessProbe.successThreshold }} + failureThreshold: {{ .Values.master.readinessProbe.failureThreshold }} + exec: + command: + - sh + - -c + - /health/ping_readiness_local.sh {{ .Values.master.readinessProbe.timeoutSeconds }} + {{- else if .Values.master.customReadinessProbe }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.master.customReadinessProbe "context" $) | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.master.resources }} + resources: {{- toYaml .Values.master.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: start-scripts + mountPath: /opt/bitnami/scripts/start-scripts + - name: health + mountPath: /health + {{- if .Values.auth.usePasswordFiles }} + - name: redis-password + mountPath: /opt/bitnami/redis/secrets/ + {{- end }} + - name: redis-data + mountPath: {{ .Values.master.persistence.path }} + subPath: {{ .Values.master.persistence.subPath }} + - name: config + mountPath: /opt/bitnami/redis/mounted-etc + - name: redis-tmp-conf + mountPath: /opt/bitnami/redis/etc/ + - name: tmp + mountPath: /tmp + {{- if .Values.tls.enabled }} + - name: redis-certificates + mountPath: /opt/bitnami/redis/certs + readOnly: true + {{- end }} + {{- if .Values.master.extraVolumeMounts }} + {{- include "common.tplvalues.render" ( dict "value" .Values.master.extraVolumeMounts "context" $ ) | nindent 12 }} + {{- end }} + {{- if .Values.metrics.enabled }} + - name: metrics + image: {{ include "redis.metrics.image" . }} + imagePullPolicy: {{ .Values.metrics.image.pullPolicy | quote }} + {{- if .Values.metrics.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.metrics.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + {{- else }} + command: + - /bin/bash + - -c + - | + if [[ -f '/secrets/redis-password' ]]; then + export REDIS_PASSWORD=$(cat /secrets/redis-password) + fi + redis_exporter{{- range $key, $value := .Values.metrics.extraArgs }} --{{ $key }}={{ $value }}{{- end }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- end }} + env: + - name: REDIS_ALIAS + value: {{ template "common.names.fullname" . }} + {{- if .Values.auth.enabled }} + - name: REDIS_USER + value: default + {{- if (not .Values.auth.usePasswordFiles) }} + - name: REDIS_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "redis.secretName" . }} + key: {{ template "redis.secretPasswordKey" . }} + {{- end }} + {{- end }} + {{- if .Values.tls.enabled }} + - name: REDIS_ADDR + value: rediss://{{ .Values.metrics.redisTargetHost }}:{{ .Values.master.containerPorts.redis }} + {{- if .Values.tls.authClients }} + - name: REDIS_EXPORTER_TLS_CLIENT_KEY_FILE + value: {{ template "redis.tlsCertKey" . }} + - name: REDIS_EXPORTER_TLS_CLIENT_CERT_FILE + value: {{ template "redis.tlsCert" . }} + {{- end }} + - name: REDIS_EXPORTER_TLS_CA_CERT_FILE + value: {{ template "redis.tlsCACert" . }} + {{- end }} + {{- if .Values.metrics.extraEnvVars }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.extraEnvVars "context" $) | nindent 12 }} + {{- end }} + ports: + - name: metrics + containerPort: 9121 + {{- if .Values.metrics.resources }} + resources: {{- toYaml .Values.metrics.resources | nindent 12 }} + {{- end }} + volumeMounts: + {{- if .Values.auth.usePasswordFiles }} + - name: redis-password + mountPath: /secrets/ + {{- end }} + {{- if .Values.tls.enabled }} + - name: redis-certificates + mountPath: /opt/bitnami/redis/certs + readOnly: true + {{- end }} + {{- if .Values.metrics.extraVolumeMounts }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.extraVolumeMounts "context" $ ) | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.master.sidecars }} + {{- include "common.tplvalues.render" (dict "value" .Values.master.sidecars "context" $) | nindent 8 }} + {{- end }} + {{- $needsVolumePermissions := and .Values.volumePermissions.enabled .Values.master.persistence.enabled .Values.master.podSecurityContext.enabled .Values.master.containerSecurityContext.enabled }} + {{- if or .Values.master.initContainers $needsVolumePermissions .Values.sysctl.enabled }} + initContainers: + {{- if .Values.master.initContainers }} + {{- include "common.tplvalues.render" (dict "value" .Values.master.initContainers "context" $) | nindent 8 }} + {{- end }} + {{- if $needsVolumePermissions }} + - name: volume-permissions + image: {{ include "redis.volumePermissions.image" . }} + imagePullPolicy: {{ .Values.volumePermissions.image.pullPolicy | quote }} + command: + - /bin/bash + - -ec + - | + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + chown -R `id -u`:`id -G | cut -d " " -f2` {{ .Values.master.persistence.path }} + {{- else }} + chown -R {{ .Values.master.containerSecurityContext.runAsUser }}:{{ .Values.master.podSecurityContext.fsGroup }} {{ .Values.master.persistence.path }} + {{- end }} + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + securityContext: {{- omit .Values.volumePermissions.containerSecurityContext "runAsUser" | toYaml | nindent 12 }} + {{- else }} + securityContext: {{- .Values.volumePermissions.containerSecurityContext | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.volumePermissions.resources }} + resources: {{- toYaml .Values.volumePermissions.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: redis-data + mountPath: {{ .Values.master.persistence.path }} + subPath: {{ .Values.master.persistence.subPath }} + {{- end }} + {{- if .Values.sysctl.enabled }} + - name: init-sysctl + image: {{ include "redis.sysctl.image" . }} + imagePullPolicy: {{ default "" .Values.sysctl.image.pullPolicy | quote }} + securityContext: + privileged: true + runAsUser: 0 + {{- if .Values.sysctl.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.sysctl.command "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.sysctl.resources }} + resources: {{- toYaml .Values.sysctl.resources | nindent 12 }} + {{- end }} + {{- if .Values.sysctl.mountHostSys }} + volumeMounts: + - name: host-sys + mountPath: /host-sys + {{- end }} + {{- end }} + {{- end }} + volumes: + - name: start-scripts + configMap: + name: {{ printf "%s-scripts" (include "common.names.fullname" .) }} + defaultMode: 0755 + - name: health + configMap: + name: {{ printf "%s-health" (include "common.names.fullname" .) }} + defaultMode: 0755 + {{- if .Values.auth.usePasswordFiles }} + - name: redis-password + secret: + secretName: {{ template "redis.secretName" . }} + items: + - key: {{ template "redis.secretPasswordKey" . }} + path: redis-password + {{- end }} + - name: config + configMap: + name: {{ include "redis.configmapName" . }} + {{- if .Values.sysctl.mountHostSys }} + - name: host-sys + hostPath: + path: /sys + {{- end }} + - name: redis-tmp-conf + {{- if .Values.master.persistence.medium }} + emptyDir: + medium: {{ .Values.master.persistence.medium | quote }} + {{- if .Values.master.persistence.sizeLimit }} + sizeLimit: {{ .Values.master.persistence.sizeLimit | quote }} + {{- end }} + {{- else }} + emptyDir: {} + {{- end }} + - name: tmp + {{- if .Values.master.persistence.medium }} + emptyDir: + medium: {{ .Values.master.persistence.medium | quote }} + {{- if .Values.master.persistence.sizeLimit }} + sizeLimit: {{ .Values.master.persistence.sizeLimit | quote }} + {{- end }} + {{- else }} + emptyDir: {} + {{- end }} + {{- if .Values.tls.enabled }} + - name: redis-certificates + secret: + secretName: {{ include "redis.tlsSecretName" . }} + defaultMode: 256 + {{- end }} + {{- if .Values.master.extraVolumes }} + {{- include "common.tplvalues.render" ( dict "value" .Values.master.extraVolumes "context" $ ) | nindent 8 }} + {{- end }} + {{- if .Values.metrics.extraVolumes }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.extraVolumes "context" $ ) | nindent 8 }} + {{- end }} + {{- if not .Values.master.persistence.enabled }} + - name: redis-data + {{- if .Values.master.persistence.medium }} + emptyDir: { + medium: {{ .Values.master.persistence.medium | quote }} + } + {{- else }} + emptyDir: {} + {{- end }} + {{- else if .Values.master.persistence.existingClaim }} + - name: redis-data + persistentVolumeClaim: + claimName: {{ printf "%s" (tpl .Values.master.persistence.existingClaim .) }} + {{- else if (eq .Values.master.kind "Deployment") }} + - name: redis-data + persistentVolumeClaim: + claimName: {{ printf "redis-data-%s-master" (include "common.names.fullname" .) }} + {{- else }} + volumeClaimTemplates: + - metadata: + name: redis-data + labels: {{- include "common.labels.matchLabels" . | nindent 10 }} + app.kubernetes.io/component: master + {{- if .Values.master.persistence.annotations }} + annotations: {{- toYaml .Values.master.persistence.annotations | nindent 10 }} + {{- end }} + spec: + accessModes: + {{- range .Values.master.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + resources: + requests: + storage: {{ .Values.master.persistence.size | quote }} + {{- if .Values.master.persistence.selector }} + selector: {{- include "common.tplvalues.render" (dict "value" .Values.master.persistence.selector "context" $) | nindent 10 }} + {{- end }} + {{- if .Values.master.persistence.dataSource }} + dataSource: {{- include "common.tplvalues.render" (dict "value" .Values.master.persistence.dataSource "context" $) | nindent 10 }} + {{- end }} + {{- include "common.storage.class" (dict "persistence" .Values.master.persistence "global" .Values.global) | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/master/psp.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/master/psp.yaml new file mode 100644 index 0000000..2ba93b6 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/master/psp.yaml @@ -0,0 +1,46 @@ +{{- $pspAvailable := (semverCompare "<1.25-0" (include "common.capabilities.kubeVersion" .)) -}} +{{- if and $pspAvailable .Values.podSecurityPolicy.create }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ printf "%s-master" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + allowPrivilegeEscalation: false + fsGroup: + rule: 'MustRunAs' + ranges: + - min: {{ .Values.master.podSecurityContext.fsGroup }} + max: {{ .Values.master.podSecurityContext.fsGroup }} + hostIPC: false + hostNetwork: false + hostPID: false + privileged: false + readOnlyRootFilesystem: false + requiredDropCapabilities: + - ALL + runAsUser: + rule: 'MustRunAs' + ranges: + - min: {{ .Values.master.containerSecurityContext.runAsUser }} + max: {{ .Values.master.containerSecurityContext.runAsUser }} + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + - min: {{ .Values.master.containerSecurityContext.runAsUser }} + max: {{ .Values.master.containerSecurityContext.runAsUser }} + volumes: + - 'configMap' + - 'secret' + - 'emptyDir' + - 'persistentVolumeClaim' +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/master/pvc.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/master/pvc.yaml new file mode 100644 index 0000000..e5fddb0 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/master/pvc.yaml @@ -0,0 +1,27 @@ +{{- if and (eq .Values.architecture "standalone") (eq .Values.master.kind "Deployment") (.Values.master.persistence.enabled) (not .Values.master.persistence.existingClaim) }} +kind: PersistentVolumeClaim +apiVersion: v1 +metadata: + name: {{ printf "redis-data-%s-master" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.matchLabels" . | nindent 4 }} + app.kubernetes.io/component: master + {{- if .Values.master.persistence.annotations }} + annotations: {{- toYaml .Values.master.persistence.annotations | nindent 4 }} + {{- end }} +spec: + accessModes: + {{- range .Values.master.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + resources: + requests: + storage: {{ .Values.master.persistence.size | quote }} + {{- if .Values.master.persistence.selector }} + selector: {{- include "common.tplvalues.render" (dict "value" .Values.master.persistence.selector "context" $) | nindent 4 }} + {{- end }} + {{- if .Values.master.persistence.dataSource }} + dataSource: {{- include "common.tplvalues.render" (dict "value" .Values.master.persistence.dataSource "context" $) | nindent 4 }} + {{- end }} + {{- include "common.storage.class" (dict "persistence" .Values.master.persistence "global" .Values.global) | nindent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/master/service.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/master/service.yaml new file mode 100644 index 0000000..92b513a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/master/service.yaml @@ -0,0 +1,58 @@ +{{- if not .Values.sentinel.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ printf "%s-master" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: master + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if or .Values.master.service.annotations .Values.commonAnnotations }} + annotations: + {{- if .Values.master.service.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.master.service.annotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- end }} +spec: + type: {{ .Values.master.service.type }} + {{- if or (eq .Values.master.service.type "LoadBalancer") (eq .Values.master.service.type "NodePort") }} + externalTrafficPolicy: {{ .Values.master.service.externalTrafficPolicy | quote }} + {{- end }} + {{- if (semverCompare ">=1.22-0" (include "common.capabilities.kubeVersion" .)) }} + internalTrafficPolicy: {{ .Values.master.service.internalTrafficPolicy }} + {{- end }} + {{- if and (eq .Values.master.service.type "LoadBalancer") (not (empty .Values.master.service.loadBalancerIP)) }} + loadBalancerIP: {{ .Values.master.service.loadBalancerIP }} + {{- end }} + {{- if and (eq .Values.master.service.type "LoadBalancer") (not (empty .Values.master.service.loadBalancerSourceRanges)) }} + loadBalancerSourceRanges: {{ .Values.master.service.loadBalancerSourceRanges }} + {{- end }} + {{- if and .Values.master.service.clusterIP (eq .Values.master.service.type "ClusterIP") }} + clusterIP: {{ .Values.master.service.clusterIP }} + {{- end }} + {{- if .Values.master.service.sessionAffinity }} + sessionAffinity: {{ .Values.master.service.sessionAffinity }} + {{- end }} + {{- if .Values.master.service.sessionAffinityConfig }} + sessionAffinityConfig: {{- include "common.tplvalues.render" (dict "value" .Values.master.service.sessionAffinityConfig "context" $) | nindent 4 }} + {{- end }} + ports: + - name: tcp-redis + port: {{ .Values.master.service.ports.redis }} + targetPort: redis + {{- if and (or (eq .Values.master.service.type "NodePort") (eq .Values.master.service.type "LoadBalancer")) .Values.master.service.nodePorts.redis}} + nodePort: {{ .Values.master.service.nodePorts.redis}} + {{- else if eq .Values.master.service.type "ClusterIP" }} + nodePort: null + {{- end }} + {{- if .Values.master.service.extraPorts }} + {{- include "common.tplvalues.render" (dict "value" .Values.master.service.extraPorts "context" $) | nindent 4 }} + {{- end }} + selector: {{- include "common.labels.matchLabels" . | nindent 4 }} + app.kubernetes.io/component: master +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/metrics-svc.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/metrics-svc.yaml new file mode 100644 index 0000000..13c552f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/metrics-svc.yaml @@ -0,0 +1,41 @@ +{{- if .Values.metrics.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ printf "%s-metrics" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: metrics + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if or .Values.metrics.service.annotations .Values.commonAnnotations }} + annotations: + {{- if .Values.metrics.service.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.service.annotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- end }} +spec: + type: {{ .Values.metrics.service.type }} + {{- if eq .Values.metrics.service.type "LoadBalancer" }} + externalTrafficPolicy: {{ .Values.metrics.service.externalTrafficPolicy }} + {{- end }} + {{- if and (eq .Values.metrics.service.type "LoadBalancer") .Values.metrics.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.metrics.service.loadBalancerIP }} + {{- end }} + {{- if and (eq .Values.metrics.service.type "LoadBalancer") .Values.metrics.service.loadBalancerSourceRanges }} + loadBalancerSourceRanges: {{- toYaml .Values.metrics.service.loadBalancerSourceRanges | nindent 4 }} + {{- end }} + ports: + - name: http-metrics + port: {{ .Values.metrics.service.port }} + protocol: TCP + targetPort: metrics + {{- if .Values.metrics.service.extraPorts }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.service.extraPorts "context" $) | nindent 4 }} + {{- end }} + selector: {{- include "common.labels.matchLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/networkpolicy.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/networkpolicy.yaml new file mode 100644 index 0000000..64c0505 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/networkpolicy.yaml @@ -0,0 +1,78 @@ +{{- if .Values.networkPolicy.enabled }} +kind: NetworkPolicy +apiVersion: {{ template "networkPolicy.apiVersion" . }} +metadata: + name: {{ template "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + podSelector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + policyTypes: + - Ingress + {{- if or (eq .Values.architecture "replication") .Values.networkPolicy.extraEgress }} + - Egress + egress: + {{- if eq .Values.architecture "replication" }} + # Allow dns resolution + - ports: + - port: 53 + protocol: UDP + # Allow outbound connections to other cluster pods + - ports: + - port: {{ .Values.master.containerPorts.redis }} + {{- if .Values.sentinel.enabled }} + - port: {{ .Values.sentinel.containerPorts.sentinel }} + {{- end }} + to: + - podSelector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 14 }} + {{- end }} + {{- if .Values.networkPolicy.extraEgress }} + {{- include "common.tplvalues.render" ( dict "value" .Values.networkPolicy.extraEgress "context" $ ) | nindent 4 }} + {{- end }} + {{- end }} + ingress: + # Allow inbound connections + - ports: + - port: {{ .Values.master.containerPorts.redis }} + {{- if .Values.sentinel.enabled }} + - port: {{ .Values.sentinel.containerPorts.sentinel }} + {{- end }} + {{- if not .Values.networkPolicy.allowExternal }} + from: + - podSelector: + matchLabels: + {{ template "common.names.fullname" . }}-client: "true" + - podSelector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 14 }} + {{- if .Values.networkPolicy.ingressNSMatchLabels }} + - namespaceSelector: + matchLabels: + {{- range $key, $value := .Values.networkPolicy.ingressNSMatchLabels }} + {{ $key | quote }}: {{ $value | quote }} + {{- end }} + {{- if .Values.networkPolicy.ingressNSPodMatchLabels }} + podSelector: + matchLabels: + {{- range $key, $value := .Values.networkPolicy.ingressNSPodMatchLabels }} + {{ $key | quote }}: {{ $value | quote }} + {{- end }} + {{- end }} + {{- end }} + {{- end }} + {{- if .Values.metrics.enabled }} + # Allow prometheus scrapes for metrics + - ports: + - port: 9121 + {{- end }} + {{- if .Values.networkPolicy.extraIngress }} + {{- include "common.tplvalues.render" ( dict "value" .Values.networkPolicy.extraIngress "context" $ ) | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/pdb.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/pdb.yaml new file mode 100644 index 0000000..f82d278 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/pdb.yaml @@ -0,0 +1,23 @@ +{{- if .Values.pdb.create }} +apiVersion: {{ include "common.capabilities.policy.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ template "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + {{- if .Values.pdb.minAvailable }} + minAvailable: {{ .Values.pdb.minAvailable }} + {{- end }} + {{- if .Values.pdb.maxUnavailable }} + maxUnavailable: {{ .Values.pdb.maxUnavailable }} + {{- end }} + selector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/prometheusrule.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/prometheusrule.yaml new file mode 100644 index 0000000..41cf6b8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/prometheusrule.yaml @@ -0,0 +1,23 @@ +{{- if and .Values.metrics.enabled .Values.metrics.prometheusRule.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ template "common.names.fullname" . }} + namespace: {{ default .Release.Namespace .Values.metrics.prometheusRule.namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.metrics.prometheusRule.additionalLabels }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.prometheusRule.additionalLabels "context" $) | nindent 4 }} + {{- end }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + {{- with .Values.metrics.prometheusRule.rules }} + groups: + - name: {{ template "common.names.name" $ }} + rules: {{- tpl (toYaml .) $ | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/replicas/hpa.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/replicas/hpa.yaml new file mode 100644 index 0000000..67d1cc1 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/replicas/hpa.yaml @@ -0,0 +1,47 @@ +{{- if and .Values.replica.autoscaling.enabled (not .Values.sentinel.enabled) }} +apiVersion: {{ include "common.capabilities.hpa.apiVersion" ( dict "context" $ ) }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ printf "%s-replicas" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: replica + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" (dict "value" .Values.commonLabels "context" $) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + scaleTargetRef: + apiVersion: {{ include "common.capabilities.deployment.apiVersion" . }} + kind: StatefulSet + name: {{ printf "%s-replicas" (include "common.names.fullname" .) }} + minReplicas: {{ .Values.replica.autoscaling.minReplicas }} + maxReplicas: {{ .Values.replica.autoscaling.maxReplicas }} + metrics: + {{- if .Values.replica.autoscaling.targetCPU }} + - type: Resource + resource: + name: cpu + {{- if semverCompare "<1.23-0" (include "common.capabilities.kubeVersion" .) }} + targetAverageUtilization: {{ .Values.replica.autoscaling.targetCPU }} + {{- else }} + target: + type: Utilization + averageUtilization: {{ .Values.replica.autoscaling.targetCPU }} + {{- end }} + {{- end }} + {{- if .Values.replica.autoscaling.targetMemory }} + - type: Resource + resource: + name: memory + {{- if semverCompare "<1.23-0" (include "common.capabilities.kubeVersion" .) }} + targetAverageUtilization: {{ .Values.replica.autoscaling.targetMemory }} + {{- else }} + target: + type: Utilization + averageUtilization: {{ .Values.replica.autoscaling.targetMemory }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/replicas/service.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/replicas/service.yaml new file mode 100644 index 0000000..f261926 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/replicas/service.yaml @@ -0,0 +1,58 @@ +{{- if and (eq .Values.architecture "replication") (not .Values.sentinel.enabled) }} +apiVersion: v1 +kind: Service +metadata: + name: {{ printf "%s-replicas" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: replica + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if or .Values.replica.service.annotations .Values.commonAnnotations }} + annotations: + {{- if .Values.replica.service.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.replica.service.annotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- end }} +spec: + type: {{ .Values.replica.service.type }} + {{- if or (eq .Values.replica.service.type "LoadBalancer") (eq .Values.replica.service.type "NodePort") }} + externalTrafficPolicy: {{ .Values.replica.service.externalTrafficPolicy | quote }} + {{- end }} + {{- if (semverCompare ">=1.22-0" (include "common.capabilities.kubeVersion" .)) }} + internalTrafficPolicy: {{ .Values.replica.service.internalTrafficPolicy }} + {{- end }} + {{- if and (eq .Values.replica.service.type "LoadBalancer") (not (empty .Values.replica.service.loadBalancerIP)) }} + loadBalancerIP: {{ .Values.replica.service.loadBalancerIP }} + {{- end }} + {{- if and (eq .Values.replica.service.type "LoadBalancer") (not (empty .Values.replica.service.loadBalancerSourceRanges)) }} + loadBalancerSourceRanges: {{ .Values.replica.service.loadBalancerSourceRanges }} + {{- end }} + {{- if and .Values.replica.service.clusterIP (eq .Values.replica.service.type "ClusterIP") }} + clusterIP: {{ .Values.replica.service.clusterIP }} + {{- end }} + {{- if .Values.replica.service.sessionAffinity }} + sessionAffinity: {{ .Values.replica.service.sessionAffinity }} + {{- end }} + {{- if .Values.replica.service.sessionAffinityConfig }} + sessionAffinityConfig: {{- include "common.tplvalues.render" (dict "value" .Values.replica.service.sessionAffinityConfig "context" $) | nindent 4 }} + {{- end }} + ports: + - name: tcp-redis + port: {{ .Values.replica.service.ports.redis }} + targetPort: redis + {{- if and (or (eq .Values.replica.service.type "NodePort") (eq .Values.replica.service.type "LoadBalancer")) .Values.replica.service.nodePorts.redis}} + nodePort: {{ .Values.replica.service.nodePorts.redis}} + {{- else if eq .Values.replica.service.type "ClusterIP" }} + nodePort: null + {{- end }} + {{- if .Values.replica.service.extraPorts }} + {{- include "common.tplvalues.render" (dict "value" .Values.replica.service.extraPorts "context" $) | nindent 4 }} + {{- end }} + selector: {{- include "common.labels.matchLabels" . | nindent 4 }} + app.kubernetes.io/component: replica +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/replicas/statefulset.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/replicas/statefulset.yaml new file mode 100644 index 0000000..8ddc86c --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/replicas/statefulset.yaml @@ -0,0 +1,471 @@ +{{- if and (eq .Values.architecture "replication") (not .Values.sentinel.enabled) }} +apiVersion: {{ include "common.capabilities.statefulset.apiVersion" . }} +kind: StatefulSet +metadata: + name: {{ printf "%s-replicas" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: replica + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + {{- if not .Values.replica.autoscaling.enabled }} + replicas: {{ .Values.replica.replicaCount }} + {{- end }} + selector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + app.kubernetes.io/component: replica + serviceName: {{ printf "%s-headless" (include "common.names.fullname" .) }} + {{- if .Values.replica.updateStrategy }} + updateStrategy: {{- toYaml .Values.replica.updateStrategy | nindent 4 }} + {{- end }} + {{- if .Values.replica.podManagementPolicy }} + podManagementPolicy: {{ .Values.replica.podManagementPolicy | quote }} + {{- end }} + template: + metadata: + labels: {{- include "common.labels.standard" . | nindent 8 }} + app.kubernetes.io/component: replica + {{- if .Values.replica.podLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.replica.podLabels "context" $ ) | nindent 8 }} + {{- end }} + {{- if and .Values.metrics.enabled .Values.metrics.podLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.podLabels "context" $ ) | nindent 8 }} + {{- end }} + annotations: + {{- if (include "redis.createConfigmap" .) }} + checksum/configmap: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + {{- end }} + checksum/health: {{ include (print $.Template.BasePath "/health-configmap.yaml") . | sha256sum }} + checksum/scripts: {{ include (print $.Template.BasePath "/scripts-configmap.yaml") . | sha256sum }} + checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }} + {{- if .Values.replica.podAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.replica.podAnnotations "context" $ ) | nindent 8 }} + {{- end }} + {{- if and .Values.metrics.enabled .Values.metrics.podAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.podAnnotations "context" $ ) | nindent 8 }} + {{- end }} + spec: + {{- include "redis.imagePullSecrets" . | nindent 6 }} + {{- if .Values.replica.hostAliases }} + hostAliases: {{- include "common.tplvalues.render" (dict "value" .Values.replica.hostAliases "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.replica.podSecurityContext.enabled }} + securityContext: {{- omit .Values.replica.podSecurityContext "enabled" | toYaml | nindent 8 }} + {{- end }} + serviceAccountName: {{ template "redis.serviceAccountName" . }} + {{- if .Values.replica.priorityClassName }} + priorityClassName: {{ .Values.replica.priorityClassName | quote }} + {{- end }} + {{- if .Values.replica.affinity }} + affinity: {{- include "common.tplvalues.render" (dict "value" .Values.replica.affinity "context" $) | nindent 8 }} + {{- else }} + affinity: + podAffinity: {{- include "common.affinities.pods" (dict "type" .Values.replica.podAffinityPreset "component" "replica" "context" $) | nindent 10 }} + podAntiAffinity: {{- include "common.affinities.pods" (dict "type" .Values.replica.podAntiAffinityPreset "component" "replica" "context" $) | nindent 10 }} + nodeAffinity: {{- include "common.affinities.nodes" (dict "type" .Values.replica.nodeAffinityPreset.type "key" .Values.replica.nodeAffinityPreset.key "values" .Values.replica.nodeAffinityPreset.values) | nindent 10 }} + {{- end }} + {{- if .Values.replica.nodeSelector }} + nodeSelector: {{- include "common.tplvalues.render" (dict "value" .Values.replica.nodeSelector "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.replica.tolerations }} + tolerations: {{- include "common.tplvalues.render" (dict "value" .Values.replica.tolerations "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.replica.topologySpreadConstraints }} + topologySpreadConstraints: {{- include "common.tplvalues.render" (dict "value" .Values.replica.topologySpreadConstraints "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.replica.shareProcessNamespace }} + shareProcessNamespace: {{ .Values.replica.shareProcessNamespace }} + {{- end }} + {{- if .Values.replica.schedulerName }} + schedulerName: {{ .Values.replica.schedulerName | quote }} + {{- end }} + {{- if .Values.replica.dnsPolicy }} + dnsPolicy: {{ .Values.replica.dnsPolicy }} + {{- end }} + {{- if .Values.replica.dnsConfig }} + dnsConfig: {{- include "common.tplvalues.render" (dict "value" .Values.replica.dnsConfig "context" $) | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.replica.terminationGracePeriodSeconds }} + containers: + - name: redis + image: {{ template "redis.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy | quote }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.replica.lifecycleHooks }} + lifecycle: {{- include "common.tplvalues.render" (dict "value" .Values.replica.lifecycleHooks "context" $) | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.replica.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.replica.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + {{- else if .Values.replica.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.replica.command "context" $) | nindent 12 }} + {{- else }} + command: + - /bin/bash + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else if .Values.replica.args }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.replica.args "context" $) | nindent 12 }} + {{- else }} + args: + - -c + - /opt/bitnami/scripts/start-scripts/start-replica.sh + {{- end }} + env: + - name: BITNAMI_DEBUG + value: {{ ternary "true" "false" (or .Values.image.debug .Values.diagnosticMode.enabled) | quote }} + - name: REDIS_REPLICATION_MODE + value: slave + - name: REDIS_MASTER_HOST + {{- if and (eq (int64 .Values.master.count) 1) (ne .Values.master.kind "Deployment") }} + value: {{ template "common.names.fullname" . }}-master-0.{{ template "common.names.fullname" . }}-headless.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }} + {{- else }} + value: {{ template "common.names.fullname" . }}-master.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }} + {{- end }} + - name: REDIS_MASTER_PORT_NUMBER + value: {{ .Values.master.containerPorts.redis | quote }} + - name: ALLOW_EMPTY_PASSWORD + value: {{ ternary "no" "yes" .Values.auth.enabled | quote }} + {{- if .Values.auth.enabled }} + {{- if .Values.auth.usePasswordFiles }} + - name: REDIS_PASSWORD_FILE + value: "/opt/bitnami/redis/secrets/redis-password" + - name: REDIS_MASTER_PASSWORD_FILE + value: "/opt/bitnami/redis/secrets/redis-password" + {{- else }} + - name: REDIS_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "redis.secretName" . }} + key: {{ template "redis.secretPasswordKey" . }} + - name: REDIS_MASTER_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "redis.secretName" . }} + key: {{ template "redis.secretPasswordKey" . }} + {{- end }} + {{- end }} + - name: REDIS_TLS_ENABLED + value: {{ ternary "yes" "no" .Values.tls.enabled | quote }} + {{- if .Values.tls.enabled }} + - name: REDIS_TLS_PORT + value: {{ .Values.replica.containerPorts.redis | quote }} + - name: REDIS_TLS_AUTH_CLIENTS + value: {{ ternary "yes" "no" .Values.tls.authClients | quote }} + - name: REDIS_TLS_CERT_FILE + value: {{ template "redis.tlsCert" . }} + - name: REDIS_TLS_KEY_FILE + value: {{ template "redis.tlsCertKey" . }} + - name: REDIS_TLS_CA_FILE + value: {{ template "redis.tlsCACert" . }} + {{- if .Values.tls.dhParamsFilename }} + - name: REDIS_TLS_DH_PARAMS_FILE + value: {{ template "redis.tlsDHParams" . }} + {{- end }} + {{- else }} + - name: REDIS_PORT + value: {{ .Values.replica.containerPorts.redis | quote }} + {{- end }} + {{- if .Values.replica.extraEnvVars }} + {{- include "common.tplvalues.render" (dict "value" .Values.replica.extraEnvVars "context" $) | nindent 12 }} + {{- end }} + {{- if or .Values.replica.extraEnvVarsCM .Values.replica.extraEnvVarsSecret }} + envFrom: + {{- if .Values.replica.extraEnvVarsCM }} + - configMapRef: + name: {{ .Values.replica.extraEnvVarsCM }} + {{- end }} + {{- if .Values.replica.extraEnvVarsSecret }} + - secretRef: + name: {{ .Values.replica.extraEnvVarsSecret }} + {{- end }} + {{- end }} + ports: + - name: redis + containerPort: {{ .Values.replica.containerPorts.redis }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.replica.startupProbe.enabled }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.replica.startupProbe "enabled") "context" $) | nindent 12 }} + tcpSocket: + port: redis + {{- else if .Values.replica.customStartupProbe }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.replica.customStartupProbe "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.replica.livenessProbe.enabled }} + livenessProbe: + initialDelaySeconds: {{ .Values.replica.livenessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.replica.livenessProbe.periodSeconds }} + timeoutSeconds: {{ add1 .Values.replica.livenessProbe.timeoutSeconds }} + successThreshold: {{ .Values.replica.livenessProbe.successThreshold }} + failureThreshold: {{ .Values.replica.livenessProbe.failureThreshold }} + exec: + command: + - sh + - -c + - /health/ping_liveness_local_and_master.sh {{ .Values.replica.livenessProbe.timeoutSeconds }} + {{- else if .Values.replica.customLivenessProbe }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.replica.customLivenessProbe "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.replica.readinessProbe.enabled }} + readinessProbe: + initialDelaySeconds: {{ .Values.replica.readinessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.replica.readinessProbe.periodSeconds }} + timeoutSeconds: {{ add1 .Values.replica.readinessProbe.timeoutSeconds }} + successThreshold: {{ .Values.replica.readinessProbe.successThreshold }} + failureThreshold: {{ .Values.replica.readinessProbe.failureThreshold }} + exec: + command: + - sh + - -c + - /health/ping_readiness_local_and_master.sh {{ .Values.replica.readinessProbe.timeoutSeconds }} + {{- else if .Values.replica.customReadinessProbe }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.replica.customReadinessProbe "context" $) | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.replica.resources }} + resources: {{- toYaml .Values.replica.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: start-scripts + mountPath: /opt/bitnami/scripts/start-scripts + - name: health + mountPath: /health + {{- if .Values.auth.usePasswordFiles }} + - name: redis-password + mountPath: /opt/bitnami/redis/secrets/ + {{- end }} + - name: redis-data + mountPath: /data + subPath: {{ .Values.replica.persistence.subPath }} + - name: config + mountPath: /opt/bitnami/redis/mounted-etc + - name: redis-tmp-conf + mountPath: /opt/bitnami/redis/etc + {{- if .Values.tls.enabled }} + - name: redis-certificates + mountPath: /opt/bitnami/redis/certs + readOnly: true + {{- end }} + {{- if .Values.replica.extraVolumeMounts }} + {{- include "common.tplvalues.render" ( dict "value" .Values.replica.extraVolumeMounts "context" $ ) | nindent 12 }} + {{- end }} + {{- if .Values.metrics.enabled }} + - name: metrics + image: {{ include "redis.metrics.image" . }} + imagePullPolicy: {{ .Values.metrics.image.pullPolicy | quote }} + {{- if .Values.metrics.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.metrics.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + {{- else if .Values.metrics.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.metrics.command "context" $) | nindent 12 }} + {{- else }} + command: + - /bin/bash + - -c + - | + if [[ -f '/secrets/redis-password' ]]; then + export REDIS_PASSWORD=$(cat /secrets/redis-password) + fi + redis_exporter{{- range $key, $value := .Values.metrics.extraArgs }} --{{ $key }}={{ $value }}{{- end }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- end }} + env: + - name: REDIS_ALIAS + value: {{ template "common.names.fullname" . }} + {{- if .Values.auth.enabled }} + - name: REDIS_USER + value: default + {{- if (not .Values.auth.usePasswordFiles) }} + - name: REDIS_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "redis.secretName" . }} + key: {{ template "redis.secretPasswordKey" . }} + {{- end }} + {{- end }} + {{- if .Values.tls.enabled }} + - name: REDIS_ADDR + value: rediss://{{ .Values.metrics.redisTargetHost }}:{{ .Values.replica.containerPorts.redis }} + {{- if .Values.tls.authClients }} + - name: REDIS_EXPORTER_TLS_CLIENT_KEY_FILE + value: {{ template "redis.tlsCertKey" . }} + - name: REDIS_EXPORTER_TLS_CLIENT_CERT_FILE + value: {{ template "redis.tlsCert" . }} + {{- end }} + - name: REDIS_EXPORTER_TLS_CA_CERT_FILE + value: {{ template "redis.tlsCACert" . }} + {{- end }} + ports: + - name: metrics + containerPort: 9121 + {{- if .Values.metrics.resources }} + resources: {{- toYaml .Values.metrics.resources | nindent 12 }} + {{- end }} + volumeMounts: + {{- if .Values.auth.usePasswordFiles }} + - name: redis-password + mountPath: /secrets/ + {{- end }} + {{- if .Values.tls.enabled }} + - name: redis-certificates + mountPath: /opt/bitnami/redis/certs + readOnly: true + {{- end }} + {{- if .Values.metrics.extraVolumeMounts }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.extraVolumeMounts "context" $ ) | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.replica.sidecars }} + {{- include "common.tplvalues.render" (dict "value" .Values.replica.sidecars "context" $) | nindent 8 }} + {{- end }} + {{- $needsVolumePermissions := and .Values.volumePermissions.enabled .Values.replica.persistence.enabled .Values.replica.podSecurityContext.enabled .Values.replica.containerSecurityContext.enabled }} + {{- if or .Values.replica.initContainers $needsVolumePermissions .Values.sysctl.enabled }} + initContainers: + {{- if .Values.replica.initContainers }} + {{- include "common.tplvalues.render" (dict "value" .Values.replica.initContainers "context" $) | nindent 8 }} + {{- end }} + {{- if $needsVolumePermissions }} + - name: volume-permissions + image: {{ include "redis.volumePermissions.image" . }} + imagePullPolicy: {{ .Values.volumePermissions.image.pullPolicy | quote }} + command: + - /bin/bash + - -ec + - | + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + chown -R `id -u`:`id -G | cut -d " " -f2` {{ .Values.replica.persistence.path }} + {{- else }} + chown -R {{ .Values.replica.containerSecurityContext.runAsUser }}:{{ .Values.replica.podSecurityContext.fsGroup }} {{ .Values.replica.persistence.path }} + {{- end }} + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + securityContext: {{- omit .Values.volumePermissions.containerSecurityContext "runAsUser" | toYaml | nindent 12 }} + {{- else }} + securityContext: {{- .Values.volumePermissions.containerSecurityContext | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.volumePermissions.resources }} + resources: {{- toYaml .Values.volumePermissions.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: redis-data + mountPath: {{ .Values.replica.persistence.path }} + subPath: {{ .Values.replica.persistence.subPath }} + {{- end }} + {{- if .Values.sysctl.enabled }} + - name: init-sysctl + image: {{ include "redis.sysctl.image" . }} + imagePullPolicy: {{ default "" .Values.sysctl.image.pullPolicy | quote }} + securityContext: + privileged: true + runAsUser: 0 + {{- if .Values.sysctl.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.sysctl.command "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.sysctl.resources }} + resources: {{- toYaml .Values.sysctl.resources | nindent 12 }} + {{- end }} + {{- if .Values.sysctl.mountHostSys }} + volumeMounts: + - name: host-sys + mountPath: /host-sys + {{- end }} + {{- end }} + {{- end }} + volumes: + - name: start-scripts + configMap: + name: {{ printf "%s-scripts" (include "common.names.fullname" .) }} + defaultMode: 0755 + - name: health + configMap: + name: {{ printf "%s-health" (include "common.names.fullname" .) }} + defaultMode: 0755 + {{- if .Values.auth.usePasswordFiles }} + - name: redis-password + secret: + secretName: {{ template "redis.secretName" . }} + items: + - key: {{ template "redis.secretPasswordKey" . }} + path: redis-password + {{- end }} + - name: config + configMap: + name: {{ include "redis.configmapName" . }} + {{- if .Values.sysctl.mountHostSys }} + - name: host-sys + hostPath: + path: /sys + {{- end }} + - name: redis-tmp-conf + {{- if .Values.replica.persistence.medium }} + emptyDir: + medium: {{ .Values.replica.persistence.medium | quote }} + {{- if .Values.replica.persistence.sizeLimit }} + sizeLimit: {{ .Values.replica.persistence.sizeLimit | quote }} + {{- end }} + {{- else }} + emptyDir: {} + {{- end }} + {{- if .Values.tls.enabled }} + - name: redis-certificates + secret: + secretName: {{ include "redis.tlsSecretName" . }} + defaultMode: 256 + {{- end }} + {{- if .Values.replica.extraVolumes }} + {{- include "common.tplvalues.render" ( dict "value" .Values.replica.extraVolumes "context" $ ) | nindent 8 }} + {{- end }} + {{- if .Values.metrics.extraVolumes }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.extraVolumes "context" $ ) | nindent 8 }} + {{- end }} + {{- if not .Values.replica.persistence.enabled }} + - name: redis-data + {{- if .Values.replica.persistence.medium }} + emptyDir: { + medium: {{ .Values.replica.persistence.medium | quote }} + } + {{- else }} + emptyDir: {} + {{- end }} + {{- else if .Values.replica.persistence.existingClaim }} + - name: redis-data + persistentVolumeClaim: + claimName: {{ printf "%s" (tpl .Values.replica.persistence.existingClaim .) }} + {{- else }} + volumeClaimTemplates: + - metadata: + name: redis-data + labels: {{- include "common.labels.matchLabels" . | nindent 10 }} + app.kubernetes.io/component: replica + {{- if .Values.replica.persistence.annotations }} + annotations: {{- toYaml .Values.replica.persistence.annotations | nindent 10 }} + {{- end }} + spec: + accessModes: + {{- range .Values.replica.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + resources: + requests: + storage: {{ .Values.replica.persistence.size | quote }} + {{- if .Values.replica.persistence.selector }} + selector: {{- include "common.tplvalues.render" (dict "value" .Values.replica.persistence.selector "context" $) | nindent 10 }} + {{- end }} + {{- if .Values.replica.persistence.dataSource }} + dataSource: {{- include "common.tplvalues.render" (dict "value" .Values.replica.persistence.dataSource "context" $) | nindent 10 }} + {{- end }} + {{- include "common.storage.class" (dict "persistence" .Values.replica.persistence "global" .Values.global) | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/role.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/role.yaml new file mode 100644 index 0000000..596466f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/role.yaml @@ -0,0 +1,28 @@ +{{- if .Values.rbac.create }} +apiVersion: {{ include "common.capabilities.rbac.apiVersion" . }} +kind: Role +metadata: + name: {{ template "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +rules: + {{- $pspAvailable := (semverCompare "<1.25-0" (include "common.capabilities.kubeVersion" .)) -}} + {{- if and $pspAvailable .Values.podSecurityPolicy.enabled }} + - apiGroups: + - '{{ template "podSecurityPolicy.apiGroup" . }}' + resources: + - 'podsecuritypolicies' + verbs: + - 'use' + resourceNames: [{{ printf "%s-master" (include "common.names.fullname" .) }}] + {{- end }} + {{- if .Values.rbac.rules }} + {{- include "common.tplvalues.render" ( dict "value" .Values.rbac.rules "context" $ ) | nindent 2 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/rolebinding.yaml new file mode 100644 index 0000000..74968b8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/rolebinding.yaml @@ -0,0 +1,21 @@ +{{- if .Values.rbac.create }} +apiVersion: {{ include "common.capabilities.rbac.apiVersion" . }} +kind: RoleBinding +metadata: + name: {{ template "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ template "common.names.fullname" . }} +subjects: + - kind: ServiceAccount + name: {{ template "redis.serviceAccountName" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/scripts-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/scripts-configmap.yaml new file mode 100644 index 0000000..7447646 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/scripts-configmap.yaml @@ -0,0 +1,627 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ printf "%s-scripts" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: +{{- if and (eq .Values.architecture "replication") .Values.sentinel.enabled }} + start-node.sh: | + #!/bin/bash + + . /opt/bitnami/scripts/libos.sh + . /opt/bitnami/scripts/liblog.sh + . /opt/bitnami/scripts/libvalidations.sh + + get_port() { + hostname="$1" + type="$2" + + port_var=$(echo "${hostname^^}_SERVICE_PORT_$type" | sed "s/-/_/g") + port=${!port_var} + + if [ -z "$port" ]; then + case $type in + "SENTINEL") + echo {{ .Values.sentinel.containerPorts.sentinel }} + ;; + "REDIS") + echo {{ .Values.master.containerPorts.redis }} + ;; + esac + else + echo $port + fi + } + + get_full_hostname() { + hostname="$1" + + {{- if .Values.useExternalDNS.enabled }} + echo "${hostname}.{{- include "redis.externalDNS.suffix" . }}" + {{- else if eq .Values.sentinel.service.type "NodePort" }} + echo "${hostname}.{{- .Release.Namespace }}" + {{- else }} + echo "${hostname}.${HEADLESS_SERVICE}" + {{- end }} + } + + REDISPORT=$(get_port "$HOSTNAME" "REDIS") + + HEADLESS_SERVICE="{{ template "common.names.fullname" . }}-headless.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }}" + + if [ -n "$REDIS_EXTERNAL_MASTER_HOST" ]; then + REDIS_SERVICE="$REDIS_EXTERNAL_MASTER_HOST" + else + REDIS_SERVICE="{{ template "common.names.fullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }}" + fi + + SENTINEL_SERVICE_PORT=$(get_port "{{ include "common.names.fullname" . }}" "TCP_SENTINEL") + validate_quorum() { + if is_boolean_yes "$REDIS_SENTINEL_TLS_ENABLED"; then + quorum_info_command="{{- if and .Values.auth.enabled .Values.auth.sentinel }}REDISCLI_AUTH="\$REDIS_PASSWORD" {{ end }}redis-cli -h $REDIS_SERVICE -p $SENTINEL_SERVICE_PORT --tls --cert ${REDIS_SENTINEL_TLS_CERT_FILE} --key ${REDIS_SENTINEL_TLS_KEY_FILE} --cacert ${REDIS_SENTINEL_TLS_CA_FILE} sentinel master {{ .Values.sentinel.masterSet }}" + else + quorum_info_command="{{- if and .Values.auth.enabled .Values.auth.sentinel }}REDISCLI_AUTH="\$REDIS_PASSWORD" {{ end }}redis-cli -h $REDIS_SERVICE -p $SENTINEL_SERVICE_PORT sentinel master {{ .Values.sentinel.masterSet }}" + fi + info "about to run the command: $quorum_info_command" + eval $quorum_info_command | grep -Fq "s_down" + } + + trigger_manual_failover() { + if is_boolean_yes "$REDIS_SENTINEL_TLS_ENABLED"; then + failover_command="{{- if and .Values.auth.enabled .Values.auth.sentinel }}REDISCLI_AUTH="\$REDIS_PASSWORD" {{ end }}redis-cli -h $REDIS_SERVICE -p $SENTINEL_SERVICE_PORT --tls --cert ${REDIS_SENTINEL_TLS_CERT_FILE} --key ${REDIS_SENTINEL_TLS_KEY_FILE} --cacert ${REDIS_SENTINEL_TLS_CA_FILE} sentinel failover {{ .Values.sentinel.masterSet }}" + else + failover_command="{{- if and .Values.auth.enabled .Values.auth.sentinel }}REDISCLI_AUTH="\$REDIS_PASSWORD" {{ end }}redis-cli -h $REDIS_SERVICE -p $SENTINEL_SERVICE_PORT sentinel failover {{ .Values.sentinel.masterSet }}" + fi + + info "about to run the command: $failover_command" + eval $failover_command + } + + get_sentinel_master_info() { + if is_boolean_yes "$REDIS_SENTINEL_TLS_ENABLED"; then + sentinel_info_command="{{- if and .Values.auth.enabled .Values.auth.sentinel }}REDISCLI_AUTH="\$REDIS_PASSWORD" {{ end }}timeout {{ .Values.sentinel.getMasterTimeout }} redis-cli -h $REDIS_SERVICE -p $SENTINEL_SERVICE_PORT --tls --cert ${REDIS_SENTINEL_TLS_CERT_FILE} --key ${REDIS_SENTINEL_TLS_KEY_FILE} --cacert ${REDIS_SENTINEL_TLS_CA_FILE} sentinel get-master-addr-by-name {{ .Values.sentinel.masterSet }}" + else + sentinel_info_command="{{- if and .Values.auth.enabled .Values.auth.sentinel }}REDISCLI_AUTH="\$REDIS_PASSWORD" {{ end }}timeout {{ .Values.sentinel.getMasterTimeout }} redis-cli -h $REDIS_SERVICE -p $SENTINEL_SERVICE_PORT sentinel get-master-addr-by-name {{ .Values.sentinel.masterSet }}" + fi + + info "about to run the command: $sentinel_info_command" + eval $sentinel_info_command + } + + {{- if and .Values.replica.containerSecurityContext.runAsUser (eq (.Values.replica.containerSecurityContext.runAsUser | int) 0) }} + useradd redis + chown -R redis {{ .Values.replica.persistence.path }} + {{- end }} + + [[ -f $REDIS_PASSWORD_FILE ]] && export REDIS_PASSWORD="$(< "${REDIS_PASSWORD_FILE}")" + [[ -f $REDIS_MASTER_PASSWORD_FILE ]] && export REDIS_MASTER_PASSWORD="$(< "${REDIS_MASTER_PASSWORD_FILE}")" + + # check if there is a master + master_in_persisted_conf="$(get_full_hostname "$HOSTNAME")" + master_port_in_persisted_conf="$REDIS_MASTER_PORT_NUMBER" + master_in_sentinel="$(get_sentinel_master_info)" + redisRetVal=$? + + {{- if .Values.sentinel.persistence.enabled }} + if [[ -f /opt/bitnami/redis-sentinel/etc/sentinel.conf ]]; then + master_in_persisted_conf="$(awk '/monitor/ {print $4}' /opt/bitnami/redis-sentinel/etc/sentinel.conf)" + master_port_in_persisted_conf="$(awk '/monitor/ {print $5}' /opt/bitnami/redis-sentinel/etc/sentinel.conf)" + info "Found previous master ${master_in_persisted_conf}:${master_port_in_persisted_conf} in /opt/bitnami/redis-sentinel/etc/sentinel.conf" + debug "$(cat /opt/bitnami/redis-sentinel/etc/sentinel.conf | grep monitor)" + touch /opt/bitnami/redis-sentinel/etc/.node_read + fi + {{- end }} + + if [[ $redisRetVal -ne 0 ]]; then + if [[ "$master_in_persisted_conf" == "$(get_full_hostname "$HOSTNAME")" ]]; then + # Case 1: No active sentinel and in previous sentinel.conf we were the master --> MASTER + info "Configuring the node as master" + export REDIS_REPLICATION_MODE="master" + else + # Case 2: No active sentinel and in previous sentinel.conf we were not master --> REPLICA + info "Configuring the node as replica" + export REDIS_REPLICATION_MODE="slave" + REDIS_MASTER_HOST=${master_in_persisted_conf} + REDIS_MASTER_PORT_NUMBER=${master_port_in_persisted_conf} + fi + else + # Fetches current master's host and port + REDIS_SENTINEL_INFO=($(get_sentinel_master_info)) + info "Current master: REDIS_SENTINEL_INFO=(${REDIS_SENTINEL_INFO[0]},${REDIS_SENTINEL_INFO[1]})" + REDIS_MASTER_HOST=${REDIS_SENTINEL_INFO[0]} + REDIS_MASTER_PORT_NUMBER=${REDIS_SENTINEL_INFO[1]} + + if [[ "$REDIS_MASTER_HOST" == "$(get_full_hostname "$HOSTNAME")" ]]; then + # Case 3: Active sentinel and master it is this node --> MASTER + info "Configuring the node as master" + export REDIS_REPLICATION_MODE="master" + else + # Case 4: Active sentinel and master is not this node --> REPLICA + info "Configuring the node as replica" + export REDIS_REPLICATION_MODE="slave" + + {{- if and .Values.sentinel.automateClusterRecovery (le (int .Values.sentinel.downAfterMilliseconds) 2000) }} + retry_count=1 + while validate_quorum + do + info "sleeping, waiting for Redis master to come up" + sleep 1s + if ! ((retry_count % 11)); then + info "Trying to manually failover" + failover_result=$(trigger_manual_failover) + + debug "Failover result: $failover_result" + fi + + ((retry_count+=1)) + done + info "Redis master is up now" + {{- end }} + fi + fi + + if [[ -n "$REDIS_EXTERNAL_MASTER_HOST" ]]; then + REDIS_MASTER_HOST="$REDIS_EXTERNAL_MASTER_HOST" + REDIS_MASTER_PORT_NUMBER="${REDIS_EXTERNAL_MASTER_PORT}" + fi + + if [[ ! -f /opt/bitnami/redis/etc/replica.conf ]];then + cp /opt/bitnami/redis/mounted-etc/replica.conf /opt/bitnami/redis/etc/replica.conf + fi + + if [[ ! -f /opt/bitnami/redis/etc/redis.conf ]];then + cp /opt/bitnami/redis/mounted-etc/redis.conf /opt/bitnami/redis/etc/redis.conf + fi + + echo "" >> /opt/bitnami/redis/etc/replica.conf + echo "replica-announce-port $REDISPORT" >> /opt/bitnami/redis/etc/replica.conf + echo "replica-announce-ip $(get_full_hostname "$HOSTNAME")" >> /opt/bitnami/redis/etc/replica.conf + + {{- if .Values.tls.enabled }} + ARGS=("--port" "0") + ARGS+=("--tls-port" "${REDIS_TLS_PORT}") + ARGS+=("--tls-cert-file" "${REDIS_TLS_CERT_FILE}") + ARGS+=("--tls-key-file" "${REDIS_TLS_KEY_FILE}") + ARGS+=("--tls-ca-cert-file" "${REDIS_TLS_CA_FILE}") + ARGS+=("--tls-auth-clients" "${REDIS_TLS_AUTH_CLIENTS}") + ARGS+=("--tls-replication" "yes") + {{- if .Values.tls.dhParamsFilename }} + ARGS+=("--tls-dh-params-file" "${REDIS_TLS_DH_PARAMS_FILE}") + {{- end }} + {{- else }} + ARGS=("--port" "${REDIS_PORT}") + {{- end }} + + if [[ "$REDIS_REPLICATION_MODE" = "slave" ]]; then + ARGS+=("--replicaof" "${REDIS_MASTER_HOST}" "${REDIS_MASTER_PORT_NUMBER}") + fi + + {{- if .Values.auth.enabled }} + ARGS+=("--requirepass" "${REDIS_PASSWORD}") + ARGS+=("--masterauth" "${REDIS_MASTER_PASSWORD}") + {{- else }} + ARGS+=("--protected-mode" "no") + {{- end }} + ARGS+=("--include" "/opt/bitnami/redis/etc/replica.conf") + ARGS+=("--include" "/opt/bitnami/redis/etc/redis.conf") + {{- if .Values.replica.extraFlags }} + {{- range .Values.replica.extraFlags }} + ARGS+=({{ . | quote }}) + {{- end }} + {{- end }} + + {{- if .Values.replica.preExecCmds }} + {{- .Values.replica.preExecCmds | nindent 4 }} + {{- end }} + + {{- if .Values.replica.command }} + exec {{ .Values.replica.command }} "${ARGS[@]}" + {{- else }} + exec redis-server "${ARGS[@]}" + {{- end }} + + start-sentinel.sh: | + #!/bin/bash + + . /opt/bitnami/scripts/libos.sh + . /opt/bitnami/scripts/libvalidations.sh + . /opt/bitnami/scripts/libfile.sh + + HEADLESS_SERVICE="{{ template "common.names.fullname" . }}-headless.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }}" + REDIS_SERVICE="{{ template "common.names.fullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }}" + + get_port() { + hostname="$1" + type="$2" + + port_var=$(echo "${hostname^^}_SERVICE_PORT_$type" | sed "s/-/_/g") + port=${!port_var} + + if [ -z "$port" ]; then + case $type in + "SENTINEL") + echo {{ .Values.sentinel.containerPorts.sentinel }} + ;; + "REDIS") + echo {{ .Values.master.containerPorts.redis }} + ;; + esac + else + echo $port + fi + } + + get_full_hostname() { + hostname="$1" + + {{- if .Values.useExternalDNS.enabled }} + echo "${hostname}.{{- include "redis.externalDNS.suffix" . }}" + {{- else if eq .Values.sentinel.service.type "NodePort" }} + echo "${hostname}.{{- .Release.Namespace }}" + {{- else }} + echo "${hostname}.${HEADLESS_SERVICE}" + {{- end }} + } + + SERVPORT=$(get_port "$HOSTNAME" "SENTINEL") + REDISPORT=$(get_port "$HOSTNAME" "REDIS") + SENTINEL_SERVICE_PORT=$(get_port "{{ include "common.names.fullname" . }}" "TCP_SENTINEL") + + sentinel_conf_set() { + local -r key="${1:?missing key}" + local value="${2:-}" + + # Sanitize inputs + value="${value//\\/\\\\}" + value="${value//&/\\&}" + value="${value//\?/\\?}" + [[ "$value" = "" ]] && value="\"$value\"" + + replace_in_file "/opt/bitnami/redis-sentinel/etc/sentinel.conf" "^#*\s*${key} .*" "${key} ${value}" false + } + sentinel_conf_add() { + echo $'\n'"$@" >> "/opt/bitnami/redis-sentinel/etc/sentinel.conf" + } + host_id() { + echo "$1" | openssl sha1 | awk '{print $2}' + } + get_sentinel_master_info() { + if is_boolean_yes "$REDIS_SENTINEL_TLS_ENABLED"; then + sentinel_info_command="{{- if and .Values.auth.enabled .Values.auth.sentinel }}REDISCLI_AUTH="\$REDIS_PASSWORD" {{ end }}redis-cli -h $REDIS_SERVICE -p $SENTINEL_SERVICE_PORT --tls --cert ${REDIS_SENTINEL_TLS_CERT_FILE} --key ${REDIS_SENTINEL_TLS_KEY_FILE} --cacert ${REDIS_SENTINEL_TLS_CA_FILE} sentinel get-master-addr-by-name {{ .Values.sentinel.masterSet }}" + else + sentinel_info_command="{{- if and .Values.auth.enabled .Values.auth.sentinel }}REDISCLI_AUTH="\$REDIS_PASSWORD" {{ end }}redis-cli -h $REDIS_SERVICE -p $SENTINEL_SERVICE_PORT sentinel get-master-addr-by-name {{ .Values.sentinel.masterSet }}" + fi + info "about to run the command: $sentinel_info_command" + eval $sentinel_info_command + } + + [[ -f $REDIS_PASSWORD_FILE ]] && export REDIS_PASSWORD="$(< "${REDIS_PASSWORD_FILE}")" + + master_in_persisted_conf="$(get_full_hostname "$HOSTNAME")" + + {{- if .Values.sentinel.persistence.enabled }} + if [[ -f /opt/bitnami/redis-sentinel/etc/sentinel.conf ]]; then + check_lock_file() { + [[ -f /opt/bitnami/redis-sentinel/etc/.node_read ]] + } + retry_while "check_lock_file" + rm -f /opt/bitnami/redis-sentinel/etc/.node_read + master_in_persisted_conf="$(awk '/monitor/ {print $4}' /opt/bitnami/redis-sentinel/etc/sentinel.conf)" + info "Found previous master $master_in_persisted_conf in /opt/bitnami/redis-sentinel/etc/sentinel.conf" + debug "$(cat /opt/bitnami/redis-sentinel/etc/sentinel.conf | grep monitor)" + fi + {{- end }} + if ! get_sentinel_master_info && [[ "$master_in_persisted_conf" == "$(get_full_hostname "$HOSTNAME")" ]]; then + # No master found, lets create a master node + export REDIS_REPLICATION_MODE="master" + + REDIS_MASTER_HOST=$(get_full_hostname "$HOSTNAME") + REDIS_MASTER_PORT_NUMBER="$REDISPORT" + else + export REDIS_REPLICATION_MODE="slave" + + # Fetches current master's host and port + REDIS_SENTINEL_INFO=($(get_sentinel_master_info)) + info "printing REDIS_SENTINEL_INFO=(${REDIS_SENTINEL_INFO[0]},${REDIS_SENTINEL_INFO[1]})" + REDIS_MASTER_HOST=${REDIS_SENTINEL_INFO[0]} + REDIS_MASTER_PORT_NUMBER=${REDIS_SENTINEL_INFO[1]} + fi + + if [[ -n "$REDIS_EXTERNAL_MASTER_HOST" ]]; then + REDIS_MASTER_HOST="$REDIS_EXTERNAL_MASTER_HOST" + REDIS_MASTER_PORT_NUMBER="${REDIS_EXTERNAL_MASTER_PORT}" + fi + + cp /opt/bitnami/redis-sentinel/mounted-etc/sentinel.conf /opt/bitnami/redis-sentinel/etc/sentinel.conf + {{- if .Values.auth.enabled }} + printf "\nsentinel auth-pass %s %s" "{{ .Values.sentinel.masterSet }}" "$REDIS_PASSWORD" >> /opt/bitnami/redis-sentinel/etc/sentinel.conf + {{- if and .Values.auth.enabled .Values.auth.sentinel }} + printf "\nrequirepass %s" "$REDIS_PASSWORD" >> /opt/bitnami/redis-sentinel/etc/sentinel.conf + {{- end }} + {{- end }} + printf "\nsentinel myid %s" "$(host_id "$HOSTNAME")" >> /opt/bitnami/redis-sentinel/etc/sentinel.conf + + sentinel_conf_set "sentinel monitor" "{{ .Values.sentinel.masterSet }} "$REDIS_MASTER_HOST" "$REDIS_MASTER_PORT_NUMBER" {{ .Values.sentinel.quorum }}" + + add_known_sentinel() { + hostname="$1" + ip="$2" + + if [[ -n "$hostname" && -n "$ip" && "$hostname" != "$HOSTNAME" ]]; then + sentinel_conf_add "sentinel known-sentinel {{ .Values.sentinel.masterSet }} $(get_full_hostname "$hostname") $(get_port "$hostname" "SENTINEL") $(host_id "$hostname")" + fi + } + add_known_replica() { + hostname="$1" + ip="$2" + + if [[ -n "$ip" && "$(get_full_hostname "$hostname")" != "$REDIS_MASTER_HOST" ]]; then + sentinel_conf_add "sentinel known-replica {{ .Values.sentinel.masterSet }} $(get_full_hostname "$hostname") $(get_port "$hostname" "REDIS")" + fi + } + + # Add available hosts on the network as known replicas & sentinels + for node in $(seq 0 $(({{ .Values.replica.replicaCount }}-1))); do + hostname="{{ template "common.names.fullname" . }}-node-$node" + ip="$(getent hosts "$hostname.$HEADLESS_SERVICE" | awk '{ print $1 }')" + add_known_sentinel "$hostname" "$ip" + add_known_replica "$hostname" "$ip" + done + + echo "" >> /opt/bitnami/redis-sentinel/etc/sentinel.conf + echo "sentinel announce-hostnames yes" >> /opt/bitnami/redis-sentinel/etc/sentinel.conf + echo "sentinel resolve-hostnames yes" >> /opt/bitnami/redis-sentinel/etc/sentinel.conf + echo "sentinel announce-port $SERVPORT" >> /opt/bitnami/redis-sentinel/etc/sentinel.conf + echo "sentinel announce-ip $(get_full_hostname "$HOSTNAME")" >> /opt/bitnami/redis-sentinel/etc/sentinel.conf + + {{- if .Values.tls.enabled }} + ARGS=("--port" "0") + ARGS+=("--tls-port" "${REDIS_SENTINEL_TLS_PORT_NUMBER}") + ARGS+=("--tls-cert-file" "${REDIS_SENTINEL_TLS_CERT_FILE}") + ARGS+=("--tls-key-file" "${REDIS_SENTINEL_TLS_KEY_FILE}") + ARGS+=("--tls-ca-cert-file" "${REDIS_SENTINEL_TLS_CA_FILE}") + ARGS+=("--tls-replication" "yes") + ARGS+=("--tls-auth-clients" "${REDIS_SENTINEL_TLS_AUTH_CLIENTS}") + {{- if .Values.tls.dhParamsFilename }} + ARGS+=("--tls-dh-params-file" "${REDIS_SENTINEL_TLS_DH_PARAMS_FILE}") + {{- end }} + {{- end }} + {{- if .Values.sentinel.preExecCmds }} + {{ .Values.sentinel.preExecCmds | nindent 4 }} + {{- end }} + exec redis-server /opt/bitnami/redis-sentinel/etc/sentinel.conf --sentinel {{- if .Values.tls.enabled }} "${ARGS[@]}" {{- end }} + prestop-sentinel.sh: | + #!/bin/bash + + . /opt/bitnami/scripts/libvalidations.sh + . /opt/bitnami/scripts/libos.sh + + HEADLESS_SERVICE="{{ template "common.names.fullname" . }}-headless.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }}" + SENTINEL_SERVICE_ENV_NAME={{ printf "%s%s" (upper (include "common.names.fullname" .)| replace "-" "_") "_SERVICE_PORT_TCP_SENTINEL" }} + SENTINEL_SERVICE_PORT=${!SENTINEL_SERVICE_ENV_NAME} + + get_full_hostname() { + hostname="$1" + + {{- if .Values.useExternalDNS.enabled }} + echo "${hostname}.{{- include "redis.externalDNS.suffix" . }}" + {{- else if eq .Values.sentinel.service.type "NodePort" }} + echo "${hostname}.{{- .Release.Namespace }}" + {{- else }} + echo "${hostname}.${HEADLESS_SERVICE}" + {{- end }} + } + run_sentinel_command() { + if is_boolean_yes "$REDIS_SENTINEL_TLS_ENABLED"; then + redis-cli -h "$REDIS_SERVICE" -p "$SENTINEL_SERVICE_PORT" --tls --cert "$REDIS_SENTINEL_TLS_CERT_FILE" --key "$REDIS_SENTINEL_TLS_KEY_FILE" --cacert "$REDIS_SENTINEL_TLS_CA_FILE" sentinel "$@" + else + redis-cli -h "$REDIS_SERVICE" -p "$SENTINEL_SERVICE_PORT" sentinel "$@" + fi + } + failover_finished() { + REDIS_SENTINEL_INFO=($(run_sentinel_command get-master-addr-by-name "{{ .Values.sentinel.masterSet }}")) + REDIS_MASTER_HOST="${REDIS_SENTINEL_INFO[0]}" + [[ "$REDIS_MASTER_HOST" != "$(get_full_hostname $HOSTNAME)" ]] + } + + REDIS_SERVICE="{{ include "common.names.fullname" . }}.{{ .Release.Namespace }}.svc.{{ .Values.clusterDomain }}" + + {{ if .Values.auth.sentinel -}} + # redis-cli automatically consumes credentials from the REDISCLI_AUTH variable + [[ -n "$REDIS_PASSWORD" ]] && export REDISCLI_AUTH="$REDIS_PASSWORD" + [[ -f "$REDIS_PASSWORD_FILE" ]] && export REDISCLI_AUTH="$(< "${REDIS_PASSWORD_FILE}")" + {{- end }} + + if ! failover_finished; then + echo "I am the master pod and you are stopping me. Starting sentinel failover" + # if I am the master, issue a command to failover once and then wait for the failover to finish + run_sentinel_command failover "{{ .Values.sentinel.masterSet }}" + if retry_while "failover_finished" "{{ sub .Values.sentinel.terminationGracePeriodSeconds 10 }}" 1; then + echo "Master has been successfuly failed over to a different pod." + exit 0 + else + echo "Master failover failed" + exit 1 + fi + else + exit 0 + fi + prestop-redis.sh: | + #!/bin/bash + + . /opt/bitnami/scripts/libvalidations.sh + . /opt/bitnami/scripts/libos.sh + + run_redis_command() { + if is_boolean_yes "$REDIS_TLS_ENABLED"; then + redis-cli -h 127.0.0.1 -p "$REDIS_TLS_PORT" --tls --cert "$REDIS_TLS_CERT_FILE" --key "$REDIS_TLS_KEY_FILE" --cacert "$REDIS_TLS_CA_FILE" "$@" + else + redis-cli -h 127.0.0.1 -p ${REDIS_PORT} "$@" + fi + } + failover_finished() { + REDIS_ROLE=$(run_redis_command role | head -1) + [[ "$REDIS_ROLE" != "master" ]] + } + + # redis-cli automatically consumes credentials from the REDISCLI_AUTH variable + [[ -n "$REDIS_PASSWORD" ]] && export REDISCLI_AUTH="$REDIS_PASSWORD" + [[ -f "$REDIS_PASSWORD_FILE" ]] && export REDISCLI_AUTH="$(< "${REDIS_PASSWORD_FILE}")" + + if ! failover_finished; then + echo "Waiting for sentinel to run failover for up to {{ sub .Values.sentinel.terminationGracePeriodSeconds 10 }}s" + retry_while "failover_finished" "{{ sub .Values.sentinel.terminationGracePeriodSeconds 10 }}" 1 + else + exit 0 + fi + +{{- else }} + start-master.sh: | + #!/bin/bash + + [[ -f $REDIS_PASSWORD_FILE ]] && export REDIS_PASSWORD="$(< "${REDIS_PASSWORD_FILE}")" + {{- if and .Values.master.containerSecurityContext.runAsUser (eq (.Values.master.containerSecurityContext.runAsUser | int) 0) }} + useradd redis + chown -R redis {{ .Values.master.persistence.path }} + {{- end }} + if [[ ! -f /opt/bitnami/redis/etc/master.conf ]];then + cp /opt/bitnami/redis/mounted-etc/master.conf /opt/bitnami/redis/etc/master.conf + fi + if [[ ! -f /opt/bitnami/redis/etc/redis.conf ]];then + cp /opt/bitnami/redis/mounted-etc/redis.conf /opt/bitnami/redis/etc/redis.conf + fi + {{- if .Values.tls.enabled }} + ARGS=("--port" "0") + ARGS+=("--tls-port" "${REDIS_TLS_PORT}") + ARGS+=("--tls-cert-file" "${REDIS_TLS_CERT_FILE}") + ARGS+=("--tls-key-file" "${REDIS_TLS_KEY_FILE}") + ARGS+=("--tls-ca-cert-file" "${REDIS_TLS_CA_FILE}") + ARGS+=("--tls-auth-clients" "${REDIS_TLS_AUTH_CLIENTS}") + {{- if .Values.tls.dhParamsFilename }} + ARGS+=("--tls-dh-params-file" "${REDIS_TLS_DH_PARAMS_FILE}") + {{- end }} + {{- else }} + ARGS=("--port" "${REDIS_PORT}") + {{- end }} + {{- if .Values.auth.enabled }} + ARGS+=("--requirepass" "${REDIS_PASSWORD}") + ARGS+=("--masterauth" "${REDIS_PASSWORD}") + {{- else }} + ARGS+=("--protected-mode" "no") + {{- end }} + ARGS+=("--include" "/opt/bitnami/redis/etc/redis.conf") + ARGS+=("--include" "/opt/bitnami/redis/etc/master.conf") + {{- if .Values.master.extraFlags }} + {{- range .Values.master.extraFlags }} + ARGS+=({{ . | quote }}) + {{- end }} + {{- end }} + {{- if .Values.master.preExecCmds }} + {{ .Values.master.preExecCmds | nindent 4 }} + {{- end }} + {{- if .Values.master.command }} + exec {{ .Values.master.command }} "${ARGS[@]}" + {{- else }} + exec redis-server "${ARGS[@]}" + {{- end }} + {{- if eq .Values.architecture "replication" }} + start-replica.sh: | + #!/bin/bash + + get_port() { + hostname="$1" + type="$2" + + port_var=$(echo "${hostname^^}_SERVICE_PORT_$type" | sed "s/-/_/g") + port=${!port_var} + + if [ -z "$port" ]; then + case $type in + "SENTINEL") + echo {{ .Values.sentinel.containerPorts.sentinel }} + ;; + "REDIS") + echo {{ .Values.master.containerPorts.redis }} + ;; + esac + else + echo $port + fi + } + + get_full_hostname() { + hostname="$1" + + {{- if .Values.useExternalDNS.enabled }} + echo "${hostname}.{{- include "redis.externalDNS.suffix" . }}" + {{- else if eq .Values.sentinel.service.type "NodePort" }} + echo "${hostname}.{{- .Release.Namespace }}" + {{- else }} + echo "${hostname}.${HEADLESS_SERVICE}" + {{- end }} + } + + REDISPORT=$(get_port "$HOSTNAME" "REDIS") + + [[ -f $REDIS_PASSWORD_FILE ]] && export REDIS_PASSWORD="$(< "${REDIS_PASSWORD_FILE}")" + [[ -f $REDIS_MASTER_PASSWORD_FILE ]] && export REDIS_MASTER_PASSWORD="$(< "${REDIS_MASTER_PASSWORD_FILE}")" + {{- if and .Values.replica.containerSecurityContext.runAsUser (eq (.Values.replica.containerSecurityContext.runAsUser | int) 0) }} + useradd redis + chown -R redis {{ .Values.replica.persistence.path }} + {{- end }} + if [[ ! -f /opt/bitnami/redis/etc/replica.conf ]];then + cp /opt/bitnami/redis/mounted-etc/replica.conf /opt/bitnami/redis/etc/replica.conf + fi + if [[ ! -f /opt/bitnami/redis/etc/redis.conf ]];then + cp /opt/bitnami/redis/mounted-etc/redis.conf /opt/bitnami/redis/etc/redis.conf + fi + + echo "" >> /opt/bitnami/redis/etc/replica.conf + echo "replica-announce-port $REDISPORT" >> /opt/bitnami/redis/etc/replica.conf + echo "replica-announce-ip $(get_full_hostname "$HOSTNAME")" >> /opt/bitnami/redis/etc/replica.conf + + {{- if .Values.tls.enabled }} + ARGS=("--port" "0") + ARGS+=("--tls-port" "${REDIS_TLS_PORT}") + ARGS+=("--tls-cert-file" "${REDIS_TLS_CERT_FILE}") + ARGS+=("--tls-key-file" "${REDIS_TLS_KEY_FILE}") + ARGS+=("--tls-ca-cert-file" "${REDIS_TLS_CA_FILE}") + ARGS+=("--tls-auth-clients" "${REDIS_TLS_AUTH_CLIENTS}") + ARGS+=("--tls-replication" "yes") + {{- if .Values.tls.dhParamsFilename }} + ARGS+=("--tls-dh-params-file" "${REDIS_TLS_DH_PARAMS_FILE}") + {{- end }} + {{- else }} + ARGS=("--port" "${REDIS_PORT}") + {{- end }} + ARGS+=("--replicaof" "${REDIS_MASTER_HOST}" "${REDIS_MASTER_PORT_NUMBER}") + {{- if .Values.auth.enabled }} + ARGS+=("--requirepass" "${REDIS_PASSWORD}") + ARGS+=("--masterauth" "${REDIS_MASTER_PASSWORD}") + {{- else }} + ARGS+=("--protected-mode" "no") + {{- end }} + ARGS+=("--include" "/opt/bitnami/redis/etc/redis.conf") + ARGS+=("--include" "/opt/bitnami/redis/etc/replica.conf") + {{- if .Values.replica.extraFlags }} + {{- range .Values.replica.extraFlags }} + ARGS+=({{ . | quote }}) + {{- end }} + {{- end }} + {{- if .Values.replica.preExecCmds }} + {{ .Values.replica.preExecCmds | nindent 4 }} + {{- end }} + {{- if .Values.replica.command }} + exec {{ .Values.replica.command }} "${ARGS[@]}" + {{- else }} + exec redis-server "${ARGS[@]}" + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/secret.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/secret.yaml new file mode 100644 index 0000000..2edc0d8 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/secret.yaml @@ -0,0 +1,23 @@ +{{- if and .Values.auth.enabled (not .Values.auth.existingSecret) -}} +apiVersion: v1 +kind: Secret +metadata: + name: {{ template "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if or .Values.secretAnnotations .Values.commonAnnotations }} + annotations: + {{- if .Values.secretAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.secretAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- end }} +type: Opaque +data: + redis-password: {{ include "redis.password" . | b64enc | quote }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/hpa.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/hpa.yaml new file mode 100644 index 0000000..69b36aa --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/hpa.yaml @@ -0,0 +1,47 @@ +{{- if and .Values.replica.autoscaling.enabled .Values.sentinel.enabled }} +apiVersion: {{ include "common.capabilities.hpa.apiVersion" ( dict "context" $ ) }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ printf "%s-node" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: replica + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" (dict "value" .Values.commonLabels "context" $) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + scaleTargetRef: + apiVersion: {{ include "common.capabilities.deployment.apiVersion" . }} + kind: StatefulSet + name: {{ printf "%s-node" (include "common.names.fullname" .) }} + minReplicas: {{ .Values.replica.autoscaling.minReplicas }} + maxReplicas: {{ .Values.replica.autoscaling.maxReplicas }} + metrics: + {{- if .Values.replica.autoscaling.targetCPU }} + - type: Resource + resource: + name: cpu + {{- if semverCompare "<1.23-0" (include "common.capabilities.kubeVersion" .) }} + targetAverageUtilization: {{ .Values.replica.autoscaling.targetCPU }} + {{- else }} + target: + type: Utilization + averageUtilization: {{ .Values.replica.autoscaling.targetCPU }} + {{- end }} + {{- end }} + {{- if .Values.replica.autoscaling.targetMemory }} + - type: Resource + resource: + name: memory + {{- if semverCompare "<1.23-0" (include "common.capabilities.kubeVersion" .) }} + targetAverageUtilization: {{ .Values.replica.autoscaling.targetMemory }} + {{- else }} + target: + type: Utilization + averageUtilization: {{ .Values.replica.autoscaling.targetMemory }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/node-services.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/node-services.yaml new file mode 100644 index 0000000..d3e635e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/node-services.yaml @@ -0,0 +1,70 @@ +{{- if and (eq .Values.architecture "replication") .Values.sentinel.enabled (eq .Values.sentinel.service.type "NodePort") (or .Release.IsUpgrade .Values.sentinel.service.nodePorts.redis ) }} + +{{- range $i := until (int .Values.replica.replicaCount) }} + +{{ $portsmap := (lookup "v1" "ConfigMap" $.Release.Namespace (printf "%s-%s" ( include "common.names.fullname" $ ) "ports-configmap")).data }} + +{{ $sentinelport := 0}} +{{ $redisport := 0}} +{{- if $portsmap }} +{{ $sentinelport = index $portsmap (printf "%s-node-%s-%s" (include "common.names.fullname" $) (toString $i) "sentinel") }} +{{ $redisport = index $portsmap (printf "%s-node-%s-%s" (include "common.names.fullname" $) (toString $i) "redis") }} +{{- else }} +{{- end }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "common.names.fullname" $ }}-node-{{ $i }} + namespace: {{ $.Release.Namespace | quote }} + labels: {{- include "common.labels.standard" $ | nindent 4 }} + app.kubernetes.io/component: node + {{- if $.Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" $.Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if or $.Values.sentinel.service.annotations $.Values.commonAnnotations }} + annotations: + {{- if $.Values.sentinel.service.annotations }} + {{- include "common.tplvalues.render" ( dict "value" $.Values.sentinel.service.annotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if $.Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" $.Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- end }} +spec: + type: NodePort + ports: + - name: sentinel + {{- if $.Values.sentinel.service.nodePorts.sentinel }} + nodePort: {{ (add $.Values.sentinel.service.nodePorts.sentinel $i 1) }} + port: {{ (add $.Values.sentinel.service.nodePorts.sentinel $i 1) }} + {{- else }} + nodePort: {{ $sentinelport }} + port: {{ $sentinelport }} + {{- end }} + protocol: TCP + targetPort: {{ $.Values.sentinel.containerPorts.sentinel }} + - name: redis + {{- if $.Values.sentinel.service.nodePorts.redis }} + nodePort: {{ (add $.Values.sentinel.service.nodePorts.redis $i 1) }} + port: {{ (add $.Values.sentinel.service.nodePorts.redis $i 1) }} + {{- else }} + nodePort: {{ $redisport }} + port: {{ $redisport }} + {{- end }} + protocol: TCP + targetPort: {{ $.Values.replica.containerPorts.redis }} + - name: sentinel-internal + nodePort: null + port: {{ $.Values.sentinel.containerPorts.sentinel }} + protocol: TCP + targetPort: {{ $.Values.sentinel.containerPorts.sentinel }} + - name: redis-internal + nodePort: null + port: {{ $.Values.replica.containerPorts.redis }} + protocol: TCP + targetPort: {{ $.Values.replica.containerPorts.redis }} + selector: + statefulset.kubernetes.io/pod-name: {{ template "common.names.fullname" $ }}-node-{{ $i }} +--- +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/ports-configmap.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/ports-configmap.yaml new file mode 100644 index 0000000..f5e7b2a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/ports-configmap.yaml @@ -0,0 +1,100 @@ +{{- if and (eq .Values.architecture "replication") .Values.sentinel.enabled (eq .Values.sentinel.service.type "NodePort") (not .Values.sentinel.service.nodePorts.redis ) }} +{{- /* create a list to keep track of ports we choose to use */}} +{{ $chosenports := (list ) }} + +{{- /* Get list of all used nodeports */}} +{{ $usedports := (list ) }} +{{- range $index, $service := (lookup "v1" "Service" "" "").items }} + {{- range.spec.ports }} + {{- if .nodePort }} + {{- $usedports = (append $usedports .nodePort) }} + {{- end }} + {{- end }} +{{- end }} + +{{- /* +comments that start with # are rendered in the output when you debug, so you can less and search for them +Vars in the comment will be rendered out, so you can check their value this way. +https://helm.sh/docs/chart_best_practices/templates/#comments-yaml-comments-vs-template-comments + +remove the template comments and leave the yaml comments to help debug +*/}} + +{{- /* Sort the list */}} +{{ $usedports = $usedports | sortAlpha }} +#usedports {{ $usedports }} + +{{- /* How many nodeports per service do we want to create, except for the main service which is always two */}} +{{ $numberofPortsPerNodeService := 2 }} + +{{- /* for every nodeport we want, loop though the used ports to get an unused port */}} +{{- range $j := until (int (add (mul (int .Values.replica.replicaCount) $numberofPortsPerNodeService) 2)) }} + {{- /* #j={{ $j }} */}} + {{- $nodeport := (add $j 30000) }} + {{- $nodeportfound := false }} + {{- range $i := $usedports }} + {{- /* #i={{ $i }} + #nodeport={{ $nodeport }} + #usedports={{ $usedports }} */}} + {{- if and (has (toString $nodeport) $usedports) (eq $nodeportfound false) }} + {{- /* nodeport conflicts with in use */}} + {{- $nodeport = (add $nodeport 1) }} + {{- else if and ( has $nodeport $chosenports) (eq $nodeportfound false) }} + {{- /* nodeport already chosen, try another */}} + {{- $nodeport = (add $nodeport 1) }} + {{- else if (eq $nodeportfound false) }} + {{- /* nodeport free to use: not already claimed and not in use */}} + {{- /* select nodeport, and place into usedports */}} + {{- $chosenports = (append $chosenports $nodeport) }} + {{- $nodeportfound = true }} + {{- else }} + {{- /* nodeport has already been chosen and locked in, just work through the rest of the list to get to the next nodeport selection */}} + {{- end }} + {{- end }} + {{- if (eq $nodeportfound false) }} + {{- $chosenports = (append $chosenports $nodeport) }} + {{- end }} + +{{- end }} + +{{- /* print the usedports and chosenports for debugging */}} +#usedports {{ $usedports }} +#chosenports {{ $chosenports }}}} + +--- +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ template "common.names.fullname" . }}-ports-configmap + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +data: +{{ $portsmap := (lookup "v1" "ConfigMap" $.Release.Namespace (printf "%s-%s" ( include "common.names.fullname" . ) "ports-configmap")).data }} +{{- if $portsmap }} +{{- /* configmap already exists, do not install again */ -}} + {{- range $name, $value := $portsmap }} + "{{ $name }}": "{{ $value }}" + {{- end }} +{{- else }} +{{- /* configmap being set for first time */ -}} + {{- range $index, $port := $chosenports }} + {{- $nodenumber := (floor (div $index 2)) }} + {{- if (eq $index 0) }} + "{{ template "common.names.fullname" $ }}-sentinel": "{{ $port }}" + {{- else if (eq $index 1) }} + "{{ template "common.names.fullname" $ }}-redis": "{{ $port }}" + {{- else if (eq (mod $index 2) 0) }} + "{{ template "common.names.fullname" $ }}-node-{{ (sub $nodenumber 1) }}-sentinel": "{{ $port }}" + {{- else if (eq (mod $index 2) 1) }} + "{{ template "common.names.fullname" $ }}-node-{{ (sub $nodenumber 1) }}-redis": "{{ $port }}" + {{- end }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/service.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/service.yaml new file mode 100644 index 0000000..362d681 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/service.yaml @@ -0,0 +1,103 @@ +{{- if or .Release.IsUpgrade (ne .Values.sentinel.service.type "NodePort") .Values.sentinel.service.nodePorts.redis -}} +{{- if and (eq .Values.architecture "replication") .Values.sentinel.enabled }} +{{ $portsmap := (lookup "v1" "ConfigMap" $.Release.Namespace (printf "%s-%s" ( include "common.names.fullname" . ) "ports-configmap")).data }} + +{{ $sentinelport := 0}} +{{ $redisport := 0}} +{{- if $portsmap }} +{{ $sentinelport = index $portsmap (printf "%s-%s" (include "common.names.fullname" $) "sentinel") }} +{{ $redisport = index $portsmap (printf "%s-%s" (include "common.names.fullname" $) "redis") }} +{{- else }} +{{- end }} + +apiVersion: v1 +kind: Service +metadata: + name: {{ template "common.names.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: node + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if or .Values.sentinel.service.annotations .Values.commonAnnotations }} + annotations: + {{- if .Values.sentinel.service.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.sentinel.service.annotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- end }} +spec: + type: {{ .Values.sentinel.service.type }} + {{- if or (eq .Values.sentinel.service.type "LoadBalancer") (eq .Values.sentinel.service.type "NodePort") }} + externalTrafficPolicy: {{ .Values.sentinel.service.externalTrafficPolicy | quote }} + {{- end }} + {{- if and (eq .Values.sentinel.service.type "LoadBalancer") (not (empty .Values.sentinel.service.loadBalancerIP)) }} + loadBalancerIP: {{ .Values.sentinel.service.loadBalancerIP }} + {{- end }} + {{- if and (eq .Values.sentinel.service.type "LoadBalancer") (not (empty .Values.sentinel.service.loadBalancerSourceRanges)) }} + loadBalancerSourceRanges: {{ .Values.sentinel.service.loadBalancerSourceRanges }} + {{- end }} + {{- if and .Values.sentinel.service.clusterIP (eq .Values.sentinel.service.type "ClusterIP") }} + clusterIP: {{ .Values.sentinel.service.clusterIP }} + {{- end }} + {{- if .Values.sentinel.service.sessionAffinity }} + sessionAffinity: {{ .Values.sentinel.service.sessionAffinity }} + {{- end }} + {{- if .Values.sentinel.service.sessionAffinityConfig }} + sessionAffinityConfig: {{- include "common.tplvalues.render" (dict "value" .Values.sentinel.service.sessionAffinityConfig "context" $) | nindent 4 }} + {{- end }} + ports: + - name: tcp-redis + {{- if and (or (eq .Values.sentinel.service.type "NodePort") (eq .Values.sentinel.service.type "LoadBalancer")) .Values.sentinel.service.nodePorts.redis }} + port: {{ .Values.sentinel.service.nodePorts.redis }} + {{- else if eq .Values.sentinel.service.type "NodePort" }} + port: {{ $redisport }} + {{- else}} + port: {{ .Values.sentinel.service.ports.redis }} + {{- end }} + targetPort: {{ .Values.replica.containerPorts.redis }} + {{- if and (or (eq .Values.sentinel.service.type "NodePort") (eq .Values.sentinel.service.type "LoadBalancer")) .Values.sentinel.service.nodePorts.redis }} + nodePort: {{ .Values.sentinel.service.nodePorts.redis }} + {{- else if eq .Values.sentinel.service.type "ClusterIP" }} + nodePort: null + {{- else if eq .Values.sentinel.service.type "NodePort" }} + nodePort: {{ $redisport }} + {{- end }} + - name: tcp-sentinel + {{- if and (or (eq .Values.sentinel.service.type "NodePort") (eq .Values.sentinel.service.type "LoadBalancer")) .Values.sentinel.service.nodePorts.sentinel }} + port: {{ .Values.sentinel.service.nodePorts.sentinel }} + {{- else if eq .Values.sentinel.service.type "NodePort" }} + port: {{ $sentinelport }} + {{- else }} + port: {{ .Values.sentinel.service.ports.sentinel }} + {{- end }} + targetPort: {{ .Values.sentinel.containerPorts.sentinel }} + {{- if and (or (eq .Values.sentinel.service.type "NodePort") (eq .Values.sentinel.service.type "LoadBalancer")) .Values.sentinel.service.nodePorts.sentinel }} + nodePort: {{ .Values.sentinel.service.nodePorts.sentinel }} + {{- else if eq .Values.sentinel.service.type "ClusterIP" }} + nodePort: null + {{- else if eq .Values.sentinel.service.type "NodePort" }} + nodePort: {{ $sentinelport }} + {{- end }} + {{- if eq .Values.sentinel.service.type "NodePort" }} + - name: sentinel-internal + nodePort: null + port: {{ .Values.sentinel.containerPorts.sentinel }} + protocol: TCP + targetPort: {{ .Values.sentinel.containerPorts.sentinel }} + - name: redis-internal + nodePort: null + port: {{ .Values.replica.containerPorts.redis }} + protocol: TCP + targetPort: {{ .Values.replica.containerPorts.redis }} + {{- end }} + {{- if .Values.sentinel.service.extraPorts }} + {{- include "common.tplvalues.render" (dict "value" .Values.sentinel.service.extraPorts "context" $) | nindent 4 }} + {{- end }} + selector: {{- include "common.labels.matchLabels" . | nindent 4 }} + app.kubernetes.io/component: node +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/statefulset.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/statefulset.yaml new file mode 100644 index 0000000..666e9ed --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/sentinel/statefulset.yaml @@ -0,0 +1,688 @@ +{{- if or .Release.IsUpgrade (ne .Values.sentinel.service.type "NodePort") .Values.sentinel.service.nodePorts.redis -}} +{{- if and (eq .Values.architecture "replication") .Values.sentinel.enabled }} +apiVersion: {{ include "common.capabilities.statefulset.apiVersion" . }} +kind: StatefulSet +metadata: + name: {{ printf "%s-node" (include "common.names.fullname" .) }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + app.kubernetes.io/component: node + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if or .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.replica.replicaCount }} + selector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + app.kubernetes.io/component: node + serviceName: {{ printf "%s-headless" (include "common.names.fullname" .) }} + {{- if .Values.replica.updateStrategy }} + updateStrategy: {{- toYaml .Values.replica.updateStrategy | nindent 4 }} + {{- end }} + {{- if .Values.replica.podManagementPolicy }} + podManagementPolicy: {{ .Values.replica.podManagementPolicy | quote }} + {{- end }} + template: + metadata: + labels: {{- include "common.labels.standard" . | nindent 8 }} + app.kubernetes.io/component: node + {{- if .Values.replica.podLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.replica.podLabels "context" $ ) | nindent 8 }} + {{- end }} + {{- if and .Values.metrics.enabled .Values.metrics.podLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.podLabels "context" $ ) | nindent 8 }} + {{- end }} + annotations: + {{- if (include "redis.createConfigmap" .) }} + checksum/configmap: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} + {{- end }} + checksum/health: {{ include (print $.Template.BasePath "/health-configmap.yaml") . | sha256sum }} + checksum/scripts: {{ include (print $.Template.BasePath "/scripts-configmap.yaml") . | sha256sum }} + checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }} + {{- if .Values.replica.podAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.replica.podAnnotations "context" $ ) | nindent 8 }} + {{- end }} + {{- if and .Values.metrics.enabled .Values.metrics.podAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.podAnnotations "context" $ ) | nindent 8 }} + {{- end }} + spec: + {{- include "redis.imagePullSecrets" . | nindent 6 }} + {{- if .Values.replica.hostAliases }} + hostAliases: {{- include "common.tplvalues.render" (dict "value" .Values.replica.hostAliases "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.replica.podSecurityContext.enabled }} + securityContext: {{- omit .Values.replica.podSecurityContext "enabled" | toYaml | nindent 8 }} + {{- end }} + serviceAccountName: {{ template "redis.serviceAccountName" . }} + {{- if .Values.replica.priorityClassName }} + priorityClassName: {{ .Values.replica.priorityClassName | quote }} + {{- end }} + {{- if .Values.replica.affinity }} + affinity: {{- include "common.tplvalues.render" (dict "value" .Values.replica.affinity "context" $) | nindent 8 }} + {{- else }} + affinity: + podAffinity: {{- include "common.affinities.pods" (dict "type" .Values.replica.podAffinityPreset "component" "node" "context" $) | nindent 10 }} + podAntiAffinity: {{- include "common.affinities.pods" (dict "type" .Values.replica.podAntiAffinityPreset "component" "node" "context" $) | nindent 10 }} + nodeAffinity: {{- include "common.affinities.nodes" (dict "type" .Values.replica.nodeAffinityPreset.type "key" .Values.replica.nodeAffinityPreset.key "values" .Values.replica.nodeAffinityPreset.values) | nindent 10 }} + {{- end }} + {{- if .Values.replica.nodeSelector }} + nodeSelector: {{- include "common.tplvalues.render" (dict "value" .Values.replica.nodeSelector "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.replica.tolerations }} + tolerations: {{- include "common.tplvalues.render" (dict "value" .Values.replica.tolerations "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.replica.topologySpreadConstraints }} + topologySpreadConstraints: {{- include "common.tplvalues.render" (dict "value" .Values.replica.topologySpreadConstraints "context" $) | nindent 8 }} + {{- end }} + {{- if .Values.replica.shareProcessNamespace }} + shareProcessNamespace: {{ .Values.replica.shareProcessNamespace }} + {{- end }} + {{- if .Values.replica.schedulerName }} + schedulerName: {{ .Values.replica.schedulerName | quote }} + {{- end }} + {{- if .Values.replica.dnsPolicy }} + dnsPolicy: {{ .Values.replica.dnsPolicy }} + {{- end }} + {{- if .Values.replica.dnsConfig }} + dnsConfig: {{- include "common.tplvalues.render" (dict "value" .Values.replica.dnsConfig "context" $) | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.sentinel.terminationGracePeriodSeconds }} + containers: + - name: redis + image: {{ template "redis.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy | quote }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.replica.lifecycleHooks }} + lifecycle: {{- include "common.tplvalues.render" (dict "value" .Values.replica.lifecycleHooks "context" $) | nindent 12 }} + {{- else }} + lifecycle: + preStop: + exec: + command: + - /bin/bash + - -c + - /opt/bitnami/scripts/start-scripts/prestop-redis.sh + {{- end }} + {{- end }} + {{- if .Values.replica.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.replica.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + {{- else if .Values.replica.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.replica.command "context" $) | nindent 12 }} + {{- else }} + command: + - /bin/bash + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else if .Values.replica.args }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.replica.args "context" $) | nindent 12 }} + {{- else }} + args: + - -c + - /opt/bitnami/scripts/start-scripts/start-node.sh + {{- end }} + env: + - name: BITNAMI_DEBUG + value: {{ ternary "true" "false" (or .Values.image.debug .Values.diagnosticMode.enabled) | quote }} + - name: REDIS_MASTER_PORT_NUMBER + value: {{ .Values.replica.containerPorts.redis | quote }} + - name: ALLOW_EMPTY_PASSWORD + value: {{ ternary "no" "yes" .Values.auth.enabled | quote }} + {{- if .Values.auth.enabled }} + {{- if .Values.auth.usePasswordFiles }} + - name: REDIS_PASSWORD_FILE + value: "/opt/bitnami/redis/secrets/redis-password" + - name: REDIS_MASTER_PASSWORD_FILE + value: "/opt/bitnami/redis/secrets/redis-password" + {{- else }} + - name: REDIS_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "redis.secretName" . }} + key: {{ template "redis.secretPasswordKey" . }} + - name: REDIS_MASTER_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "redis.secretName" . }} + key: {{ template "redis.secretPasswordKey" . }} + {{- end }} + {{- end }} + - name: REDIS_TLS_ENABLED + value: {{ ternary "yes" "no" .Values.tls.enabled | quote }} + {{- if .Values.tls.enabled }} + - name: REDIS_TLS_PORT + value: {{ .Values.replica.containerPorts.redis | quote }} + - name: REDIS_TLS_AUTH_CLIENTS + value: {{ ternary "yes" "no" .Values.tls.authClients | quote }} + - name: REDIS_TLS_CERT_FILE + value: {{ template "redis.tlsCert" . }} + - name: REDIS_TLS_KEY_FILE + value: {{ template "redis.tlsCertKey" . }} + - name: REDIS_TLS_CA_FILE + value: {{ template "redis.tlsCACert" . }} + {{- if .Values.tls.dhParamsFilename }} + - name: REDIS_TLS_DH_PARAMS_FILE + value: {{ template "redis.tlsDHParams" . }} + {{- end }} + {{- else }} + - name: REDIS_PORT + value: {{ .Values.replica.containerPorts.redis | quote }} + {{- end }} + - name: REDIS_DATA_DIR + value: {{ .Values.replica.persistence.path }} + {{- if .Values.replica.externalMaster.enabled }} + - name: REDIS_EXTERNAL_MASTER_HOST + value: {{ .Values.replica.externalMaster.host | quote }} + - name: REDIS_EXTERNAL_MASTER_PORT + value: {{ .Values.replica.externalMaster.port | quote }} + {{- end }} + {{- if .Values.replica.extraEnvVars }} + {{- include "common.tplvalues.render" ( dict "value" .Values.replica.extraEnvVars "context" $ ) | nindent 12 }} + {{- end }} + {{- if or .Values.replica.extraEnvVarsCM .Values.replica.extraEnvVarsSecret }} + envFrom: + {{- if .Values.replica.extraEnvVarsCM }} + - configMapRef: + name: {{ .Values.replica.extraEnvVarsCM }} + {{- end }} + {{- if .Values.replica.extraEnvVarsSecret }} + - secretRef: + name: {{ .Values.replica.extraEnvVarsSecret }} + {{- end }} + {{- end }} + ports: + - name: redis + containerPort: {{ .Values.replica.containerPorts.redis }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.replica.startupProbe.enabled }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.replica.startupProbe "enabled") "context" $) | nindent 12 }} + tcpSocket: + port: redis + {{- else if .Values.replica.customStartupProbe }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.replica.customStartupProbe "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.replica.livenessProbe.enabled }} + livenessProbe: + initialDelaySeconds: {{ .Values.replica.livenessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.replica.livenessProbe.periodSeconds }} + timeoutSeconds: {{ .Values.replica.livenessProbe.timeoutSeconds }} + successThreshold: {{ .Values.replica.livenessProbe.successThreshold }} + failureThreshold: {{ .Values.replica.livenessProbe.failureThreshold }} + exec: + command: + - sh + - -c + - /health/ping_liveness_local.sh {{ .Values.replica.livenessProbe.timeoutSeconds }} + {{- else if .Values.replica.customLivenessProbe }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.replica.customLivenessProbe "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.replica.readinessProbe.enabled }} + readinessProbe: + initialDelaySeconds: {{ .Values.replica.readinessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.replica.readinessProbe.periodSeconds }} + timeoutSeconds: {{ .Values.replica.readinessProbe.timeoutSeconds }} + successThreshold: {{ .Values.replica.readinessProbe.successThreshold }} + failureThreshold: {{ .Values.replica.readinessProbe.failureThreshold }} + exec: + command: + - sh + - -c + - /health/ping_readiness_local.sh {{ .Values.replica.readinessProbe.timeoutSeconds }} + {{- else if .Values.replica.customReadinessProbe }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.replica.customReadinessProbe "context" $) | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.replica.resources }} + resources: {{- toYaml .Values.replica.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: start-scripts + mountPath: /opt/bitnami/scripts/start-scripts + - name: health + mountPath: /health + {{- if .Values.sentinel.persistence.enabled }} + - name: sentinel-data + mountPath: /opt/bitnami/redis-sentinel/etc + {{- end }} + {{- if .Values.auth.usePasswordFiles }} + - name: redis-password + mountPath: /opt/bitnami/redis/secrets/ + {{- end }} + - name: redis-data + mountPath: {{ .Values.replica.persistence.path }} + subPath: {{ .Values.replica.persistence.subPath }} + - name: config + mountPath: /opt/bitnami/redis/mounted-etc + - name: redis-tmp-conf + mountPath: /opt/bitnami/redis/etc + - name: tmp + mountPath: /tmp + {{- if .Values.tls.enabled }} + - name: redis-certificates + mountPath: /opt/bitnami/redis/certs + readOnly: true + {{- end }} + {{- if .Values.replica.extraVolumeMounts }} + {{- include "common.tplvalues.render" ( dict "value" .Values.replica.extraVolumeMounts "context" $ ) | nindent 12 }} + {{- end }} + - name: sentinel + image: {{ template "redis.sentinel.image" . }} + imagePullPolicy: {{ .Values.sentinel.image.pullPolicy | quote }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.sentinel.lifecycleHooks }} + lifecycle: {{- include "common.tplvalues.render" (dict "value" .Values.sentinel.lifecycleHooks "context" $) | nindent 12 }} + {{- else }} + lifecycle: + preStop: + exec: + command: + - /bin/bash + - -c + - /opt/bitnami/scripts/start-scripts/prestop-sentinel.sh + {{- end }} + {{- end }} + {{- if .Values.sentinel.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.sentinel.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + {{- else if .Values.sentinel.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.sentinel.command "context" $) | nindent 12 }} + {{- else }} + command: + - /bin/bash + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- else if .Values.sentinel.args }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.sentinel.args "context" $) | nindent 12 }} + {{- else }} + args: + - -c + - /opt/bitnami/scripts/start-scripts/start-sentinel.sh + {{- end }} + env: + - name: BITNAMI_DEBUG + value: {{ ternary "true" "false" (or .Values.sentinel.image.debug .Values.diagnosticMode.enabled) | quote }} + {{- if .Values.auth.enabled }} + {{- if .Values.auth.usePasswordFiles }} + - name: REDIS_PASSWORD_FILE + value: "/opt/bitnami/redis/secrets/redis-password" + {{- else }} + - name: REDIS_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "redis.secretName" . }} + key: {{ template "redis.secretPasswordKey" . }} + {{- end }} + {{- else }} + - name: ALLOW_EMPTY_PASSWORD + value: "yes" + {{- end }} + - name: REDIS_SENTINEL_TLS_ENABLED + value: {{ ternary "yes" "no" .Values.tls.enabled | quote }} + {{- if .Values.tls.enabled }} + - name: REDIS_SENTINEL_TLS_PORT_NUMBER + value: {{ .Values.sentinel.containerPorts.sentinel | quote }} + - name: REDIS_SENTINEL_TLS_AUTH_CLIENTS + value: {{ ternary "yes" "no" .Values.tls.authClients | quote }} + - name: REDIS_SENTINEL_TLS_CERT_FILE + value: {{ template "redis.tlsCert" . }} + - name: REDIS_SENTINEL_TLS_KEY_FILE + value: {{ template "redis.tlsCertKey" . }} + - name: REDIS_SENTINEL_TLS_CA_FILE + value: {{ template "redis.tlsCACert" . }} + {{- if .Values.tls.dhParamsFilename }} + - name: REDIS_SENTINEL_TLS_DH_PARAMS_FILE + value: {{ template "redis.tls.dhParamsFilename" . }} + {{- end }} + {{- else }} + - name: REDIS_SENTINEL_PORT + value: {{ .Values.sentinel.containerPorts.sentinel | quote }} + {{- end }} + {{- if .Values.sentinel.externalMaster.enabled }} + - name: REDIS_EXTERNAL_MASTER_HOST + value: {{ .Values.sentinel.externalMaster.host | quote }} + - name: REDIS_EXTERNAL_MASTER_PORT + value: {{ .Values.sentinel.externalMaster.port | quote }} + {{- end }} + {{- if .Values.sentinel.extraEnvVars }} + {{- include "common.tplvalues.render" ( dict "value" .Values.sentinel.extraEnvVars "context" $ ) | nindent 12 }} + {{- end }} + {{- if or .Values.sentinel.extraEnvVarsCM .Values.sentinel.extraEnvVarsSecret }} + envFrom: + {{- if .Values.sentinel.extraEnvVarsCM }} + - configMapRef: + name: {{ .Values.sentinel.extraEnvVarsCM }} + {{- end }} + {{- if .Values.sentinel.extraEnvVarsSecret }} + - secretRef: + name: {{ .Values.sentinel.extraEnvVarsSecret }} + {{- end }} + {{- end }} + ports: + - name: redis-sentinel + containerPort: {{ .Values.sentinel.containerPorts.sentinel }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.sentinel.startupProbe.enabled }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" (omit .Values.sentinel.startupProbe "enabled") "context" $) | nindent 12 }} + tcpSocket: + port: redis-sentinel + {{- else if .Values.sentinel.customStartupProbe }} + startupProbe: {{- include "common.tplvalues.render" (dict "value" .Values.sentinel.customStartupProbe "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.sentinel.livenessProbe.enabled }} + livenessProbe: + initialDelaySeconds: {{ .Values.sentinel.livenessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.sentinel.livenessProbe.periodSeconds }} + timeoutSeconds: {{ .Values.sentinel.livenessProbe.timeoutSeconds }} + successThreshold: {{ .Values.sentinel.livenessProbe.successThreshold }} + failureThreshold: {{ .Values.sentinel.livenessProbe.failureThreshold }} + exec: + command: + - sh + - -c + - /health/ping_sentinel.sh {{ .Values.sentinel.livenessProbe.timeoutSeconds }} + {{- else if .Values.sentinel.customLivenessProbe }} + livenessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.sentinel.customLivenessProbe "context" $) | nindent 12 }} + {{- end }} + {{- end }} + {{- if not .Values.diagnosticMode.enabled }} + {{- if .Values.sentinel.readinessProbe.enabled }} + readinessProbe: + initialDelaySeconds: {{ .Values.sentinel.readinessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.sentinel.readinessProbe.periodSeconds }} + timeoutSeconds: {{ .Values.sentinel.readinessProbe.timeoutSeconds }} + successThreshold: {{ .Values.sentinel.readinessProbe.successThreshold }} + failureThreshold: {{ .Values.sentinel.readinessProbe.failureThreshold }} + exec: + command: + - sh + - -c + - /health/ping_sentinel.sh {{ .Values.sentinel.livenessProbe.timeoutSeconds }} + {{- else if .Values.sentinel.customReadinessProbe }} + readinessProbe: {{- include "common.tplvalues.render" (dict "value" .Values.sentinel.customReadinessProbe "context" $) | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.sentinel.resources }} + resources: {{- toYaml .Values.sentinel.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: start-scripts + mountPath: /opt/bitnami/scripts/start-scripts + - name: health + mountPath: /health + - name: sentinel-data + mountPath: /opt/bitnami/redis-sentinel/etc + {{- if .Values.auth.usePasswordFiles }} + - name: redis-password + mountPath: /opt/bitnami/redis/secrets/ + {{- end }} + - name: redis-data + mountPath: {{ .Values.replica.persistence.path }} + subPath: {{ .Values.replica.persistence.subPath }} + - name: config + mountPath: /opt/bitnami/redis-sentinel/mounted-etc + {{- if .Values.tls.enabled }} + - name: redis-certificates + mountPath: /opt/bitnami/redis/certs + readOnly: true + {{- end }} + {{- if .Values.sentinel.extraVolumeMounts }} + {{- include "common.tplvalues.render" ( dict "value" .Values.sentinel.extraVolumeMounts "context" $ ) | nindent 12 }} + {{- end }} + {{- if .Values.metrics.enabled }} + - name: metrics + image: {{ template "redis.metrics.image" . }} + imagePullPolicy: {{ .Values.metrics.image.pullPolicy | quote }} + {{- if .Values.metrics.containerSecurityContext.enabled }} + securityContext: {{- omit .Values.metrics.containerSecurityContext "enabled" | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 12 }} + {{- else }} + command: + - /bin/bash + - -c + - | + if [[ -f '/secrets/redis-password' ]]; then + export REDIS_PASSWORD=$(cat /secrets/redis-password) + fi + redis_exporter{{- range $key, $value := .Values.metrics.extraArgs }} --{{ $key }}={{ $value }}{{- end }} + {{- end }} + {{- if .Values.diagnosticMode.enabled }} + args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 12 }} + {{- end }} + env: + - name: REDIS_ALIAS + value: {{ template "common.names.fullname" . }} + {{- if .Values.auth.enabled }} + - name: REDIS_USER + value: default + {{- if (not .Values.auth.usePasswordFiles) }} + - name: REDIS_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "redis.secretName" . }} + key: {{ template "redis.secretPasswordKey" . }} + {{- end }} + {{- end }} + {{- if .Values.tls.enabled }} + - name: REDIS_ADDR + value: rediss://{{ .Values.metrics.redisTargetHost }}:{{ .Values.replica.containerPorts.redis }} + {{- if .Values.tls.authClients }} + - name: REDIS_EXPORTER_TLS_CLIENT_KEY_FILE + value: {{ template "redis.tlsCertKey" . }} + - name: REDIS_EXPORTER_TLS_CLIENT_CERT_FILE + value: {{ template "redis.tlsCert" . }} + {{- end }} + - name: REDIS_EXPORTER_TLS_CA_CERT_FILE + value: {{ template "redis.tlsCACert" . }} + {{- end }} + {{- if .Values.metrics.extraEnvVars }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.extraEnvVars "context" $) | nindent 12 }} + {{- end }} + ports: + - name: metrics + containerPort: 9121 + {{- if .Values.metrics.resources }} + resources: {{- toYaml .Values.metrics.resources | nindent 12 }} + {{- end }} + volumeMounts: + {{- if .Values.auth.usePasswordFiles }} + - name: redis-password + mountPath: /secrets/ + {{- end }} + {{- if .Values.tls.enabled }} + - name: redis-certificates + mountPath: /opt/bitnami/redis/certs + readOnly: true + {{- end }} + {{- if .Values.metrics.extraVolumeMounts }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.extraVolumeMounts "context" $ ) | nindent 12 }} + {{- end }} + {{- end }} + {{- if .Values.replica.sidecars }} + {{- include "common.tplvalues.render" (dict "value" .Values.replica.sidecars "context" $) | nindent 8 }} + {{- end }} + {{- $needsVolumePermissions := and .Values.volumePermissions.enabled .Values.replica.persistence.enabled .Values.replica.podSecurityContext.enabled .Values.replica.containerSecurityContext.enabled }} + {{- if or .Values.replica.initContainers $needsVolumePermissions .Values.sysctl.enabled }} + initContainers: + {{- if .Values.replica.initContainers }} + {{- include "common.tplvalues.render" (dict "value" .Values.replica.initContainers "context" $) | nindent 8 }} + {{- end }} + {{- if $needsVolumePermissions }} + - name: volume-permissions + image: {{ include "redis.volumePermissions.image" . }} + imagePullPolicy: {{ .Values.volumePermissions.image.pullPolicy | quote }} + command: + - /bin/bash + - -ec + - | + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + chown -R `id -u`:`id -G | cut -d " " -f2` {{ .Values.replica.persistence.path }} + {{- else }} + chown -R {{ .Values.replica.containerSecurityContext.runAsUser }}:{{ .Values.replica.podSecurityContext.fsGroup }} {{ .Values.replica.persistence.path }} + {{- end }} + {{- if eq ( toString ( .Values.volumePermissions.containerSecurityContext.runAsUser )) "auto" }} + securityContext: {{- omit .Values.volumePermissions.containerSecurityContext "runAsUser" | toYaml | nindent 12 }} + {{- else }} + securityContext: {{- .Values.volumePermissions.containerSecurityContext | toYaml | nindent 12 }} + {{- end }} + {{- if .Values.volumePermissions.resources }} + resources: {{- toYaml .Values.volumePermissions.resources | nindent 12 }} + {{- end }} + volumeMounts: + - name: redis-data + mountPath: {{ .Values.replica.persistence.path }} + subPath: {{ .Values.replica.persistence.subPath }} + {{- end }} + {{- if .Values.sysctl.enabled }} + - name: init-sysctl + image: {{ include "redis.sysctl.image" . }} + imagePullPolicy: {{ default "" .Values.sysctl.image.pullPolicy | quote }} + securityContext: + privileged: true + runAsUser: 0 + {{- if .Values.sysctl.command }} + command: {{- include "common.tplvalues.render" (dict "value" .Values.sysctl.command "context" $) | nindent 12 }} + {{- end }} + {{- if .Values.sysctl.resources }} + resources: {{- toYaml .Values.sysctl.resources | nindent 12 }} + {{- end }} + {{- if .Values.sysctl.mountHostSys }} + volumeMounts: + - name: host-sys + mountPath: /host-sys + {{- end }} + {{- end }} + {{- end }} + volumes: + - name: start-scripts + configMap: + name: {{ printf "%s-scripts" (include "common.names.fullname" .) }} + defaultMode: 0755 + - name: health + configMap: + name: {{ printf "%s-health" (include "common.names.fullname" .) }} + defaultMode: 0755 + {{- if .Values.auth.usePasswordFiles }} + - name: redis-password + secret: + secretName: {{ template "redis.secretName" . }} + items: + - key: {{ template "redis.secretPasswordKey" . }} + path: redis-password + {{- end }} + - name: config + configMap: + name: {{ include "redis.configmapName" . }} + {{- if .Values.sysctl.mountHostSys }} + - name: host-sys + hostPath: + path: /sys + {{- end }} + {{- if not .Values.sentinel.persistence.enabled }} + - name: sentinel-data + {{- if .Values.sentinel.persistence.medium }} + emptyDir: { + medium: {{ .Values.sentinel.persistence.medium | quote }} + } + {{- else }} + emptyDir: {} + {{- end }} + {{- end }} + - name: redis-tmp-conf + {{- if .Values.replica.persistence.medium }} + emptyDir: { + medium: {{ .Values.replica.persistence.medium | quote }} + } + {{- else }} + emptyDir: {} + {{- end }} + - name: tmp + {{- if .Values.replica.persistence.medium }} + emptyDir: { + medium: {{ .Values.replica.persistence.medium | quote }} + } + {{- else }} + emptyDir: {} + {{- end }} + {{- if .Values.replica.extraVolumes }} + {{- include "common.tplvalues.render" ( dict "value" .Values.replica.extraVolumes "context" $ ) | nindent 8 }} + {{- end }} + {{- if .Values.metrics.extraVolumes }} + {{- include "common.tplvalues.render" ( dict "value" .Values.metrics.extraVolumes "context" $ ) | nindent 8 }} + {{- end }} + {{- if .Values.sentinel.extraVolumes }} + {{- include "common.tplvalues.render" ( dict "value" .Values.sentinel.extraVolumes "context" $ ) | nindent 8 }} + {{- end }} + {{- if .Values.tls.enabled }} + - name: redis-certificates + secret: + secretName: {{ include "redis.tlsSecretName" . }} + defaultMode: 256 + {{- end }} + {{- if not .Values.replica.persistence.enabled }} + - name: redis-data + {{- if .Values.replica.persistence.medium }} + emptyDir: { + medium: {{ .Values.replica.persistence.medium | quote }} + } + {{- else }} + emptyDir: {} + {{- end }} + {{- else }} + volumeClaimTemplates: + - metadata: + name: redis-data + labels: {{- include "common.labels.matchLabels" . | nindent 10 }} + app.kubernetes.io/component: node + {{- if .Values.replica.persistence.annotations }} + annotations: {{- toYaml .Values.replica.persistence.annotations | nindent 10 }} + {{- end }} + spec: + accessModes: + {{- range .Values.replica.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + resources: + requests: + storage: {{ .Values.replica.persistence.size | quote }} + {{- if .Values.replica.persistence.selector }} + selector: {{- include "common.tplvalues.render" ( dict "value" .Values.replica.persistence.selector "context" $) | nindent 10 }} + {{- end }} + {{- include "common.storage.class" (dict "persistence" .Values.replica.persistence "global" .Values.global) | nindent 8 }} + {{- if .Values.sentinel.persistence.enabled }} + - metadata: + name: sentinel-data + labels: {{- include "common.labels.matchLabels" . | nindent 10 }} + app.kubernetes.io/component: node + {{- if .Values.sentinel.persistence.annotations }} + annotations: {{- toYaml .Values.sentinel.persistence.annotations | nindent 10 }} + {{- end }} + spec: + accessModes: + {{- range .Values.sentinel.persistence.accessModes }} + - {{ . | quote }} + {{- end }} + resources: + requests: + storage: {{ .Values.sentinel.persistence.size | quote }} + {{- if .Values.sentinel.persistence.selector }} + selector: {{- include "common.tplvalues.render" ( dict "value" .Values.sentinel.persistence.selector "context" $) | nindent 10 }} + {{- end }} + {{- if .Values.sentinel.persistence.dataSource }} + dataSource: {{- include "common.tplvalues.render" (dict "value" .Values.sentinel.persistence.dataSource "context" $) | nindent 10 }} + {{- end }} + {{- include "common.storage.class" (dict "persistence" .Values.sentinel.persistence "global" .Values.global) | nindent 8 }} + {{- end }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/serviceaccount.yaml new file mode 100644 index 0000000..1ce68a7 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/serviceaccount.yaml @@ -0,0 +1,21 @@ +{{- if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }} +metadata: + name: {{ template "redis.serviceAccountName" . }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if or .Values.commonAnnotations .Values.serviceAccount.annotations }} + annotations: + {{- if or .Values.commonAnnotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.serviceAccount.annotations }} + {{- include "common.tplvalues.render" ( dict "value" .Values.serviceAccount.annotations "context" $ ) | nindent 4 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/servicemonitor.yaml new file mode 100644 index 0000000..40754c2 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/servicemonitor.yaml @@ -0,0 +1,41 @@ +{{- if and .Values.metrics.enabled .Values.metrics.serviceMonitor.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "common.names.fullname" . }} + namespace: {{ default .Release.Namespace .Values.metrics.serviceMonitor.namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.metrics.serviceMonitor.additionalLabels }} + {{- include "common.tplvalues.render" (dict "value" .Values.metrics.serviceMonitor.additionalLabels "context" $) | nindent 4 }} + {{- end }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +spec: + endpoints: + - port: http-metrics + {{- if .Values.metrics.serviceMonitor.interval }} + interval: {{ .Values.metrics.serviceMonitor.interval }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.metrics.serviceMonitor.scrapeTimeout }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.honorLabels }} + honorLabels: {{ .Values.metrics.serviceMonitor.honorLabels }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.relabellings }} + relabelings: {{- toYaml .Values.metrics.serviceMonitor.relabellings | nindent 6 }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.metricRelabelings }} + metricRelabelings: {{- toYaml .Values.metrics.serviceMonitor.metricRelabelings | nindent 6 }} + {{- end }} + namespaceSelector: + matchNames: + - {{ .Release.Namespace }} + selector: + matchLabels: {{- include "common.labels.matchLabels" . | nindent 6 }} + app.kubernetes.io/component: metrics +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/templates/tls-secret.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/tls-secret.yaml new file mode 100644 index 0000000..4ab7acb --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/templates/tls-secret.yaml @@ -0,0 +1,29 @@ +{{- if (include "redis.createTlsSecret" .) }} +{{- $secretName := printf "%s-crt" (include "common.names.fullname" .) }} +{{- $existingCerts := (lookup "v1" "Secret" .Release.Namespace $secretName).data | default dict }} +{{- $ca := genCA "redis-ca" 365 }} +{{- $releaseNamespace := .Release.Namespace }} +{{- $clusterDomain := .Values.clusterDomain }} +{{- $fullname := include "common.names.fullname" . }} +{{- $serviceName := include "common.names.fullname" . }} +{{- $headlessServiceName := printf "%s-headless" (include "common.names.fullname" .) }} +{{- $altNames := list (printf "*.%s.%s.svc.%s" $serviceName $releaseNamespace $clusterDomain) (printf "%s.%s.svc.%s" $serviceName $releaseNamespace $clusterDomain) (printf "*.%s.%s.svc.%s" $headlessServiceName $releaseNamespace $clusterDomain) (printf "%s.%s.svc.%s" $headlessServiceName $releaseNamespace $clusterDomain) "127.0.0.1" "localhost" $fullname }} +{{- $crt := genSignedCert $fullname nil $altNames 365 $ca }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ $secretName }} + namespace: {{ .Release.Namespace | quote }} + labels: {{- include "common.labels.standard" . | nindent 4 }} + {{- if .Values.commonLabels }} + {{- include "common.tplvalues.render" ( dict "value" .Values.commonLabels "context" $ ) | nindent 4 }} + {{- end }} + {{- if .Values.commonAnnotations }} + annotations: {{- include "common.tplvalues.render" ( dict "value" .Values.commonAnnotations "context" $ ) | nindent 4 }} + {{- end }} +type: kubernetes.io/tls +data: + ca.crt: {{ (get $existingCerts "ca.crt") | default ($ca.Cert | b64enc | quote ) }} + tls.crt: {{ (get $existingCerts "tls.crt") | default ($crt.Cert | b64enc | quote) }} + tls.key: {{ (get $existingCerts "tls.key") | default ($crt.Key | b64enc | quote) }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/values.schema.json b/observability/lgtm-distributed/charts/oncall/charts/redis/values.schema.json new file mode 100644 index 0000000..d6e226b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/values.schema.json @@ -0,0 +1,156 @@ +{ + "$schema": "http://json-schema.org/schema#", + "type": "object", + "properties": { + "architecture": { + "type": "string", + "title": "Redis architecture", + "form": true, + "description": "Allowed values: `standalone` or `replication`", + "enum": ["standalone", "replication"] + }, + "auth": { + "type": "object", + "title": "Authentication configuration", + "form": true, + "properties": { + "enabled": { + "type": "boolean", + "form": true, + "title": "Use password authentication" + }, + "password": { + "type": "string", + "title": "Redis password", + "form": true, + "description": "Defaults to a random 10-character alphanumeric string if not set", + "hidden": { + "value": false, + "path": "auth/enabled" + } + } + } + }, + "master": { + "type": "object", + "title": "Master replicas settings", + "form": true, + "properties": { + "kind": { + "type": "string", + "title": "Workload Kind", + "form": true, + "description": "Allowed values: `Deployment` or `StatefulSet`", + "enum": ["Deployment", "StatefulSet"] + }, + "persistence": { + "type": "object", + "title": "Persistence for master replicas", + "form": true, + "properties": { + "enabled": { + "type": "boolean", + "form": true, + "title": "Enable persistence", + "description": "Enable persistence using Persistent Volume Claims" + }, + "size": { + "type": "string", + "title": "Persistent Volume Size", + "form": true, + "render": "slider", + "sliderMin": 1, + "sliderMax": 100, + "sliderUnit": "Gi", + "hidden": { + "value": false, + "path": "master/persistence/enabled" + } + } + } + } + } + }, + "replica": { + "type": "object", + "title": "Redis replicas settings", + "form": true, + "hidden": { + "value": "standalone", + "path": "architecture" + }, + "properties": { + "replicaCount": { + "type": "integer", + "form": true, + "title": "Number of Redis replicas" + }, + "persistence": { + "type": "object", + "title": "Persistence for Redis replicas", + "form": true, + "properties": { + "enabled": { + "type": "boolean", + "form": true, + "title": "Enable persistence", + "description": "Enable persistence using Persistent Volume Claims" + }, + "size": { + "type": "string", + "title": "Persistent Volume Size", + "form": true, + "render": "slider", + "sliderMin": 1, + "sliderMax": 100, + "sliderUnit": "Gi", + "hidden": { + "value": false, + "path": "replica/persistence/enabled" + } + } + } + } + } + }, + "volumePermissions": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean", + "form": true, + "title": "Enable Init Containers", + "description": "Use an init container to set required folder permissions on the data volume before mounting it in the final destination" + } + } + }, + "metrics": { + "type": "object", + "form": true, + "title": "Prometheus metrics details", + "properties": { + "enabled": { + "type": "boolean", + "title": "Create Prometheus metrics exporter", + "description": "Create a side-car container to expose Prometheus metrics", + "form": true + }, + "serviceMonitor": { + "type": "object", + "properties": { + "enabled": { + "type": "boolean", + "title": "Create Prometheus Operator ServiceMonitor", + "description": "Create a ServiceMonitor to track metrics using Prometheus Operator", + "form": true, + "hidden": { + "value": false, + "path": "metrics/enabled" + } + } + } + } + } + } + } +} diff --git a/observability/lgtm-distributed/charts/oncall/charts/redis/values.yaml b/observability/lgtm-distributed/charts/oncall/charts/redis/values.yaml new file mode 100644 index 0000000..c25a3b2 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/charts/redis/values.yaml @@ -0,0 +1,1621 @@ +## @section Global parameters +## Global Docker image parameters +## Please, note that this will override the image parameters, including dependencies, configured to use the global value +## Current available global Docker image parameters: imageRegistry, imagePullSecrets and storageClass +## + +## @param global.imageRegistry Global Docker image registry +## @param global.imagePullSecrets Global Docker registry secret names as an array +## @param global.storageClass Global StorageClass for Persistent Volume(s) +## @param global.redis.password Global Redis® password (overrides `auth.password`) +## +global: + imageRegistry: "" + ## E.g. + ## imagePullSecrets: + ## - myRegistryKeySecretName + ## + imagePullSecrets: [] + storageClass: "" + redis: + password: "" + +## @section Common parameters +## + +## @param kubeVersion Override Kubernetes version +## +kubeVersion: "" +## @param nameOverride String to partially override common.names.fullname +## +nameOverride: "" +## @param fullnameOverride String to fully override common.names.fullname +## +fullnameOverride: "" +## @param commonLabels Labels to add to all deployed objects +## +commonLabels: {} +## @param commonAnnotations Annotations to add to all deployed objects +## +commonAnnotations: {} +## @param secretAnnotations Annotations to add to secret +## +secretAnnotations: {} +## @param clusterDomain Kubernetes cluster domain name +## +clusterDomain: cluster.local +## @param extraDeploy Array of extra objects to deploy with the release +## +extraDeploy: [] + +## Enable diagnostic mode in the deployment +## +diagnosticMode: + ## @param diagnosticMode.enabled Enable diagnostic mode (all probes will be disabled and the command will be overridden) + ## + enabled: false + ## @param diagnosticMode.command Command to override all containers in the deployment + ## + command: + - sleep + ## @param diagnosticMode.args Args to override all containers in the deployment + ## + args: + - infinity + +## @section Redis® Image parameters +## + +## Bitnami Redis® image +## ref: https://hub.docker.com/r/bitnami/redis/tags/ +## @param image.registry Redis® image registry +## @param image.repository Redis® image repository +## @param image.tag Redis® image tag (immutable tags are recommended) +## @param image.pullPolicy Redis® image pull policy +## @param image.pullSecrets Redis® image pull secrets +## @param image.debug Enable image debug mode +## +image: + registry: docker.io + repository: bitnami/redis + tag: 6.2.7-debian-11-r11 + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## e.g: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## Enable debug mode + ## + debug: false + +## @section Redis® common configuration parameters +## https://github.com/bitnami/bitnami-docker-redis#configuration +## + +## @param architecture Redis® architecture. Allowed values: `standalone` or `replication` +## +architecture: replication +## Redis® Authentication parameters +## ref: https://github.com/bitnami/bitnami-docker-redis#setting-the-server-password-on-first-run +## +auth: + ## @param auth.enabled Enable password authentication + ## + enabled: true + ## @param auth.sentinel Enable password authentication on sentinels too + ## + sentinel: true + ## @param auth.password Redis® password + ## Defaults to a random 10-character alphanumeric string if not set + ## + password: "" + ## @param auth.existingSecret The name of an existing secret with Redis® credentials + ## NOTE: When it's set, the previous `auth.password` parameter is ignored + ## + existingSecret: "" + ## @param auth.existingSecretPasswordKey Password key to be retrieved from existing secret + ## NOTE: ignored unless `auth.existingSecret` parameter is set + ## + existingSecretPasswordKey: "" + ## @param auth.usePasswordFiles Mount credentials as files instead of using an environment variable + ## + usePasswordFiles: false + +## @param commonConfiguration [string] Common configuration to be added into the ConfigMap +## ref: https://redis.io/topics/config +## +commonConfiguration: |- + # Enable AOF https://redis.io/topics/persistence#append-only-file + appendonly yes + # Disable RDB persistence, AOF persistence already enabled. + save "" +## @param existingConfigmap The name of an existing ConfigMap with your custom configuration for Redis® nodes +## +existingConfigmap: "" + +## @section Redis® master configuration parameters +## + +master: + ## @param master.count Number of Redis® master instances to deploy (experimental, requires additional configuration) + ## + count: 1 + ## @param master.configuration Configuration for Redis® master nodes + ## ref: https://redis.io/topics/config + ## + configuration: "" + ## @param master.disableCommands Array with Redis® commands to disable on master nodes + ## Commands will be completely disabled by renaming each to an empty string. + ## ref: https://redis.io/topics/security#disabling-of-specific-commands + ## + disableCommands: + - FLUSHDB + - FLUSHALL + ## @param master.command Override default container command (useful when using custom images) + ## + command: [] + ## @param master.args Override default container args (useful when using custom images) + ## + args: [] + ## @param master.preExecCmds Additional commands to run prior to starting Redis® master + ## + preExecCmds: [] + ## @param master.extraFlags Array with additional command line flags for Redis® master + ## e.g: + ## extraFlags: + ## - "--maxmemory-policy volatile-ttl" + ## - "--repl-backlog-size 1024mb" + ## + extraFlags: [] + ## @param master.extraEnvVars Array with extra environment variables to add to Redis® master nodes + ## e.g: + ## extraEnvVars: + ## - name: FOO + ## value: "bar" + ## + extraEnvVars: [] + ## @param master.extraEnvVarsCM Name of existing ConfigMap containing extra env vars for Redis® master nodes + ## + extraEnvVarsCM: "" + ## @param master.extraEnvVarsSecret Name of existing Secret containing extra env vars for Redis® master nodes + ## + extraEnvVarsSecret: "" + ## @param master.containerPorts.redis Container port to open on Redis® master nodes + ## + containerPorts: + redis: 6379 + ## Configure extra options for Redis® containers' liveness and readiness probes + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes + ## @param master.startupProbe.enabled Enable startupProbe on Redis® master nodes + ## @param master.startupProbe.initialDelaySeconds Initial delay seconds for startupProbe + ## @param master.startupProbe.periodSeconds Period seconds for startupProbe + ## @param master.startupProbe.timeoutSeconds Timeout seconds for startupProbe + ## @param master.startupProbe.failureThreshold Failure threshold for startupProbe + ## @param master.startupProbe.successThreshold Success threshold for startupProbe + ## + startupProbe: + enabled: false + initialDelaySeconds: 20 + periodSeconds: 5 + timeoutSeconds: 5 + successThreshold: 1 + failureThreshold: 5 + ## @param master.livenessProbe.enabled Enable livenessProbe on Redis® master nodes + ## @param master.livenessProbe.initialDelaySeconds Initial delay seconds for livenessProbe + ## @param master.livenessProbe.periodSeconds Period seconds for livenessProbe + ## @param master.livenessProbe.timeoutSeconds Timeout seconds for livenessProbe + ## @param master.livenessProbe.failureThreshold Failure threshold for livenessProbe + ## @param master.livenessProbe.successThreshold Success threshold for livenessProbe + ## + livenessProbe: + enabled: true + initialDelaySeconds: 20 + periodSeconds: 5 + timeoutSeconds: 5 + successThreshold: 1 + failureThreshold: 5 + ## @param master.readinessProbe.enabled Enable readinessProbe on Redis® master nodes + ## @param master.readinessProbe.initialDelaySeconds Initial delay seconds for readinessProbe + ## @param master.readinessProbe.periodSeconds Period seconds for readinessProbe + ## @param master.readinessProbe.timeoutSeconds Timeout seconds for readinessProbe + ## @param master.readinessProbe.failureThreshold Failure threshold for readinessProbe + ## @param master.readinessProbe.successThreshold Success threshold for readinessProbe + ## + readinessProbe: + enabled: true + initialDelaySeconds: 20 + periodSeconds: 5 + timeoutSeconds: 1 + successThreshold: 1 + failureThreshold: 5 + ## @param master.customStartupProbe Custom startupProbe that overrides the default one + ## + customStartupProbe: {} + ## @param master.customLivenessProbe Custom livenessProbe that overrides the default one + ## + customLivenessProbe: {} + ## @param master.customReadinessProbe Custom readinessProbe that overrides the default one + ## + customReadinessProbe: {} + ## Redis® master resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## @param master.resources.limits The resources limits for the Redis® master containers + ## @param master.resources.requests The requested resources for the Redis® master containers + ## + resources: + limits: {} + requests: {} + ## Configure Pods Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-pod + ## @param master.podSecurityContext.enabled Enabled Redis® master pods' Security Context + ## @param master.podSecurityContext.fsGroup Set Redis® master pod's Security Context fsGroup + ## + podSecurityContext: + enabled: true + fsGroup: 1001 + ## Configure Container Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-pod + ## @param master.containerSecurityContext.enabled Enabled Redis® master containers' Security Context + ## @param master.containerSecurityContext.runAsUser Set Redis® master containers' Security Context runAsUser + ## + containerSecurityContext: + enabled: true + runAsUser: 1001 + ## @param master.kind Use either Deployment or StatefulSet (default) + ## ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/ + ## + kind: StatefulSet + ## @param master.schedulerName Alternate scheduler for Redis® master pods + ## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ + ## + schedulerName: "" + ## @param master.updateStrategy.type Redis® master statefulset strategy type + ## @skip master.updateStrategy.rollingUpdate + ## ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#update-strategies + ## + updateStrategy: + ## StrategyType + ## Can be set to RollingUpdate or OnDelete + ## + type: RollingUpdate + rollingUpdate: {} + ## @param master.priorityClassName Redis® master pods' priorityClassName + ## + priorityClassName: "" + ## @param master.hostAliases Redis® master pods host aliases + ## https://kubernetes.io/docs/concepts/services-networking/add-entries-to-pod-etc-hosts-with-host-aliases/ + ## + hostAliases: [] + ## @param master.podLabels Extra labels for Redis® master pods + ## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + ## + podLabels: {} + ## @param master.podAnnotations Annotations for Redis® master pods + ## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/ + ## + podAnnotations: {} + ## @param master.shareProcessNamespace Share a single process namespace between all of the containers in Redis® master pods + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/share-process-namespace/ + ## + shareProcessNamespace: false + ## @param master.podAffinityPreset Pod affinity preset. Ignored if `master.affinity` is set. Allowed values: `soft` or `hard` + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity + ## + podAffinityPreset: "" + ## @param master.podAntiAffinityPreset Pod anti-affinity preset. Ignored if `master.affinity` is set. Allowed values: `soft` or `hard` + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity + ## + podAntiAffinityPreset: soft + ## Node master.affinity preset + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#node-affinity + ## + nodeAffinityPreset: + ## @param master.nodeAffinityPreset.type Node affinity preset type. Ignored if `master.affinity` is set. Allowed values: `soft` or `hard` + ## + type: "" + ## @param master.nodeAffinityPreset.key Node label key to match. Ignored if `master.affinity` is set + ## + key: "" + ## @param master.nodeAffinityPreset.values Node label values to match. Ignored if `master.affinity` is set + ## E.g. + ## values: + ## - e2e-az1 + ## - e2e-az2 + ## + values: [] + ## @param master.affinity Affinity for Redis® master pods assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + ## NOTE: `master.podAffinityPreset`, `master.podAntiAffinityPreset`, and `master.nodeAffinityPreset` will be ignored when it's set + ## + affinity: {} + ## @param master.nodeSelector Node labels for Redis® master pods assignment + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + ## + nodeSelector: {} + ## @param master.tolerations Tolerations for Redis® master pods assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + ## + tolerations: [] + ## @param master.topologySpreadConstraints Spread Constraints for Redis® master pod assignment + ## ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ + ## E.g. + ## topologySpreadConstraints: + ## - maxSkew: 1 + ## topologyKey: node + ## whenUnsatisfiable: DoNotSchedule + ## + topologySpreadConstraints: [] + ## @param master.dnsPolicy DNS Policy for Redis® master pod + ## ref: https://kubernetes.io/docs/concepts/services-networking/dns-pod-service/ + ## E.g. + ## dnsPolicy: ClusterFirst + dnsPolicy: "" + ## @param master.dnsConfig DNS Configuration for Redis® master pod + ## ref: https://kubernetes.io/docs/concepts/services-networking/dns-pod-service/ + ## E.g. + ## dnsConfig: + ## options: + ## - name: ndots + ## value: "4" + ## - name: single-request-reopen + dnsConfig: {} + ## @param master.lifecycleHooks for the Redis® master container(s) to automate configuration before or after startup + ## + lifecycleHooks: {} + ## @param master.extraVolumes Optionally specify extra list of additional volumes for the Redis® master pod(s) + ## + extraVolumes: [] + ## @param master.extraVolumeMounts Optionally specify extra list of additional volumeMounts for the Redis® master container(s) + ## + extraVolumeMounts: [] + ## @param master.sidecars Add additional sidecar containers to the Redis® master pod(s) + ## e.g: + ## sidecars: + ## - name: your-image-name + ## image: your-image + ## imagePullPolicy: Always + ## ports: + ## - name: portname + ## containerPort: 1234 + ## + sidecars: [] + ## @param master.initContainers Add additional init containers to the Redis® master pod(s) + ## ref: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/ + ## e.g: + ## initContainers: + ## - name: your-image-name + ## image: your-image + ## imagePullPolicy: Always + ## command: ['sh', '-c', 'echo "hello world"'] + ## + initContainers: [] + ## Persistence parameters + ## ref: https://kubernetes.io/docs/user-guide/persistent-volumes/ + ## + persistence: + ## @param master.persistence.enabled Enable persistence on Redis® master nodes using Persistent Volume Claims + ## + enabled: true + ## @param master.persistence.medium Provide a medium for `emptyDir` volumes. + ## + medium: "" + ## @param master.persistence.sizeLimit Set this to enable a size limit for `emptyDir` volumes. + ## + sizeLimit: "" + ## @param master.persistence.path The path the volume will be mounted at on Redis® master containers + ## NOTE: Useful when using different Redis® images + ## + path: /data + ## @param master.persistence.subPath The subdirectory of the volume to mount on Redis® master containers + ## NOTE: Useful in dev environments + ## + subPath: "" + ## @param master.persistence.storageClass Persistent Volume storage class + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is set, choosing the default provisioner + ## + storageClass: "" + ## @param master.persistence.accessModes Persistent Volume access modes + ## + accessModes: + - ReadWriteOnce + ## @param master.persistence.size Persistent Volume size + ## + size: 8Gi + ## @param master.persistence.annotations Additional custom annotations for the PVC + ## + annotations: {} + ## @param master.persistence.selector Additional labels to match for the PVC + ## e.g: + ## selector: + ## matchLabels: + ## app: my-app + ## + selector: {} + ## @param master.persistence.dataSource Custom PVC data source + ## + dataSource: {} + ## @param master.persistence.existingClaim Use a existing PVC which must be created manually before bound + ## NOTE: requires master.persistence.enabled: true + ## + existingClaim: "" + ## Redis® master service parameters + ## + service: + ## @param master.service.type Redis® master service type + ## + type: ClusterIP + ## @param master.service.ports.redis Redis® master service port + ## + ports: + redis: 6379 + ## @param master.service.nodePorts.redis Node port for Redis® master + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#type-nodeport + ## NOTE: choose port between <30000-32767> + ## + nodePorts: + redis: "" + ## @param master.service.externalTrafficPolicy Redis® master service external traffic policy + ## ref: https://kubernetes.io/docs/tasks/access-application-cluster/create-external-load-balancer/#preserving-the-client-source-ip + ## + externalTrafficPolicy: Cluster + ## @param master.service.extraPorts Extra ports to expose (normally used with the `sidecar` value) + ## + extraPorts: [] + ## @param master.service.internalTrafficPolicy Redis® master service internal traffic policy (requires Kubernetes v1.22 or greater to be usable) + ## ref: https://kubernetes.io/docs/concepts/services-networking/service-traffic-policy/ + ## + internalTrafficPolicy: Cluster + ## @param master.service.clusterIP Redis® master service Cluster IP + ## + clusterIP: "" + ## @param master.service.loadBalancerIP Redis® master service Load Balancer IP + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#internal-load-balancer + ## + loadBalancerIP: "" + ## @param master.service.loadBalancerSourceRanges Redis® master service Load Balancer sources + ## https://kubernetes.io/docs/tasks/access-application-cluster/configure-cloud-provider-firewall/#restrict-access-for-loadbalancer-service + ## e.g. + ## loadBalancerSourceRanges: + ## - 10.10.10.0/24 + ## + loadBalancerSourceRanges: [] + ## @param master.service.annotations Additional custom annotations for Redis® master service + ## + annotations: {} + ## @param master.service.sessionAffinity Session Affinity for Kubernetes service, can be "None" or "ClientIP" + ## If "ClientIP", consecutive client requests will be directed to the same Pod + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#virtual-ips-and-service-proxies + ## + sessionAffinity: None + ## @param master.service.sessionAffinityConfig Additional settings for the sessionAffinity + ## sessionAffinityConfig: + ## clientIP: + ## timeoutSeconds: 300 + ## + sessionAffinityConfig: {} + ## @param master.terminationGracePeriodSeconds Integer setting the termination grace period for the redis-master pods + ## + terminationGracePeriodSeconds: 30 + +## @section Redis® replicas configuration parameters +## + +replica: + ## @param replica.replicaCount Number of Redis® replicas to deploy + ## + replicaCount: 3 + ## @param replica.configuration Configuration for Redis® replicas nodes + ## ref: https://redis.io/topics/config + ## + configuration: "" + ## @param replica.disableCommands Array with Redis® commands to disable on replicas nodes + ## Commands will be completely disabled by renaming each to an empty string. + ## ref: https://redis.io/topics/security#disabling-of-specific-commands + ## + disableCommands: + - FLUSHDB + - FLUSHALL + ## @param replica.command Override default container command (useful when using custom images) + ## + command: [] + ## @param replica.args Override default container args (useful when using custom images) + ## + args: [] + ## @param replica.preExecCmds Additional commands to run prior to starting Redis® replicas + ## + preExecCmds: [] + ## @param replica.extraFlags Array with additional command line flags for Redis® replicas + ## e.g: + ## extraFlags: + ## - "--maxmemory-policy volatile-ttl" + ## - "--repl-backlog-size 1024mb" + ## + extraFlags: [] + ## @param replica.extraEnvVars Array with extra environment variables to add to Redis® replicas nodes + ## e.g: + ## extraEnvVars: + ## - name: FOO + ## value: "bar" + ## + extraEnvVars: [] + ## @param replica.extraEnvVarsCM Name of existing ConfigMap containing extra env vars for Redis® replicas nodes + ## + extraEnvVarsCM: "" + ## @param replica.extraEnvVarsSecret Name of existing Secret containing extra env vars for Redis® replicas nodes + ## + extraEnvVarsSecret: "" + ## @param replica.externalMaster.enabled Use external master for bootstrapping + ## @param replica.externalMaster.host External master host to bootstrap from + ## @param replica.externalMaster.port Port for Redis service external master host + ## + externalMaster: + enabled: false + host: "" + port: 6379 + ## @param replica.containerPorts.redis Container port to open on Redis® replicas nodes + ## + containerPorts: + redis: 6379 + ## Configure extra options for Redis® containers' liveness and readiness probes + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes + ## @param replica.startupProbe.enabled Enable startupProbe on Redis® replicas nodes + ## @param replica.startupProbe.initialDelaySeconds Initial delay seconds for startupProbe + ## @param replica.startupProbe.periodSeconds Period seconds for startupProbe + ## @param replica.startupProbe.timeoutSeconds Timeout seconds for startupProbe + ## @param replica.startupProbe.failureThreshold Failure threshold for startupProbe + ## @param replica.startupProbe.successThreshold Success threshold for startupProbe + ## + startupProbe: + enabled: true + initialDelaySeconds: 10 + periodSeconds: 10 + timeoutSeconds: 5 + successThreshold: 1 + failureThreshold: 22 + ## @param replica.livenessProbe.enabled Enable livenessProbe on Redis® replicas nodes + ## @param replica.livenessProbe.initialDelaySeconds Initial delay seconds for livenessProbe + ## @param replica.livenessProbe.periodSeconds Period seconds for livenessProbe + ## @param replica.livenessProbe.timeoutSeconds Timeout seconds for livenessProbe + ## @param replica.livenessProbe.failureThreshold Failure threshold for livenessProbe + ## @param replica.livenessProbe.successThreshold Success threshold for livenessProbe + ## + livenessProbe: + enabled: true + initialDelaySeconds: 20 + periodSeconds: 5 + timeoutSeconds: 5 + successThreshold: 1 + failureThreshold: 5 + ## @param replica.readinessProbe.enabled Enable readinessProbe on Redis® replicas nodes + ## @param replica.readinessProbe.initialDelaySeconds Initial delay seconds for readinessProbe + ## @param replica.readinessProbe.periodSeconds Period seconds for readinessProbe + ## @param replica.readinessProbe.timeoutSeconds Timeout seconds for readinessProbe + ## @param replica.readinessProbe.failureThreshold Failure threshold for readinessProbe + ## @param replica.readinessProbe.successThreshold Success threshold for readinessProbe + ## + readinessProbe: + enabled: true + initialDelaySeconds: 20 + periodSeconds: 5 + timeoutSeconds: 1 + successThreshold: 1 + failureThreshold: 5 + ## @param replica.customStartupProbe Custom startupProbe that overrides the default one + ## + customStartupProbe: {} + ## @param replica.customLivenessProbe Custom livenessProbe that overrides the default one + ## + customLivenessProbe: {} + ## @param replica.customReadinessProbe Custom readinessProbe that overrides the default one + ## + customReadinessProbe: {} + ## Redis® replicas resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## @param replica.resources.limits The resources limits for the Redis® replicas containers + ## @param replica.resources.requests The requested resources for the Redis® replicas containers + ## + resources: + # We usually recommend not to specify default resources and to leave this as a conscious + # choice for the user. This also increases chances charts run on environments with little + # resources, such as Minikube. If you do want to specify resources, uncomment the following + # lines, adjust them as necessary, and remove the curly braces after 'resources:'. + limits: {} + # cpu: 250m + # memory: 256Mi + requests: {} + # cpu: 250m + # memory: 256Mi + ## Configure Pods Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-pod + ## @param replica.podSecurityContext.enabled Enabled Redis® replicas pods' Security Context + ## @param replica.podSecurityContext.fsGroup Set Redis® replicas pod's Security Context fsGroup + ## + podSecurityContext: + enabled: true + fsGroup: 1001 + ## Configure Container Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-pod + ## @param replica.containerSecurityContext.enabled Enabled Redis® replicas containers' Security Context + ## @param replica.containerSecurityContext.runAsUser Set Redis® replicas containers' Security Context runAsUser + ## + containerSecurityContext: + enabled: true + runAsUser: 1001 + ## @param replica.schedulerName Alternate scheduler for Redis® replicas pods + ## ref: https://kubernetes.io/docs/tasks/administer-cluster/configure-multiple-schedulers/ + ## + schedulerName: "" + ## @param replica.updateStrategy.type Redis® replicas statefulset strategy type + ## @skip replica.updateStrategy.rollingUpdate + ## ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#update-strategies + ## + updateStrategy: + ## StrategyType + ## Can be set to RollingUpdate or OnDelete + ## + type: RollingUpdate + rollingUpdate: {} + ## @param replica.priorityClassName Redis® replicas pods' priorityClassName + ## + priorityClassName: "" + ## @param replica.podManagementPolicy podManagementPolicy to manage scaling operation of %%MAIN_CONTAINER_NAME%% pods + ## ref: https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#pod-management-policies + ## + podManagementPolicy: "" + ## @param replica.hostAliases Redis® replicas pods host aliases + ## https://kubernetes.io/docs/concepts/services-networking/add-entries-to-pod-etc-hosts-with-host-aliases/ + ## + hostAliases: [] + ## @param replica.podLabels Extra labels for Redis® replicas pods + ## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + ## + podLabels: {} + ## @param replica.podAnnotations Annotations for Redis® replicas pods + ## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/ + ## + podAnnotations: {} + ## @param replica.shareProcessNamespace Share a single process namespace between all of the containers in Redis® replicas pods + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/share-process-namespace/ + ## + shareProcessNamespace: false + ## @param replica.podAffinityPreset Pod affinity preset. Ignored if `replica.affinity` is set. Allowed values: `soft` or `hard` + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity + ## + podAffinityPreset: "" + ## @param replica.podAntiAffinityPreset Pod anti-affinity preset. Ignored if `replica.affinity` is set. Allowed values: `soft` or `hard` + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#inter-pod-affinity-and-anti-affinity + ## + podAntiAffinityPreset: soft + ## Node affinity preset + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#node-affinity + ## + nodeAffinityPreset: + ## @param replica.nodeAffinityPreset.type Node affinity preset type. Ignored if `replica.affinity` is set. Allowed values: `soft` or `hard` + ## + type: "" + ## @param replica.nodeAffinityPreset.key Node label key to match. Ignored if `replica.affinity` is set + ## + key: "" + ## @param replica.nodeAffinityPreset.values Node label values to match. Ignored if `replica.affinity` is set + ## E.g. + ## values: + ## - e2e-az1 + ## - e2e-az2 + ## + values: [] + ## @param replica.affinity Affinity for Redis® replicas pods assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + ## NOTE: `replica.podAffinityPreset`, `replica.podAntiAffinityPreset`, and `replica.nodeAffinityPreset` will be ignored when it's set + ## + affinity: {} + ## @param replica.nodeSelector Node labels for Redis® replicas pods assignment + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + ## + nodeSelector: {} + ## @param replica.tolerations Tolerations for Redis® replicas pods assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + ## + tolerations: [] + ## @param replica.topologySpreadConstraints Spread Constraints for Redis® replicas pod assignment + ## ref: https://kubernetes.io/docs/concepts/workloads/pods/pod-topology-spread-constraints/ + ## E.g. + ## topologySpreadConstraints: + ## - maxSkew: 1 + ## topologyKey: node + ## whenUnsatisfiable: DoNotSchedule + ## + topologySpreadConstraints: [] + ## @param replica.dnsPolicy DNS Policy for Redis® replica pods + ## ref: https://kubernetes.io/docs/concepts/services-networking/dns-pod-service/ + ## E.g. + ## dnsPolicy: ClusterFirst + dnsPolicy: "" + ## @param replica.dnsConfig DNS Configuration for Redis® replica pods + ## ref: https://kubernetes.io/docs/concepts/services-networking/dns-pod-service/ + ## E.g. + ## dnsConfig: + ## options: + ## - name: ndots + ## value: "4" + ## - name: single-request-reopen + dnsConfig: {} + ## @param replica.lifecycleHooks for the Redis® replica container(s) to automate configuration before or after startup + ## + lifecycleHooks: {} + ## @param replica.extraVolumes Optionally specify extra list of additional volumes for the Redis® replicas pod(s) + ## + extraVolumes: [] + ## @param replica.extraVolumeMounts Optionally specify extra list of additional volumeMounts for the Redis® replicas container(s) + ## + extraVolumeMounts: [] + ## @param replica.sidecars Add additional sidecar containers to the Redis® replicas pod(s) + ## e.g: + ## sidecars: + ## - name: your-image-name + ## image: your-image + ## imagePullPolicy: Always + ## ports: + ## - name: portname + ## containerPort: 1234 + ## + sidecars: [] + ## @param replica.initContainers Add additional init containers to the Redis® replicas pod(s) + ## ref: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/ + ## e.g: + ## initContainers: + ## - name: your-image-name + ## image: your-image + ## imagePullPolicy: Always + ## command: ['sh', '-c', 'echo "hello world"'] + ## + initContainers: [] + ## Persistence Parameters + ## ref: https://kubernetes.io/docs/user-guide/persistent-volumes/ + ## + persistence: + ## @param replica.persistence.enabled Enable persistence on Redis® replicas nodes using Persistent Volume Claims + ## + enabled: true + ## @param replica.persistence.medium Provide a medium for `emptyDir` volumes. + ## + medium: "" + ## @param replica.persistence.sizeLimit Set this to enable a size limit for `emptyDir` volumes. + ## + sizeLimit: "" + ## @param replica.persistence.path The path the volume will be mounted at on Redis® replicas containers + ## NOTE: Useful when using different Redis® images + ## + path: /data + ## @param replica.persistence.subPath The subdirectory of the volume to mount on Redis® replicas containers + ## NOTE: Useful in dev environments + ## + subPath: "" + ## @param replica.persistence.storageClass Persistent Volume storage class + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is set, choosing the default provisioner + ## + storageClass: "" + ## @param replica.persistence.accessModes Persistent Volume access modes + ## + accessModes: + - ReadWriteOnce + ## @param replica.persistence.size Persistent Volume size + ## + size: 8Gi + ## @param replica.persistence.annotations Additional custom annotations for the PVC + ## + annotations: {} + ## @param replica.persistence.selector Additional labels to match for the PVC + ## e.g: + ## selector: + ## matchLabels: + ## app: my-app + ## + selector: {} + ## @param replica.persistence.dataSource Custom PVC data source + ## + dataSource: {} + ## @param replica.persistence.existingClaim Use a existing PVC which must be created manually before bound + ## NOTE: requires replica.persistence.enabled: true + ## + existingClaim: "" + ## Redis® replicas service parameters + ## + service: + ## @param replica.service.type Redis® replicas service type + ## + type: ClusterIP + ## @param replica.service.ports.redis Redis® replicas service port + ## + ports: + redis: 6379 + ## @param replica.service.nodePorts.redis Node port for Redis® replicas + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#type-nodeport + ## NOTE: choose port between <30000-32767> + ## + nodePorts: + redis: "" + ## @param replica.service.externalTrafficPolicy Redis® replicas service external traffic policy + ## ref: https://kubernetes.io/docs/tasks/access-application-cluster/create-external-load-balancer/#preserving-the-client-source-ip + ## + externalTrafficPolicy: Cluster + ## @param replica.service.internalTrafficPolicy Redis® replicas service internal traffic policy (requires Kubernetes v1.22 or greater to be usable) + ## ref: https://kubernetes.io/docs/concepts/services-networking/service-traffic-policy/ + ## + internalTrafficPolicy: Cluster + ## @param replica.service.extraPorts Extra ports to expose (normally used with the `sidecar` value) + ## + extraPorts: [] + ## @param replica.service.clusterIP Redis® replicas service Cluster IP + ## + clusterIP: "" + ## @param replica.service.loadBalancerIP Redis® replicas service Load Balancer IP + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#internal-load-balancer + ## + loadBalancerIP: "" + ## @param replica.service.loadBalancerSourceRanges Redis® replicas service Load Balancer sources + ## https://kubernetes.io/docs/tasks/access-application-cluster/configure-cloud-provider-firewall/#restrict-access-for-loadbalancer-service + ## e.g. + ## loadBalancerSourceRanges: + ## - 10.10.10.0/24 + ## + loadBalancerSourceRanges: [] + ## @param replica.service.annotations Additional custom annotations for Redis® replicas service + ## + annotations: {} + ## @param replica.service.sessionAffinity Session Affinity for Kubernetes service, can be "None" or "ClientIP" + ## If "ClientIP", consecutive client requests will be directed to the same Pod + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#virtual-ips-and-service-proxies + ## + sessionAffinity: None + ## @param replica.service.sessionAffinityConfig Additional settings for the sessionAffinity + ## sessionAffinityConfig: + ## clientIP: + ## timeoutSeconds: 300 + ## + sessionAffinityConfig: {} + ## @param replica.terminationGracePeriodSeconds Integer setting the termination grace period for the redis-replicas pods + ## + terminationGracePeriodSeconds: 30 + ## Autoscaling configuration + ## + autoscaling: + ## @param replica.autoscaling.enabled Enable replica autoscaling settings + ## + enabled: false + ## @param replica.autoscaling.minReplicas Minimum replicas for the pod autoscaling + ## + minReplicas: 1 + ## @param replica.autoscaling.maxReplicas Maximum replicas for the pod autoscaling + ## + maxReplicas: 11 + ## @param replica.autoscaling.targetCPU Percentage of CPU to consider when autoscaling + ## + targetCPU: "" + ## @param replica.autoscaling.targetMemory Percentage of Memory to consider when autoscaling + ## + targetMemory: "" + +## @section Redis® Sentinel configuration parameters +## + +sentinel: + ## @param sentinel.enabled Use Redis® Sentinel on Redis® pods. + ## IMPORTANT: this will disable the master and replicas services and + ## create a single Redis® service exposing both the Redis and Sentinel ports + ## + enabled: false + ## Bitnami Redis® Sentinel image version + ## ref: https://hub.docker.com/r/bitnami/redis-sentinel/tags/ + ## @param sentinel.image.registry Redis® Sentinel image registry + ## @param sentinel.image.repository Redis® Sentinel image repository + ## @param sentinel.image.tag Redis® Sentinel image tag (immutable tags are recommended) + ## @param sentinel.image.pullPolicy Redis® Sentinel image pull policy + ## @param sentinel.image.pullSecrets Redis® Sentinel image pull secrets + ## @param sentinel.image.debug Enable image debug mode + ## + image: + registry: docker.io + repository: bitnami/redis-sentinel + tag: 6.2.7-debian-11-r12 + ## Specify a imagePullPolicy + ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent' + ## ref: https://kubernetes.io/docs/user-guide/images/#pre-pulling-images + ## + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## e.g: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## Enable debug mode + ## + debug: false + ## @param sentinel.masterSet Master set name + ## + masterSet: mymaster + ## @param sentinel.quorum Sentinel Quorum + ## + quorum: 2 + ## @param sentinel.getMasterTimeout Amount of time to allow before get_sentinel_master_info() times out. + ## NOTE: This is directly related to the startupProbes which are configured to run every 10 seconds for a total of 22 failures. If adjusting this value, also adjust the startupProbes. + getMasterTimeout: 220 + ## @param sentinel.automateClusterRecovery Automate cluster recovery in cases where the last replica is not considered a good replica and Sentinel won't automatically failover to it. + ## This also prevents any new replica from starting until the last remaining replica is elected as master to guarantee that it is the one to be elected by Sentinel, and not a newly started replica with no data. + ## NOTE: This feature requires a "downAfterMilliseconds" value less or equal to 2000. + ## + automateClusterRecovery: false + ## Sentinel timing restrictions + ## @param sentinel.downAfterMilliseconds Timeout for detecting a Redis® node is down + ## @param sentinel.failoverTimeout Timeout for performing a election failover + ## + downAfterMilliseconds: 60000 + failoverTimeout: 18000 + ## @param sentinel.parallelSyncs Number of replicas that can be reconfigured in parallel to use the new master after a failover + ## + parallelSyncs: 1 + ## @param sentinel.configuration Configuration for Redis® Sentinel nodes + ## ref: https://redis.io/topics/sentinel + ## + configuration: "" + ## @param sentinel.command Override default container command (useful when using custom images) + ## + command: [] + ## @param sentinel.args Override default container args (useful when using custom images) + ## + args: [] + ## @param sentinel.preExecCmds Additional commands to run prior to starting Redis® Sentinel + ## + preExecCmds: [] + ## @param sentinel.extraEnvVars Array with extra environment variables to add to Redis® Sentinel nodes + ## e.g: + ## extraEnvVars: + ## - name: FOO + ## value: "bar" + ## + extraEnvVars: [] + ## @param sentinel.extraEnvVarsCM Name of existing ConfigMap containing extra env vars for Redis® Sentinel nodes + ## + extraEnvVarsCM: "" + ## @param sentinel.extraEnvVarsSecret Name of existing Secret containing extra env vars for Redis® Sentinel nodes + ## + extraEnvVarsSecret: "" + ## @param sentinel.externalMaster.enabled Use external master for bootstrapping + ## @param sentinel.externalMaster.host External master host to bootstrap from + ## @param sentinel.externalMaster.port Port for Redis service external master host + ## + externalMaster: + enabled: false + host: "" + port: 6379 + ## @param sentinel.containerPorts.sentinel Container port to open on Redis® Sentinel nodes + ## + containerPorts: + sentinel: 26379 + ## Configure extra options for Redis® containers' liveness and readiness probes + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes + ## @param sentinel.startupProbe.enabled Enable startupProbe on Redis® Sentinel nodes + ## @param sentinel.startupProbe.initialDelaySeconds Initial delay seconds for startupProbe + ## @param sentinel.startupProbe.periodSeconds Period seconds for startupProbe + ## @param sentinel.startupProbe.timeoutSeconds Timeout seconds for startupProbe + ## @param sentinel.startupProbe.failureThreshold Failure threshold for startupProbe + ## @param sentinel.startupProbe.successThreshold Success threshold for startupProbe + ## + startupProbe: + enabled: true + initialDelaySeconds: 10 + periodSeconds: 10 + timeoutSeconds: 5 + successThreshold: 1 + failureThreshold: 22 + ## @param sentinel.livenessProbe.enabled Enable livenessProbe on Redis® Sentinel nodes + ## @param sentinel.livenessProbe.initialDelaySeconds Initial delay seconds for livenessProbe + ## @param sentinel.livenessProbe.periodSeconds Period seconds for livenessProbe + ## @param sentinel.livenessProbe.timeoutSeconds Timeout seconds for livenessProbe + ## @param sentinel.livenessProbe.failureThreshold Failure threshold for livenessProbe + ## @param sentinel.livenessProbe.successThreshold Success threshold for livenessProbe + ## + livenessProbe: + enabled: true + initialDelaySeconds: 20 + periodSeconds: 5 + timeoutSeconds: 5 + successThreshold: 1 + failureThreshold: 5 + ## @param sentinel.readinessProbe.enabled Enable readinessProbe on Redis® Sentinel nodes + ## @param sentinel.readinessProbe.initialDelaySeconds Initial delay seconds for readinessProbe + ## @param sentinel.readinessProbe.periodSeconds Period seconds for readinessProbe + ## @param sentinel.readinessProbe.timeoutSeconds Timeout seconds for readinessProbe + ## @param sentinel.readinessProbe.failureThreshold Failure threshold for readinessProbe + ## @param sentinel.readinessProbe.successThreshold Success threshold for readinessProbe + ## + readinessProbe: + enabled: true + initialDelaySeconds: 20 + periodSeconds: 5 + timeoutSeconds: 1 + successThreshold: 1 + failureThreshold: 5 + ## @param sentinel.customStartupProbe Custom startupProbe that overrides the default one + ## + customStartupProbe: {} + ## @param sentinel.customLivenessProbe Custom livenessProbe that overrides the default one + ## + customLivenessProbe: {} + ## @param sentinel.customReadinessProbe Custom readinessProbe that overrides the default one + ## + customReadinessProbe: {} + ## Persistence parameters + ## ref: https://kubernetes.io/docs/user-guide/persistent-volumes/ + ## + persistence: + ## @param sentinel.persistence.enabled Enable persistence on Redis® sentinel nodes using Persistent Volume Claims (Experimental) + ## + enabled: false + ## @param sentinel.persistence.storageClass Persistent Volume storage class + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is set, choosing the default provisioner + ## + storageClass: "" + ## @param sentinel.persistence.accessModes Persistent Volume access modes + ## + accessModes: + - ReadWriteOnce + ## @param sentinel.persistence.size Persistent Volume size + ## + size: 100Mi + ## @param sentinel.persistence.annotations Additional custom annotations for the PVC + ## + annotations: {} + ## @param sentinel.persistence.selector Additional labels to match for the PVC + ## e.g: + ## selector: + ## matchLabels: + ## app: my-app + ## + selector: {} + ## @param sentinel.persistence.dataSource Custom PVC data source + ## + dataSource: {} + ## @param sentinel.persistence.medium Provide a medium for `emptyDir` volumes. + ## + medium: "" + ## Redis® Sentinel resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## @param sentinel.resources.limits The resources limits for the Redis® Sentinel containers + ## @param sentinel.resources.requests The requested resources for the Redis® Sentinel containers + ## + resources: + limits: {} + requests: {} + ## Configure Container Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-pod + ## @param sentinel.containerSecurityContext.enabled Enabled Redis® Sentinel containers' Security Context + ## @param sentinel.containerSecurityContext.runAsUser Set Redis® Sentinel containers' Security Context runAsUser + ## + containerSecurityContext: + enabled: true + runAsUser: 1001 + ## @param sentinel.lifecycleHooks for the Redis® sentinel container(s) to automate configuration before or after startup + ## + lifecycleHooks: {} + ## @param sentinel.extraVolumes Optionally specify extra list of additional volumes for the Redis® Sentinel + ## + extraVolumes: [] + ## @param sentinel.extraVolumeMounts Optionally specify extra list of additional volumeMounts for the Redis® Sentinel container(s) + ## + extraVolumeMounts: [] + ## Redis® Sentinel service parameters + ## + service: + ## @param sentinel.service.type Redis® Sentinel service type + ## + type: ClusterIP + ## @param sentinel.service.ports.redis Redis® service port for Redis® + ## @param sentinel.service.ports.sentinel Redis® service port for Redis® Sentinel + ## + ports: + redis: 6379 + sentinel: 26379 + ## @param sentinel.service.nodePorts.redis Node port for Redis® + ## @param sentinel.service.nodePorts.sentinel Node port for Sentinel + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#type-nodeport + ## NOTE: choose port between <30000-32767> + ## NOTE: By leaving these values blank, they will be generated by ports-configmap + ## If setting manually, please leave at least replica.replicaCount + 1 in between sentinel.service.nodePorts.redis and sentinel.service.nodePorts.sentinel to take into account the ports that will be created while incrementing that base port + ## + nodePorts: + redis: "" + sentinel: "" + ## @param sentinel.service.externalTrafficPolicy Redis® Sentinel service external traffic policy + ## ref: https://kubernetes.io/docs/tasks/access-application-cluster/create-external-load-balancer/#preserving-the-client-source-ip + ## + externalTrafficPolicy: Cluster + ## @param sentinel.service.extraPorts Extra ports to expose (normally used with the `sidecar` value) + ## + extraPorts: [] + ## @param sentinel.service.clusterIP Redis® Sentinel service Cluster IP + ## + clusterIP: "" + ## @param sentinel.service.loadBalancerIP Redis® Sentinel service Load Balancer IP + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#internal-load-balancer + ## + loadBalancerIP: "" + ## @param sentinel.service.loadBalancerSourceRanges Redis® Sentinel service Load Balancer sources + ## https://kubernetes.io/docs/tasks/access-application-cluster/configure-cloud-provider-firewall/#restrict-access-for-loadbalancer-service + ## e.g. + ## loadBalancerSourceRanges: + ## - 10.10.10.0/24 + ## + loadBalancerSourceRanges: [] + ## @param sentinel.service.annotations Additional custom annotations for Redis® Sentinel service + ## + annotations: {} + ## @param sentinel.service.sessionAffinity Session Affinity for Kubernetes service, can be "None" or "ClientIP" + ## If "ClientIP", consecutive client requests will be directed to the same Pod + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#virtual-ips-and-service-proxies + ## + sessionAffinity: None + ## @param sentinel.service.sessionAffinityConfig Additional settings for the sessionAffinity + ## sessionAffinityConfig: + ## clientIP: + ## timeoutSeconds: 300 + ## + sessionAffinityConfig: {} + ## @param sentinel.terminationGracePeriodSeconds Integer setting the termination grace period for the redis-node pods + ## + terminationGracePeriodSeconds: 30 + +## @section Other Parameters +## + +## Network Policy configuration +## ref: https://kubernetes.io/docs/concepts/services-networking/network-policies/ +## +networkPolicy: + ## @param networkPolicy.enabled Enable creation of NetworkPolicy resources + ## + enabled: false + ## @param networkPolicy.allowExternal Don't require client label for connections + ## When set to false, only pods with the correct client label will have network access to the ports + ## Redis® is listening on. When true, Redis® will accept connections from any source + ## (with the correct destination port). + ## + allowExternal: true + ## @param networkPolicy.extraIngress Add extra ingress rules to the NetworkPolicy + ## e.g: + ## extraIngress: + ## - ports: + ## - port: 1234 + ## from: + ## - podSelector: + ## - matchLabels: + ## - role: frontend + ## - podSelector: + ## - matchExpressions: + ## - key: role + ## operator: In + ## values: + ## - frontend + ## + extraIngress: [] + ## @param networkPolicy.extraEgress Add extra egress rules to the NetworkPolicy + ## e.g: + ## extraEgress: + ## - ports: + ## - port: 1234 + ## to: + ## - podSelector: + ## - matchLabels: + ## - role: frontend + ## - podSelector: + ## - matchExpressions: + ## - key: role + ## operator: In + ## values: + ## - frontend + ## + extraEgress: [] + ## @param networkPolicy.ingressNSMatchLabels Labels to match to allow traffic from other namespaces + ## @param networkPolicy.ingressNSPodMatchLabels Pod labels to match to allow traffic from other namespaces + ## + ingressNSMatchLabels: {} + ingressNSPodMatchLabels: {} +## PodSecurityPolicy configuration +## ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/ +## +podSecurityPolicy: + ## @param podSecurityPolicy.create Whether to create a PodSecurityPolicy. WARNING: PodSecurityPolicy is deprecated in Kubernetes v1.21 or later, unavailable in v1.25 or later + ## + create: false + ## @param podSecurityPolicy.enabled Enable PodSecurityPolicy's RBAC rules + ## + enabled: false +## RBAC configuration +## +rbac: + ## @param rbac.create Specifies whether RBAC resources should be created + ## + create: false + ## @param rbac.rules Custom RBAC rules to set + ## e.g: + ## rules: + ## - apiGroups: + ## - "" + ## resources: + ## - pods + ## verbs: + ## - get + ## - list + ## + rules: [] +## ServiceAccount configuration +## +serviceAccount: + ## @param serviceAccount.create Specifies whether a ServiceAccount should be created + ## + create: true + ## @param serviceAccount.name The name of the ServiceAccount to use. + ## If not set and create is true, a name is generated using the common.names.fullname template + ## + name: "" + ## @param serviceAccount.automountServiceAccountToken Whether to auto mount the service account token + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/#use-the-default-service-account-to-access-the-api-server + ## + automountServiceAccountToken: true + ## @param serviceAccount.annotations Additional custom annotations for the ServiceAccount + ## + annotations: {} +## Redis® Pod Disruption Budget configuration +## ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/ +## +pdb: + ## @param pdb.create Specifies whether a PodDisruptionBudget should be created + ## + create: false + ## @param pdb.minAvailable Min number of pods that must still be available after the eviction + ## + minAvailable: 1 + ## @param pdb.maxUnavailable Max number of pods that can be unavailable after the eviction + ## + maxUnavailable: "" +## TLS configuration +## +tls: + ## @param tls.enabled Enable TLS traffic + ## + enabled: false + ## @param tls.authClients Require clients to authenticate + ## + authClients: true + ## @param tls.autoGenerated Enable autogenerated certificates + ## + autoGenerated: false + ## @param tls.existingSecret The name of the existing secret that contains the TLS certificates + ## + existingSecret: "" + ## @param tls.certificatesSecret DEPRECATED. Use existingSecret instead. + ## + certificatesSecret: "" + ## @param tls.certFilename Certificate filename + ## + certFilename: "" + ## @param tls.certKeyFilename Certificate Key filename + ## + certKeyFilename: "" + ## @param tls.certCAFilename CA Certificate filename + ## + certCAFilename: "" + ## @param tls.dhParamsFilename File containing DH params (in order to support DH based ciphers) + ## + dhParamsFilename: "" + +## @section Metrics Parameters +## + +metrics: + ## @param metrics.enabled Start a sidecar prometheus exporter to expose Redis® metrics + ## + enabled: false + ## Bitnami Redis® Exporter image + ## ref: https://hub.docker.com/r/bitnami/redis-exporter/tags/ + ## @param metrics.image.registry Redis® Exporter image registry + ## @param metrics.image.repository Redis® Exporter image repository + ## @param metrics.image.tag Redis® Redis® Exporter image tag (immutable tags are recommended) + ## @param metrics.image.pullPolicy Redis® Exporter image pull policy + ## @param metrics.image.pullSecrets Redis® Exporter image pull secrets + ## + image: + registry: docker.io + repository: bitnami/redis-exporter + tag: 1.43.0-debian-11-r4 + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## e.g: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## @param metrics.command Override default metrics container init command (useful when using custom images) + ## + command: [] + ## @param metrics.redisTargetHost A way to specify an alternative Redis® hostname + ## Useful for certificate CN/SAN matching + ## + redisTargetHost: "localhost" + ## @param metrics.extraArgs Extra arguments for Redis® exporter, for example: + ## e.g.: + ## extraArgs: + ## check-keys: myKey,myOtherKey + ## + extraArgs: {} + ## @param metrics.extraEnvVars Array with extra environment variables to add to Redis® exporter + ## e.g: + ## extraEnvVars: + ## - name: FOO + ## value: "bar" + ## + extraEnvVars: [] + ## Configure Container Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-pod + ## @param metrics.containerSecurityContext.enabled Enabled Redis® exporter containers' Security Context + ## @param metrics.containerSecurityContext.runAsUser Set Redis® exporter containers' Security Context runAsUser + ## + containerSecurityContext: + enabled: true + runAsUser: 1001 + ## @param metrics.extraVolumes Optionally specify extra list of additional volumes for the Redis® metrics sidecar + ## + extraVolumes: [] + ## @param metrics.extraVolumeMounts Optionally specify extra list of additional volumeMounts for the Redis® metrics sidecar + ## + extraVolumeMounts: [] + ## Redis® exporter resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## @param metrics.resources.limits The resources limits for the Redis® exporter container + ## @param metrics.resources.requests The requested resources for the Redis® exporter container + ## + resources: + limits: {} + requests: {} + ## @param metrics.podLabels Extra labels for Redis® exporter pods + ## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + ## + podLabels: {} + ## @param metrics.podAnnotations [object] Annotations for Redis® exporter pods + ## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/ + ## + podAnnotations: + prometheus.io/scrape: "true" + prometheus.io/port: "9121" + ## Redis® exporter service parameters + ## + service: + ## @param metrics.service.type Redis® exporter service type + ## + type: ClusterIP + ## @param metrics.service.port Redis® exporter service port + ## + port: 9121 + ## @param metrics.service.externalTrafficPolicy Redis® exporter service external traffic policy + ## ref: https://kubernetes.io/docs/tasks/access-application-cluster/create-external-load-balancer/#preserving-the-client-source-ip + ## + externalTrafficPolicy: Cluster + ## @param metrics.service.extraPorts Extra ports to expose (normally used with the `sidecar` value) + ## + extraPorts: [] + ## @param metrics.service.loadBalancerIP Redis® exporter service Load Balancer IP + ## ref: https://kubernetes.io/docs/concepts/services-networking/service/#internal-load-balancer + ## + loadBalancerIP: "" + ## @param metrics.service.loadBalancerSourceRanges Redis® exporter service Load Balancer sources + ## https://kubernetes.io/docs/tasks/access-application-cluster/configure-cloud-provider-firewall/#restrict-access-for-loadbalancer-service + ## e.g. + ## loadBalancerSourceRanges: + ## - 10.10.10.0/24 + ## + loadBalancerSourceRanges: [] + ## @param metrics.service.annotations Additional custom annotations for Redis® exporter service + ## + annotations: {} + ## Prometheus Service Monitor + ## ref: https://github.com/coreos/prometheus-operator + ## https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#endpoint + ## + serviceMonitor: + ## @param metrics.serviceMonitor.enabled Create ServiceMonitor resource(s) for scraping metrics using PrometheusOperator + ## + enabled: false + ## @param metrics.serviceMonitor.namespace The namespace in which the ServiceMonitor will be created + ## + namespace: "" + ## @param metrics.serviceMonitor.interval The interval at which metrics should be scraped + ## + interval: 30s + ## @param metrics.serviceMonitor.scrapeTimeout The timeout after which the scrape is ended + ## + scrapeTimeout: "" + ## @param metrics.serviceMonitor.relabellings Metrics RelabelConfigs to apply to samples before scraping. + ## + relabellings: [] + ## @param metrics.serviceMonitor.metricRelabelings Metrics RelabelConfigs to apply to samples before ingestion. + ## + metricRelabelings: [] + ## @param metrics.serviceMonitor.honorLabels Specify honorLabels parameter to add the scrape endpoint + ## + honorLabels: false + ## @param metrics.serviceMonitor.additionalLabels Additional labels that can be used so ServiceMonitor resource(s) can be discovered by Prometheus + ## + additionalLabels: {} + ## Custom PrometheusRule to be defined + ## ref: https://github.com/coreos/prometheus-operator#customresourcedefinitions + ## + prometheusRule: + ## @param metrics.prometheusRule.enabled Create a custom prometheusRule Resource for scraping metrics using PrometheusOperator + ## + enabled: false + ## @param metrics.prometheusRule.namespace The namespace in which the prometheusRule will be created + ## + namespace: "" + ## @param metrics.prometheusRule.additionalLabels Additional labels for the prometheusRule + ## + additionalLabels: {} + ## @param metrics.prometheusRule.rules Custom Prometheus rules + ## e.g: + ## rules: + ## - alert: RedisDown + ## expr: redis_up{service="{{ template "common.names.fullname" . }}-metrics"} == 0 + ## for: 2m + ## labels: + ## severity: error + ## annotations: + ## summary: Redis® instance {{ "{{ $labels.instance }}" }} down + ## description: Redis® instance {{ "{{ $labels.instance }}" }} is down + ## - alert: RedisMemoryHigh + ## expr: > + ## redis_memory_used_bytes{service="{{ template "common.names.fullname" . }}-metrics"} * 100 + ## / + ## redis_memory_max_bytes{service="{{ template "common.names.fullname" . }}-metrics"} + ## > 90 + ## for: 2m + ## labels: + ## severity: error + ## annotations: + ## summary: Redis® instance {{ "{{ $labels.instance }}" }} is using too much memory + ## description: | + ## Redis® instance {{ "{{ $labels.instance }}" }} is using {{ "{{ $value }}" }}% of its available memory. + ## - alert: RedisKeyEviction + ## expr: | + ## increase(redis_evicted_keys_total{service="{{ template "common.names.fullname" . }}-metrics"}[5m]) > 0 + ## for: 1s + ## labels: + ## severity: error + ## annotations: + ## summary: Redis® instance {{ "{{ $labels.instance }}" }} has evicted keys + ## description: | + ## Redis® instance {{ "{{ $labels.instance }}" }} has evicted {{ "{{ $value }}" }} keys in the last 5 minutes. + ## + rules: [] + +## @section Init Container Parameters +## + +## 'volumePermissions' init container parameters +## Changes the owner and group of the persistent volume mount point to runAsUser:fsGroup values +## based on the *podSecurityContext/*containerSecurityContext parameters +## +volumePermissions: + ## @param volumePermissions.enabled Enable init container that changes the owner/group of the PV mount point to `runAsUser:fsGroup` + ## + enabled: false + ## Bitnami Shell image + ## ref: https://hub.docker.com/r/bitnami/bitnami-shell/tags/ + ## @param volumePermissions.image.registry Bitnami Shell image registry + ## @param volumePermissions.image.repository Bitnami Shell image repository + ## @param volumePermissions.image.tag Bitnami Shell image tag (immutable tags are recommended) + ## @param volumePermissions.image.pullPolicy Bitnami Shell image pull policy + ## @param volumePermissions.image.pullSecrets Bitnami Shell image pull secrets + ## + image: + registry: docker.io + repository: bitnami/bitnami-shell + tag: 11-debian-11-r11 + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## e.g: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## Init container's resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## @param volumePermissions.resources.limits The resources limits for the init container + ## @param volumePermissions.resources.requests The requested resources for the init container + ## + resources: + limits: {} + requests: {} + ## Init container Container Security Context + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-container + ## @param volumePermissions.containerSecurityContext.runAsUser Set init container's Security Context runAsUser + ## NOTE: when runAsUser is set to special value "auto", init container will try to chown the + ## data folder to auto-determined user&group, using commands: `id -u`:`id -G | cut -d" " -f2` + ## "auto" is especially useful for OpenShift which has scc with dynamic user ids (and 0 is not allowed) + ## + containerSecurityContext: + runAsUser: 0 + +## init-sysctl container parameters +## used to perform sysctl operation to modify Kernel settings (needed sometimes to avoid warnings) +## +sysctl: + ## @param sysctl.enabled Enable init container to modify Kernel settings + ## + enabled: false + ## Bitnami Shell image + ## ref: https://hub.docker.com/r/bitnami/bitnami-shell/tags/ + ## @param sysctl.image.registry Bitnami Shell image registry + ## @param sysctl.image.repository Bitnami Shell image repository + ## @param sysctl.image.tag Bitnami Shell image tag (immutable tags are recommended) + ## @param sysctl.image.pullPolicy Bitnami Shell image pull policy + ## @param sysctl.image.pullSecrets Bitnami Shell image pull secrets + ## + image: + registry: docker.io + repository: bitnami/bitnami-shell + tag: 11-debian-11-r11 + pullPolicy: IfNotPresent + ## Optionally specify an array of imagePullSecrets. + ## Secrets must be manually created in the namespace. + ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ + ## e.g: + ## pullSecrets: + ## - myRegistryKeySecretName + ## + pullSecrets: [] + ## @param sysctl.command Override default init-sysctl container command (useful when using custom images) + ## + command: [] + ## @param sysctl.mountHostSys Mount the host `/sys` folder to `/host-sys` + ## + mountHostSys: false + ## Init container's resource requests and limits + ## ref: https://kubernetes.io/docs/user-guide/compute-resources/ + ## @param sysctl.resources.limits The resources limits for the init container + ## @param sysctl.resources.requests The requested resources for the init container + ## + resources: + limits: {} + requests: {} + +## @section useExternalDNS Parameters +## +## @param useExternalDNS.enabled Enable various syntax that would enable external-dns to work. Note this requires a working installation of `external-dns` to be usable. +## @param useExternalDNS.additionalAnnotations Extra annotations to be utilized when `external-dns` is enabled. +## @param useExternalDNS.annotationKey The annotation key utilized when `external-dns` is enabled. +## @param useExternalDNS.suffix The DNS suffix utilized when `external-dns` is enabled. Note that we prepend the suffix with the full name of the release. +## +useExternalDNS: + enabled: false + suffix: "" + annotationKey: external-dns.alpha.kubernetes.io/ + additionalAnnotations: {} diff --git a/observability/lgtm-distributed/charts/oncall/templates/NOTES.txt b/observability/lgtm-distributed/charts/oncall/templates/NOTES.txt new file mode 100644 index 0000000..4eee164 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/NOTES.txt @@ -0,0 +1,41 @@ +================================================================= +📞 Grafana OnCall Notes +================================================================= + +đź‘‹ Your Grafana OnCall instance has been successfully deployed + +{{- if not .Values.migrate.enabled }} + 🤖 To migrate the database run these commands: + + export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "oncall.name" . }},app.kubernetes.io/instance={{ .Release.Name }},app.kubernetes.io/component=engine" -o jsonpath="{.items[0].metadata.name}") + kubectl exec -it $POD_NAME -c wait-for-db -- bash -c "python manage.py migrate;" +{{- end }} + + âť— Set up a DNS record for your domain (use A Record and "@" to point a root domain to the IP address) + Get the external IP address by running the following commands and point {{ .Values.base_url }} to it: + + kubectl get ingress {{ include "oncall.fullname" . }} -o jsonpath="{.status.loadBalancer.ingress[0].ip}" + + Wait until the dns record got propagated. + NOTE: Check with the following command: nslookup {{ .Values.base_url }} + Try reaching https://{{ .Values.base_url }}/ready/ from the browser, make sure it is not cached locally + +{{- if .Values.grafana.enabled }} + 🦎 Grafana was installed as a part of this helm release. Open https://{{ .Values.base_url }}/grafana/plugins/grafana-oncall-app + The User is {{ .Values.grafana.adminUser }} + Get password by running this command: + + kubectl get secret --namespace {{ .Release.Namespace }} {{ template "oncall.grafana.fullname" . }} -o jsonpath="{.data.admin-password}" | base64 --decode ; echo + +{{- else }} + 🦎 Grafana was NOT installed as a part of this helm release. Open external Grafana, go to "Configuration" - "Plugins" and find Grafana OnCall plugin + NOTE: Make sure your external Grafana is available by the network for the containers installed by this release. +{{- end }} + + đź”— Connect Grafana OnCall Plugin to Grafana OnCall backend: + + Fill the Grafana OnCall Backend URL: + + http://{{ include "oncall.engine.fullname" . }}:8080 + +🎉🎉🎉 Done! 🎉🎉🎉 diff --git a/observability/lgtm-distributed/charts/oncall/templates/_env.tpl b/observability/lgtm-distributed/charts/oncall/templates/_env.tpl new file mode 100644 index 0000000..6821d2a --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/_env.tpl @@ -0,0 +1,663 @@ +{{- define "snippet.oncall.env" -}} +- name: BASE_URL + value: {{ .Values.base_url_protocol }}://{{ .Values.base_url }} +- name: SECRET_KEY + valueFrom: + secretKeyRef: + name: {{ include "snippet.oncall.secret.name" . }} + key: {{ include "snippet.oncall.secret.secretKey" . | quote }} +- name: MIRAGE_SECRET_KEY + valueFrom: + secretKeyRef: + name: {{ include "snippet.oncall.secret.name" . }} + key: {{ include "snippet.oncall.secret.mirageSecretKey" . | quote }} +- name: MIRAGE_CIPHER_IV + value: {{ .Values.oncall.mirageCipherIV | default "1234567890abcdef" | quote }} +- name: DJANGO_SETTINGS_MODULE + value: "settings.helm" +- name: AMIXR_DJANGO_ADMIN_PATH + value: "admin" +- name: OSS + value: "True" +- name: DETACHED_INTEGRATIONS_SERVER + value: {{ .Values.detached_integrations.enabled | toString | title | quote }} +{{- include "snippet.oncall.uwsgi" . }} +- name: BROKER_TYPE + value: {{ .Values.broker.type | default "rabbitmq" }} +- name: GRAFANA_API_URL + value: {{ include "snippet.grafana.url" . | quote }} +{{- end }} + +{{- define "snippet.oncall.secret.name" -}} +{{ if .Values.oncall.secrets.existingSecret -}} + {{ .Values.oncall.secrets.existingSecret }} +{{- else -}} + {{ include "oncall.fullname" . }} +{{- end }} +{{- end }} + +{{- define "snippet.oncall.secret.secretKey" -}} +{{ if .Values.oncall.secrets.existingSecret -}} + {{ required "oncall.secrets.secretKey is required if oncall.secret.existingSecret is not empty" .Values.oncall.secrets.secretKey }} +{{- else -}} + SECRET_KEY +{{- end }} +{{- end }} + +{{- define "snippet.oncall.secret.mirageSecretKey" -}} +{{ if .Values.oncall.secrets.existingSecret -}} + {{ required "oncall.secrets.mirageSecretKey is required if oncall.secret.existingSecret is not empty" .Values.oncall.secrets.mirageSecretKey }} +{{- else -}} + MIRAGE_SECRET_KEY +{{- end }} +{{- end }} + +{{- define "snippet.oncall.uwsgi" -}} +{{- if .Values.uwsgi }} + {{- range $key, $value := .Values.uwsgi }} +- name: UWSGI_{{ $key | upper | replace "-" "_" }} + value: {{ $value | quote }} + {{- end }} +{{- end }} +{{- end }} + +{{- define "snippet.oncall.slack.env" -}} +- name: FEATURE_SLACK_INTEGRATION_ENABLED + value: {{ .Values.oncall.slack.enabled | toString | title | quote }} +{{- if .Values.oncall.slack.enabled }} +{{- if .Values.oncall.slack.existingSecret }} +- name: SLACK_CLIENT_OAUTH_ID + valueFrom: + secretKeyRef: + name: {{ .Values.oncall.slack.existingSecret }} + key: {{ required "oncall.slack.clientIdKey is required if oncall.slack.existingSecret is not empty" .Values.oncall.slack.clientIdKey | quote }} +- name: SLACK_CLIENT_OAUTH_SECRET + valueFrom: + secretKeyRef: + name: {{ .Values.oncall.slack.existingSecret }} + key: {{ required "oncall.slack.clientSecretKey is required if oncall.slack.existingSecret is not empty" .Values.oncall.slack.clientSecretKey | quote }} +- name: SLACK_SIGNING_SECRET + valueFrom: + secretKeyRef: + name: {{ .Values.oncall.slack.existingSecret }} + key: {{ required "oncall.slack.signingSecretKey is required if oncall.slack.existingSecret is not empty" .Values.oncall.slack.signingSecretKey | quote }} +{{- else }} +- name: SLACK_CLIENT_OAUTH_ID + value: {{ .Values.oncall.slack.clientId | default "" | quote }} +- name: SLACK_CLIENT_OAUTH_SECRET + value: {{ .Values.oncall.slack.clientSecret | default "" | quote }} +- name: SLACK_SIGNING_SECRET + value: {{ .Values.oncall.slack.signingSecret | default "" | quote }} +{{- end }} +- name: SLACK_INSTALL_RETURN_REDIRECT_HOST + value: {{ .Values.oncall.slack.redirectHost | default (printf "https://%s" .Values.base_url) | quote }} +{{- end }} +{{- end }} + +{{- define "snippet.oncall.telegram.env" -}} +{{- if .Values.telegramPolling.enabled -}} +{{- $_ := set .Values.oncall.telegram "enabled" true -}} +{{- end -}} +- name: FEATURE_TELEGRAM_INTEGRATION_ENABLED + value: {{ .Values.oncall.telegram.enabled | toString | title | quote }} +{{- if .Values.oncall.telegram.enabled }} +{{- if .Values.telegramPolling.enabled }} +- name: FEATURE_TELEGRAM_LONG_POLLING_ENABLED + value: {{ .Values.telegramPolling.enabled | toString | title | quote }} +{{- end }} +- name: TELEGRAM_WEBHOOK_HOST + value: {{ .Values.oncall.telegram.webhookUrl | default (printf "https://%s" .Values.base_url) | quote }} +{{- if .Values.oncall.telegram.existingSecret }} +- name: TELEGRAM_TOKEN + valueFrom: + secretKeyRef: + name: {{ .Values.oncall.telegram.existingSecret }} + key: {{ required "oncall.telegram.tokenKey is required if oncall.telegram.existingSecret is not empty" .Values.oncall.telegram.tokenKey | quote }} +{{- else }} +- name: TELEGRAM_TOKEN + value: {{ .Values.oncall.telegram.token | default "" | quote }} +{{- end }} +{{- end }} +{{- end }} + +{{- define "snippet.oncall.twilio.env" }} +{{- with .Values.oncall.twilio }} +{{- if .existingSecret }} +- name: TWILIO_ACCOUNT_SID + valueFrom: + secretKeyRef: + name: {{ .existingSecret }} + key: {{ required "oncall.twilio.accountSid is required if oncall.twilio.existingSecret is not empty" .accountSid | quote }} +{{- if .authTokenKey }} +- name: TWILIO_AUTH_TOKEN + valueFrom: + secretKeyRef: + name: {{ .existingSecret }} + key: {{ required "oncall.twilio.authTokenKey is required if oncall.twilio.existingSecret is not empty" .authTokenKey | quote }} +{{- end }} +- name: TWILIO_NUMBER + valueFrom: + secretKeyRef: + name: {{ .existingSecret }} + key: {{ required "oncall.twilio.phoneNumberKey is required if oncall.twilio.existingSecret is not empty" .phoneNumberKey | quote }} +- name: TWILIO_VERIFY_SERVICE_SID + valueFrom: + secretKeyRef: + name: {{ .existingSecret }} + key: {{ required "oncall.twilio.verifySidKey is required if oncall.twilio.existingSecret is not empty" .verifySidKey | quote }} +{{- if and .apiKeySidKey .apiKeySecretKey }} +- name: TWILIO_API_KEY_SID + valueFrom: + secretKeyRef: + name: {{ .existingSecret }} + key: {{ required "oncall.twilio.apiKeySidKey is required if oncall.twilio.existingSecret is not empty" .apiKeySidKey | quote }} +- name: TWILIO_API_KEY_SECRET + valueFrom: + secretKeyRef: + name: {{ .existingSecret }} + key: {{ required "oncall.twilio.apiKeySecretKey is required if oncall.twilio.existingSecret is not empty" .apiKeySecretKey | quote }} +{{- end }} +{{- else }} +{{- if .accountSid }} +- name: TWILIO_ACCOUNT_SID + value: {{ .accountSid | quote }} +{{- end }} +{{- if .authToken }} +- name: TWILIO_AUTH_TOKEN + value: {{ .authToken | quote }} +{{- end }} +{{- if .phoneNumber }} +- name: TWILIO_NUMBER + value: {{ .phoneNumber | quote }} +{{- end }} +{{- if .verifySid }} +- name: TWILIO_VERIFY_SERVICE_SID + value: {{ .verifySid | quote }} +{{- end }} +{{- if .apiKeySid }} +- name: TWILIO_API_KEY_SID + value: {{ .apiKeySid | quote }} +{{- end }} +{{- if .apiKeySecret }} +- name: TWILIO_API_KEY_SECRET + value: {{ .apiKeySecret | quote }} +{{- end }} +{{- end }} +{{- if .limitPhone }} +- name: PHONE_NOTIFICATIONS_LIMIT + value: {{ .limitPhone | quote }} +{{- end }} +{{- end }} +{{- end }} + +{{- define "snippet.celery.env" }} +{{- if .Values.celery.worker_queue }} +- name: CELERY_WORKER_QUEUE + value: {{ .Values.celery.worker_queue | quote }} +{{- end }} +{{- if .Values.celery.worker_concurrency }} +- name: CELERY_WORKER_CONCURRENCY + value: {{ .Values.celery.worker_concurrency | quote }} +{{- end }} +{{- if .Values.celery.worker_max_tasks_per_child }} +- name: CELERY_WORKER_MAX_TASKS_PER_CHILD + value: {{ .Values.celery.worker_max_tasks_per_child | quote }} +{{- end }} +{{- if .Values.celery.worker_beat_enabled }} +- name: CELERY_WORKER_BEAT_ENABLED + value: {{ .Values.celery.worker_beat_enabled | quote }} +{{- end }} +{{- if .Values.celery.worker_shutdown_interval }} +- name: CELERY_WORKER_SHUTDOWN_INTERVAL + value: {{ .Values.celery.worker_shutdown_interval | quote }} +{{- end }} +{{- end }} + +{{- define "snippet.grafana.url" -}} +{{ if .Values.grafana.enabled -}} + http://{{ include "oncall.grafana.fullname" . }} +{{- else -}} + {{ required "externalGrafana.url is required when not grafana.enabled" .Values.externalGrafana.url }} +{{- end }} +{{- end }} + +{{- define "snippet.mysql.env" -}} +- name: MYSQL_HOST + value: {{ include "snippet.mysql.host" . | quote }} +- name: MYSQL_PORT + value: {{ include "snippet.mysql.port" . | quote }} +- name: MYSQL_DB_NAME + value: {{ include "snippet.mysql.db" . | quote }} +- name: MYSQL_USER +{{- if and (not .Values.mariadb.enabled) .Values.externalMysql.existingSecret .Values.externalMysql.usernameKey (not .Values.externalMysql.user) }} + valueFrom: + secretKeyRef: + name: {{ include "snippet.mysql.password.secret.name" . }} + key: {{ .Values.externalMysql.usernameKey | quote }} +{{- else }} + value: {{ include "snippet.mysql.user" . | quote }} +{{- end }} +- name: MYSQL_PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "snippet.mysql.password.secret.name" . }} + key: {{ include "snippet.mysql.password.secret.key" . | quote }} +{{- if not .Values.mariadb.enabled }} +{{- with .Values.externalMysql.options }} +- name: MYSQL_OPTIONS + value: {{ . | quote }} +{{- end }} +{{- end }} +{{- end }} + +{{- define "snippet.mysql.password.secret.name" -}} +{{ if .Values.mariadb.enabled -}} + {{ if .Values.mariadb.auth.existingSecret -}} + {{ .Values.mariadb.auth.existingSecret }} + {{- else -}} + {{ include "oncall.mariadb.fullname" . }} + {{- end }} +{{- else -}} + {{ if .Values.externalMysql.existingSecret -}} + {{ .Values.externalMysql.existingSecret }} + {{- else -}} + {{ include "oncall.fullname" . }}-mysql-external + {{- end }} +{{- end }} +{{- end }} + +{{- define "snippet.mysql.password.secret.key" -}} +{{ if and (not .Values.mariadb.enabled) .Values.externalMysql.existingSecret .Values.externalMysql.passwordKey -}} + {{ .Values.externalMysql.passwordKey }} +{{- else -}} + mariadb-root-password +{{- end }} +{{- end }} + +{{- define "snippet.mysql.host" -}} +{{ if and (not .Values.mariadb.enabled) .Values.externalMysql.host -}} + {{ .Values.externalMysql.host }} +{{- else -}} + {{ include "oncall.mariadb.fullname" . }} +{{- end }} +{{- end }} + +{{- define "snippet.mysql.port" -}} +{{ if and (not .Values.mariadb.enabled) .Values.externalMysql.port -}} + {{ .Values.externalMysql.port }} +{{- else -}} + 3306 +{{- end }} +{{- end }} + +{{- define "snippet.mysql.db" -}} +{{ if and (not .Values.mariadb.enabled) .Values.externalMysql.db_name -}} + {{ .Values.externalMysql.db_name }} +{{- else -}} + {{ .Values.mariadb.auth.database | default "oncall" }} +{{- end }} +{{- end }} + +{{- define "snippet.mysql.user" -}} +{{ if and (not .Values.mariadb.enabled) .Values.externalMysql.user -}} + {{ .Values.externalMysql.user }} +{{- else -}} + {{ .Values.mariadb.auth.username | default "root" }} +{{- end }} +{{- end }} + +{{- define "snippet.postgresql.env" -}} +- name: DATABASE_TYPE + value: {{ .Values.database.type | quote }} +- name: DATABASE_HOST + value: {{ include "snippet.postgresql.host" . | quote }} +- name: DATABASE_PORT + value: {{ include "snippet.postgresql.port" . | quote }} +- name: DATABASE_NAME + value: {{ include "snippet.postgresql.db" . | quote }} +- name: DATABASE_USER + value: {{ include "snippet.postgresql.user" . | quote }} +- name: DATABASE_PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "snippet.postgresql.password.secret.name" . }} + key: {{ include "snippet.postgresql.password.secret.key" . | quote }} +{{- if not .Values.postgresql.enabled }} +{{- with .Values.externalPostgresql.options }} +- name: DATABASE_OPTIONS + value: {{ . | quote }} +{{- end }} +{{- end }} +{{- end }} + +{{- define "snippet.sqlite.env" -}} +- name: DATABASE_TYPE + value: sqlite3 +- name: DATABASE_NAME + value: /etc/app/oncall.db +{{- end }} + +{{- define "snippet.postgresql.password.secret.name" -}} +{{ if .Values.postgresql.enabled -}} + {{ if .Values.postgresql.auth.existingSecret -}} + {{ .Values.postgresql.auth.existingSecret }} + {{- else -}} + {{ include "oncall.postgresql.fullname" . }} + {{- end }} +{{- else -}} + {{ if .Values.externalPostgresql.existingSecret -}} + {{ .Values.externalPostgresql.existingSecret }} + {{- else -}} + {{ include "oncall.fullname" . }}-postgresql-external + {{- end }} +{{- end }} +{{- end }} + +{{- define "snippet.postgresql.password.secret.key" -}} +{{ if .Values.postgresql.enabled -}} + {{ if .Values.postgresql.auth.existingSecret -}} + {{ required "postgresql.auth.secretKeys.adminPasswordKey is required if database.type=postgres and postgresql.enabled and postgresql.auth.existingSecret" .Values.postgresql.auth.secretKeys.adminPasswordKey }} + {{- else -}} + {{ include "postgresql.userPasswordKey" .Subcharts.postgresql }} + {{- end }} +{{- else -}} + {{ if .Values.externalPostgresql.existingSecret -}} + {{ required "externalPostgresql.passwordKey is required if database.type=postgres and not postgresql.enabled and postgresql.auth.existingSecret" .Values.externalPostgresql.passwordKey }} + {{- else -}} + postgres-password + {{- end }} +{{- end }} +{{- end }} + +{{- define "snippet.postgresql.host" -}} +{{ if not .Values.postgresql.enabled -}} + {{ required "externalPostgresql.host is required if database.type=postgres and not postgresql.enabled" .Values.externalPostgresql.host }} +{{- else -}} + {{ include "oncall.postgresql.fullname" . }} +{{- end }} +{{- end }} + +{{- define "snippet.postgresql.port" -}} +{{ if and (not .Values.postgresql.enabled) .Values.externalPostgresql.port -}} + {{ .Values.externalPostgresql.port }} +{{- else -}} + 5432 +{{- end }} +{{- end }} + +{{- define "snippet.postgresql.db" -}} +{{ if not .Values.postgresql.enabled -}} + {{ .Values.externalPostgresql.db_name | default "oncall" }} +{{- else -}} + {{ .Values.postgresql.auth.database | default "oncall" }} +{{- end }} +{{- end }} + +{{- define "snippet.postgresql.user" -}} +{{ if not .Values.postgresql.enabled -}} + {{ .Values.externalPostgresql.user | default "postgres" }} +{{- else -}} + {{ .Values.postgresql.auth.username | default "postgres" }} +{{- end }} +{{- end }} + +{{- define "snippet.rabbitmq.env" }} +- name: RABBITMQ_USERNAME +{{- if and (not .Values.rabbitmq.enabled) .Values.externalRabbitmq.existingSecret .Values.externalRabbitmq.usernameKey (not .Values.externalRabbitmq.user) }} + valueFrom: + secretKeyRef: + name: {{ include "snippet.rabbitmq.password.secret.name" . }} + key: {{ .Values.externalRabbitmq.usernameKey | quote }} +{{- else }} + value: {{ include "snippet.rabbitmq.user" . | quote }} +{{- end }} +- name: RABBITMQ_PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "snippet.rabbitmq.password.secret.name" . }} + key: {{ include "snippet.rabbitmq.password.secret.key" . | quote }} +- name: RABBITMQ_HOST + value: {{ include "snippet.rabbitmq.host" . | quote }} +- name: RABBITMQ_PORT + value: {{ include "snippet.rabbitmq.port" . | quote }} +- name: RABBITMQ_PROTOCOL + value: {{ include "snippet.rabbitmq.protocol" . | quote }} +- name: RABBITMQ_VHOST + value: {{ include "snippet.rabbitmq.vhost" . | quote }} +{{- end }} + +{{- define "snippet.rabbitmq.user" -}} +{{ if not .Values.rabbitmq.enabled -}} + {{ required "externalRabbitmq.user is required if not rabbitmq.enabled" .Values.externalRabbitmq.user }} +{{- else -}} + user +{{- end }} +{{- end }} + +{{- define "snippet.rabbitmq.host" -}} +{{ if not .Values.rabbitmq.enabled -}} + {{ required "externalRabbitmq.host is required if not rabbitmq.enabled" .Values.externalRabbitmq.host }} +{{- else -}} + {{ include "oncall.rabbitmq.fullname" . }} +{{- end }} +{{- end }} + +{{- define "snippet.rabbitmq.port" -}} +{{ if and (not .Values.rabbitmq.enabled) .Values.externalRabbitmq.port -}} + {{ required "externalRabbitmq.port is required if not rabbitmq.enabled" .Values.externalRabbitmq.port }} +{{- else -}} + 5672 +{{- end }} +{{- end }} + +{{- define "snippet.rabbitmq.protocol" -}} +{{ if and (not .Values.rabbitmq.enabled) .Values.externalRabbitmq.protocol -}} + {{ .Values.externalRabbitmq.protocol }} +{{- else -}} + amqp +{{- end }} +{{- end }} + +{{- define "snippet.rabbitmq.vhost" -}} +{{ if and (not .Values.rabbitmq.enabled) .Values.externalRabbitmq.vhost -}} + {{ .Values.externalRabbitmq.vhost }} +{{- end }} +{{- end }} + +{{- define "snippet.rabbitmq.password.secret.name" -}} +{{ if .Values.rabbitmq.enabled -}} + {{ if .Values.rabbitmq.auth.existingPasswordSecret -}} + {{ .Values.rabbitmq.auth.existingPasswordSecret }} + {{- else -}} + {{ include "oncall.rabbitmq.fullname" . }} + {{- end }} +{{- else -}} + {{ if .Values.externalRabbitmq.existingSecret -}} + {{ .Values.externalRabbitmq.existingSecret }} + {{- else -}} + {{ include "oncall.fullname" . }}-rabbitmq-external + {{- end }} +{{- end }} +{{- end }} + +{{- define "snippet.rabbitmq.password.secret.key" -}} +{{ if and (not .Values.rabbitmq.enabled) .Values.externalRabbitmq.passwordKey -}} + {{ .Values.externalRabbitmq.passwordKey }} +{{- else -}} + rabbitmq-password +{{- end }} +{{- end }} + +{{- define "snippet.redis.protocol" -}} +{{ default "redis" .Values.externalRedis.protocol | quote }} +{{- end }} + +{{- define "snippet.redis.host" -}} +{{ if not .Values.redis.enabled -}} + {{ required "externalRedis.host is required if not redis.enabled" .Values.externalRedis.host | quote }} +{{- else -}} + {{ include "oncall.redis.fullname" . }}-master +{{- end }} +{{- end }} + +{{- define "snippet.redis.port" -}} +{{ default 6379 .Values.externalRedis.port | quote }} +{{- end }} + +{{- define "snippet.redis.database" -}} +{{ default 0 .Values.externalRedis.database | quote }} +{{- end }} + +{{- define "snippet.redis.password.secret.name" -}} +{{ if .Values.redis.enabled -}} + {{ if .Values.redis.auth.existingSecret -}} + {{ .Values.redis.auth.existingSecret }} + {{- else -}} + {{ include "oncall.redis.fullname" . }} + {{- end }} +{{- else -}} + {{ if .Values.externalRedis.existingSecret -}} + {{ .Values.externalRedis.existingSecret }} + {{- else -}} + {{ include "oncall.fullname" . }}-redis-external + {{- end }} +{{- end }} +{{- end }} + +{{- define "snippet.redis.password.secret.key" -}} +{{ if .Values.redis.enabled -}} + {{ if .Values.redis.auth.existingSecret -}} + {{ required "redis.auth.existingSecretPasswordKey is required if redis.auth.existingSecret is non-empty" .Values.redis.auth.existingSecretPasswordKey }} + {{- else -}} + redis-password + {{- end }} +{{- else -}} + {{ if .Values.externalRedis.existingSecret -}} + {{ required "externalRedis.passwordKey is required if externalRedis.existingSecret is non-empty" .Values.externalRedis.passwordKey }} + {{- else -}} + redis-password + {{- end }} +{{- end }} +{{- end }} + +{{- define "snippet.redis.env" -}} +- name: REDIS_PROTOCOL + value: {{ include "snippet.redis.protocol" . }} +- name: REDIS_HOST + value: {{ include "snippet.redis.host" . }} +- name: REDIS_PORT + value: {{ include "snippet.redis.port" . }} +- name: REDIS_DATABASE + value: {{ include "snippet.redis.database" . }} +- name: REDIS_USERNAME + value: {{ default "" .Values.externalRedis.username | quote }} +- name: REDIS_PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "snippet.redis.password.secret.name" . }} + key: {{ include "snippet.redis.password.secret.key" . | quote}} +{{- if and (not .Values.redis.enabled) .Values.externalRedis.ssl_options.enabled }} +- name: REDIS_USE_SSL + value: "true" +{{- with .Values.externalRedis.ssl_options.ca_certs }} +- name: REDIS_SSL_CA_CERTS + value: {{ . | quote }} +{{- end }} +{{- with .Values.externalRedis.ssl_options.certfile }} +- name: REDIS_SSL_CERTFILE + value: {{ . | quote }} +{{- end }} +{{- with .Values.externalRedis.ssl_options.keyfile }} +- name: REDIS_SSL_KEYFILE + value: {{ . | quote }} +{{- end }} +{{- with .Values.externalRedis.ssl_options.cert_reqs }} +- name: REDIS_SSL_CERT_REQS + value: {{ . | quote }} +{{- end }} +{{- end }} +{{- end }} + +{{- /* +when broker.type != rabbitmq, we do not need to include rabbitmq environment variables +*/}} +{{- define "snippet.broker.env" -}} +{{- include "snippet.redis.env" . }} +{{- if eq .Values.broker.type "rabbitmq" -}} +{{- include "snippet.rabbitmq.env" . }} +{{- end }} +{{- end }} + +{{- define "snippet.db.env" -}} +{{- if eq .Values.database.type "mysql" }} +{{- include "snippet.mysql.env" . }} +{{- else if eq .Values.database.type "postgresql" }} +{{- include "snippet.postgresql.env" . }} +{{- else if eq .Values.database.type "sqlite" -}} +{{- include "snippet.sqlite.env" . }} +{{- else -}} +{{- fail "value for .Values.db.type must be either 'mysql', 'postgresql', or 'sqlite'" }} +{{- end }} +{{- end }} + +{{- define "snippet.oncall.smtp.env" -}} + {{- $smtpTLS:=.Values.oncall.smtp.tls | default true | toString | title | quote }} + {{- $smtpSSL:=.Values.oncall.smtp.ssl | default false | toString | title | quote }} + {{- if eq $smtpTLS "\"True\"" }} + {{- if eq $smtpSSL "\"True\"" }} + {{- fail "cannot set Email (SMTP) to use SSL and TLS at the same time" }} + {{- end }} + {{- end }} +- name: FEATURE_EMAIL_INTEGRATION_ENABLED + value: {{ .Values.oncall.smtp.enabled | toString | title | quote }} +{{- if .Values.oncall.smtp.enabled }} +- name: EMAIL_HOST + value: {{ .Values.oncall.smtp.host | quote }} +- name: EMAIL_PORT + value: {{ .Values.oncall.smtp.port | default "587" | quote }} +- name: EMAIL_HOST_USER + value: {{ .Values.oncall.smtp.username | quote }} +- name: EMAIL_HOST_PASSWORD + valueFrom: + secretKeyRef: + name: {{ include "oncall.fullname" . }}-smtp + key: smtp-password + optional: true +- name: EMAIL_USE_TLS + value: {{ $smtpTLS }} +- name: EMAIL_USE_SSL + value: {{ $smtpSSL }} +- name: EMAIL_FROM_ADDRESS + value: {{ .Values.oncall.smtp.fromEmail | quote }} +- name: EMAIL_NOTIFICATIONS_LIMIT + value: {{ .Values.oncall.smtp.limitEmail | default "200" | quote }} +{{- end }} +{{- end }} + +{{- define "snippet.oncall.exporter.env" -}} +{{ if .Values.oncall.exporter.enabled -}} +- name: FEATURE_PROMETHEUS_EXPORTER_ENABLED + value: {{ .Values.oncall.exporter.enabled | toString | title | quote }} +- name: PROMETHEUS_EXPORTER_SECRET + valueFrom: + secretKeyRef: + name: {{ include "oncall.fullname" . }}-exporter + key: exporter-secret + optional: true +{{- else -}} +- name: FEATURE_PROMETHEUS_EXPORTER_ENABLED + value: {{ .Values.oncall.exporter.enabled | toString | title | quote }} +{{- end }} +{{- end }} + +{{- define "snippet.oncall.engine.env" -}} +{{ include "snippet.oncall.env" . }} +{{ include "snippet.oncall.slack.env" . }} +{{ include "snippet.oncall.telegram.env" . }} +{{ include "snippet.oncall.smtp.env" . }} +{{ include "snippet.oncall.twilio.env" . }} +{{ include "snippet.oncall.exporter.env" . }} +{{ include "snippet.db.env" . }} +{{ include "snippet.broker.env" . }} +{{ include "oncall.extraEnvs" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/templates/_helpers.tpl new file mode 100644 index 0000000..6486bfe --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/_helpers.tpl @@ -0,0 +1,121 @@ +{{/* +Expand the name of the chart. +*/}} +{{- define "oncall.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "oncall.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default .Chart.Name .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "oncall.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "oncall.labels" -}} +helm.sh/chart: {{ include "oncall.chart" . }} +{{ include "oncall.selectorLabels" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "oncall.selectorLabels" -}} +app.kubernetes.io/name: {{ include "oncall.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Create the name of the service account to use +*/}} +{{- define "oncall.serviceAccountName" -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "oncall.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} + +{{/* Generate the fullname of mariadb subchart */}} +{{- define "oncall.mariadb.fullname" -}} +{{- printf "%s-%s" .Release.Name "mariadb" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* Generate the fullname of postgresql subchart */}} +{{- define "oncall.postgresql.fullname" -}} +{{- printf "%s-%s" .Release.Name "postgresql" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{- define "oncall.grafana.fullname" -}} +{{- printf "%s-%s" .Release.Name "grafana" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* Generate the fullname of rabbitmq subchart */}} +{{- define "oncall.rabbitmq.fullname" -}} +{{- printf "%s-%s" .Release.Name "rabbitmq" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* Generate the fullname of redis subchart */}} +{{- define "oncall.redis.fullname" -}} +{{- printf "%s-%s" .Release.Name "redis" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* Generate engine image name */}} +{{- define "oncall.engine.image" -}} +{{- printf "%s:%s" .Values.image.repository (.Values.image.tag | default .Chart.AppVersion) }} +{{- end }} + +{{- define "oncall.initContainer" }} +- name: wait-for-db + image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + command: ['sh', '-c', "until (python manage.py migrate --check); do echo Waiting for database migrations; sleep 2; done"] + securityContext: + {{ toYaml .Values.init.securityContext | nindent 4 }} + resources: + {{ toYaml .Values.init.resources | nindent 4 }} + env: + {{- include "snippet.oncall.env" . | nindent 4 }} + {{- include "snippet.db.env" . | nindent 4 }} + {{- include "snippet.broker.env" . | nindent 4 }} + {{- include "oncall.extraEnvs" . | nindent 4 }} +{{- end }} + +{{- define "oncall.extraEnvs" -}} +{{- if .Values.env }} + {{- if (kindIs "map" .Values.env) }} + {{- range $key, $value := .Values.env }} +- name: {{ $key }} + value: {{ $value }} + {{- end -}} + {{/* support previous schema */}} + {{- else }} +{{- toYaml .Values.env }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/celery/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/templates/celery/_helpers.tpl new file mode 100644 index 0000000..8c37e95 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/celery/_helpers.tpl @@ -0,0 +1,26 @@ +{{/* +Maximum of 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "oncall.celery.name" -}} +{{ include "oncall.name" . | trunc 55 }}-celery +{{- end }} + +{{- define "oncall.celery.fullname" -}} +{{ include "oncall.fullname" . | trunc 55 }}-celery +{{- end }} + +{{/* +Engine common labels +*/}} +{{- define "oncall.celery.labels" -}} +{{ include "oncall.labels" . }} +app.kubernetes.io/component: celery +{{- end }} + +{{/* +Engine selector labels +*/}} +{{- define "oncall.celery.selectorLabels" -}} +{{ include "oncall.selectorLabels" . }} +app.kubernetes.io/component: celery +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/celery/deployment.yaml b/observability/lgtm-distributed/charts/oncall/templates/celery/deployment.yaml new file mode 100644 index 0000000..b2498dd --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/celery/deployment.yaml @@ -0,0 +1,89 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "oncall.celery.fullname" . }} + labels: + {{- include "oncall.celery.labels" . | nindent 4 }} +spec: + replicas: {{ .Values.celery.replicaCount }} + selector: + matchLabels: + {{- include "oncall.celery.selectorLabels" . | nindent 6 }} + template: + metadata: + {{- with .Values.podAnnotations }} + annotations: + random-annotation: {{ randAlphaNum 10 | lower }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "oncall.celery.selectorLabels" . | nindent 8 }} + {{- if .Values.celery.podLabels }} + {{- toYaml .Values.celery.podLabels | nindent 8}} + {{- end }} + spec: + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "oncall.serviceAccountName" . }} + securityContext: + {{- toYaml .Values.podSecurityContext | nindent 8 }} + initContainers: + {{- include "oncall.initContainer" . | indent 8 }} + {{- with .Values.celery.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.celery.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.celery.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.celery.topologySpreadConstraints }} + topologySpreadConstraints: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.celery.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + containers: + - name: {{ .Chart.Name }} + securityContext: + {{- toYaml .Values.securityContext | nindent 12 }} + image: {{ include "oncall.engine.image" . }} + {{- if .Values.oncall.devMode }} + command: ["python", "manage.py", "start_celery"] + {{- else }} + command: ["./celery_with_exporter.sh"] + {{- end }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + env: + {{- include "snippet.celery.env" . | nindent 12 }} + {{- include "snippet.oncall.engine.env" . | nindent 12 }} + {{- if .Values.celery.livenessProbe.enabled }} + livenessProbe: + exec: + command: [ + "bash", + "-c", + "celery -A engine inspect ping -d celery@$HOSTNAME" + ] + initialDelaySeconds: {{ .Values.celery.livenessProbe.initialDelaySeconds }} + periodSeconds: {{ .Values.celery.livenessProbe.periodSeconds }} + timeoutSeconds: {{ .Values.celery.livenessProbe.timeoutSeconds }} + {{- end }} + resources: + {{- toYaml .Values.celery.resources | nindent 12 }} + {{- with .Values.celery.extraVolumeMounts }} + volumeMounts: {{- . | toYaml | nindent 12 }} + {{- end }} + {{- with .Values.celery.extraContainers }} + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.celery.extraVolumes }} + volumes: {{- . | toYaml | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/cert-issuer.yaml b/observability/lgtm-distributed/charts/oncall/templates/cert-issuer.yaml new file mode 100644 index 0000000..8b1716f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/cert-issuer.yaml @@ -0,0 +1,22 @@ +{{- if (index .Values "cert-manager").enabled }} +apiVersion: cert-manager.io/v1 +kind: Issuer +metadata: + name: letsencrypt-prod + annotations: + "helm.sh/hook": post-install,post-upgrade +spec: + acme: + # The ACME server URL + server: https://acme-v02.api.letsencrypt.org/directory + # Email address used for ACME registration + email: no-reply@{{ .Values.base_url }} + # Name of a secret used to store the ACME account private key + privateKeySecretRef: + name: letsencrypt-prod + # Enable the HTTP-01 challenge provider + solvers: + - http01: + ingress: + class: nginx +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/engine/_helpers-engine.tpl b/observability/lgtm-distributed/charts/oncall/templates/engine/_helpers-engine.tpl new file mode 100644 index 0000000..6d498e9 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/engine/_helpers-engine.tpl @@ -0,0 +1,26 @@ +{{/* +Maximum of 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "oncall.engine.name" -}} +{{ include "oncall.name" . | trunc 55 }}-engine +{{- end }} + +{{- define "oncall.engine.fullname" -}} +{{ include "oncall.fullname" . | trunc 55 }}-engine +{{- end }} + +{{/* +Engine common labels +*/}} +{{- define "oncall.engine.labels" -}} +{{ include "oncall.labels" . }} +app.kubernetes.io/component: engine +{{- end }} + +{{/* +Engien selector labels +*/}} +{{- define "oncall.engine.selectorLabels" -}} +{{ include "oncall.selectorLabels" . }} +app.kubernetes.io/component: engine +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/engine/deployment.yaml b/observability/lgtm-distributed/charts/oncall/templates/engine/deployment.yaml new file mode 100644 index 0000000..ccb770d --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/engine/deployment.yaml @@ -0,0 +1,98 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "oncall.engine.fullname" . }} + labels: + {{- include "oncall.engine.labels" . | nindent 4 }} +spec: + replicas: {{ .Values.engine.replicaCount }} + selector: + matchLabels: + {{- include "oncall.engine.selectorLabels" . | nindent 6 }} + strategy: + {{- toYaml .Values.engine.updateStrategy | nindent 4 }} + template: + metadata: + {{- with .Values.podAnnotations }} + annotations: + random-annotation: {{ randAlphaNum 10 | lower }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "oncall.engine.selectorLabels" . | nindent 8 }} + {{- if .Values.engine.podLabels }} + {{- toYaml .Values.engine.podLabels | nindent 8}} + {{- end }} + spec: + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "oncall.serviceAccountName" . }} + securityContext: + {{- toYaml .Values.podSecurityContext | nindent 8 }} + initContainers: + {{- include "oncall.initContainer" . | indent 8 }} + containers: + - name: {{ .Chart.Name }} + securityContext: + {{- toYaml .Values.securityContext | nindent 12 }} + image: {{ include "oncall.engine.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + {{- if .Values.oncall.devMode }} + command: ["sh", "-c", "uwsgi --disable-logging --py-autoreload 3 --ini uwsgi.ini"] + {{- end }} + ports: + - name: http + containerPort: 8080 + protocol: TCP + env: + {{- include "snippet.oncall.engine.env" . | nindent 12 }} + livenessProbe: + httpGet: + path: /health/ + port: http + periodSeconds: 60 + timeoutSeconds: 3 + readinessProbe: + httpGet: + path: /ready/ + port: http + periodSeconds: 60 + timeoutSeconds: 3 + startupProbe: + httpGet: + path: /startupprobe/ + port: http + periodSeconds: 10 + timeoutSeconds: 3 + resources: + {{- toYaml .Values.engine.resources | nindent 12 }} + {{- with .Values.engine.extraVolumeMounts }} + volumeMounts: {{- . | toYaml | nindent 12 }} + {{- end }} + {{- with .Values.engine.extraContainers }} + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.engine.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.engine.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.engine.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.engine.topologySpreadConstraints }} + topologySpreadConstraints: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.engine.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.engine.extraVolumes }} + volumes: {{- . | toYaml | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/engine/job-migrate.yaml b/observability/lgtm-distributed/charts/oncall/templates/engine/job-migrate.yaml new file mode 100644 index 0000000..0978295 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/engine/job-migrate.yaml @@ -0,0 +1,102 @@ +{{- if .Values.migrate.enabled -}} +apiVersion: batch/v1 +kind: Job +metadata: + {{- if .Values.migrate.useHook }} + name: {{ printf "%s-migrate" (include "oncall.engine.fullname" .) }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade + "helm.sh/hook-weight": "-1" + {{- with .Values.migrate.annotations }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- else }} + name: {{ printf "%s-migrate-%s" (include "oncall.engine.fullname" .) (now | date "2006-01-02-15-04-05") }} + {{- with .Values.migrate.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- end }} + labels: + {{- include "oncall.engine.labels" . | nindent 4 }} +spec: + backoffLimit: 15 + {{- if .Values.migrate.ttlSecondsAfterFinished }} + ttlSecondsAfterFinished: {{ .Values.migrate.ttlSecondsAfterFinished }} + {{- end }} + template: + metadata: + name: {{ printf "%s-migrate-%s" (include "oncall.engine.fullname" .) (now | date "2006-01-02-15-04-05") }} + {{- with .Values.podAnnotations }} + annotations: + random-annotation: {{ randAlphaNum 10 | lower }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "oncall.engine.selectorLabels" . | nindent 8 }} + spec: + restartPolicy: Never + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "oncall.serviceAccountName" . }} + securityContext: + {{- toYaml .Values.podSecurityContext | nindent 8 }} + {{- with .Values.migrate.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.migrate.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.migrate.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: {{ .Chart.Name }}-migrate + securityContext: + {{- toYaml .Values.securityContext | nindent 12 }} + image: {{ include "oncall.engine.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + command: + - /bin/sh + - -c + {{- if eq .Values.database.type "mysql" }} + - | + until (nc -vz $MYSQL_HOST $MYSQL_PORT); + do + echo "waiting for MySQL"; sleep 1; + done + python manage.py migrate + {{- else if eq .Values.database.type "postgresql" }} + - | + until (nc -vz $DATABASE_HOST $DATABASE_PORT); + do + echo "waiting for PostgreSQL"; sleep 1; + done + python manage.py migrate + {{- else }} + - python manage.py migrate + {{- end }} + env: + {{- include "snippet.oncall.env" . | nindent 12 }} + {{- include "snippet.oncall.smtp.env" . | nindent 12 }} + {{- include "snippet.oncall.exporter.env" . | nindent 12 }} + {{- include "snippet.db.env" . | nindent 12 }} + {{- include "snippet.broker.env" . | nindent 12 }} + {{- include "oncall.extraEnvs" . | nindent 12 }} + resources: + {{- toYaml .Values.migrate.resources | nindent 12 }} + {{- with .Values.migrate.extraVolumeMounts }} + volumeMounts: {{- . | toYaml | nindent 10 }} + {{- end }} + {{- with .Values.migrate.extraContainers }} + {{- tpl . $ | nindent 6 }} + {{- end }} + {{- with .Values.migrate.extraVolumes }} + volumes: {{- . | toYaml | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/engine/service-external.yaml b/observability/lgtm-distributed/charts/oncall/templates/engine/service-external.yaml new file mode 100644 index 0000000..eec1f0b --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/engine/service-external.yaml @@ -0,0 +1,24 @@ +{{- if .Values.service.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "oncall.engine.fullname" . }}-external + labels: + {{- include "oncall.engine.labels" . | nindent 4 }} + {{- with .Values.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.service.type }} + ports: + - port: {{ .Values.service.port }} + targetPort: http + protocol: TCP + name: http + {{- if and (eq .Values.service.type "NodePort") (.Values.service.nodePort) }} + nodePort: {{ .Values.service.nodePort }} + {{- end }} + selector: + {{- include "oncall.engine.selectorLabels" . | nindent 4 }} +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/oncall/templates/engine/service-internal.yaml b/observability/lgtm-distributed/charts/oncall/templates/engine/service-internal.yaml new file mode 100644 index 0000000..0778503 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/engine/service-internal.yaml @@ -0,0 +1,15 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "oncall.engine.fullname" . }} + labels: + {{- include "oncall.engine.labels" . | nindent 4 }} +spec: + type: ClusterIP + ports: + - port: 8080 + targetPort: http + protocol: TCP + name: http + selector: + {{- include "oncall.engine.selectorLabels" . | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/ingress-regular.yaml b/observability/lgtm-distributed/charts/oncall/templates/ingress-regular.yaml new file mode 100644 index 0000000..9a5357f --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/ingress-regular.yaml @@ -0,0 +1,65 @@ +{{- if .Values.ingress.enabled -}} +{{- $fullName := include "oncall.fullname" . -}} +{{- $svcPort := .Values.service.port -}} +{{- if and .Values.ingress.className (not (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion)) }} + {{- if not (hasKey .Values.ingress.annotations "kubernetes.io/ingress.class") }} + {{- $_ := set .Values.ingress.annotations "kubernetes.io/ingress.class" .Values.ingress.className}} + {{- end }} +{{- end }} +{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion -}} +apiVersion: networking.k8s.io/v1 +{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}} +apiVersion: networking.k8s.io/v1beta1 +{{- else -}} +apiVersion: extensions/v1beta1 +{{- end }} +kind: Ingress +metadata: + name: {{ $fullName }} + labels: + {{- include "oncall.labels" . | nindent 4 }} + {{- with .Values.ingress.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if and .Values.ingress.className (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion) }} + ingressClassName: {{ .Values.ingress.className }} + {{- end }} + {{- if .Values.ingress.tls }} + tls: + {{- tpl (toYaml .Values.ingress.tls) . | nindent 4 }} + {{- end }} + rules: + - host: {{ .Values.base_url | quote }} + http: + paths: +{{- if .Values.ingress.extraPaths }} +{{ toYaml .Values.ingress.extraPaths | indent 6}} +{{- end }} + - path: / + pathType: Prefix + backend: + service: + name: {{ include "oncall.engine.fullname" . }} + port: + number: 8080 + {{ if .Values.grafana.enabled }} + - path: /grafana + pathType: Prefix + backend: + service: + name: {{ include "oncall.grafana.fullname" . }} + port: + number: 80 + {{- end }} + {{ if .Values.detached_integrations.enabled }} + - path: /integrations + pathType: Prefix + backend: + service: + name: {{ include "oncall.detached_integrations.fullname" . }} + port: + number: 8080 + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/integrations/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/templates/integrations/_helpers.tpl new file mode 100644 index 0000000..6727ed4 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/integrations/_helpers.tpl @@ -0,0 +1,26 @@ +{{/* +Maximum of 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "oncall.detached_integrations.name" -}} +{{ include "oncall.name" . | trunc 55 }}-integrations +{{- end }} + +{{- define "oncall.detached_integrations.fullname" -}} +{{ include "oncall.fullname" . | trunc 55 }}-integrations +{{- end }} + +{{/* +Integrations common labels +*/}} +{{- define "oncall.detached_integrations.labels" -}} +{{ include "oncall.labels" . }} +app.kubernetes.io/component: integrations +{{- end }} + +{{/* +Integrations selector labels +*/}} +{{- define "oncall.detached_integrations.selectorLabels" -}} +{{ include "oncall.selectorLabels" . }} +app.kubernetes.io/component: integrations +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/integrations/deployment.yaml b/observability/lgtm-distributed/charts/oncall/templates/integrations/deployment.yaml new file mode 100644 index 0000000..5e08eaf --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/integrations/deployment.yaml @@ -0,0 +1,99 @@ +{{- if .Values.detached_integrations.enabled -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "oncall.detached_integrations.fullname" . }} + labels: + {{- include "oncall.detached_integrations.labels" . | nindent 4 }} +spec: + replicas: {{ .Values.detached_integrations.replicaCount }} + selector: + matchLabels: + {{- include "oncall.detached_integrations.selectorLabels" . | nindent 6 }} + strategy: + {{- toYaml .Values.detached_integrations.updateStrategy | nindent 4 }} + template: + metadata: + {{- with .Values.podAnnotations }} + annotations: + random-annotation: {{ randAlphaNum 10 | lower }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "oncall.detached_integrations.selectorLabels" . | nindent 8 }} + spec: + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "oncall.serviceAccountName" . }} + securityContext: + {{- toYaml .Values.podSecurityContext | nindent 8 }} + initContainers: + {{- include "oncall.initContainer" . | indent 8 }} + containers: + - name: {{ .Chart.Name }} + securityContext: + {{- toYaml .Values.securityContext | nindent 12 }} + image: {{ include "oncall.engine.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + {{- if .Values.oncall.devMode }} + command: ["sh", "-c", "uwsgi --disable-logging --py-autoreload 3 --ini uwsgi.ini"] + {{- end }} + ports: + - name: http + containerPort: 8080 + protocol: TCP + env: + {{- include "snippet.oncall.engine.env" . | nindent 12 }} + - name: ROOT_URLCONF + value: "engine.integrations_urls" + livenessProbe: + httpGet: + path: /health/ + port: http + periodSeconds: 60 + timeoutSeconds: 3 + readinessProbe: + httpGet: + path: /ready/ + port: http + periodSeconds: 60 + timeoutSeconds: 3 + startupProbe: + httpGet: + path: /startupprobe/ + port: http + periodSeconds: 10 + timeoutSeconds: 3 + resources: + {{- toYaml .Values.detached_integrations.resources | nindent 12 }} + {{- with .Values.detached_integrations.extraVolumeMounts }} + volumeMounts: {{- . | toYaml | nindent 12 }} + {{- end }} + {{- with .Values.detached_integrations.extraContainers }} + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.detached_integrations.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.detached_integrations.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.detached_integrations.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.detached_integrations.topologySpreadConstraints }} + topologySpreadConstraints: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.detached_integrations.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.detached_integrations.extraVolumes }} + volumes: {{- . | toYaml | nindent 8 }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/templates/integrations/service-external.yaml b/observability/lgtm-distributed/charts/oncall/templates/integrations/service-external.yaml new file mode 100644 index 0000000..455d4aa --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/integrations/service-external.yaml @@ -0,0 +1,24 @@ +{{- if .Values.detached_integrations_service.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "oncall.detached_integrations.fullname" . }}-external + labels: + {{- include "oncall.detached_integrations.labels" . | nindent 4 }} + {{- with .Values.detached_integrations_service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.detached_integrations_service.type }} + ports: + - port: {{ .Values.detached_integrations_service.port }} + targetPort: http + protocol: TCP + name: http + {{- if and (eq .Values.detached_integrations_service.type "NodePort") (.Values.detached_integrations_service.nodePort) }} + nodePort: {{ .Values.detached_integrations_service.nodePort }} + {{- end }} + selector: + {{- include "oncall.detached_integrations.selectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/integrations/service-internal.yaml b/observability/lgtm-distributed/charts/oncall/templates/integrations/service-internal.yaml new file mode 100644 index 0000000..3527b24 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/integrations/service-internal.yaml @@ -0,0 +1,17 @@ +{{- if .Values.detached_integrations.enabled -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "oncall.detached_integrations.fullname" . }} + labels: + {{- include "oncall.detached_integrations.labels" . | nindent 4 }} +spec: + type: ClusterIP + ports: + - port: 8080 + targetPort: http + protocol: TCP + name: http + selector: + {{- include "oncall.detached_integrations.selectorLabels" . | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/templates/secrets.yaml b/observability/lgtm-distributed/charts/oncall/templates/secrets.yaml new file mode 100644 index 0000000..a4c3284 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/secrets.yaml @@ -0,0 +1,98 @@ +{{- if not .Values.oncall.secrets.existingSecret }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "oncall.fullname" . }} + labels: + {{- include "oncall.labels" . | nindent 4 }} + {{- if .Values.migrate.useHook }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade + "helm.sh/hook-weight": "-5" + {{- end }} +type: Opaque +data: + {{ include "snippet.oncall.secret.secretKey" . }}: {{ (.Values.oncall.secrets.secretKey | default (randAlphaNum 40)) | b64enc | quote }} + {{ include "snippet.oncall.secret.mirageSecretKey" . }}: {{ (.Values.oncall.secrets.mirageSecretKey | default (randAlphaNum 40)) | b64enc | quote }} +--- +{{- end }} +{{- if and (eq .Values.database.type "mysql") (not .Values.mariadb.enabled) (not .Values.externalMysql.existingSecret) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "oncall.fullname" . }}-mysql-external + {{- if .Values.migrate.useHook }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade + "helm.sh/hook-weight": "-5" + {{- end }} +type: Opaque +data: + mariadb-root-password: {{ required "externalMysql.password is required if not mariadb.enabled and not externalMysql.existingSecret" .Values.externalMysql.password | b64enc | quote }} +--- +{{- end }} +{{- if and (not .Values.postgresql.enabled) (eq .Values.database.type "postgresql") (not .Values.externalPostgresql.existingSecret) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "oncall.fullname" . }}-postgresql-external + {{- if .Values.migrate.useHook }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade + "helm.sh/hook-weight": "-5" + {{- end }} +type: Opaque +data: + postgres-password: {{ required "externalPostgresql.password is required if not postgresql.enabled and not externalPostgresql.existingSecret" .Values.externalPostgresql.password | b64enc | quote }} +--- +{{- end }} +{{- if and (eq .Values.broker.type "rabbitmq") (.Values.externalRabbitmq.password) (not .Values.rabbitmq.enabled) (not .Values.externalRabbitmq.existingSecret) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "oncall.fullname" . }}-rabbitmq-external + {{- if .Values.migrate.useHook }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade + "helm.sh/hook-weight": "-5" + {{- end }} +type: Opaque +data: + rabbitmq-password: {{ required "externalRabbitmq.password is required if not rabbitmq.enabled and not externalRabbitmq.existingSecret" .Values.externalRabbitmq.password | b64enc | quote }} +--- +{{- end }} +{{- if and (.Values.externalRedis.host) (not .Values.redis.enabled) (not .Values.externalRedis.existingSecret) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "oncall.fullname" . }}-redis-external + {{- if .Values.migrate.useHook }} + annotations: + "helm.sh/hook": pre-install,pre-upgrade + "helm.sh/hook-weight": "-5" + {{- end }} +type: Opaque +data: + redis-password: {{ required "externalRedis.password is required if not redis.enabled and not externalRedis.existingSecret" .Values.externalRedis.password | b64enc | quote }} +--- +{{- end }} +{{- if and .Values.oncall.smtp.enabled .Values.oncall.smtp.password }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "oncall.fullname" . }}-smtp +type: Opaque +data: + smtp-password: {{ .Values.oncall.smtp.password | b64enc | quote }} +--- +{{- end }} +{{- if and .Values.oncall.exporter.enabled .Values.oncall.exporter.authToken }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "oncall.fullname" . }}-exporter +type: Opaque +data: + exporter-secret: {{ .Values.oncall.exporter.authToken | b64enc | quote }} +--- +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/oncall/templates/serviceaccount.yaml new file mode 100644 index 0000000..d0a5a9e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/serviceaccount.yaml @@ -0,0 +1,18 @@ +{{- if .Values.serviceAccount.create -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "oncall.serviceAccountName" . }} + labels: + {{- include "oncall.labels" . | nindent 4 }} + {{- if or (.Values.migrate.useHook) (.Values.serviceAccount.annotations) }} + annotations: + {{- if .Values.migrate.useHook }} + "helm.sh/hook": pre-install,pre-upgrade + "helm.sh/hook-weight": "-5" + {{- end }} + {{- with .Values.serviceAccount.annotations }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/telegram-polling/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/templates/telegram-polling/_helpers.tpl new file mode 100644 index 0000000..d2053dc --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/telegram-polling/_helpers.tpl @@ -0,0 +1,22 @@ +{{/* +Maximum of 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +*/}} +{{- define "oncall.telegramPolling.fullname" -}} +{{ include "oncall.fullname" . | trunc 45 }}-telegram-polling +{{- end }} + +{{/* +Telegram polling common labels +*/}} +{{- define "oncall.telegramPolling.labels" -}} +{{ include "oncall.labels" . }} +app.kubernetes.io/component: telegram-polling +{{- end }} + +{{/* +Telegram polling selector labels +*/}} +{{- define "oncall.telegramPolling.selectorLabels" -}} +{{ include "oncall.selectorLabels" . }} +app.kubernetes.io/component: telegram-polling +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/telegram-polling/deployment.yaml b/observability/lgtm-distributed/charts/oncall/templates/telegram-polling/deployment.yaml new file mode 100644 index 0000000..2e44889 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/telegram-polling/deployment.yaml @@ -0,0 +1,53 @@ +{{- if .Values.telegramPolling.enabled -}} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "oncall.telegramPolling.fullname" . }} + labels: + {{- include "oncall.telegramPolling.labels" . | nindent 4 }} +spec: + replicas: 1 + selector: + matchLabels: + {{- include "oncall.telegramPolling.selectorLabels" . | nindent 6 }} + template: + metadata: + labels: + {{- include "oncall.telegramPolling.selectorLabels" . | nindent 8 }} + {{- if .Values.telegramPolling.podLabels }} + {{- toYaml .Values.telegramPolling.podLabels | nindent 8 }} + {{- end }} + spec: + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "oncall.serviceAccountName" . }} + securityContext: + {{- toYaml .Values.podSecurityContext | nindent 8 }} + initContainers: + {{- include "oncall.initContainer" . | nindent 8 }} + containers: + - name: telegram-polling + securityContext: + {{- toYaml .Values.securityContext | nindent 12 }} + image: {{ include "oncall.engine.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + command: ['sh', '-c', 'python manage.py start_telegram_polling'] + env: + {{- include "snippet.oncall.env" . | nindent 12 }} + {{- include "snippet.oncall.telegram.env" . | nindent 12 }} + {{- include "snippet.db.env" . | nindent 12 }} + {{- include "snippet.broker.env" . | nindent 12 }} + {{- include "oncall.extraEnvs" . | nindent 12 }} + {{- with .Values.telegramPolling.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.telegramPolling.extraVolumeMounts }} + volumeMounts: {{- . | toYaml | nindent 12 }} + {{- end }} + {{- with .Values.telegramPolling.extraVolumes }} + volumes: {{- . | toYaml | nindent 8 }} + {{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/oncall/templates/ui/_helpers.tpl b/observability/lgtm-distributed/charts/oncall/templates/ui/_helpers.tpl new file mode 100644 index 0000000..49dcc2e --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/ui/_helpers.tpl @@ -0,0 +1,8 @@ +{{- define "ui.env" -}} +{{- if .Values.ui.env }} + {{- range $key, $value := .Values.ui.env }} +- name: {{ $key }} + value: "{{ $value }}" + {{- end -}} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/templates/ui/deployment.yaml b/observability/lgtm-distributed/charts/oncall/templates/ui/deployment.yaml new file mode 100644 index 0000000..c094368 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/templates/ui/deployment.yaml @@ -0,0 +1,31 @@ +{{- if .Values.ui.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: oncall-ui + labels: + app.kubernetes.io/component: oncall-ui +spec: + replicas: 1 + selector: + matchLabels: + app.kubernetes.io/component: oncall-ui + template: + metadata: + labels: + app.kubernetes.io/component: oncall-ui + spec: + containers: + - name: oncall-ui + image: "{{ .Values.ui.image.repository }}:{{ .Values.ui.image.tag | default .Chart.AppVersion }}" + imagePullPolicy: IfNotPresent + env: + {{- include "ui.env" . | nindent 12 }} + volumeMounts: + - mountPath: /etc/app + name: hot-reloaded-plugin + volumes: + - name: hot-reloaded-plugin + hostPath: + path: /oncall-plugin +{{- end }} diff --git a/observability/lgtm-distributed/charts/oncall/values.yaml b/observability/lgtm-distributed/charts/oncall/values.yaml new file mode 100644 index 0000000..f7d4c30 --- /dev/null +++ b/observability/lgtm-distributed/charts/oncall/values.yaml @@ -0,0 +1,718 @@ +# Values for configuring the deployment of Grafana OnCall + +# Set the domain name Grafana OnCall will be installed on. +# If you want to install grafana as a part of this release make sure to configure grafana.grafana.ini.server.domain too +base_url: example.com +base_url_protocol: https + +## Optionally specify an array of imagePullSecrets. +## Secrets must be manually created in the namespace. +## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/ +## e.g: +## imagePullSecrets: +## - name: myRegistryKeySecretName +imagePullSecrets: [] + +image: + # Grafana OnCall docker image repository + repository: grafana/oncall + tag: + pullPolicy: Always + +# Whether to create additional service for external connections +# ClusterIP service is always created +service: + enabled: false + type: LoadBalancer + port: 8080 + annotations: {} + +# Engine pods configuration +engine: + replicaCount: 1 + resources: + {} + # limits: + # cpu: 100m + # memory: 128Mi + # requests: + # cpu: 100m + # memory: 128Mi + + # Labels for engine pods + podLabels: {} + + ## Deployment update strategy + ## ref: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy + updateStrategy: + rollingUpdate: + maxSurge: 25% + maxUnavailable: 0 + type: RollingUpdate + + ## Affinity for pod assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + affinity: {} + + ## Node labels for pod assignment + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + nodeSelector: {} + + ## Tolerations for pod assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + tolerations: [] + + ## Topology spread constraints for pod assignment + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/topology-spread-constraints/ + topologySpreadConstraints: [] + + ## Priority class for the pods + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/pod-priority-preemption/ + priorityClassName: "" + + # Extra containers which runs as sidecar + extraContainers: "" + # extraContainers: | + # - name: cloud-sql-proxy + # image: gcr.io/cloud-sql-connectors/cloud-sql-proxy:2.1.2 + # args: + # - --private-ip + # - --port=5432 + # - example:europe-west3:grafana-oncall-db + + # Extra volume mounts for the main app container + extraVolumeMounts: [] + # - mountPath: /mnt/postgres-tls + # name: postgres-tls + # - mountPath: /mnt/redis-tls + # name: redis-tls + + # Extra volumes for the pod + extraVolumes: [] + # - name: postgres-tls + # configMap: + # name: my-postgres-tls + # defaultMode: 0640 + # - name: redis-tls + # configMap: + # name: my-redis-tls + # defaultMode: 0640 + +detached_integrations_service: + enabled: false + type: LoadBalancer + port: 8080 + annotations: {} + +# Integrations pods configuration +detached_integrations: + enabled: false + replicaCount: 1 + resources: + {} + # limits: + # cpu: 100m + # memory: 128Mi + # requests: + # cpu: 100m + # memory: 128Mi + + ## Deployment update strategy + ## ref: https://kubernetes.io/docs/concepts/workloads/controllers/deployment/#strategy + updateStrategy: + rollingUpdate: + maxSurge: 25% + maxUnavailable: 0 + type: RollingUpdate + + ## Affinity for pod assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + affinity: {} + + ## Node labels for pod assignment + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + nodeSelector: {} + + ## Tolerations for pod assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + tolerations: [] + + ## Topology spread constraints for pod assignment + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/topology-spread-constraints/ + topologySpreadConstraints: [] + + ## Priority class for the pods + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/pod-priority-preemption/ + priorityClassName: "" + + # Extra containers which runs as sidecar + extraContainers: "" + # extraContainers: | + # - name: cloud-sql-proxy + # image: gcr.io/cloud-sql-connectors/cloud-sql-proxy:2.1.2 + # args: + # - --private-ip + # - --port=5432 + # - example:europe-west3:grafana-oncall-db + + # Extra volume mounts for the container + extraVolumeMounts: [] + # - mountPath: /mnt/postgres-tls + # name: postgres-tls + # - mountPath: /mnt/redis-tls + # name: redis-tls + + # Extra volumes for the pod + extraVolumes: [] + # - name: postgres-tls + # configMap: + # name: my-postgres-tls + # defaultMode: 0640 + # - name: redis-tls + # configMap: + # name: my-redis-tls + # defaultMode: 0640 + +# Celery workers pods configuration +celery: + replicaCount: 1 + worker_queue: "default,critical,long,slack,telegram,webhook,celery,grafana,retry" + worker_concurrency: "1" + worker_max_tasks_per_child: "100" + worker_beat_enabled: "True" + ## Restart of the celery workers once in a given interval as an additional precaution to the probes + ## If this setting is enabled TERM signal will be sent to celery workers + ## It will lead to warm shutdown (waiting for the tasks to complete) and restart the container + ## If this setting is set numbers of pod restarts will increase + ## Comment this line out if you want to remove restarts + worker_shutdown_interval: "65m" + livenessProbe: + enabled: true + initialDelaySeconds: 30 + periodSeconds: 300 + timeoutSeconds: 10 + resources: + {} + # limits: + # cpu: 100m + # memory: 128Mi + # requests: + # cpu: 100m + # memory: 128Mi + + # Labels for celery pods + podLabels: {} + + ## Affinity for pod assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + affinity: {} + + ## Node labels for pod assignment + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + nodeSelector: {} + + ## Tolerations for pod assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + tolerations: [] + + ## Topology spread constraints for pod assignment + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/topology-spread-constraints/ + topologySpreadConstraints: [] + + ## Priority class for the pods + ## ref: https://kubernetes.io/docs/concepts/scheduling-eviction/pod-priority-preemption/ + priorityClassName: "" + + # Extra containers which runs as sidecar + extraContainers: "" + # extraContainers: | + # - name: cloud-sql-proxy + # image: gcr.io/cloud-sql-connectors/cloud-sql-proxy:2.1.2 + # args: + # - --private-ip + # - --port=5432 + # - example:europe-west3:grafana-oncall-db + + # Extra volume mounts for the main container + extraVolumeMounts: [] + # - mountPath: /mnt/postgres-tls + # name: postgres-tls + # - mountPath: /mnt/redis-tls + # name: redis-tls + + # Extra volumes for the pod + extraVolumes: [] + # - name: postgres-tls + # configMap: + # name: my-postgres-tls + # defaultMode: 0640 + # - name: redis-tls + # configMap: + # name: my-redis-tls + # defaultMode: 0640 + +# Telegram polling pod configuration +telegramPolling: + enabled: false + resources: + {} + # limits: + # cpu: 100m + # memory: 128Mi + # requests: + # cpu: 100m + # memory: 128Mi + + # Labels for telegram-polling pods + podLabels: {} + + # Extra volume mounts for the main container + extraVolumeMounts: [] + # - mountPath: /mnt/postgres-tls + # name: postgres-tls + # - mountPath: /mnt/redis-tls + # name: redis-tls + + # Extra volumes for the pod + extraVolumes: [] + # - name: postgres-tls + # configMap: + # name: my-postgres-tls + # defaultMode: 0640 + # - name: redis-tls + # configMap: + # name: my-redis-tls + # defaultMode: 0640 + +oncall: + # this is intended to be used for local development. In short, it will mount the ./engine dir into + # any backend related containers, to allow hot-reloading + also run the containers with slightly modified + # startup commands (which configures the hot-reloading) + devMode: false + + # Override default MIRAGE_CIPHER_IV (must be 16 bytes long) + # For existing installation, this should not be changed. + # mirageCipherIV: 1234567890abcdef + # oncall secrets + secrets: + # Use existing secret. (secretKey and mirageSecretKey is required) + existingSecret: "" + # The key in the secret containing secret key + secretKey: "" + # The key in the secret containing mirage secret key + mirageSecretKey: "" + # Slack configures the Grafana Oncall Slack ChatOps integration. + slack: + # Enable the Slack ChatOps integration for the Oncall Engine. + enabled: false + # clientId configures the Slack app OAuth2 client ID. + # api.slack.com/apps/ -> Basic Information -> App Credentials -> Client ID + clientId: ~ + # clientSecret configures the Slack app OAuth2 client secret. + # api.slack.com/apps/ -> Basic Information -> App Credentials -> Client Secret + clientSecret: ~ + # signingSecret - configures the Slack app signature secret used to sign + # requests comming from Slack. + # api.slack.com/apps/ -> Basic Information -> App Credentials -> Signing Secret + signingSecret: ~ + # Use existing secret for clientId, clientSecret and signingSecret. + # clientIdKey, clientSecretKey and signingSecretKey are required + existingSecret: "" + # The key in the secret containing OAuth2 client ID + clientIdKey: "" + # The key in the secret containing OAuth2 client secret + clientSecretKey: "" + # The key in the secret containing the Slack app signature secret + signingSecretKey: "" + # OnCall external URL + redirectHost: ~ + telegram: + enabled: false + token: ~ + webhookUrl: ~ + # Use existing secret. (tokenKey is required) + existingSecret: "" + # The key in the secret containing Telegram token + tokenKey: "" + smtp: + enabled: true + host: ~ + port: ~ + username: ~ + password: ~ + tls: ~ + ssl: ~ + fromEmail: ~ + exporter: + enabled: false + authToken: ~ + twilio: + # Twilio account SID/username to allow OnCall to send SMSes and make phone calls + accountSid: "" + # Twilio password to allow OnCall to send SMSes and make calls + authToken: "" + # Number from which you will receive calls and SMS + # (NOTE: must be quoted, otherwise would be rendered as float value) + phoneNumber: "" + # SID of Twilio service for number verification. You can create a service in Twilio web interface. + # twilio.com -> verify -> create new service + verifySid: "" + # Twilio API key SID/username to allow OnCall to send SMSes and make phone calls + apiKeySid: "" + # Twilio API key secret/password to allow OnCall to send SMSes and make phone calls + apiKeySecret: "" + # Use existing secret for authToken, phoneNumber, verifySid, apiKeySid and apiKeySecret. + existingSecret: "" + # Twilio password to allow OnCall to send SMSes and make calls + # The key in the secret containing the auth token + authTokenKey: "" + # The key in the secret containing the phone number + phoneNumberKey: "" + # The key in the secret containing verify service sid + verifySidKey: "" + # The key in the secret containing api key sid + apiKeySidKey: "" + # The key in the secret containing the api key secret + apiKeySecretKey: "" + # Phone notifications limit (the only non-secret value). + # TODO: rename to phoneNotificationLimit + limitPhone: + +# Whether to run django database migrations automatically +migrate: + enabled: true + # TTL can be unset by setting ttlSecondsAfterFinished: "" + ttlSecondsAfterFinished: 20 + # use a helm hook to manage the migration job + useHook: false + annotations: {} + + ## Affinity for pod assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/#affinity-and-anti-affinity + affinity: {} + + ## Node labels for pod assignment + ## ref: https://kubernetes.io/docs/user-guide/node-selection/ + nodeSelector: {} + + ## Tolerations for pod assignment + ## ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/ + tolerations: [] + + # Extra containers which runs as sidecar + extraContainers: "" + # extraContainers: | + # - name: cloud-sql-proxy + # image: gcr.io/cloud-sql-connectors/cloud-sql-proxy:2.1.2 + # args: + # - --private-ip + # - --port=5432 + # - example:europe-west3:grafana-oncall-db + resources: + {} + # limits: + # cpu: 100m + # memory: 128Mi + # requests: + # cpu: 100m + # memory: 128Mi + + # Extra volume mounts for the main container + extraVolumeMounts: [] + # - mountPath: /mnt/postgres-tls + # name: postgres-tls + # - mountPath: /mnt/redis-tls + # name: redis-tls + + # Extra volumes for the pod + extraVolumes: [] + # - name: postgres-tls + # configMap: + # name: my-postgres-tls + # defaultMode: 0640 + # - name: redis-tls + # configMap: + # name: my-redis-tls + # defaultMode: 0640 + +# Sets environment variables with name capitalized and prefixed with UWSGI_, +# and dashes are substituted with underscores. +# see more: https://uwsgi-docs.readthedocs.io/en/latest/Configuration.html#environment-variables +# Set null to disable all UWSGI environment variables +uwsgi: + listen: 1024 + +# Additional env variables to add to deployments +env: {} + +# Enable ingress object for external access to the resources +ingress: + enabled: true + # className: "" + annotations: + kubernetes.io/ingress.class: "nginx" + cert-manager.io/issuer: "letsencrypt-prod" + tls: + - hosts: + - "{{ .Values.base_url }}" + secretName: certificate-tls + # Extra paths to prepend to the host configuration. If using something + # like an ALB ingress controller, you may want to configure SSL redirects + extraPaths: [] + # - path: /* + # backend: + # serviceName: ssl-redirect + # servicePort: use-annotation + ## Or for k8s > 1.19 + # - path: /* + # pathType: Prefix + # backend: + # service: + # name: ssl-redirect + # port: + # name: use-annotation + +# Whether to install ingress controller +ingress-nginx: + enabled: true + +# Install cert-manager as a part of the release +cert-manager: + enabled: true + # Instal CRD resources + installCRDs: true + webhook: + timeoutSeconds: 30 + # cert-manager tries to use the already used port, changing to another one + # https://github.com/cert-manager/cert-manager/issues/3237 + # https://cert-manager.io/docs/installation/compatibility/ + securePort: 10260 + # Fix self-checks https://github.com/jetstack/cert-manager/issues/4286 + podDnsPolicy: None + podDnsConfig: + nameservers: + - 8.8.8.8 + - 1.1.1.1 + +database: + # can be either mysql or postgresql + type: mysql + +# MySQL is included into this release for the convenience. +# It is recommended to host it separately from this release +# Set mariadb.enabled = false and configure externalMysql +mariadb: + enabled: true + auth: + database: oncall + existingSecret: + primary: + extraEnvVars: + - name: MARIADB_COLLATE + value: utf8mb4_unicode_ci + - name: MARIADB_CHARACTER_SET + value: utf8mb4 + secondary: + extraEnvVars: + - name: MARIADB_COLLATE + value: utf8mb4_unicode_ci + - name: MARIADB_CHARACTER_SET + value: utf8mb4 + +# Make sure to create the database with the following parameters: +# CREATE DATABASE oncall CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci; +externalMysql: + host: + port: + db_name: + user: + password: + # Use an existing secret for the mysql password. + existingSecret: + # The key in the secret containing the mysql username + usernameKey: + # The key in the secret containing the mysql password + passwordKey: + # Extra options (see example below) + # Reference: https://pymysql.readthedocs.io/en/latest/modules/connections.html + options: + # options: >- + # ssl_verify_cert=true + # ssl_verify_identity=true + # ssl_ca=/mnt/mysql-tls/ca.crt + # ssl_cert=/mnt/mysql-tls/client.crt + # ssl_key=/mnt/mysql-tls/client.key + +# PostgreSQL is included into this release for the convenience. +# It is recommended to host it separately from this release +# Set postgresql.enabled = false and configure externalPostgresql +postgresql: + enabled: false + auth: + database: oncall + existingSecret: + +# Make sure to create the database with the following parameters: +# CREATE DATABASE oncall WITH ENCODING UTF8; +externalPostgresql: + host: + port: + db_name: + user: + password: + # Use an existing secret for the database password + existingSecret: + # The key in the secret containing the database password + passwordKey: + # Extra options (see example below) + # Reference: https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-PARAMKEYWORDS + options: + # options: >- + # sslmode=verify-full + # sslrootcert=/mnt/postgres-tls/ca.crt + # sslcert=/mnt/postgres-tls/client.crt + # sslkey=/mnt/postgres-tls/client.key + +# RabbitMQ is included into this release for the convenience. +# It is recommended to host it separately from this release +# Set rabbitmq.enabled = false and configure externalRabbitmq +rabbitmq: + enabled: true + auth: + existingPasswordSecret: + +broker: + type: rabbitmq + +externalRabbitmq: + host: + port: + user: + password: + protocol: + vhost: + # Use an existing secret for the rabbitmq password + existingSecret: + # The key in the secret containing the rabbitmq password + passwordKey: "" + # The key in the secret containing the rabbitmq username + usernameKey: username + +# Redis is included into this release for the convenience. +# It is recommended to host it separately from this release +redis: + enabled: true + auth: + existingSecret: + +externalRedis: + protocol: + host: + port: + database: + username: + password: + # Use an existing secret for the redis password + existingSecret: + # The key in the secret containing the redis password + passwordKey: + + # SSL options + ssl_options: + enabled: false + # CA certificate + ca_certs: + # Client SSL certs + certfile: + keyfile: + # SSL verification mode: "cert_none" | "cert_optional" | "cert_required" + cert_reqs: + +# Grafana is included into this release for the convenience. +# It is recommended to host it separately from this release +grafana: + enabled: true + grafana.ini: + server: + domain: example.com + root_url: "%(protocol)s://%(domain)s/grafana" + serve_from_sub_path: true + persistence: + enabled: true + # Disable psp as PodSecurityPolicy is deprecated in v1.21+, unavailable in v1.25+ + rbac: + pspEnabled: false + plugins: + - grafana-oncall-app + +externalGrafana: + # Example: https://grafana.mydomain.com + url: + +nameOverride: "" +fullnameOverride: "" + +serviceAccount: + # Specifies whether a service account should be created + create: true + # Annotations to add to the service account + annotations: {} + # The name of the service account to use. + # If not set and create is true, a name is generated using the fullname template + name: "" + +podAnnotations: {} + +podSecurityContext: + {} + # fsGroup: 2000 + +securityContext: + {} + # capabilities: + # drop: + # - ALL + # readOnlyRootFilesystem: true + # runAsNonRoot: true + # runAsGroup: 2000 + # runAsUser: 1000 + +init: + securityContext: + {} + # allowPrivilegeEscalation: false + # capabilities: + # drop: + # - ALL + # privileged: false + # readOnlyRootFilesystem: true + # runAsGroup: 2000 + # runAsNonRoot: true + # runAsUser: 1000 + resources: + {} + # limits: + # cpu: 100m + # memory: 128Mi + # requests: + # cpu: 100m + # memory: 128Mi + +ui: + # this is intended to be used for local development. In short, it will spin up an additional container + # running the plugin frontend, such that hot reloading can be enabled + enabled: false + image: + repository: oncall/ui + tag: dev + # Additional env vars for the ui container + env: {} + +prometheus: + enabled: false + # extraScrapeConfigs: | + # - job_name: 'oncall-exporter' + # metrics_path: /metrics/ + # static_configs: + # - targets: + # - oncall-dev-engine.default.svc.cluster.local:8080 diff --git a/observability/lgtm-distributed/charts/tempo-distributed/.helmignore b/observability/lgtm-distributed/charts/tempo-distributed/.helmignore new file mode 100644 index 0000000..371a431 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/.helmignore @@ -0,0 +1,25 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*.orig +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ +doc.yaml +README.tpl diff --git a/observability/lgtm-distributed/charts/tempo-distributed/Chart.lock b/observability/lgtm-distributed/charts/tempo-distributed/Chart.lock new file mode 100644 index 0000000..4c3ac25 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/Chart.lock @@ -0,0 +1,12 @@ +dependencies: +- name: minio + repository: https://charts.min.io/ + version: 4.0.12 +- name: grafana-agent-operator + repository: https://grafana.github.io/helm-charts + version: 0.2.2 +- name: rollout-operator + repository: https://grafana.github.io/helm-charts + version: 0.15.0 +digest: sha256:7be5c7a4c0d1a71dc6de69b8e99ac5a61c1771d6241e7f9105393cc7117d4f0a +generated: "2024-05-27T19:15:20.601670632+03:00" diff --git a/observability/lgtm-distributed/charts/tempo-distributed/Chart.yaml b/observability/lgtm-distributed/charts/tempo-distributed/Chart.yaml new file mode 100644 index 0000000..f26ff81 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/Chart.yaml @@ -0,0 +1,39 @@ +apiVersion: v2 +appVersion: 2.5.0 +dependencies: +- alias: minio + condition: minio.enabled + name: minio + repository: https://charts.min.io/ + version: 4.0.12 +- alias: grafana-agent-operator + condition: metaMonitoring.grafanaAgent.installOperator + name: grafana-agent-operator + repository: https://grafana.github.io/helm-charts + version: 0.2.2 +- alias: rollout_operator + condition: rollout_operator.enabled + name: rollout-operator + repository: https://grafana.github.io/helm-charts + version: 0.15.0 +description: Grafana Tempo in MicroService mode +home: https://grafana.com/docs/tempo/latest/ +icon: https://raw.githubusercontent.com/grafana/tempo/master/docs/tempo/website/logo_and_name.png +maintainers: +- email: number101010@gmail.com + name: joe-elliott +- email: 9215868@gmail.com + name: swartz-k +- name: annanay25 +- name: mdisibio +- name: mapno +- name: BitProcessor +- name: faustodavid +- name: zalegrala +- email: sheikhabubaker761@gmail.com + name: Sheikh-Abubaker +name: tempo-distributed +sources: +- https://github.com/grafana/tempo +type: application +version: 1.13.2 diff --git a/observability/lgtm-distributed/charts/tempo-distributed/README.md b/observability/lgtm-distributed/charts/tempo-distributed/README.md new file mode 100644 index 0000000..90fedec --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/README.md @@ -0,0 +1,971 @@ +# tempo-distributed + +![Version: 1.13.2](https://img.shields.io/badge/Version-1.13.2-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 2.5.0](https://img.shields.io/badge/AppVersion-2.5.0-informational?style=flat-square) + +Grafana Tempo in MicroService mode + +## Source Code + +* + +## Requirements + +| Repository | Name | Version | +|------------|------|---------| +| https://charts.min.io/ | minio(minio) | 4.0.12 | +| https://grafana.github.io/helm-charts | grafana-agent-operator(grafana-agent-operator) | 0.2.2 | +| https://grafana.github.io/helm-charts | rollout_operator(rollout-operator) | 0.15.0 | + +## Chart Repo + +Add the following repo to use the chart: + +```console +helm repo add grafana https://grafana.github.io/helm-charts +``` + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```console +helm install my-release grafana/tempo-distributed +``` + +## Uninstalling the Chart + +To uninstall/delete the my-release deployment: + +```console +helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + +## Upgrading + +A major chart version change indicates that there is an incompatible breaking change needing manual actions. + +### from Chart versions < 1.13.0 + +EXPERIMENTAL: Zone Aware Replication has been added to the ingester statefulset. +Attention, the calculation of the pods per AZ is as follows ```(.values.ingester.replicas + numberOfZones -1)/numberOfZones``` + +### From Chart versions < 1.8.0 + +Switch to new overrides format, see https://grafana.com/docs/tempo/latest/configuration/#overrides. + +### From Chart versions < 1.6.0 + +The metrics generator component in the chart has been disabled by default, but the configuration for the processors was not empty, resulting error sin the distributor log. Here we align the default metrics generator config settings to both disable the generator and remove processors. Users who wish to keep the their processors enabled, will need to update their values. + +### From Chart versions < 1.5.0 + +Please be aware that we've updated the minor version to Tempo 2.2, which includes breaking changes. +We recommend reviewing the [release notes](https://github.com/grafana/tempo/releases/tag/v2.2.0) before upgrading. + +### From Chart versions < 1.3.0 + +Please be aware that we've updated the minor version to Tempo 2.1, which includes breaking changes. +We recommend reviewing the [release notes](https://github.com/grafana/tempo/releases/tag/v2.1.0/) before upgrading. + +### From Chart versions < 1.0.0 + +Please note that we've incremented the major version when upgrading to Tempo 2.0. There were a large number of +changes in this release (breaking and otherwise). It is encouraged to review the [release notes](https://grafana.com/docs/tempo/latest/release-notes/v2-0/) +and [1.5 -> 2.0 upgrade guide](https://grafana.com/docs/tempo/latest/setup/upgrade/) before upgrading. + +### From chart version < 0.27.0 + +Version 0.27.0: + +Many changes have been introduced, including some breaking changes. + +The [PR](https://github.com/grafana/helm-charts/pull/1759) includes additional details. + +* **BREAKING CHANGE** centralize selector label handling -- users who wish to keep old values should still be able to use the `nameOverride` and `fullNameOverride` top level keys in their values. + +* **BREAKING CHANGE** serviceMonitor has been nested under metaMonitoring -- metamonitoring can be used scrape services as well as install the operator with the following values. Note also that the port names have changed from `http` to `http-metrics`. +```yaml +metaMonitoring: + serviceMonitor: + enabled: true + grafanaAgent: + enabled: true + installOperator: true +``` +* minio can now be enabled as part of this chart using the following values +```yaml +minio: + enabled: true +``` +* allow configuration to be stored in a secret. See the documentation for `useExternalConfig` and `configStorageType` in the values file for more details. + +### From chart version < 0.26.0 + +Version 0.26.0 + +* Moves metricsGenerator.config.storage_remote_write to metricsGenerator.config.storage.remote_write +* Moves metricsGenerator.config.service_graphs_max_items to metricsGenerator.config.processor.service_graphs.max_items + +### From chart version < 0.23.0 + +Version 0.23.0: + +* Adds /var/tempo emptyDir mount for querier, queryfrontend, distributor and compactor. Previously, /var/tempo was directory inside container. + +* Sets queryFrontend.query.enabled to false. tempo-query is only required for grafana version <7.5 for compatibility with jaeger-ui. Please also note that tempo-query is incompatible with securityContext readOnlyRootFilesystem set to true. + +* Sets stricter default securityContext: +```yaml +tempo: + securityContext: + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + runAsNonRoot: true + runAsUser: 1000 + runAsGroup: 1000 + allowPrivilegeEscalation: false + podSecurityContext: + fsGroup: 1000 +``` +If you had ingester persistence enabled, you might need to manually change ownership of files in your PV if your CSI doesn't support fsGroup + +### From Chart version >= 0.22.0 +Align Istio GRPC named port syntax. For example, + +- otlp-grpc -> grpc-otlp +- distributor-otlp-grpc -> grpc-distributor-otlp +- jaeger-grpc -> grpc-jaeger +- distributor-jaeger-grpc -> grpc-distributor-jaeger + +In case you need to rollback, please search the right hand side pattern and replace with left hand side pattern. + +### From Chart version < 0.20.0 +The image's attributes must be set under the `image` key for the Memcached service. +```yaml +memcached: + image: + registry: docker.io + repository: memcached + tag: "1.5.17-alpine" + pullPolicy: "IfNotPresent" +``` + +### From Chart version < 0.18.0 +Trace ingestion must now be enabled with the `enabled` key: +```yaml +traces: + otlp: + grpc: + enabled: true + http: + enabled: true + zipkin: + enabled: true + jaeger: + thriftHttp: + enabled: true + opencensus: + enabled: true +``` + +### From Chart versions < 0.9.0 + +This release the component label was shortened to be more aligned with the Loki-distributed chart and the [mixin](https://github.com/grafana/tempo/tree/master/operations/tempo-mixin) dashboards. + +Due to the label changes, an existing installation cannot be upgraded without manual interaction. There are basically two options: + +Option 1 +Uninstall the old release and re-install the new one. There will be no data loss, as the collectors/agents can cache for a short period. + +Option 2 +Add new selector labels to the existing pods. This option will make your pods also temporarely unavailable, option 1 is faster: + +``` +kubectl label pod -n -l app.kubernetes.io/component=-tempo-distributed-,app.kubernetes.io/instance= app.kubernetes.io/component= --overwrite +``` + +Perform a non-cascading deletion of the Deployments and Statefulsets which will keep the pods running: + +``` +kubectl delete -n -l app.kubernetes.io/component=-tempo-distributed-,app.kubernetes.io/instance= --cascade=false +``` + +Perform a regular Helm upgrade on the existing release. The new Deployment/Statefulset will pick up the existing pods and perform a rolling upgrade. + +### From Chart versions < 0.8.0 + +By default all tracing protocols are disabled and you need to specify which protocols to enable for ingestion. + +For example to enable Jaeger grpc thrift http and zipkin protocols: +```yaml +traces: + jaeger: + grpc: true + thriftHttp: true + zipkin: true +``` + +The distributor service is now called {{tempo.fullname}}-distributor. That could impact your ingestion towards this service. + +### From Chart Versions < 0.7.0 + +The memcached default args are removed and should be provided manually. The settings for the `memcached.exporter` moved to `memcachedExporter` + +## Values + +| Key | Type | Default | Description | +|-----|------|---------|-------------| +| adminApi.affinity | string | Soft node and soft zone anti-affinity | Affinity for admin-api pods. Passed through `tpl` and, thus, to be configured as string | +| adminApi.annotations | object | `{}` | | +| adminApi.containerSecurityContext | object | `{"readOnlyRootFilesystem":true}` | The SecurityContext for admin_api containers | +| adminApi.env | list | `[]` | | +| adminApi.extraArgs | object | `{}` | | +| adminApi.extraContainers | list | `[]` | | +| adminApi.extraEnvFrom | list | `[]` | | +| adminApi.extraVolumeMounts | list | `[]` | | +| adminApi.extraVolumes | list | `[]` | | +| adminApi.hostAliases | list | `[]` | hostAliases to add | +| adminApi.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` | +| adminApi.image.registry | string | `nil` | The Docker registry for the adminApi image. Overrides `tempo.image.registry` | +| adminApi.image.repository | string | `nil` | Docker image repository for the adminApi image. Overrides `tempo.image.repository` | +| adminApi.image.tag | string | `nil` | Docker image tag for the adminApi image. Overrides `tempo.image.tag` | +| adminApi.initContainers | list | `[]` | | +| adminApi.nodeSelector | object | `{}` | | +| adminApi.persistence.subPath | string | `nil` | | +| adminApi.podAnnotations | object | `{}` | | +| adminApi.podDisruptionBudget | object | `{}` | | +| adminApi.podLabels | object | `{}` | | +| adminApi.readinessProbe.httpGet.path | string | `"/ready"` | | +| adminApi.readinessProbe.httpGet.port | string | `"http-metrics"` | | +| adminApi.readinessProbe.initialDelaySeconds | int | `45` | | +| adminApi.replicas | int | `1` | | +| adminApi.resources.requests.cpu | string | `"10m"` | | +| adminApi.resources.requests.memory | string | `"32Mi"` | | +| adminApi.securityContext | object | `{}` | | +| adminApi.service.annotations | object | `{}` | | +| adminApi.service.labels | object | `{}` | | +| adminApi.strategy.rollingUpdate.maxSurge | int | `0` | | +| adminApi.strategy.rollingUpdate.maxUnavailable | int | `1` | | +| adminApi.strategy.type | string | `"RollingUpdate"` | | +| adminApi.terminationGracePeriodSeconds | int | `60` | | +| adminApi.tolerations | list | `[]` | | +| adminApi.topologySpreadConstraints | string | Defaults to allow skew no more then 1 node per AZ | topologySpread for admin-api pods. Passed through `tpl` and, thus, to be configured as string | +| cache.caches[0].memcached.consistent_hash | bool | `true` | | +| cache.caches[0].memcached.host | string | `"{{ include \"tempo.fullname\" . }}-memcached"` | | +| cache.caches[0].memcached.service | string | `"memcached-client"` | | +| cache.caches[0].memcached.timeout | string | `"500ms"` | | +| cache.caches[0].roles[0] | string | `"parquet-footer"` | | +| cache.caches[0].roles[1] | string | `"bloom"` | | +| cache.caches[0].roles[2] | string | `"frontend-search"` | | +| compactor.config.compaction.block_retention | string | `"48h"` | Duration to keep blocks | +| compactor.config.compaction.compacted_block_retention | string | `"1h"` | | +| compactor.config.compaction.compaction_cycle | string | `"30s"` | The time between compaction cycles | +| compactor.config.compaction.compaction_window | string | `"1h"` | Blocks in this time window will be compacted together | +| compactor.config.compaction.max_block_bytes | int | `107374182400` | Maximum size of a compacted block in bytes | +| compactor.config.compaction.max_compaction_objects | int | `6000000` | Maximum number of traces in a compacted block. WARNING: Deprecated. Use max_block_bytes instead. | +| compactor.config.compaction.max_time_per_tenant | string | `"5m"` | The maximum amount of time to spend compacting a single tenant before moving to the next | +| compactor.config.compaction.retention_concurrency | int | `10` | Number of tenants to process in parallel during retention | +| compactor.config.compaction.v2_in_buffer_bytes | int | `5242880` | Amount of data to buffer from input blocks | +| compactor.config.compaction.v2_out_buffer_bytes | int | `20971520` | Flush data to backend when buffer is this large | +| compactor.config.compaction.v2_prefetch_traces_count | int | `1000` | Number of traces to buffer in memory during compaction | +| compactor.dnsConfigOverides.dnsConfig.options[0].name | string | `"ndots"` | | +| compactor.dnsConfigOverides.dnsConfig.options[0].value | string | `"3"` | | +| compactor.dnsConfigOverides.enabled | bool | `false` | | +| compactor.extraArgs | list | `[]` | Additional CLI args for the compactor | +| compactor.extraEnv | list | `[]` | Environment variables to add to the compactor pods | +| compactor.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the compactor pods | +| compactor.extraVolumeMounts | list | `[]` | Extra volumes for compactor pods | +| compactor.extraVolumes | list | `[]` | Extra volumes for compactor deployment | +| compactor.hostAliases | list | `[]` | hostAliases to add | +| compactor.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` | +| compactor.image.registry | string | `nil` | The Docker registry for the compactor image. Overrides `tempo.image.registry` | +| compactor.image.repository | string | `nil` | Docker image repository for the compactor image. Overrides `tempo.image.repository` | +| compactor.image.tag | string | `nil` | Docker image tag for the compactor image. Overrides `tempo.image.tag` | +| compactor.nodeSelector | object | `{}` | Node selector for compactor pods | +| compactor.podAnnotations | object | `{}` | Annotations for compactor pods | +| compactor.podLabels | object | `{}` | Labels for compactor pods | +| compactor.priorityClassName | string | `nil` | The name of the PriorityClass for compactor pods | +| compactor.replicas | int | `1` | Number of replicas for the compactor | +| compactor.resources | object | `{}` | Resource requests and limits for the compactor | +| compactor.service.annotations | object | `{}` | Annotations for compactor service | +| compactor.terminationGracePeriodSeconds | int | `30` | Grace period to allow the compactor to shutdown before it is killed | +| compactor.tolerations | list | `[]` | Tolerations for compactor pods | +| config | string | See values.yaml | Config file contents for Tempo distributed. Passed through the `tpl` function to allow templating | +| configStorageType | string | `"ConfigMap"` | Defines what kind of object stores the configuration, a ConfigMap or a Secret. In order to move sensitive information (such as credentials) from the ConfigMap/Secret to a more secure location (e.g. vault), it is possible to use [environment variables in the configuration](https://grafana.com/docs/mimir/latest/operators-guide/configuring/reference-configuration-parameters/#use-environment-variables-in-the-configuration). Such environment variables can be then stored in a separate Secret and injected via the global.extraEnvFrom value. For details about environment injection from a Secret please see [Secrets](https://kubernetes.io/docs/concepts/configuration/secret/#use-case-as-container-environment-variables). | +| distributor.affinity | string | Hard node and soft zone anti-affinity | Affinity for distributor pods. Passed through `tpl` and, thus, to be configured as string | +| distributor.appProtocol | object | `{"grpc":null}` | Adds the appProtocol field to the distributor service. This allows distributor to work with istio protocol selection. | +| distributor.appProtocol.grpc | string | `nil` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| distributor.autoscaling.behavior | object | `{}` | Autoscaling behavior configuration for the distributor | +| distributor.autoscaling.enabled | bool | `false` | Enable autoscaling for the distributor | +| distributor.autoscaling.maxReplicas | int | `3` | Maximum autoscaling replicas for the distributor | +| distributor.autoscaling.minReplicas | int | `1` | Minimum autoscaling replicas for the distributor | +| distributor.autoscaling.targetCPUUtilizationPercentage | int | `60` | Target CPU utilisation percentage for the distributor | +| distributor.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | Target memory utilisation percentage for the distributor | +| distributor.config.extend_writes | string | `nil` | Disables write extension with inactive ingesters | +| distributor.config.log_received_spans | object | `{"enabled":false,"filter_by_status_error":false,"include_all_attributes":false}` | Enable to log every received span to help debug ingestion or calculate span error distributions using the logs | +| distributor.config.log_received_traces | string | `nil` | WARNING: Deprecated. Use log_received_spans instead. | +| distributor.extraArgs | list | `[]` | Additional CLI args for the distributor | +| distributor.extraEnv | list | `[]` | Environment variables to add to the distributor pods | +| distributor.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the distributor pods | +| distributor.extraVolumeMounts | list | `[]` | Extra volumes for distributor pods | +| distributor.extraVolumes | list | `[]` | Extra volumes for distributor deployment | +| distributor.hostAliases | list | `[]` | hostAliases to add | +| distributor.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` | +| distributor.image.registry | string | `nil` | The Docker registry for the ingester image. Overrides `tempo.image.registry` | +| distributor.image.repository | string | `nil` | Docker image repository for the ingester image. Overrides `tempo.image.repository` | +| distributor.image.tag | string | `nil` | Docker image tag for the ingester image. Overrides `tempo.image.tag` | +| distributor.nodeSelector | object | `{}` | Node selector for distributor pods | +| distributor.podAnnotations | object | `{}` | Annotations for distributor pods | +| distributor.podLabels | object | `{}` | Labels for distributor pods | +| distributor.priorityClassName | string | `nil` | The name of the PriorityClass for distributor pods | +| distributor.replicas | int | `1` | Number of replicas for the distributor | +| distributor.resources | object | `{}` | Resource requests and limits for the distributor | +| distributor.service.annotations | object | `{}` | Annotations for distributor service | +| distributor.service.labels | object | `{}` | Labels for distributor service | +| distributor.service.loadBalancerIP | string | `""` | If type is LoadBalancer you can assign the IP to the LoadBalancer | +| distributor.service.loadBalancerSourceRanges | list | `[]` | If type is LoadBalancer limit incoming traffic from IPs. | +| distributor.service.type | string | `"ClusterIP"` | Type of service for the distributor | +| distributor.serviceDiscovery.annotations | object | `{}` | Annotations for distributorDiscovery service | +| distributor.serviceDiscovery.labels | object | `{}` | Labels for distributorDiscovery service | +| distributor.terminationGracePeriodSeconds | int | `30` | Grace period to allow the distributor to shutdown before it is killed | +| distributor.tolerations | list | `[]` | Tolerations for distributor pods | +| distributor.topologySpreadConstraints | string | Defaults to allow skew no more then 1 node per AZ | topologySpread for distributor pods. Passed through `tpl` and, thus, to be configured as string | +| enterprise.enabled | bool | `false` | | +| enterprise.image.repository | string | `"grafana/enterprise-traces"` | Grafana Enterprise Metrics container image repository. Note: for Grafana Tempo use the value 'image.repository' | +| enterprise.image.tag | string | `"v2.4.0"` | Grafana Enterprise Metrics container image tag. Note: for Grafana Tempo use the value 'image.tag' | +| enterpriseFederationFrontend.affinity | string | Hard node and soft zone anti-affinity | Affinity for federation-frontend pods. Passed through `tpl` and, thus, to be configured as string | +| enterpriseFederationFrontend.autoscaling.enabled | bool | `false` | Enable autoscaling for the federation-frontend | +| enterpriseFederationFrontend.autoscaling.maxReplicas | int | `3` | Maximum autoscaling replicas for the federation-frontend | +| enterpriseFederationFrontend.autoscaling.minReplicas | int | `1` | Minimum autoscaling replicas for the federation-frontend | +| enterpriseFederationFrontend.autoscaling.targetCPUUtilizationPercentage | int | `60` | Target CPU utilisation percentage for the federation-frontend | +| enterpriseFederationFrontend.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | Target memory utilisation percentage for the federation-frontend | +| enterpriseFederationFrontend.enabled | bool | `false` | Specifies whether a federation-frontend should be deployed | +| enterpriseFederationFrontend.extraArgs | list | `[]` | Additional CLI args for the federation-frontend | +| enterpriseFederationFrontend.extraEnv | list | `[]` | Environment variables to add to the federation-frontend pods | +| enterpriseFederationFrontend.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the federation-frontend pods | +| enterpriseFederationFrontend.extraVolumeMounts | list | `[]` | Extra volumes for federation-frontend pods | +| enterpriseFederationFrontend.extraVolumes | list | `[]` | Extra volumes for federation-frontend deployment | +| enterpriseFederationFrontend.hostAliases | list | `[]` | hostAliases to add | +| enterpriseFederationFrontend.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` | +| enterpriseFederationFrontend.image.registry | string | `nil` | The Docker registry for the federation-frontend image. Overrides `tempo.image.registry` | +| enterpriseFederationFrontend.image.repository | string | `nil` | Docker image repository for the federation-frontend image. Overrides `tempo.image.repository` | +| enterpriseFederationFrontend.image.tag | string | `nil` | Docker image tag for the federation-frontend image. Overrides `tempo.image.tag` | +| enterpriseFederationFrontend.nodeSelector | object | `{}` | Node selector for federation-frontend pods | +| enterpriseFederationFrontend.podAnnotations | object | `{}` | Annotations for federation-frontend pods | +| enterpriseFederationFrontend.podLabels | object | `{}` | Labels for enterpriseFederationFrontend pods | +| enterpriseFederationFrontend.priorityClassName | string | `nil` | The name of the PriorityClass for federation-frontend pods | +| enterpriseFederationFrontend.proxy_targets | list | `[]` | | +| enterpriseFederationFrontend.replicas | int | `1` | Number of replicas for the federation-frontend | +| enterpriseFederationFrontend.resources | object | `{}` | Resource requests and limits for the federation-frontend | +| enterpriseFederationFrontend.service.annotations | object | `{}` | Annotations for enterpriseFederationFrontend service | +| enterpriseFederationFrontend.service.loadBalancerIP | string | `""` | If type is LoadBalancer you can assign the IP to the LoadBalancer | +| enterpriseFederationFrontend.service.loadBalancerSourceRanges | list | `[]` | If type is LoadBalancer limit incoming traffic from IPs. | +| enterpriseFederationFrontend.service.port | int | `3100` | Port of the federation-frontend service | +| enterpriseFederationFrontend.service.type | string | `"ClusterIP"` | Type of service for the enterpriseFederationFrontend | +| enterpriseFederationFrontend.terminationGracePeriodSeconds | int | `30` | Grace period to allow the federation-frontend to shutdown before it is killed | +| enterpriseFederationFrontend.tolerations | list | `[]` | Tolerations for federation-frontend pods | +| enterpriseFederationFrontend.topologySpreadConstraints | string | Defaults to allow skew no more then 1 node per AZ | topologySpread for federation-frontend pods. Passed through `tpl` and, thus, to be configured as string | +| enterpriseGateway.affinity | string | Soft node and soft zone anti-affinity | Affinity for enterprise-gateway pods. Passed through `tpl` and, thus, to be configured as string | +| enterpriseGateway.annotations | object | `{}` | | +| enterpriseGateway.containerSecurityContext | object | `{"readOnlyRootFilesystem":true}` | The SecurityContext for gateway containers | +| enterpriseGateway.env | list | `[]` | | +| enterpriseGateway.extraArgs | object | `{}` | | +| enterpriseGateway.extraContainers | list | `[]` | | +| enterpriseGateway.extraEnvFrom | list | `[]` | | +| enterpriseGateway.extraVolumeMounts | list | `[]` | | +| enterpriseGateway.extraVolumes | list | `[]` | | +| enterpriseGateway.hostAliases | list | `[]` | hostAliases to add | +| enterpriseGateway.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` | +| enterpriseGateway.image.registry | string | `nil` | The Docker registry for the enterpriseGateway image. Overrides `tempo.image.registry` | +| enterpriseGateway.image.repository | string | `nil` | Docker image repository for the enterpriseGateway image. Overrides `tempo.image.repository` | +| enterpriseGateway.image.tag | string | `nil` | Docker image tag for the enterpriseGateway image. Overrides `tempo.image.tag` | +| enterpriseGateway.ingress.annotations | object | `{}` | Annotations for the gateway ingress | +| enterpriseGateway.ingress.enabled | bool | `false` | Specifies whether an ingress for the gateway should be created | +| enterpriseGateway.ingress.hosts | list | `[{"host":"gateway.gem.example.com","paths":[{"path":"/"}]}]` | Hosts configuration for the gateway ingress | +| enterpriseGateway.ingress.tls | list | `[{"hosts":["gateway.gem.example.com"],"secretName":"gem-gateway-tls"}]` | TLS configuration for the gateway ingress | +| enterpriseGateway.initContainers | list | `[]` | | +| enterpriseGateway.nodeSelector | object | `{}` | | +| enterpriseGateway.persistence.subPath | string | `nil` | | +| enterpriseGateway.podAnnotations | object | `{}` | | +| enterpriseGateway.podDisruptionBudget | object | `{}` | | +| enterpriseGateway.podLabels | object | `{}` | | +| enterpriseGateway.proxy | object | `{}` | Proxy URLs defined in this object will be used if useDefaultProxyURLs is set to false. | +| enterpriseGateway.readinessProbe.httpGet.path | string | `"/ready"` | | +| enterpriseGateway.readinessProbe.httpGet.port | string | `"http-metrics"` | | +| enterpriseGateway.readinessProbe.initialDelaySeconds | int | `45` | | +| enterpriseGateway.replicas | int | `1` | | +| enterpriseGateway.resources.requests.cpu | string | `"10m"` | | +| enterpriseGateway.resources.requests.memory | string | `"32Mi"` | | +| enterpriseGateway.securityContext | object | `{}` | | +| enterpriseGateway.service.annotations | object | `{}` | Annotations for the enterprise gateway service | +| enterpriseGateway.service.clusterIP | string | `nil` | ClusterIP of the enterprise gateway service | +| enterpriseGateway.service.labels | object | `{}` | Labels for enterprise gateway service | +| enterpriseGateway.service.loadBalancerIP | string | `nil` | Load balancer IPO address if service type is LoadBalancer for enterprise gateway service | +| enterpriseGateway.service.port | string | `nil` | Port of the enterprise gateway service; if left undefined, the service will listen on the same port as the pod | +| enterpriseGateway.service.type | string | `"ClusterIP"` | Type of the enterprise gateway service | +| enterpriseGateway.strategy.rollingUpdate.maxSurge | int | `0` | | +| enterpriseGateway.strategy.rollingUpdate.maxUnavailable | int | `1` | | +| enterpriseGateway.strategy.type | string | `"RollingUpdate"` | | +| enterpriseGateway.terminationGracePeriodSeconds | int | `60` | | +| enterpriseGateway.tolerations | list | `[]` | | +| enterpriseGateway.topologySpreadConstraints | string | Defaults to allow skew no more then 1 node per AZ | topologySpread for enterprise-gateway pods. Passed through `tpl` and, thus, to be configured as string | +| enterpriseGateway.useDefaultProxyURLs | bool | `true` | If you want to use your own proxy URLs, set this to false. | +| externalConfigSecretName | string | `"{{ include \"tempo.resourceName\" (dict \"ctx\" . \"component\" \"config\") }}"` | Name of the Secret or ConfigMap that contains the configuration (used for naming even if config is internal). | +| externalConfigVersion | string | `"0"` | When 'useExternalConfig' is true, then changing 'externalConfigVersion' triggers restart of services - otherwise changes to the configuration cause a restart. | +| externalRuntimeConfigName | string | `"{{ include \"tempo.resourceName\" (dict \"ctx\" . \"component\" \"runtime\") }}"` | Name of the Secret or ConfigMap that contains the runtime configuration (used for naming even if config is internal). | +| extraObjects | list | `[]` | Create extra manifests via values. | +| fullnameOverride | string | `""` | | +| gateway.affinity | string | Hard node and soft zone anti-affinity | Affinity for gateway pods. Passed through `tpl` and, thus, to be configured as string | +| gateway.autoscaling.behavior | object | `{}` | Autoscaling behavior configuration for the gateway | +| gateway.autoscaling.enabled | bool | `false` | Enable autoscaling for the gateway | +| gateway.autoscaling.maxReplicas | int | `3` | Maximum autoscaling replicas for the gateway | +| gateway.autoscaling.minReplicas | int | `1` | Minimum autoscaling replicas for the gateway | +| gateway.autoscaling.targetCPUUtilizationPercentage | int | `60` | Target CPU utilisation percentage for the gateway | +| gateway.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | Target memory utilisation percentage for the gateway | +| gateway.basicAuth.enabled | bool | `false` | Enables basic authentication for the gateway | +| gateway.basicAuth.existingSecret | string | `nil` | Existing basic auth secret to use. Must contain '.htpasswd' | +| gateway.basicAuth.htpasswd | string | `"{{ htpasswd (required \"'gateway.basicAuth.username' is required\" .Values.gateway.basicAuth.username) (required \"'gateway.basicAuth.password' is required\" .Values.gateway.basicAuth.password) }}"` | Uses the specified username and password to compute a htpasswd using Sprig's `htpasswd` function. The value is templated using `tpl`. Override this to use a custom htpasswd, e.g. in case the default causes high CPU load. | +| gateway.basicAuth.password | string | `nil` | The basic auth password for the gateway | +| gateway.basicAuth.username | string | `nil` | The basic auth username for the gateway | +| gateway.enabled | bool | `false` | Specifies whether the gateway should be enabled | +| gateway.extraArgs | list | `[]` | Additional CLI args for the gateway | +| gateway.extraEnv | list | `[]` | Environment variables to add to the gateway pods | +| gateway.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the gateway pods | +| gateway.extraVolumeMounts | list | `[]` | Volume mounts to add to the gateway pods | +| gateway.extraVolumes | list | `[]` | Volumes to add to the gateway pods | +| gateway.hostAliases | list | `[]` | hostAliases to add | +| gateway.image.pullPolicy | string | `"IfNotPresent"` | The gateway image pull policy | +| gateway.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `global.image.pullSecrets` | +| gateway.image.registry | string | `nil` | The Docker registry for the gateway image. Overrides `global.image.registry` | +| gateway.image.repository | string | `"nginxinc/nginx-unprivileged"` | The gateway image repository | +| gateway.image.tag | string | `"1.19-alpine"` | The gateway image tag | +| gateway.ingress.annotations | object | `{}` | Annotations for the gateway ingress | +| gateway.ingress.enabled | bool | `false` | Specifies whether an ingress for the gateway should be created | +| gateway.ingress.hosts | list | `[{"host":"gateway.tempo.example.com","paths":[{"path":"/"}]}]` | Hosts configuration for the gateway ingress | +| gateway.ingress.labels | object | `{}` | Labels for the gateway ingress | +| gateway.ingress.tls | list | `[{"hosts":["gateway.tempo.example.com"],"secretName":"tempo-gateway-tls"}]` | TLS configuration for the gateway ingress | +| gateway.nginxConfig.file | string | See values.yaml | Config file contents for Nginx. Passed through the `tpl` function to allow templating | +| gateway.nginxConfig.httpSnippet | string | `""` | Allows appending custom configuration to the http block | +| gateway.nginxConfig.logFormat | string | `"main '$remote_addr - $remote_user [$time_local] $status '\n '\"$request\" $body_bytes_sent \"$http_referer\" '\n '\"$http_user_agent\" \"$http_x_forwarded_for\"';"` | NGINX log format | +| gateway.nginxConfig.resolver | string | `""` | Allows overriding the DNS resolver address nginx will use | +| gateway.nginxConfig.serverSnippet | string | `""` | Allows appending custom configuration to the server block | +| gateway.nodeSelector | object | `{}` | Node selector for gateway pods | +| gateway.podAnnotations | object | `{}` | Annotations for gateway pods | +| gateway.podLabels | object | `{}` | Labels for gateway pods | +| gateway.priorityClassName | string | `nil` | The name of the PriorityClass for gateway pods | +| gateway.readinessProbe.httpGet.path | string | `"/"` | | +| gateway.readinessProbe.httpGet.port | string | `"http-metrics"` | | +| gateway.readinessProbe.initialDelaySeconds | int | `15` | | +| gateway.readinessProbe.timeoutSeconds | int | `1` | | +| gateway.replicas | int | `1` | Number of replicas for the gateway | +| gateway.resources | object | `{}` | Resource requests and limits for the gateway | +| gateway.service.additionalPorts | list | `[]` | Additional ports to be opneed on gateway service (e.g. for RPC connections) | +| gateway.service.annotations | object | `{}` | Annotations for the gateway service | +| gateway.service.clusterIP | string | `nil` | ClusterIP of the gateway service | +| gateway.service.labels | object | `{}` | Labels for gateway service | +| gateway.service.loadBalancerIP | string | `nil` | Load balancer IPO address if service type is LoadBalancer | +| gateway.service.nodePort | string | `nil` | Node port if service type is NodePort | +| gateway.service.port | int | `80` | Port of the gateway service | +| gateway.service.type | string | `"ClusterIP"` | Type of the gateway service | +| gateway.terminationGracePeriodSeconds | int | `30` | Grace period to allow the gateway to shutdown before it is killed | +| gateway.tolerations | list | `[]` | Tolerations for gateway pods | +| gateway.topologySpreadConstraints | string | Defaults to allow skew no more then 1 node per AZ | topologySpread for gateway pods. Passed through `tpl` and, thus, to be configured as string | +| gateway.verboseLogging | bool | `true` | Enable logging of 2xx and 3xx HTTP requests | +| global.clusterDomain | string | `"cluster.local"` | configures cluster domain ("cluster.local" by default) | +| global.dnsNamespace | string | `"kube-system"` | configures DNS service namespace | +| global.dnsService | string | `"kube-dns"` | configures DNS service name | +| global.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets for all images, excluding enterprise. Names of existing secrets with private container registry credentials. Ref: https://kubernetes.io/docs/concepts/containers/images/#specifying-imagepullsecrets-on-a-pod Example: pullSecrets: [ my-dockerconfigjson-secret ] | +| global.image.registry | string | `"docker.io"` | Overrides the Docker registry globally for all images, excluding enterprise. | +| global.priorityClassName | string | `nil` | Overrides the priorityClassName for all pods | +| global_overrides.per_tenant_override_config | string | `"/runtime-config/overrides.yaml"` | | +| ingester.affinity | string | Soft node and soft zone anti-affinity | Affinity for ingester pods. Passed through `tpl` and, thus, to be configured as string | +| ingester.annotations | object | `{}` | Annotations for the ingester StatefulSet | +| ingester.appProtocol | object | `{"grpc":null}` | Adds the appProtocol field to the ingester service. This allows ingester to work with istio protocol selection. | +| ingester.appProtocol.grpc | string | `nil` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| ingester.autoscaling.behavior | object | `{}` | Autoscaling behavior configuration for the ingester | +| ingester.autoscaling.enabled | bool | `false` | Enable autoscaling for the ingester. WARNING: Autoscaling ingesters can result in lost data. Only do this if you know what you're doing. | +| ingester.autoscaling.maxReplicas | int | `3` | Maximum autoscaling replicas for the ingester | +| ingester.autoscaling.minReplicas | int | `2` | Minimum autoscaling replicas for the ingester | +| ingester.autoscaling.targetCPUUtilizationPercentage | int | `60` | Target CPU utilisation percentage for the ingester | +| ingester.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | Target memory utilisation percentage for the ingester | +| ingester.config.complete_block_timeout | string | `nil` | Duration to keep blocks in the ingester after they have been flushed | +| ingester.config.flush_all_on_shutdown | bool | `false` | Flush all traces to backend when ingester is stopped | +| ingester.config.flush_check_period | string | `nil` | How often to sweep all tenants and move traces from live -> wal -> completed blocks. | +| ingester.config.max_block_bytes | string | `nil` | Maximum size of a block before cutting it | +| ingester.config.max_block_duration | string | `nil` | Maximum length of time before cutting a block | +| ingester.config.replication_factor | int | `3` | Number of copies of spans to store in the ingester ring | +| ingester.config.trace_idle_period | string | `nil` | Amount of time a trace must be idle before flushing it to the wal. | +| ingester.extraArgs | list | `[]` | Additional CLI args for the ingester | +| ingester.extraEnv | list | `[]` | Environment variables to add to the ingester pods | +| ingester.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the ingester pods | +| ingester.extraVolumeMounts | list | `[]` | Extra volumes for ingester pods | +| ingester.extraVolumes | list | `[]` | Extra volumes for ingester deployment | +| ingester.hostAliases | list | `[]` | hostAliases to add | +| ingester.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` | +| ingester.image.registry | string | `nil` | The Docker registry for the ingester image. Overrides `tempo.image.registry` | +| ingester.image.repository | string | `nil` | Docker image repository for the ingester image. Overrides `tempo.image.repository` | +| ingester.image.tag | string | `nil` | Docker image tag for the ingester image. Overrides `tempo.image.tag` | +| ingester.initContainers | list | `[]` | | +| ingester.nodeSelector | object | `{}` | Node selector for ingester pods | +| ingester.persistence.annotations | object | `{}` | Annotations for ingester's persist volume claim | +| ingester.persistence.enabled | bool | `false` | Enable creating PVCs which is required when using boltdb-shipper | +| ingester.persistence.inMemory | bool | `false` | use emptyDir with ramdisk instead of PVC. **Please note that all data in ingester will be lost on pod restart** | +| ingester.persistence.size | string | `"10Gi"` | Size of persistent or memory disk | +| ingester.persistence.storageClass | string | `nil` | Storage class to be used. If defined, storageClassName: . If set to "-", storageClassName: "", which disables dynamic provisioning. If empty or set to null, no storageClassName spec is set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). | +| ingester.podAnnotations | object | `{}` | Annotations for ingester pods | +| ingester.podLabels | object | `{}` | Labels for ingester pods | +| ingester.priorityClassName | string | `nil` | The name of the PriorityClass for ingester pods | +| ingester.replicas | int | `3` | Number of replicas for the ingester | +| ingester.resources | object | `{}` | Resource requests and limits for the ingester | +| ingester.service.annotations | object | `{}` | Annotations for ingester service | +| ingester.terminationGracePeriodSeconds | int | `300` | Grace period to allow the ingester to shutdown before it is killed. Especially for the ingestor, this must be increased. It must be long enough so ingesters can be gracefully shutdown flushing/transferring all data and to successfully leave the member ring on shutdown. | +| ingester.tolerations | list | `[]` | Tolerations for ingester pods | +| ingester.topologySpreadConstraints | string | Defaults to allow skew no more then 1 node per AZ | topologySpread for ingester pods. Passed through `tpl` and, thus, to be configured as string | +| ingester.zoneAwareReplication | object | `{"enabled":false,"maxUnavailable":50,"topologyKey":null,"zones":[{"extraAffinity":{},"name":"zone-a","nodeSelector":null,"storageClass":null},{"extraAffinity":{},"name":"zone-b","nodeSelector":null,"storageClass":null},{"extraAffinity":{},"name":"zone-c","nodeSelector":null,"storageClass":null}]}` | EXPERIMENTAL Feature, disabled by default | +| ingester.zoneAwareReplication.enabled | bool | `false` | Enable zone-aware replication for ingester | +| ingester.zoneAwareReplication.maxUnavailable | int | `50` | Maximum number of ingesters that can be unavailable per zone during rollout | +| ingester.zoneAwareReplication.topologyKey | string | `nil` | topologyKey to use in pod anti-affinity. If unset, no anti-affinity rules are generated. If set, the generated anti-affinity rule makes sure that pods from different zones do not mix. E.g.: topologyKey: 'kubernetes.io/hostname' | +| ingester.zoneAwareReplication.zones | list | `[{"extraAffinity":{},"name":"zone-a","nodeSelector":null,"storageClass":null},{"extraAffinity":{},"name":"zone-b","nodeSelector":null,"storageClass":null},{"extraAffinity":{},"name":"zone-c","nodeSelector":null,"storageClass":null}]` | Zone definitions for ingester zones. Note: you have to redefine the whole list to change parts as YAML does not allow to modify parts of a list. | +| ingester.zoneAwareReplication.zones[0] | object | `{"extraAffinity":{},"name":"zone-a","nodeSelector":null,"storageClass":null}` | Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ | +| ingester.zoneAwareReplication.zones[0].extraAffinity | object | `{}` | extraAffinity adds user defined custom affinity rules (merged with generated rules) | +| ingester.zoneAwareReplication.zones[0].nodeSelector | string | `nil` | nodeselector to restrict where pods of this zone can be placed. E.g.: nodeSelector: topology.kubernetes.io/zone: zone-a | +| ingester.zoneAwareReplication.zones[0].storageClass | string | `nil` | Ingester data Persistent Volume Storage Class If defined, storageClassName: If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning If undefined or set to null (the default), then fall back to the value of `ingester.persistentVolume.storageClass`. | +| ingester.zoneAwareReplication.zones[1] | object | `{"extraAffinity":{},"name":"zone-b","nodeSelector":null,"storageClass":null}` | Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ | +| ingester.zoneAwareReplication.zones[1].extraAffinity | object | `{}` | extraAffinity adds user defined custom affinity rules (merged with generated rules) | +| ingester.zoneAwareReplication.zones[1].nodeSelector | string | `nil` | nodeselector to restrict where pods of this zone can be placed. E.g.: nodeSelector: topology.kubernetes.io/zone: zone-b | +| ingester.zoneAwareReplication.zones[1].storageClass | string | `nil` | Ingester data Persistent Volume Storage Class If defined, storageClassName: If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning If undefined or set to null (the default), then fall back to the value of `ingester.persistentVolume.storageClass`. | +| ingester.zoneAwareReplication.zones[2] | object | `{"extraAffinity":{},"name":"zone-c","nodeSelector":null,"storageClass":null}` | Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ | +| ingester.zoneAwareReplication.zones[2].extraAffinity | object | `{}` | extraAffinity adds user defined custom affinity rules (merged with generated rules) | +| ingester.zoneAwareReplication.zones[2].nodeSelector | string | `nil` | nodeselector to restrict where pods of this zone can be placed. E.g.: nodeSelector: topology.kubernetes.io/zone: zone-c | +| ingester.zoneAwareReplication.zones[2].storageClass | string | `nil` | Ingester data Persistent Volume Storage Class If defined, storageClassName: If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning If undefined or set to null (the default), then fall back to the value of `ingester.persistentVolume.storageClass`. | +| license.contents | string | `"NOTAVALIDLICENSE"` | | +| license.external | bool | `false` | | +| license.secretName | string | `"{{ include \"tempo.resourceName\" (dict \"ctx\" . \"component\" \"license\") }}"` | | +| memberlist | object | `{"abort_if_cluster_join_fails":false,"bind_addr":[],"bind_port":7946,"gossip_interval":"1s","gossip_nodes":2,"gossip_to_dead_nodes_time":"30s","leave_timeout":"5s","left_ingesters_timeout":"5m","max_join_backoff":"1m","max_join_retries":10,"min_join_backoff":"1s","node_name":"","packet_dial_timeout":"5s","packet_write_timeout":"5s","pull_push_interval":"30s","randomize_node_name":true,"rejoin_interval":"0s","retransmit_factor":2,"stream_timeout":"10s"}` | Memberlist configuration. Please refer to https://grafana.com/docs/tempo/latest/configuration/#memberlist | +| memcached.affinity | string | Hard node and soft zone anti-affinity | Affinity for memcached pods. Passed through `tpl` and, thus, to be configured as string | +| memcached.enabled | bool | `true` | Specified whether the memcached cachce should be enabled | +| memcached.extraArgs | list | `[]` | Additional CLI args for memcached | +| memcached.extraEnv | list | `[]` | Environment variables to add to memcached pods | +| memcached.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to memcached pods | +| memcached.host | string | `"memcached"` | | +| memcached.image.pullPolicy | string | `"IfNotPresent"` | Memcached Docker image pull policy | +| memcached.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `global.image.pullSecrets` | +| memcached.image.registry | string | `nil` | The Docker registry for the Memcached image. Overrides `global.image.registry` | +| memcached.image.repository | string | `"memcached"` | Memcached Docker image repository | +| memcached.image.tag | string | `"1.6.23-alpine"` | Memcached Docker image tag | +| memcached.podAnnotations | object | `{}` | Annotations for memcached pods | +| memcached.podLabels | object | `{}` | Labels for memcached pods | +| memcached.replicas | int | `1` | | +| memcached.resources | object | `{}` | Resource requests and limits for memcached | +| memcached.service.annotations | object | `{}` | Annotations for memcached service | +| memcached.topologySpreadConstraints | string | Defaults to allow skew no more then 1 node per AZ | topologySpread for memcached pods. Passed through `tpl` and, thus, to be configured as string | +| memcachedExporter.enabled | bool | `false` | Specifies whether the Memcached Exporter should be enabled | +| memcachedExporter.hostAliases | list | `[]` | hostAliases to add | +| memcachedExporter.image.pullPolicy | string | `"IfNotPresent"` | Memcached Exporter Docker image pull policy | +| memcachedExporter.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `global.image.pullSecrets` | +| memcachedExporter.image.registry | string | `nil` | The Docker registry for the Memcached Exporter image. Overrides `global.image.registry` | +| memcachedExporter.image.repository | string | `"prom/memcached-exporter"` | Memcached Exporter Docker image repository | +| memcachedExporter.image.tag | string | `"v0.8.0"` | Memcached Exporter Docker image tag | +| memcachedExporter.resources | object | `{}` | | +| metaMonitoring.grafanaAgent.annotations | object | `{}` | Annotations to add to all monitoring.grafana.com custom resources. Does not affect the ServiceMonitors for kubernetes metrics; use serviceMonitor.annotations for that. | +| metaMonitoring.grafanaAgent.enabled | bool | `false` | Controls whether to create PodLogs, MetricsInstance, LogsInstance, and GrafanaAgent CRs to scrape the ServiceMonitors of the chart and ship metrics and logs to the remote endpoints below. Note that you need to configure serviceMonitor in order to have some metrics available. | +| metaMonitoring.grafanaAgent.installOperator | bool | `false` | Controls whether to install the Grafana Agent Operator and its CRDs. Note that helm will not install CRDs if this flag is enabled during an upgrade. In that case install the CRDs manually from https://github.com/grafana/agent/tree/main/production/operator/crds | +| metaMonitoring.grafanaAgent.labels | object | `{}` | Labels to add to all monitoring.grafana.com custom resources. Does not affect the ServiceMonitors for kubernetes metrics; use serviceMonitor.labels for that. | +| metaMonitoring.grafanaAgent.logs.additionalClientConfigs | list | `[]` | Client configurations for the LogsInstance that will scrape Mimir pods. Follows the format of .remote. | +| metaMonitoring.grafanaAgent.logs.remote | object | `{"auth":{"passwordSecretKey":"","passwordSecretName":"","tenantId":"","username":""},"url":""}` | Default destination for logs. The config here is translated to Promtail client configuration to write logs to this Loki-compatible remote. Optional. | +| metaMonitoring.grafanaAgent.logs.remote.auth.passwordSecretKey | string | `""` | The value under this key in passwordSecretName will be used as the basic authentication password. Required only if passwordSecretName is set. | +| metaMonitoring.grafanaAgent.logs.remote.auth.passwordSecretName | string | `""` | The value under key passwordSecretKey in this secret will be used as the basic authentication password. Required only if passwordSecretKey is set. | +| metaMonitoring.grafanaAgent.logs.remote.auth.tenantId | string | `""` | Used to set X-Scope-OrgID header on requests. Usually not used in combination with username and password. | +| metaMonitoring.grafanaAgent.logs.remote.auth.username | string | `""` | Basic authentication username. Optional. | +| metaMonitoring.grafanaAgent.logs.remote.url | string | `""` | Full URL for Loki push endpoint. Usually ends in /loki/api/v1/push | +| metaMonitoring.grafanaAgent.metrics.additionalRemoteWriteConfigs | list | `[]` | Additional remote-write for the MetricsInstance that will scrape Mimir pods. Follows the format of .remote. | +| metaMonitoring.grafanaAgent.metrics.remote | object | `{"auth":{"passwordSecretKey":"","passwordSecretName":"","username":""},"headers":{},"url":""}` | Default destination for metrics. The config here is translated to remote_write configuration to push metrics to this Prometheus-compatible remote. Optional. Note that you need to configure serviceMonitor in order to have some metrics available. | +| metaMonitoring.grafanaAgent.metrics.remote.auth.passwordSecretKey | string | `""` | The value under this key in passwordSecretName will be used as the basic authentication password. Required only if passwordSecretName is set. | +| metaMonitoring.grafanaAgent.metrics.remote.auth.passwordSecretName | string | `""` | The value under key passwordSecretKey in this secret will be used as the basic authentication password. Required only if passwordSecretKey is set. | +| metaMonitoring.grafanaAgent.metrics.remote.auth.username | string | `""` | Basic authentication username. Optional. | +| metaMonitoring.grafanaAgent.metrics.remote.headers | object | `{}` | Used to add HTTP headers to remote-write requests. | +| metaMonitoring.grafanaAgent.metrics.remote.url | string | `""` | Full URL for Prometheus remote-write. Usually ends in /push | +| metaMonitoring.grafanaAgent.metrics.scrapeK8s.enabled | bool | `true` | When grafanaAgent.enabled and serviceMonitor.enabled, controls whether to create ServiceMonitors CRs for cadvisor, kubelet, and kube-state-metrics. The scraped metrics are reduced to those pertaining to Mimir pods only. | +| metaMonitoring.grafanaAgent.metrics.scrapeK8s.kubeStateMetrics | object | `{"labelSelectors":{"app.kubernetes.io/name":"kube-state-metrics"},"namespace":"kube-system"}` | Controls service discovery of kube-state-metrics. | +| metaMonitoring.grafanaAgent.namespace | string | `""` | Sets the namespace of the resources. Leave empty or unset to use the same namespace as the Helm release. | +| metaMonitoring.serviceMonitor.annotations | object | `{}` | ServiceMonitor annotations | +| metaMonitoring.serviceMonitor.enabled | bool | `false` | If enabled, ServiceMonitor resources for Prometheus Operator are created | +| metaMonitoring.serviceMonitor.interval | string | `nil` | ServiceMonitor scrape interval | +| metaMonitoring.serviceMonitor.labels | object | `{}` | Additional ServiceMonitor labels | +| metaMonitoring.serviceMonitor.metricRelabelings | list | `[]` | ServiceMonitor metric relabel configs to apply to samples before ingestion https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#endpoint | +| metaMonitoring.serviceMonitor.namespace | string | `nil` | Alternative namespace for ServiceMonitor resources | +| metaMonitoring.serviceMonitor.namespaceSelector | object | `{}` | Namespace selector for ServiceMonitor resources | +| metaMonitoring.serviceMonitor.relabelings | list | `[]` | ServiceMonitor relabel configs to apply to samples before scraping https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig | +| metaMonitoring.serviceMonitor.scheme | string | `"http"` | ServiceMonitor will use http by default, but you can pick https as well | +| metaMonitoring.serviceMonitor.scrapeTimeout | string | `nil` | ServiceMonitor scrape timeout in Go duration format (e.g. 15s) | +| metaMonitoring.serviceMonitor.tlsConfig | string | `nil` | ServiceMonitor will use these tlsConfig settings to make the health check requests | +| metricsGenerator.affinity | string | Hard node and soft zone anti-affinity | Affinity for metrics-generator pods. Passed through `tpl` and, thus, to be configured as string | +| metricsGenerator.annotations | object | `{}` | Annotations for the metrics-generator StatefulSet | +| metricsGenerator.appProtocol | object | `{"grpc":null}` | Adds the appProtocol field to the metricsGenerator service. This allows metricsGenerator to work with istio protocol selection. | +| metricsGenerator.appProtocol.grpc | string | `nil` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| metricsGenerator.config | object | `{"metrics_ingestion_time_range_slack":"30s","processor":{"service_graphs":{"dimensions":[],"histogram_buckets":[0.1,0.2,0.4,0.8,1.6,3.2,6.4,12.8],"max_items":10000,"wait":"10s","workers":10},"span_metrics":{"dimensions":[],"histogram_buckets":[0.002,0.004,0.008,0.016,0.032,0.064,0.128,0.256,0.512,1.02,2.05,4.1]}},"registry":{"collection_interval":"15s","external_labels":{},"stale_duration":"15m"},"storage":{"path":"/var/tempo/wal","remote_write":[],"remote_write_add_org_id_header":true,"remote_write_flush_deadline":"1m","wal":null},"traces_storage":{"path":"/var/tempo/traces"}}` | More information on configuration: https://grafana.com/docs/tempo/latest/configuration/#metrics-generator | +| metricsGenerator.config.processor.service_graphs | object | `{"dimensions":[],"histogram_buckets":[0.1,0.2,0.4,0.8,1.6,3.2,6.4,12.8],"max_items":10000,"wait":"10s","workers":10}` | For processors to be enabled and generate metrics, pass the names of the processors to overrides.metrics_generator_processors value like [service-graphs, span-metrics] | +| metricsGenerator.config.processor.service_graphs.dimensions | list | `[]` | resource and span attributes and are added to the metrics if present. | +| metricsGenerator.config.processor.span_metrics.dimensions | list | `[]` | Dimensions are searched for in the resource and span attributes and are added to the metrics if present. | +| metricsGenerator.config.storage.remote_write | list | `[]` | https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_write | +| metricsGenerator.config.traces_storage | object | `{"path":"/var/tempo/traces"}` | Used by the local blocks processor to store a wal for traces. | +| metricsGenerator.enabled | bool | `false` | Specifies whether a metrics-generator should be deployed | +| metricsGenerator.extraArgs | list | `[]` | Additional CLI args for the metrics-generator | +| metricsGenerator.extraEnv | list | `[]` | Environment variables to add to the metrics-generator pods | +| metricsGenerator.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the metrics-generator pods | +| metricsGenerator.extraVolumeMounts | list | `[]` | Extra volumes for metrics-generator pods | +| metricsGenerator.extraVolumes | list | `[]` | Extra volumes for metrics-generator deployment | +| metricsGenerator.hostAliases | list | `[]` | hostAliases to add | +| metricsGenerator.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` | +| metricsGenerator.image.registry | string | `nil` | The Docker registry for the metrics-generator image. Overrides `tempo.image.registry` | +| metricsGenerator.image.repository | string | `nil` | Docker image repository for the metrics-generator image. Overrides `tempo.image.repository` | +| metricsGenerator.image.tag | string | `nil` | Docker image tag for the metrics-generator image. Overrides `tempo.image.tag` | +| metricsGenerator.initContainers | list | `[]` | | +| metricsGenerator.kind | string | `"Deployment"` | Kind of deployment [StatefulSet/Deployment] | +| metricsGenerator.nodeSelector | object | `{}` | Node selector for metrics-generator pods | +| metricsGenerator.persistence | object | `{"annotations":{},"enabled":false,"size":"10Gi","storageClass":null}` | Persistence configuration for metrics-generator | +| metricsGenerator.persistence.annotations | object | `{}` | Annotations for metrics generator PVCs | +| metricsGenerator.persistence.enabled | bool | `false` | Enable creating PVCs if you have kind set to StatefulSet. This disables using local disk or memory configured in walEmptyDir | +| metricsGenerator.persistence.storageClass | string | `nil` | Storage class to be used. If defined, storageClassName: . If set to "-", storageClassName: "", which disables dynamic provisioning. If empty or set to null, no storageClassName spec is set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). | +| metricsGenerator.podAnnotations | object | `{}` | Annotations for metrics-generator pods | +| metricsGenerator.podLabels | object | `{}` | Labels for metrics-generator pods | +| metricsGenerator.ports | list | `[{"name":"grpc","port":9095,"service":true},{"name":"http-memberlist","port":7946,"service":false},{"name":"http-metrics","port":3100,"service":true}]` | Default ports | +| metricsGenerator.priorityClassName | string | `nil` | The name of the PriorityClass for metrics-generator pods | +| metricsGenerator.replicas | int | `1` | Number of replicas for the metrics-generator | +| metricsGenerator.resources | object | `{}` | Resource requests and limits for the metrics-generator | +| metricsGenerator.service.annotations | object | `{}` | Annotations for Metrics Generator service | +| metricsGenerator.terminationGracePeriodSeconds | int | `300` | Grace period to allow the metrics-generator to shutdown before it is killed. Especially for the ingestor, this must be increased. It must be long enough so metrics-generators can be gracefully shutdown flushing/transferring all data and to successfully leave the member ring on shutdown. | +| metricsGenerator.tolerations | list | `[]` | Tolerations for metrics-generator pods | +| metricsGenerator.topologySpreadConstraints | string | Defaults to allow skew no more then 1 node per AZ | topologySpread for metrics-generator pods. Passed through `tpl` and, thus, to be configured as string | +| metricsGenerator.walEmptyDir | object | `{}` | The EmptyDir location where the /var/tempo will be mounted on. Defaults to local disk, can be set to memory. | +| minio.buckets[0].name | string | `"tempo-traces"` | | +| minio.buckets[0].policy | string | `"none"` | | +| minio.buckets[0].purge | bool | `false` | | +| minio.buckets[1].name | string | `"enterprise-traces"` | | +| minio.buckets[1].policy | string | `"none"` | | +| minio.buckets[1].purge | bool | `false` | | +| minio.buckets[2].name | string | `"enterprise-traces-admin"` | | +| minio.buckets[2].policy | string | `"none"` | | +| minio.buckets[2].purge | bool | `false` | | +| minio.configPathmc | string | `"/tmp/minio/mc/"` | | +| minio.enabled | bool | `false` | | +| minio.mode | string | `"standalone"` | | +| minio.persistence.size | string | `"5Gi"` | | +| minio.resources.requests.cpu | string | `"100m"` | | +| minio.resources.requests.memory | string | `"128Mi"` | | +| minio.rootPassword | string | `"supersecret"` | | +| minio.rootUser | string | `"grafana-tempo"` | | +| multitenancyEnabled | bool | `false` | | +| overrides | string | `"overrides: {}\n"` | | +| prometheusRule.annotations | object | `{}` | PrometheusRule annotations | +| prometheusRule.enabled | bool | `false` | If enabled, a PrometheusRule resource for Prometheus Operator is created | +| prometheusRule.groups | list | `[]` | Contents of Prometheus rules file | +| prometheusRule.labels | object | `{}` | Additional PrometheusRule labels | +| prometheusRule.namespace | string | `nil` | Alternative namespace for the PrometheusRule resource | +| querier.affinity | string | Hard node and soft zone anti-affinity | Affinity for querier pods. Passed through `tpl` and, thus, to be configured as string | +| querier.appProtocol | object | `{"grpc":null}` | Adds the appProtocol field to the querier service. This allows querier to work with istio protocol selection. | +| querier.appProtocol.grpc | string | `nil` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| querier.autoscaling.behavior | object | `{}` | Autoscaling behavior configuration for the querier | +| querier.autoscaling.enabled | bool | `false` | Enable autoscaling for the querier | +| querier.autoscaling.maxReplicas | int | `3` | Maximum autoscaling replicas for the querier | +| querier.autoscaling.minReplicas | int | `1` | Minimum autoscaling replicas for the querier | +| querier.autoscaling.targetCPUUtilizationPercentage | int | `60` | Target CPU utilisation percentage for the querier | +| querier.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | Target memory utilisation percentage for the querier | +| querier.config.frontend_worker.grpc_client_config | object | `{}` | grpc client configuration | +| querier.config.max_concurrent_queries | int | `20` | This value controls the overall number of simultaneous subqueries that the querier will service at once. It does not distinguish between the types of queries. | +| querier.config.search.external_backend | string | `""` | credentials when querying the external backend. | +| querier.config.search.external_endpoints | list | `[]` | A list of external endpoints that the querier will use to offload backend search requests | +| querier.config.search.external_hedge_requests_at | string | `"8s"` | If set to a non-zero value a second request will be issued at the provided duration. Recommended to be set to p99 of external search requests to reduce long tail latency. | +| querier.config.search.external_hedge_requests_up_to | int | `2` | The maximum number of requests to execute when hedging. Requires hedge_requests_at to be set. | +| querier.config.search.google_cloud_run | object | `{}` | external_backend is "google_cloud_run". | +| querier.config.search.prefer_self | int | `10` | If search_external_endpoints is set then the querier will primarily act as a proxy for whatever serverless backend you have configured. This setting allows the operator to have the querier prefer itself for a configurable number of subqueries. | +| querier.config.search.query_timeout | string | `"30s"` | Timeout for search requests | +| querier.config.trace_by_id.query_timeout | string | `"10s"` | Timeout for trace lookup requests | +| querier.extraArgs | list | `[]` | Additional CLI args for the querier | +| querier.extraEnv | list | `[]` | Environment variables to add to the querier pods | +| querier.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the querier pods | +| querier.extraVolumeMounts | list | `[]` | Extra volumes for querier pods | +| querier.extraVolumes | list | `[]` | Extra volumes for querier deployment | +| querier.hostAliases | list | `[]` | hostAliases to add | +| querier.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` | +| querier.image.registry | string | `nil` | The Docker registry for the querier image. Overrides `tempo.image.registry` | +| querier.image.repository | string | `nil` | Docker image repository for the querier image. Overrides `tempo.image.repository` | +| querier.image.tag | string | `nil` | Docker image tag for the querier image. Overrides `tempo.image.tag` | +| querier.nodeSelector | object | `{}` | Node selector for querier pods | +| querier.podAnnotations | object | `{}` | Annotations for querier pods | +| querier.podLabels | object | `{}` | Labels for querier pods | +| querier.priorityClassName | string | `nil` | The name of the PriorityClass for querier pods | +| querier.replicas | int | `1` | Number of replicas for the querier | +| querier.resources | object | `{}` | Resource requests and limits for the querier | +| querier.service.annotations | object | `{}` | Annotations for querier service | +| querier.terminationGracePeriodSeconds | int | `30` | Grace period to allow the querier to shutdown before it is killed | +| querier.tolerations | list | `[]` | Tolerations for querier pods | +| querier.topologySpreadConstraints | string | Defaults to allow skew no more then 1 node per AZ | topologySpread for querier pods. Passed through `tpl` and, thus, to be configured as string | +| queryFrontend.affinity | string | Hard node and soft zone anti-affinity | Affinity for query-frontend pods. Passed through `tpl` and, thus, to be configured as string | +| queryFrontend.appProtocol | object | `{"grpc":null}` | Adds the appProtocol field to the queryFrontend service. This allows queryFrontend to work with istio protocol selection. | +| queryFrontend.appProtocol.grpc | string | `nil` | Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" | +| queryFrontend.autoscaling.behavior | object | `{}` | Autoscaling behavior configuration for the query-frontend | +| queryFrontend.autoscaling.enabled | bool | `false` | Enable autoscaling for the query-frontend | +| queryFrontend.autoscaling.maxReplicas | int | `3` | Maximum autoscaling replicas for the query-frontend | +| queryFrontend.autoscaling.minReplicas | int | `1` | Minimum autoscaling replicas for the query-frontend | +| queryFrontend.autoscaling.targetCPUUtilizationPercentage | int | `60` | Target CPU utilisation percentage for the query-frontend | +| queryFrontend.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | Target memory utilisation percentage for the query-frontend | +| queryFrontend.config.max_outstanding_per_tenant | int | `2000` | Maximum number of outstanding requests per tenant per frontend; requests beyond this error with HTTP 429. | +| queryFrontend.config.max_retries | int | `2` | Number of times to retry a request sent to a querier | +| queryFrontend.config.search.concurrent_jobs | int | `1000` | The number of concurrent jobs to execute when searching the backend | +| queryFrontend.config.search.target_bytes_per_job | int | `104857600` | The target number of bytes for each job to handle when performing a backend search | +| queryFrontend.config.trace_by_id | object | `{"query_shards":50}` | Trace by ID lookup configuration | +| queryFrontend.config.trace_by_id.query_shards | int | `50` | The number of shards to split a trace by id query into. | +| queryFrontend.extraArgs | list | `[]` | Additional CLI args for the query-frontend | +| queryFrontend.extraEnv | list | `[]` | Environment variables to add to the query-frontend pods | +| queryFrontend.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the query-frontend pods | +| queryFrontend.extraVolumeMounts | list | `[]` | Extra volumes for query-frontend pods | +| queryFrontend.extraVolumes | list | `[]` | Extra volumes for query-frontend deployment | +| queryFrontend.hostAliases | list | `[]` | hostAliases to add | +| queryFrontend.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` | +| queryFrontend.image.registry | string | `nil` | The Docker registry for the query-frontend image. Overrides `tempo.image.registry` | +| queryFrontend.image.repository | string | `nil` | Docker image repository for the query-frontend image. Overrides `tempo.image.repository` | +| queryFrontend.image.tag | string | `nil` | Docker image tag for the query-frontend image. Overrides `tempo.image.tag` | +| queryFrontend.ingress.annotations | object | `{}` | Annotations for the Jaeger ingress | +| queryFrontend.ingress.enabled | bool | `false` | Specifies whether an ingress for the Jaeger should be created | +| queryFrontend.ingress.hosts | list | `[{"host":"query.tempo.example.com","paths":[{"path":"/"}]}]` | Hosts configuration for the Jaeger ingress | +| queryFrontend.ingress.tls | list | `[{"hosts":["query.tempo.example.com"],"secretName":"tempo-query-tls"}]` | TLS configuration for the Jaeger ingress | +| queryFrontend.nodeSelector | object | `{}` | Node selector for query-frontend pods | +| queryFrontend.podAnnotations | object | `{}` | Annotations for query-frontend pods | +| queryFrontend.podLabels | object | `{}` | Labels for queryFrontend pods | +| queryFrontend.priorityClassName | string | `nil` | The name of the PriorityClass for query-frontend pods | +| queryFrontend.query.config | string | `"backend: 127.0.0.1:3100\n"` | | +| queryFrontend.query.enabled | bool | `false` | Required for grafana version <7.5 for compatibility with jaeger-ui. Doesn't work on ARM arch | +| queryFrontend.query.extraArgs | list | `[]` | Additional CLI args for tempo-query pods | +| queryFrontend.query.extraEnv | list | `[]` | Environment variables to add to the tempo-query pods | +| queryFrontend.query.extraEnvFrom | list | `[]` | Environment variables from secrets or configmaps to add to the tempo-query pods | +| queryFrontend.query.extraVolumeMounts | list | `[]` | Extra volumes for tempo-query pods | +| queryFrontend.query.extraVolumes | list | `[]` | Extra volumes for tempo-query deployment | +| queryFrontend.query.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` | +| queryFrontend.query.image.registry | string | `nil` | The Docker registry for the query-frontend image. Overrides `tempo.image.registry` | +| queryFrontend.query.image.repository | string | `"grafana/tempo-query"` | Docker image repository for the query-frontend image. Overrides `tempo.image.repository` | +| queryFrontend.query.image.tag | string | `nil` | Docker image tag for the query-frontend image. Overrides `tempo.image.tag` | +| queryFrontend.query.resources | object | `{}` | Resource requests and limits for the query | +| queryFrontend.replicas | int | `1` | Number of replicas for the query-frontend | +| queryFrontend.resources | object | `{}` | Resource requests and limits for the query-frontend | +| queryFrontend.service.annotations | object | `{}` | Annotations for queryFrontend service | +| queryFrontend.service.labels | object | `{}` | Labels for queryFrontend service | +| queryFrontend.service.loadBalancerIP | string | `""` | If type is LoadBalancer you can assign the IP to the LoadBalancer | +| queryFrontend.service.loadBalancerSourceRanges | list | `[]` | If type is LoadBalancer limit incoming traffic from IPs. | +| queryFrontend.service.port | int | `16686` | Port of the query-frontend service | +| queryFrontend.service.type | string | `"ClusterIP"` | Type of service for the queryFrontend | +| queryFrontend.serviceDiscovery.annotations | object | `{}` | Annotations for queryFrontendDiscovery service | +| queryFrontend.serviceDiscovery.labels | object | `{}` | Labels for queryFrontendDiscovery service | +| queryFrontend.terminationGracePeriodSeconds | int | `30` | Grace period to allow the query-frontend to shutdown before it is killed | +| queryFrontend.tolerations | list | `[]` | Tolerations for query-frontend pods | +| queryFrontend.topologySpreadConstraints | string | Defaults to allow skew no more then 1 node per AZ | topologySpread for query-frontend pods. Passed through `tpl` and, thus, to be configured as string | +| rbac.create | bool | `false` | Specifies whether RBAC manifests should be created | +| rbac.pspEnabled | bool | `false` | Specifies whether a PodSecurityPolicy should be created | +| reportingEnabled | bool | `true` | If true, Tempo will report anonymous usage data about the shape of a deployment to Grafana Labs | +| rollout_operator.enabled | bool | `false` | Enable rollout-operator. It must be enabled when using Zone Aware Replication. | +| rollout_operator.podSecurityContext.fsGroup | int | `10001` | | +| rollout_operator.podSecurityContext.runAsGroup | int | `10001` | | +| rollout_operator.podSecurityContext.runAsNonRoot | bool | `true` | | +| rollout_operator.podSecurityContext.runAsUser | int | `10001` | | +| rollout_operator.podSecurityContext.seccompProfile.type | string | `"RuntimeDefault"` | | +| rollout_operator.securityContext.allowPrivilegeEscalation | bool | `false` | | +| rollout_operator.securityContext.capabilities.drop[0] | string | `"ALL"` | | +| rollout_operator.securityContext.readOnlyRootFilesystem | bool | `true` | | +| server.grpc_server_max_recv_msg_size | int | `4194304` | Max gRPC message size that can be received | +| server.grpc_server_max_send_msg_size | int | `4194304` | Max gRPC message size that can be sent | +| server.httpListenPort | int | `3100` | HTTP server listen host | +| server.http_server_read_timeout | string | `"30s"` | Read timeout for HTTP server | +| server.http_server_write_timeout | string | `"30s"` | Write timeout for HTTP server | +| server.logFormat | string | `"logfmt"` | Log format. Can be set to logfmt (default) or json. | +| server.logLevel | string | `"info"` | Log level. Can be set to trace, debug, info (default), warn, error, fatal, panic | +| serviceAccount.annotations | object | `{}` | Annotations for the service account | +| serviceAccount.automountServiceAccountToken | bool | `false` | | +| serviceAccount.create | bool | `true` | Specifies whether a ServiceAccount should be created | +| serviceAccount.imagePullSecrets | list | `[]` | Image pull secrets for the service account | +| serviceAccount.name | string | `nil` | The name of the ServiceAccount to use. If not set and create is true, a name is generated using the fullname template | +| storage.admin.backend | string | `"filesystem"` | The supported storage backends are gcs, s3 and azure, as specified in https://grafana.com/docs/enterprise-traces/latest/config/reference/#admin_client_config | +| storage.trace.backend | string | `"local"` | The supported storage backends are gcs, s3 and azure, as specified in https://grafana.com/docs/tempo/latest/configuration/#storage | +| storage.trace.block.dedicated_columns | list | `[]` | Lis with dedicated attribute columns (only for vParquet3 or later) | +| storage.trace.block.version | string | `nil` | The supported block versions are specified here https://grafana.com/docs/tempo/latest/configuration/parquet/ | +| storage.trace.pool.max_workers | int | `400` | Total number of workers pulling jobs from the queue | +| storage.trace.pool.queue_depth | int | `20000` | Length of job queue. imporatant for querier as it queues a job for every block it has to search | +| tempo.image.pullPolicy | string | `"IfNotPresent"` | | +| tempo.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `global.image.pullSecrets` | +| tempo.image.registry | string | `"docker.io"` | The Docker registry | +| tempo.image.repository | string | `"grafana/tempo"` | Docker image repository | +| tempo.image.tag | string | `nil` | Overrides the image tag whose default is the chart's appVersion | +| tempo.memberlist | object | `{"appProtocol":null}` | Memberlist service configuration. | +| tempo.memberlist.appProtocol | string | `nil` | Adds the appProtocol field to the memberlist service. This allows memberlist to work with istio protocol selection. Set the optional service protocol. Ex: "tcp", "http" or "https". | +| tempo.podAnnotations | object | `{}` | Common annotations for all pods | +| tempo.podLabels | object | `{}` | Global labels for all tempo pods | +| tempo.podSecurityContext | object | `{"fsGroup":1000}` | podSecurityContext holds pod-level security attributes and common container settings | +| tempo.readinessProbe.httpGet.path | string | `"/ready"` | | +| tempo.readinessProbe.httpGet.port | string | `"http-metrics"` | | +| tempo.readinessProbe.initialDelaySeconds | int | `30` | | +| tempo.readinessProbe.timeoutSeconds | int | `1` | | +| tempo.securityContext | object | `{"allowPrivilegeEscalation":false,"capabilities":{"drop":["ALL"]},"readOnlyRootFilesystem":true,"runAsGroup":1000,"runAsNonRoot":true,"runAsUser":1000}` | SecurityContext holds container-level security attributes and common container settings | +| tempo.structuredConfig | object | `{}` | Structured tempo configuration | +| tokengenJob.annotations | object | `{}` | | +| tokengenJob.containerSecurityContext | object | `{"readOnlyRootFilesystem":true}` | The SecurityContext for tokenjobgen containers | +| tokengenJob.enable | bool | `true` | | +| tokengenJob.env | list | `[]` | | +| tokengenJob.extraArgs | object | `{}` | | +| tokengenJob.extraEnvFrom | list | `[]` | | +| tokengenJob.hostAliases | list | `[]` | hostAliases to add | +| tokengenJob.image.pullSecrets | list | `[]` | Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` | +| tokengenJob.image.registry | string | `nil` | The Docker registry for the tokengenJob image. Overrides `tempo.image.registry` | +| tokengenJob.image.repository | string | `nil` | Docker image repository for the tokengenJob image. Overrides `tempo.image.repository` | +| tokengenJob.image.tag | string | `nil` | Docker image tag for the tokengenJob image. Overrides `tempo.image.tag` | +| tokengenJob.initContainers | list | `[]` | | +| traces.jaeger.grpc.enabled | bool | `false` | Enable Tempo to ingest Jaeger GRPC traces | +| traces.jaeger.grpc.receiverConfig | object | `{}` | Jaeger GRPC receiver config | +| traces.jaeger.thriftBinary.enabled | bool | `false` | Enable Tempo to ingest Jaeger Thrift Binary traces | +| traces.jaeger.thriftBinary.receiverConfig | object | `{}` | Jaeger Thrift Binary receiver config | +| traces.jaeger.thriftCompact.enabled | bool | `false` | Enable Tempo to ingest Jaeger Thrift Compact traces | +| traces.jaeger.thriftCompact.receiverConfig | object | `{}` | Jaeger Thrift Compact receiver config | +| traces.jaeger.thriftHttp.enabled | bool | `false` | Enable Tempo to ingest Jaeger Thrift HTTP traces | +| traces.jaeger.thriftHttp.receiverConfig | object | `{}` | Jaeger Thrift HTTP receiver config | +| traces.kafka | object | `{}` | Enable Tempo to ingest traces from Kafka. Reference: https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/receiver/kafkareceiver | +| traces.opencensus.enabled | bool | `false` | Enable Tempo to ingest Open Census traces | +| traces.opencensus.receiverConfig | object | `{}` | Open Census receiver config | +| traces.otlp.grpc.enabled | bool | `false` | Enable Tempo to ingest Open Telemetry GRPC traces | +| traces.otlp.grpc.receiverConfig | object | `{}` | GRPC receiver advanced config | +| traces.otlp.http.enabled | bool | `false` | Enable Tempo to ingest Open Telemetry HTTP traces | +| traces.otlp.http.receiverConfig | object | `{}` | HTTP receiver advanced config | +| traces.zipkin.enabled | bool | `false` | Enable Tempo to ingest Zipkin traces | +| traces.zipkin.receiverConfig | object | `{}` | Zipkin receiver config | +| useExternalConfig | bool | `false` | Configuration is loaded from the secret called 'externalConfigSecretName'. If 'useExternalConfig' is true, then the configuration is not generated, just consumed. Top level keys for `tempo.yaml` and `overrides.yaml` are to be provided by the user. | + +## Components + +The chart supports the components shown in the following table. +Ingester, distributor, querier, query-frontend, and compactor are always installed. +The other components are optional and must be explicitly enabled. + +| Component | Optional | +| --- | --- | +| ingester | no | +| distributor | no | +| querier | no | +| query-frontend | no | +| compactor | no | +| metrics-generator | yes | +| memcached | yes | +| gateway | yes | + +## [Configuration](https://grafana.com/docs/tempo/latest/configuration/) + +This chart configures Tempo in microservices mode. + +**NOTE:** +In its default configuration, the chart uses `local` filesystem as storage. +The reason for this is that the chart can be validated and installed in a CI pipeline. +However, this setup is not fully functional. +The recommendation is to use object storage, such as S3, GCS, MinIO, etc., or one of the other options documented at https://grafana.com/docs/tempo/latest/configuration/#storage. + +Alternatively, in order to quickly test Tempo using the filestore, the [single binary chart](https://github.com/grafana/helm-charts/tree/main/charts/tempo) can be used. + +### Overriding configuration variables with structuredConfig + +tempo.structuredConfig variable can be used to alter individual values in the configuration and it's structured YAML instead of text. It takes precedence over all other variable adjustments inside tempo.yaml config file, ie s3 storage settings. + +Example: + +```yaml +tempo: + structuredConfig: + query_frontend: + search: + max_duration: 12h0m0s +``` + +### Activate metrics generator + +Metrics-generator is disabled by default and can be activated by configuring the following values: + +```yaml +metricsGenerator: + enabled: true + config: + storage_remote_write: + - url: http://cortex/api/v1/push + send_exemplars: true + # headers: + # x-scope-orgid: operations +# Global overrides +global_overrides: + defaults: + metrics_generator: + processors: + - service-graphs + - span-metrics +``` + +---- + +### Directory and File Locations + +* Volumes are mounted to `/var/tempo`. The various directories Tempo needs should be configured as subdirectories (e. g. `/var/tempo/wal`, `/var/tempo/traces`). Tempo will create the directories automatically. +* The config file is mounted to `/conf/tempo-query.yaml` and passed as CLI arg. + +### Example configuration using S3 for storage + +```yaml +config: | + multitenancy_enabled: false + compactor: + compaction: + block_retention: 48h + ring: + kvstore: + store: memberlist + distributor: + receivers: + jaeger: + protocols: + grpc: + endpoint: 0.0.0.0:14250 + thrift_binary: + endpoint: 0.0.0.0:6832 + thrift_compact: + endpoint: 0.0.0.0:6831 + thrift_http: + endpoint: 0.0.0.0:14268 + querier: + frontend_worker: + frontend_address: {{ include "tempo.resourceName" (dict "ctx" . "component" "query-frontend") }}:9095 + ingester: + lifecycler: + ring: + replication_factor: 1 + memberlist: + abort_if_cluster_join_fails: false + join_members: + - {{ include "tempo.fullname" . }}-memberlist + overrides: + per_tenant_override_config: /runtime-config/overrides.yaml + server: + http_listen_port: 3100 + storage: + trace: + backend: s3 + s3: + access_key: tempo + bucket: + endpoint: minio:9000 + insecure: true + secret_key: supersecret + pool: + queue_depth: 2000 + wal: + path: /var/tempo/wal + memcached: + consistent_hash: true + host: a-tempo-distributed-memcached + service: memcached-client + timeout: 500ms +``` diff --git a/observability/lgtm-distributed/charts/tempo-distributed/README.md.gotmpl b/observability/lgtm-distributed/charts/tempo-distributed/README.md.gotmpl new file mode 100644 index 0000000..2436bb8 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/README.md.gotmpl @@ -0,0 +1,344 @@ +{{ template "chart.header" . }} + +{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }} + +{{ template "chart.description" . }} + +{{ template "chart.sourcesSection" . }} + +{{ template "chart.requirementsSection" . }} + +## Chart Repo + +Add the following repo to use the chart: + +```console +helm repo add grafana https://grafana.github.io/helm-charts +``` + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```console +helm install my-release grafana/tempo-distributed +``` + +## Uninstalling the Chart + +To uninstall/delete the my-release deployment: + +```console +helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + + +## Upgrading + +A major chart version change indicates that there is an incompatible breaking change needing manual actions. + +### from Chart versions < 1.13.0 + +EXPERIMENTAL: Zone Aware Replication has been added to the ingester statefulset. +Attention, the calculation of the pods per AZ is as follows ```(.values.ingester.replicas + numberOfZones -1)/numberOfZones``` + +### From Chart versions < 1.8.0 + +Switch to new overrides format, see https://grafana.com/docs/tempo/latest/configuration/#overrides. + +### From Chart versions < 1.6.0 + +The metrics generator component in the chart has been disabled by default, but the configuration for the processors was not empty, resulting error sin the distributor log. Here we align the default metrics generator config settings to both disable the generator and remove processors. Users who wish to keep the their processors enabled, will need to update their values. + +### From Chart versions < 1.5.0 + +Please be aware that we've updated the minor version to Tempo 2.2, which includes breaking changes. +We recommend reviewing the [release notes](https://github.com/grafana/tempo/releases/tag/v2.2.0) before upgrading. + +### From Chart versions < 1.3.0 + +Please be aware that we've updated the minor version to Tempo 2.1, which includes breaking changes. +We recommend reviewing the [release notes](https://github.com/grafana/tempo/releases/tag/v2.1.0/) before upgrading. + +### From Chart versions < 1.0.0 + +Please note that we've incremented the major version when upgrading to Tempo 2.0. There were a large number of +changes in this release (breaking and otherwise). It is encouraged to review the [release notes](https://grafana.com/docs/tempo/latest/release-notes/v2-0/) +and [1.5 -> 2.0 upgrade guide](https://grafana.com/docs/tempo/latest/setup/upgrade/) before upgrading. + +### From chart version < 0.27.0 + +Version 0.27.0: + +Many changes have been introduced, including some breaking changes. + +The [PR](https://github.com/grafana/helm-charts/pull/1759) includes additional details. + +* **BREAKING CHANGE** centralize selector label handling -- users who wish to keep old values should still be able to use the `nameOverride` and `fullNameOverride` top level keys in their values. + +* **BREAKING CHANGE** serviceMonitor has been nested under metaMonitoring -- metamonitoring can be used scrape services as well as install the operator with the following values. Note also that the port names have changed from `http` to `http-metrics`. +```yaml +metaMonitoring: + serviceMonitor: + enabled: true + grafanaAgent: + enabled: true + installOperator: true +``` +* minio can now be enabled as part of this chart using the following values +```yaml +minio: + enabled: true +``` +* allow configuration to be stored in a secret. See the documentation for `useExternalConfig` and `configStorageType` in the values file for more details. + + +### From chart version < 0.26.0 + +Version 0.26.0 + +* Moves metricsGenerator.config.storage_remote_write to metricsGenerator.config.storage.remote_write +* Moves metricsGenerator.config.service_graphs_max_items to metricsGenerator.config.processor.service_graphs.max_items + +### From chart version < 0.23.0 + +Version 0.23.0: + +* Adds /var/tempo emptyDir mount for querier, queryfrontend, distributor and compactor. Previously, /var/tempo was directory inside container. + +* Sets queryFrontend.query.enabled to false. tempo-query is only required for grafana version <7.5 for compatibility with jaeger-ui. Please also note that tempo-query is incompatible with securityContext readOnlyRootFilesystem set to true. + +* Sets stricter default securityContext: +```yaml +tempo: + securityContext: + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + runAsNonRoot: true + runAsUser: 1000 + runAsGroup: 1000 + allowPrivilegeEscalation: false + podSecurityContext: + fsGroup: 1000 +``` +If you had ingester persistence enabled, you might need to manually change ownership of files in your PV if your CSI doesn't support fsGroup + +### From Chart version >= 0.22.0 +Align Istio GRPC named port syntax. For example, + +- otlp-grpc -> grpc-otlp +- distributor-otlp-grpc -> grpc-distributor-otlp +- jaeger-grpc -> grpc-jaeger +- distributor-jaeger-grpc -> grpc-distributor-jaeger + +In case you need to rollback, please search the right hand side pattern and replace with left hand side pattern. + +### From Chart version < 0.20.0 +The image's attributes must be set under the `image` key for the Memcached service. +```yaml +memcached: + image: + registry: docker.io + repository: memcached + tag: "1.5.17-alpine" + pullPolicy: "IfNotPresent" +``` + +### From Chart version < 0.18.0 +Trace ingestion must now be enabled with the `enabled` key: +```yaml +traces: + otlp: + grpc: + enabled: true + http: + enabled: true + zipkin: + enabled: true + jaeger: + thriftHttp: + enabled: true + opencensus: + enabled: true +``` + +### From Chart versions < 0.9.0 + +This release the component label was shortened to be more aligned with the Loki-distributed chart and the [mixin](https://github.com/grafana/tempo/tree/master/operations/tempo-mixin) dashboards. + +Due to the label changes, an existing installation cannot be upgraded without manual interaction. There are basically two options: + +Option 1 +Uninstall the old release and re-install the new one. There will be no data loss, as the collectors/agents can cache for a short period. + +Option 2 +Add new selector labels to the existing pods. This option will make your pods also temporarely unavailable, option 1 is faster: + +``` +kubectl label pod -n -l app.kubernetes.io/component=-tempo-distributed-,app.kubernetes.io/instance= app.kubernetes.io/component= --overwrite +``` + +Perform a non-cascading deletion of the Deployments and Statefulsets which will keep the pods running: + +``` +kubectl delete -n -l app.kubernetes.io/component=-tempo-distributed-,app.kubernetes.io/instance= --cascade=false +``` + +Perform a regular Helm upgrade on the existing release. The new Deployment/Statefulset will pick up the existing pods and perform a rolling upgrade. + +### From Chart versions < 0.8.0 + +By default all tracing protocols are disabled and you need to specify which protocols to enable for ingestion. + +For example to enable Jaeger grpc thrift http and zipkin protocols: +```yaml +traces: + jaeger: + grpc: true + thriftHttp: true + zipkin: true +``` + +The distributor service is now called {{"{{"}}tempo.fullname{{"}}"}}-distributor. That could impact your ingestion towards this service. + +### From Chart Versions < 0.7.0 + +The memcached default args are removed and should be provided manually. The settings for the `memcached.exporter` moved to `memcachedExporter` + +{{ template "chart.valuesSection" . }} + +## Components + +The chart supports the components shown in the following table. +Ingester, distributor, querier, query-frontend, and compactor are always installed. +The other components are optional and must be explicitly enabled. + +| Component | Optional | +| --- | --- | +| ingester | no | +| distributor | no | +| querier | no | +| query-frontend | no | +| compactor | no | +| metrics-generator | yes | +| memcached | yes | +| gateway | yes | + + +## [Configuration](https://grafana.com/docs/tempo/latest/configuration/) + +This chart configures Tempo in microservices mode. + +**NOTE:** +In its default configuration, the chart uses `local` filesystem as storage. +The reason for this is that the chart can be validated and installed in a CI pipeline. +However, this setup is not fully functional. +The recommendation is to use object storage, such as S3, GCS, MinIO, etc., or one of the other options documented at https://grafana.com/docs/tempo/latest/configuration/#storage. + +Alternatively, in order to quickly test Tempo using the filestore, the [single binary chart](https://github.com/grafana/helm-charts/tree/main/charts/tempo) can be used. + +### Overriding configuration variables with structuredConfig + +tempo.structuredConfig variable can be used to alter individual values in the configuration and it's structured YAML instead of text. It takes precedence over all other variable adjustments inside tempo.yaml config file, ie s3 storage settings. + +Example: + +```yaml +tempo: + structuredConfig: + query_frontend: + search: + max_duration: 12h0m0s +``` + +### Activate metrics generator + +Metrics-generator is disabled by default and can be activated by configuring the following values: + +```yaml +metricsGenerator: + enabled: true + config: + storage_remote_write: + - url: http://cortex/api/v1/push + send_exemplars: true + # headers: + # x-scope-orgid: operations +# Global overrides +global_overrides: + defaults: + metrics_generator: + processors: + - service-graphs + - span-metrics +``` + +---- + +### Directory and File Locations + +* Volumes are mounted to `/var/tempo`. The various directories Tempo needs should be configured as subdirectories (e. g. `/var/tempo/wal`, `/var/tempo/traces`). Tempo will create the directories automatically. +* The config file is mounted to `/conf/tempo-query.yaml` and passed as CLI arg. + + +### Example configuration using S3 for storage + +```yaml +config: | + multitenancy_enabled: false + compactor: + compaction: + block_retention: 48h + ring: + kvstore: + store: memberlist + distributor: + receivers: + jaeger: + protocols: + grpc: + endpoint: 0.0.0.0:14250 + thrift_binary: + endpoint: 0.0.0.0:6832 + thrift_compact: + endpoint: 0.0.0.0:6831 + thrift_http: + endpoint: 0.0.0.0:14268 + querier: + frontend_worker: + frontend_address: {{"{{"}} include "tempo.resourceName" (dict "ctx" . "component" "query-frontend") {{"}}"}}:9095 + ingester: + lifecycler: + ring: + replication_factor: 1 + memberlist: + abort_if_cluster_join_fails: false + join_members: + - {{"{{"}} include "tempo.fullname" . {{"}}"}}-memberlist + overrides: + per_tenant_override_config: /runtime-config/overrides.yaml + server: + http_listen_port: 3100 + storage: + trace: + backend: s3 + s3: + access_key: tempo + bucket: + endpoint: minio:9000 + insecure: true + secret_key: supersecret + pool: + queue_depth: 2000 + wal: + path: /var/tempo/wal + memcached: + consistent_hash: true + host: a-tempo-distributed-memcached + service: memcached-client + timeout: 500ms +``` diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/.helmignore b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/.helmignore new file mode 100644 index 0000000..50af031 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/.helmignore @@ -0,0 +1,22 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/Chart.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/Chart.yaml new file mode 100644 index 0000000..81d9994 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/Chart.yaml @@ -0,0 +1,13 @@ +apiVersion: v2 +appVersion: 0.25.1 +description: A Helm chart for Grafana Agent Operator +home: https://grafana.com/docs/agent/latest/ +icon: https://raw.githubusercontent.com/grafana/agent/v0.25.1/docs/assets/logo_and_name.png +maintainers: +- email: grafana-agent-team@googlegroups.com + name: Grafana Agent Team +name: grafana-agent-operator +sources: +- https://github.com/grafana/agent/tree/v0.25.1/pkg/operator +type: application +version: 0.2.2 diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/README.md b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/README.md new file mode 100644 index 0000000..878e915 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/README.md @@ -0,0 +1,75 @@ +# grafana-agent-operator + +![Version: 0.2.2](https://img.shields.io/badge/Version-0.2.2-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 0.25.1](https://img.shields.io/badge/AppVersion-0.25.1-informational?style=flat-square) + +A Helm chart for Grafana Agent Operator + +⚠️ **Please create issues relating to this Helm chart in the [Agent](https://github.com/grafana/agent/issues) repo.** + +## Source Code + +* + +Note that this chart does not provision custom resources like `GrafanaAgent` and `MetricsInstance` (formerly `PrometheusInstance`) or any `*Monitor` resources. + +To learn how to deploy these resources, please see Grafana's [Agent Operator getting started guide](https://grafana.com/docs/agent/latest/operator/getting-started/). + +## CRDs + +The CRDs are synced into this chart manually (for now) from the Grafana Agent [GitHub repo](https://github.com/grafana/agent/tree/main/production/operator/crds). To learn more about how Helm manages CRDs, please see [Custom Resource Definitions](https://helm.sh/docs/chart_best_practices/custom_resource_definitions/) from the Helm docs. + +## Get Repo Info + +```console +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update +``` + +_See [helm repo](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```console +helm install my-release grafana/grafana-agent-operator +``` + +## Uninstalling the Chart + +To uninstall/delete the my-release deployment: + +```console +helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + +## Upgrading an existing Release to a new major version + +A major chart version change (like v1.2.3 -> v2.0.0) indicates that there is an incompatible breaking change needing manual actions. Until this chart's version reaches `v1.0`, there are no promises of backwards compatibility. + +## Values + +| Key | Type | Default | Description | +|-----|------|---------|-------------| +| affinity | object | `{}` | Pod affinity configuration | +| annotations | object | `{}` | Annotations for the Deployment | +| extraArgs | list | `[]` | List of additional cli arguments to configure agent-operator (example: `--log.level`) | +| fullnameOverride | string | `""` | Overrides the chart's computed fullname | +| image.pullPolicy | string | `"IfNotPresent"` | Image pull policy | +| image.pullSecrets | list | `[]` | Image pull secrets | +| image.registry | string | `"docker.io"` | Image registry | +| image.repository | string | `"grafana/agent-operator"` | Image repo | +| image.tag | string | `"v0.25.1"` | Image tag | +| kubeletService | object | `{"namespace":"default","serviceName":"kubelet"}` | If both are set, Agent Operator will create and maintain a service for scraping kubelets https://grafana.com/docs/agent/latest/operator/getting-started/#monitor-kubelets | +| nameOverride | string | `""` | Overrides the chart's name | +| nodeSelector | object | `{}` | nodeSelector configuration | +| podAnnotations | object | `{}` | Annotations for the Deployment Pods | +| podLabels | object | `{}` | Annotations for the Deployment Pods | +| podSecurityContext | object | `{}` | Pod security context (runAsUser, etc.) | +| rbac | object | `{"create":true}` | Toggle to create ClusterRole and ClusterRoleBinding | +| resources | object | `{}` | Resource limits and requests config | +| serviceAccount.create | bool | `true` | Toggle to create ServiceAccount | +| serviceAccount.name | string | `nil` | Service account name | +| tolerations | list | `[]` | Tolerations applied to Pods | diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/README.md.gotmpl b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/README.md.gotmpl new file mode 100644 index 0000000..5b08d32 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/README.md.gotmpl @@ -0,0 +1,52 @@ +{{ template "chart.header" . }} + +{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }} + +{{ template "chart.description" . }} + +⚠️ **Please create issues relating to this Helm chart in the [Agent](https://github.com/grafana/agent/issues) repo.** + +{{ template "chart.sourcesSection" . }} + +{{ template "chart.requirementsSection" . }} + +Note that this chart does not provision custom resources like `GrafanaAgent` and `MetricsInstance` (formerly `PrometheusInstance`) or any `*Monitor` resources. + +To learn how to deploy these resources, please see Grafana's [Agent Operator getting started guide](https://grafana.com/docs/agent/latest/operator/getting-started/). + +## CRDs + +The CRDs are synced into this chart manually (for now) from the Grafana Agent [GitHub repo](https://github.com/grafana/agent/tree/main/production/operator/crds). To learn more about how Helm manages CRDs, please see [Custom Resource Definitions](https://helm.sh/docs/chart_best_practices/custom_resource_definitions/) from the Helm docs. + +## Get Repo Info + +```console +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update +``` + +_See [helm repo](https://helm.sh/docs/helm/helm_repo/) for command documentation._ + +## Installing the Chart + +To install the chart with the release name `my-release`: + +```console +helm install my-release grafana/grafana-agent-operator +``` + +## Uninstalling the Chart + +To uninstall/delete the my-release deployment: + +```console +helm delete my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. + +## Upgrading an existing Release to a new major version + +A major chart version change (like v1.2.3 -> v2.0.0) indicates that there is an incompatible breaking change needing manual actions. Until this chart's version reaches `v1.0`, there are no promises of backwards compatibility. + +{{ template "chart.valuesSection" . }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_podmonitors.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_podmonitors.yaml new file mode 100644 index 0000000..825a2da --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_podmonitors.yaml @@ -0,0 +1,612 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.8.0 + creationTimestamp: null + name: podmonitors.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + categories: + - prometheus-operator + kind: PodMonitor + listKind: PodMonitorList + plural: podmonitors + singular: podmonitor + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + description: PodMonitor defines monitoring for a set of pods. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation + of an object. Servers should convert recognized schemas to the latest + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this + object represents. Servers may infer this from the endpoint the client + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Specification of desired Pod selection for target discovery + by Prometheus. + properties: + jobLabel: + description: The label to use to retrieve the job name from. + type: string + labelLimit: + description: Per-scrape limit on number of labels that will be accepted + for a sample. Only valid in Prometheus versions 2.27.0 and newer. + format: int64 + type: integer + labelNameLengthLimit: + description: Per-scrape limit on length of labels name that will be + accepted for a sample. Only valid in Prometheus versions 2.27.0 + and newer. + format: int64 + type: integer + labelValueLengthLimit: + description: Per-scrape limit on length of labels value that will + be accepted for a sample. Only valid in Prometheus versions 2.27.0 + and newer. + format: int64 + type: integer + namespaceSelector: + description: Selector to select which namespaces the Endpoints objects + are discovered from. + properties: + any: + description: Boolean describing whether all namespaces are selected + in contrast to a list restricting them. + type: boolean + matchNames: + description: List of namespace names to select from. + items: + type: string + type: array + type: object + podMetricsEndpoints: + description: A list of endpoints allowed as part of this PodMonitor. + items: + description: PodMetricsEndpoint defines a scrapeable endpoint of + a Kubernetes Pod serving Prometheus metrics. + properties: + authorization: + description: Authorization section for this endpoint + properties: + credentials: + description: The secret's key that contains the credentials + of the request + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + type: + description: Set the authentication type. Defaults to Bearer, + Basic will cause an error + type: string + type: object + basicAuth: + description: 'BasicAuth allow an endpoint to authenticate over + basic authentication. More info: https://prometheus.io/docs/operating/configuration/#endpoint' + properties: + password: + description: The secret in the service monitor namespace + that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace + that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + type: object + bearerTokenSecret: + description: Secret to mount to read bearer token for scraping + targets. The secret needs to be in the same namespace as the + pod monitor and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + followRedirects: + description: FollowRedirects configures whether scrape requests + follow HTTP 3xx redirects. + type: boolean + honorLabels: + description: HonorLabels chooses the metric's labels on collisions + with target labels. + type: boolean + honorTimestamps: + description: HonorTimestamps controls whether Prometheus respects + the timestamps present in scraped data. + type: boolean + interval: + description: Interval at which metrics should be scraped + type: string + metricRelabelings: + description: MetricRelabelConfigs to apply to samples before + ingestion. + items: + description: 'RelabelConfig allows dynamic rewriting of the + label set, being applied to samples before ingestion. It + defines ``-section of Prometheus + configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. + Default is 'replace' + enum: + - replace + - keep + - drop + - hashmod + - labelmap + - labeldrop + - labelkeep + type: string + modulus: + description: Modulus to take of the hash of the source + label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted + value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace + is performed if the regular expression matches. Regex + capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source + label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing + labels. Their content is concatenated using the configured + separator and matched against the configured regular + expression for the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label name + which may only contain ASCII letters, numbers, as + well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written + in a replace action. It is mandatory for replace actions. + Regex capture groups are available. + type: string + type: object + type: array + oauth2: + description: OAuth2 for the URL. Only valid in Prometheus versions + 2.27.0 and newer. + properties: + clientId: + description: The secret or configmap containing the OAuth2 + client id + properties: + configMap: + description: ConfigMap containing data to use for the + targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or its + key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + params: + additionalProperties: + items: + type: string + type: array + description: Optional HTTP URL parameters + type: object + path: + description: HTTP path to scrape for metrics. + type: string + port: + description: Name of the pod port this endpoint refers to. Mutually + exclusive with targetPort. + type: string + proxyUrl: + description: ProxyURL eg http://proxyserver:2195 Directs scrapes + to proxy through this endpoint. + type: string + relabelings: + description: 'RelabelConfigs to apply to samples before scraping. + Prometheus Operator automatically adds relabelings for a few + standard Kubernetes fields. The original scrape job''s name + is available via the `__tmp_prometheus_job_name` label. More + info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config' + items: + description: 'RelabelConfig allows dynamic rewriting of the + label set, being applied to samples before ingestion. It + defines ``-section of Prometheus + configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. + Default is 'replace' + enum: + - replace + - keep + - drop + - hashmod + - labelmap + - labeldrop + - labelkeep + type: string + modulus: + description: Modulus to take of the hash of the source + label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted + value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace + is performed if the regular expression matches. Regex + capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source + label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing + labels. Their content is concatenated using the configured + separator and matched against the configured regular + expression for the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label name + which may only contain ASCII letters, numbers, as + well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written + in a replace action. It is mandatory for replace actions. + Regex capture groups are available. + type: string + type: object + type: array + scheme: + description: HTTP scheme to use for scraping. + type: string + scrapeTimeout: + description: Timeout after which the scrape is ended + type: string + targetPort: + anyOf: + - type: integer + - type: string + description: 'Deprecated: Use ''port'' instead.' + x-kubernetes-int-or-string: true + tlsConfig: + description: TLS configuration to use when scraping the endpoint. + properties: + ca: + description: Struct containing the CA cert to use for the + targets. + properties: + configMap: + description: ConfigMap containing data to use for the + targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or its + key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + cert: + description: Struct containing the client cert file for + the targets. + properties: + configMap: + description: ConfigMap containing data to use for the + targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or its + key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the + targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + type: array + podTargetLabels: + description: PodTargetLabels transfers labels on the Kubernetes Pod + onto the target. + items: + type: string + type: array + sampleLimit: + description: SampleLimit defines per-scrape limit on number of scraped + samples that will be accepted. + format: int64 + type: integer + selector: + description: Selector to select Pod objects. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: A label selector requirement is a selector that + contains values, a key, and an operator that relates the key + and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: operator represents a key's relationship to + a set of values. Valid operators are In, NotIn, Exists + and DoesNotExist. + type: string + values: + description: values is an array of string values. If the + operator is In or NotIn, the values array must be non-empty. + If the operator is Exists or DoesNotExist, the values + array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single + {key,value} in the matchLabels map is equivalent to an element + of matchExpressions, whose key field is "key", the operator + is "In", and the values array contains only "value". The requirements + are ANDed. + type: object + type: object + targetLimit: + description: TargetLimit defines a limit on the number of scraped + targets that will be accepted. + format: int64 + type: integer + required: + - podMetricsEndpoints + - selector + type: object + required: + - spec + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_probes.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_probes.yaml new file mode 100644 index 0000000..259f5a4 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_probes.yaml @@ -0,0 +1,654 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.8.0 + creationTimestamp: null + name: probes.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + categories: + - prometheus-operator + kind: Probe + listKind: ProbeList + plural: probes + singular: probe + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + description: Probe defines monitoring for a set of static targets or ingresses. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation + of an object. Servers should convert recognized schemas to the latest + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this + object represents. Servers may infer this from the endpoint the client + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Specification of desired Ingress selection for target discovery + by Prometheus. + properties: + authorization: + description: Authorization section for this endpoint + properties: + credentials: + description: The secret's key that contains the credentials of + the request + properties: + key: + description: The key of the secret to select from. Must be + a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be + defined + type: boolean + required: + - key + type: object + type: + description: Set the authentication type. Defaults to Bearer, + Basic will cause an error + type: string + type: object + basicAuth: + description: 'BasicAuth allow an endpoint to authenticate over basic + authentication. More info: https://prometheus.io/docs/operating/configuration/#endpoint' + properties: + password: + description: The secret in the service monitor namespace that + contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be + a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be + defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that + contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be + a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be + defined + type: boolean + required: + - key + type: object + type: object + bearerTokenSecret: + description: Secret to mount to read bearer token for scraping targets. + The secret needs to be in the same namespace as the probe and accessible + by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a + valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + interval: + description: Interval at which targets are probed using the configured + prober. If not specified Prometheus' global scrape interval is used. + type: string + jobName: + description: The job name assigned to scraped metrics by default. + type: string + labelLimit: + description: Per-scrape limit on number of labels that will be accepted + for a sample. Only valid in Prometheus versions 2.27.0 and newer. + format: int64 + type: integer + labelNameLengthLimit: + description: Per-scrape limit on length of labels name that will be + accepted for a sample. Only valid in Prometheus versions 2.27.0 + and newer. + format: int64 + type: integer + labelValueLengthLimit: + description: Per-scrape limit on length of labels value that will + be accepted for a sample. Only valid in Prometheus versions 2.27.0 + and newer. + format: int64 + type: integer + metricRelabelings: + description: MetricRelabelConfigs to apply to samples before ingestion. + items: + description: 'RelabelConfig allows dynamic rewriting of the label + set, being applied to samples before ingestion. It defines ``-section + of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. Default + is 'replace' + enum: + - replace + - keep + - drop + - hashmod + - labelmap + - labeldrop + - labelkeep + type: string + modulus: + description: Modulus to take of the hash of the source label + values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted + value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace + is performed if the regular expression matches. Regex capture + groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label + values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. + Their content is concatenated using the configured separator + and matched against the configured regular expression for + the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label name which + may only contain ASCII letters, numbers, as well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in + a replace action. It is mandatory for replace actions. Regex + capture groups are available. + type: string + type: object + type: array + module: + description: 'The module to use for probing specifying how to probe + the target. Example module configuring in the blackbox exporter: + https://github.com/prometheus/blackbox_exporter/blob/master/example.yml' + type: string + oauth2: + description: OAuth2 for the URL. Only valid in Prometheus versions + 2.27.0 and newer. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client + id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key + must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be + a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be + defined + type: boolean + required: + - key + type: object + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + prober: + description: Specification for the prober to use for probing targets. + The prober.URL parameter is required. Targets cannot be probed if + left empty. + properties: + path: + description: Path to collect metrics from. Defaults to `/probe`. + type: string + proxyUrl: + description: Optional ProxyURL. + type: string + scheme: + description: HTTP scheme to use for scraping. Defaults to `http`. + type: string + url: + description: Mandatory URL of the prober. + type: string + required: + - url + type: object + sampleLimit: + description: SampleLimit defines per-scrape limit on number of scraped + samples that will be accepted. + format: int64 + type: integer + scrapeTimeout: + description: Timeout for scraping metrics from the Prometheus exporter. + type: string + targetLimit: + description: TargetLimit defines a limit on the number of scraped + targets that will be accepted. + format: int64 + type: integer + targets: + description: Targets defines a set of static or dynamically discovered + targets to probe. + properties: + ingress: + description: ingress defines the Ingress objects to probe and + the relabeling configuration. If `staticConfig` is also defined, + `staticConfig` takes precedence. + properties: + namespaceSelector: + description: From which namespaces to select Ingress objects. + properties: + any: + description: Boolean describing whether all namespaces + are selected in contrast to a list restricting them. + type: boolean + matchNames: + description: List of namespace names to select from. + items: + type: string + type: array + type: object + relabelingConfigs: + description: 'RelabelConfigs to apply to the label set of + the target before it gets scraped. The original ingress + address is available via the `__tmp_prometheus_ingress_address` + label. It can be used to customize the probed URL. The original + scrape job''s name is available via the `__tmp_prometheus_job_name` + label. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config' + items: + description: 'RelabelConfig allows dynamic rewriting of + the label set, being applied to samples before ingestion. + It defines ``-section of Prometheus + configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. + Default is 'replace' + enum: + - replace + - keep + - drop + - hashmod + - labelmap + - labeldrop + - labelkeep + type: string + modulus: + description: Modulus to take of the hash of the source + label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted + value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex + replace is performed if the regular expression matches. + Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source + label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing + labels. Their content is concatenated using the configured + separator and matched against the configured regular + expression for the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label + name which may only contain ASCII letters, numbers, + as well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written + in a replace action. It is mandatory for replace actions. + Regex capture groups are available. + type: string + type: object + type: array + selector: + description: Selector to select the Ingress objects. + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector + that contains values, a key, and an operator that + relates the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are In, NotIn, + Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. + If the operator is In or NotIn, the values array + must be non-empty. If the operator is Exists or + DoesNotExist, the values array must be empty. + This array is replaced during a strategic merge + patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. + A single {key,value} in the matchLabels map is equivalent + to an element of matchExpressions, whose key field is + "key", the operator is "In", and the values array contains + only "value". The requirements are ANDed. + type: object + type: object + type: object + staticConfig: + description: 'staticConfig defines the static list of targets + to probe and the relabeling configuration. If `ingress` is also + defined, `staticConfig` takes precedence. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config.' + properties: + labels: + additionalProperties: + type: string + description: Labels assigned to all metrics scraped from the + targets. + type: object + relabelingConfigs: + description: 'RelabelConfigs to apply to the label set of + the targets before it gets scraped. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config' + items: + description: 'RelabelConfig allows dynamic rewriting of + the label set, being applied to samples before ingestion. + It defines ``-section of Prometheus + configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. + Default is 'replace' + enum: + - replace + - keep + - drop + - hashmod + - labelmap + - labeldrop + - labelkeep + type: string + modulus: + description: Modulus to take of the hash of the source + label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted + value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex + replace is performed if the regular expression matches. + Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source + label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing + labels. Their content is concatenated using the configured + separator and matched against the configured regular + expression for the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label + name which may only contain ASCII letters, numbers, + as well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written + in a replace action. It is mandatory for replace actions. + Regex capture groups are available. + type: string + type: object + type: array + static: + description: The list of hosts to probe. + items: + type: string + type: array + type: object + type: object + tlsConfig: + description: TLS configuration to use when scraping the endpoint. + properties: + ca: + description: Struct containing the CA cert to use for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key + must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + type: object + cert: + description: Struct containing the client cert file for the targets. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key + must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be + a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be + defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + required: + - spec + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_servicemonitors.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_servicemonitors.yaml new file mode 100644 index 0000000..8f8f8ae --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.coreos.com_servicemonitors.yaml @@ -0,0 +1,638 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.8.0 + creationTimestamp: null + name: servicemonitors.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + categories: + - prometheus-operator + kind: ServiceMonitor + listKind: ServiceMonitorList + plural: servicemonitors + singular: servicemonitor + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + description: ServiceMonitor defines monitoring for a set of services. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation + of an object. Servers should convert recognized schemas to the latest + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this + object represents. Servers may infer this from the endpoint the client + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Specification of desired Service selection for target discovery + by Prometheus. + properties: + endpoints: + description: A list of endpoints allowed as part of this ServiceMonitor. + items: + description: Endpoint defines a scrapeable endpoint serving Prometheus + metrics. + properties: + authorization: + description: Authorization section for this endpoint + properties: + credentials: + description: The secret's key that contains the credentials + of the request + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + type: + description: Set the authentication type. Defaults to Bearer, + Basic will cause an error + type: string + type: object + basicAuth: + description: 'BasicAuth allow an endpoint to authenticate over + basic authentication More info: https://prometheus.io/docs/operating/configuration/#endpoints' + properties: + password: + description: The secret in the service monitor namespace + that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace + that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + type: object + bearerTokenFile: + description: File to read bearer token for scraping targets. + type: string + bearerTokenSecret: + description: Secret to mount to read bearer token for scraping + targets. The secret needs to be in the same namespace as the + service monitor and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + followRedirects: + description: FollowRedirects configures whether scrape requests + follow HTTP 3xx redirects. + type: boolean + honorLabels: + description: HonorLabels chooses the metric's labels on collisions + with target labels. + type: boolean + honorTimestamps: + description: HonorTimestamps controls whether Prometheus respects + the timestamps present in scraped data. + type: boolean + interval: + description: Interval at which metrics should be scraped + type: string + metricRelabelings: + description: MetricRelabelConfigs to apply to samples before + ingestion. + items: + description: 'RelabelConfig allows dynamic rewriting of the + label set, being applied to samples before ingestion. It + defines ``-section of Prometheus + configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. + Default is 'replace' + enum: + - replace + - keep + - drop + - hashmod + - labelmap + - labeldrop + - labelkeep + type: string + modulus: + description: Modulus to take of the hash of the source + label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted + value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace + is performed if the regular expression matches. Regex + capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source + label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing + labels. Their content is concatenated using the configured + separator and matched against the configured regular + expression for the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label name + which may only contain ASCII letters, numbers, as + well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written + in a replace action. It is mandatory for replace actions. + Regex capture groups are available. + type: string + type: object + type: array + oauth2: + description: OAuth2 for the URL. Only valid in Prometheus versions + 2.27.0 and newer. + properties: + clientId: + description: The secret or configmap containing the OAuth2 + client id + properties: + configMap: + description: ConfigMap containing data to use for the + targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or its + key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + params: + additionalProperties: + items: + type: string + type: array + description: Optional HTTP URL parameters + type: object + path: + description: HTTP path to scrape for metrics. + type: string + port: + description: Name of the service port this endpoint refers to. + Mutually exclusive with targetPort. + type: string + proxyUrl: + description: ProxyURL eg http://proxyserver:2195 Directs scrapes + to proxy through this endpoint. + type: string + relabelings: + description: 'RelabelConfigs to apply to samples before scraping. + Prometheus Operator automatically adds relabelings for a few + standard Kubernetes fields. The original scrape job''s name + is available via the `__tmp_prometheus_job_name` label. More + info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config' + items: + description: 'RelabelConfig allows dynamic rewriting of the + label set, being applied to samples before ingestion. It + defines ``-section of Prometheus + configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. + Default is 'replace' + enum: + - replace + - keep + - drop + - hashmod + - labelmap + - labeldrop + - labelkeep + type: string + modulus: + description: Modulus to take of the hash of the source + label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted + value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace + is performed if the regular expression matches. Regex + capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source + label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing + labels. Their content is concatenated using the configured + separator and matched against the configured regular + expression for the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label name + which may only contain ASCII letters, numbers, as + well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written + in a replace action. It is mandatory for replace actions. + Regex capture groups are available. + type: string + type: object + type: array + scheme: + description: HTTP scheme to use for scraping. + type: string + scrapeTimeout: + description: Timeout after which the scrape is ended + type: string + targetPort: + anyOf: + - type: integer + - type: string + description: Name or number of the target port of the Pod behind + the Service, the port must be specified with container port + property. Mutually exclusive with port. + x-kubernetes-int-or-string: true + tlsConfig: + description: TLS configuration to use when scraping the endpoint + properties: + ca: + description: Struct containing the CA cert to use for the + targets. + properties: + configMap: + description: ConfigMap containing data to use for the + targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or its + key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container + to use for the targets. + type: string + cert: + description: Struct containing the client cert file for + the targets. + properties: + configMap: + description: ConfigMap containing data to use for the + targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or its + key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus + container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus + container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the + targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + type: array + jobLabel: + description: "Chooses the label of the Kubernetes `Endpoints`. Its + value will be used for the `job`-label's value of the created metrics. + \n Default & fallback value: the name of the respective Kubernetes + `Endpoint`." + type: string + labelLimit: + description: Per-scrape limit on number of labels that will be accepted + for a sample. Only valid in Prometheus versions 2.27.0 and newer. + format: int64 + type: integer + labelNameLengthLimit: + description: Per-scrape limit on length of labels name that will be + accepted for a sample. Only valid in Prometheus versions 2.27.0 + and newer. + format: int64 + type: integer + labelValueLengthLimit: + description: Per-scrape limit on length of labels value that will + be accepted for a sample. Only valid in Prometheus versions 2.27.0 + and newer. + format: int64 + type: integer + namespaceSelector: + description: Selector to select which namespaces the Kubernetes Endpoints + objects are discovered from. + properties: + any: + description: Boolean describing whether all namespaces are selected + in contrast to a list restricting them. + type: boolean + matchNames: + description: List of namespace names to select from. + items: + type: string + type: array + type: object + podTargetLabels: + description: PodTargetLabels transfers labels on the Kubernetes `Pod` + onto the created metrics. + items: + type: string + type: array + sampleLimit: + description: SampleLimit defines per-scrape limit on number of scraped + samples that will be accepted. + format: int64 + type: integer + selector: + description: Selector to select Endpoints objects. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: A label selector requirement is a selector that + contains values, a key, and an operator that relates the key + and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: operator represents a key's relationship to + a set of values. Valid operators are In, NotIn, Exists + and DoesNotExist. + type: string + values: + description: values is an array of string values. If the + operator is In or NotIn, the values array must be non-empty. + If the operator is Exists or DoesNotExist, the values + array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single + {key,value} in the matchLabels map is equivalent to an element + of matchExpressions, whose key field is "key", the operator + is "In", and the values array contains only "value". The requirements + are ANDed. + type: object + type: object + targetLabels: + description: TargetLabels transfers labels from the Kubernetes `Service` + onto the created metrics. + items: + type: string + type: array + targetLimit: + description: TargetLimit defines a limit on the number of scraped + targets that will be accepted. + format: int64 + type: integer + required: + - endpoints + - selector + type: object + required: + - spec + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_grafanaagents.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_grafanaagents.yaml new file mode 100644 index 0000000..69a5abc --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_grafanaagents.yaml @@ -0,0 +1,7087 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.8.0 + creationTimestamp: null + name: grafanaagents.monitoring.grafana.com +spec: + group: monitoring.grafana.com + names: + categories: + - agent-operator + kind: GrafanaAgent + listKind: GrafanaAgentList + plural: grafanaagents + singular: grafanaagent + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: GrafanaAgent defines a Grafana Agent deployment. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation + of an object. Servers should convert recognized schemas to the latest + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this + object represents. Servers may infer this from the endpoint the client + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Spec holds the specification of the desired behavior for + the Grafana Agent cluster. + properties: + affinity: + description: Affinity, if specified, controls pod scheduling constraints. + properties: + nodeAffinity: + description: Describes node affinity scheduling rules for the + pod. + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to + nodes that satisfy the affinity expressions specified by + this field, but it may choose a node that violates one or + more of the expressions. The node that is most preferred + is the one with the greatest sum of weights, i.e. for each + node that meets all of the scheduling requirements (resource + request, requiredDuringScheduling affinity expressions, + etc.), compute a sum by iterating through the elements of + this field and adding "weight" to the sum if the node matches + the corresponding matchExpressions; the node(s) with the + highest sum are the most preferred. + items: + description: An empty preferred scheduling term matches + all objects with implicit weight 0 (i.e. it's a no-op). + A null preferred scheduling term matches no objects (i.e. + is also a no-op). + properties: + preference: + description: A node selector term, associated with the + corresponding weight. + properties: + matchExpressions: + description: A list of node selector requirements + by node's labels. + items: + description: A node selector requirement is a + selector that contains values, a key, and an + operator that relates the key and values. + properties: + key: + description: The label key that the selector + applies to. + type: string + operator: + description: Represents a key's relationship + to a set of values. Valid operators are + In, NotIn, Exists, DoesNotExist. Gt, and + Lt. + type: string + values: + description: An array of string values. If + the operator is In or NotIn, the values + array must be non-empty. If the operator + is Exists or DoesNotExist, the values array + must be empty. If the operator is Gt or + Lt, the values array must have a single + element, which will be interpreted as an + integer. This array is replaced during a + strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + description: A list of node selector requirements + by node's fields. + items: + description: A node selector requirement is a + selector that contains values, a key, and an + operator that relates the key and values. + properties: + key: + description: The label key that the selector + applies to. + type: string + operator: + description: Represents a key's relationship + to a set of values. Valid operators are + In, NotIn, Exists, DoesNotExist. Gt, and + Lt. + type: string + values: + description: An array of string values. If + the operator is In or NotIn, the values + array must be non-empty. If the operator + is Exists or DoesNotExist, the values array + must be empty. If the operator is Gt or + Lt, the values array must have a single + element, which will be interpreted as an + integer. This array is replaced during a + strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + weight: + description: Weight associated with matching the corresponding + nodeSelectorTerm, in the range 1-100. + format: int32 + type: integer + required: + - preference + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this + field are not met at scheduling time, the pod will not be + scheduled onto the node. If the affinity requirements specified + by this field cease to be met at some point during pod execution + (e.g. due to an update), the system may or may not try to + eventually evict the pod from its node. + properties: + nodeSelectorTerms: + description: Required. A list of node selector terms. + The terms are ORed. + items: + description: A null or empty node selector term matches + no objects. The requirements of them are ANDed. The + TopologySelectorTerm type implements a subset of the + NodeSelectorTerm. + properties: + matchExpressions: + description: A list of node selector requirements + by node's labels. + items: + description: A node selector requirement is a + selector that contains values, a key, and an + operator that relates the key and values. + properties: + key: + description: The label key that the selector + applies to. + type: string + operator: + description: Represents a key's relationship + to a set of values. Valid operators are + In, NotIn, Exists, DoesNotExist. Gt, and + Lt. + type: string + values: + description: An array of string values. If + the operator is In or NotIn, the values + array must be non-empty. If the operator + is Exists or DoesNotExist, the values array + must be empty. If the operator is Gt or + Lt, the values array must have a single + element, which will be interpreted as an + integer. This array is replaced during a + strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + description: A list of node selector requirements + by node's fields. + items: + description: A node selector requirement is a + selector that contains values, a key, and an + operator that relates the key and values. + properties: + key: + description: The label key that the selector + applies to. + type: string + operator: + description: Represents a key's relationship + to a set of values. Valid operators are + In, NotIn, Exists, DoesNotExist. Gt, and + Lt. + type: string + values: + description: An array of string values. If + the operator is In or NotIn, the values + array must be non-empty. If the operator + is Exists or DoesNotExist, the values array + must be empty. If the operator is Gt or + Lt, the values array must have a single + element, which will be interpreted as an + integer. This array is replaced during a + strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + type: array + required: + - nodeSelectorTerms + type: object + type: object + podAffinity: + description: Describes pod affinity scheduling rules (e.g. co-locate + this pod in the same node, zone, etc. as some other pod(s)). + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to + nodes that satisfy the affinity expressions specified by + this field, but it may choose a node that violates one or + more of the expressions. The node that is most preferred + is the one with the greatest sum of weights, i.e. for each + node that meets all of the scheduling requirements (resource + request, requiredDuringScheduling affinity expressions, + etc.), compute a sum by iterating through the elements of + this field and adding "weight" to the sum if the node has + pods which matches the corresponding podAffinityTerm; the + node(s) with the highest sum are the most preferred. + items: + description: The weights of all of the matched WeightedPodAffinityTerm + fields are added per-node to find the most preferred node(s) + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated + with the corresponding weight. + properties: + labelSelector: + description: A label query over a set of resources, + in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label + selector requirements. The requirements are + ANDed. + items: + description: A label selector requirement + is a selector that contains values, a key, + and an operator that relates the key and + values. + properties: + key: + description: key is the label key that + the selector applies to. + type: string + operator: + description: operator represents a key's + relationship to a set of values. Valid + operators are In, NotIn, Exists and + DoesNotExist. + type: string + values: + description: values is an array of string + values. If the operator is In or NotIn, + the values array must be non-empty. + If the operator is Exists or DoesNotExist, + the values array must be empty. This + array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} + pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, + whose key field is "key", the operator is + "In", and the values array contains only "value". + The requirements are ANDed. + type: object + type: object + namespaceSelector: + description: A label query over the set of namespaces + that the term applies to. The term is applied + to the union of the namespaces selected by this + field and the ones listed in the namespaces field. + null selector and null or empty namespaces list + means "this pod's namespace". An empty selector + ({}) matches all namespaces. This field is beta-level + and is only honored when PodAffinityNamespaceSelector + feature is enabled. + properties: + matchExpressions: + description: matchExpressions is a list of label + selector requirements. The requirements are + ANDed. + items: + description: A label selector requirement + is a selector that contains values, a key, + and an operator that relates the key and + values. + properties: + key: + description: key is the label key that + the selector applies to. + type: string + operator: + description: operator represents a key's + relationship to a set of values. Valid + operators are In, NotIn, Exists and + DoesNotExist. + type: string + values: + description: values is an array of string + values. If the operator is In or NotIn, + the values array must be non-empty. + If the operator is Exists or DoesNotExist, + the values array must be empty. This + array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} + pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, + whose key field is "key", the operator is + "In", and the values array contains only "value". + The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies a static list + of namespace names that the term applies to. The + term is applied to the union of the namespaces + listed in this field and the ones selected by + namespaceSelector. null or empty namespaces list + and null namespaceSelector means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) + or not co-located (anti-affinity) with the pods + matching the labelSelector in the specified namespaces, + where co-located is defined as running on a node + whose value of the label with key topologyKey + matches that of any node on which any of the selected + pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + weight: + description: weight associated with matching the corresponding + podAffinityTerm, in the range 1-100. + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this + field are not met at scheduling time, the pod will not be + scheduled onto the node. If the affinity requirements specified + by this field cease to be met at some point during pod execution + (e.g. due to a pod label update), the system may or may + not try to eventually evict the pod from its node. When + there are multiple elements, the lists of nodes corresponding + to each podAffinityTerm are intersected, i.e. all terms + must be satisfied. + items: + description: Defines a set of pods (namely those matching + the labelSelector relative to the given namespace(s)) + that this pod should be co-located (affinity) or not co-located + (anti-affinity) with, where co-located is defined as running + on a node whose value of the label with key + matches that of any node on which a pod of the set of + pods is running + properties: + labelSelector: + description: A label query over a set of resources, + in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label + selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a + selector that contains values, a key, and an + operator that relates the key and values. + properties: + key: + description: key is the label key that the + selector applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are + In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string + values. If the operator is In or NotIn, + the values array must be non-empty. If the + operator is Exists or DoesNotExist, the + values array must be empty. This array is + replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} + pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, + whose key field is "key", the operator is "In", + and the values array contains only "value". The + requirements are ANDed. + type: object + type: object + namespaceSelector: + description: A label query over the set of namespaces + that the term applies to. The term is applied to the + union of the namespaces selected by this field and + the ones listed in the namespaces field. null selector + and null or empty namespaces list means "this pod's + namespace". An empty selector ({}) matches all namespaces. + This field is beta-level and is only honored when + PodAffinityNamespaceSelector feature is enabled. + properties: + matchExpressions: + description: matchExpressions is a list of label + selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a + selector that contains values, a key, and an + operator that relates the key and values. + properties: + key: + description: key is the label key that the + selector applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are + In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string + values. If the operator is In or NotIn, + the values array must be non-empty. If the + operator is Exists or DoesNotExist, the + values array must be empty. This array is + replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} + pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, + whose key field is "key", the operator is "In", + and the values array contains only "value". The + requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies a static list of namespace + names that the term applies to. The term is applied + to the union of the namespaces listed in this field + and the ones selected by namespaceSelector. null or + empty namespaces list and null namespaceSelector means + "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) + or not co-located (anti-affinity) with the pods matching + the labelSelector in the specified namespaces, where + co-located is defined as running on a node whose value + of the label with key topologyKey matches that of + any node on which any of the selected pods is running. + Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + type: array + type: object + podAntiAffinity: + description: Describes pod anti-affinity scheduling rules (e.g. + avoid putting this pod in the same node, zone, etc. as some + other pod(s)). + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to + nodes that satisfy the anti-affinity expressions specified + by this field, but it may choose a node that violates one + or more of the expressions. The node that is most preferred + is the one with the greatest sum of weights, i.e. for each + node that meets all of the scheduling requirements (resource + request, requiredDuringScheduling anti-affinity expressions, + etc.), compute a sum by iterating through the elements of + this field and adding "weight" to the sum if the node has + pods which matches the corresponding podAffinityTerm; the + node(s) with the highest sum are the most preferred. + items: + description: The weights of all of the matched WeightedPodAffinityTerm + fields are added per-node to find the most preferred node(s) + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated + with the corresponding weight. + properties: + labelSelector: + description: A label query over a set of resources, + in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label + selector requirements. The requirements are + ANDed. + items: + description: A label selector requirement + is a selector that contains values, a key, + and an operator that relates the key and + values. + properties: + key: + description: key is the label key that + the selector applies to. + type: string + operator: + description: operator represents a key's + relationship to a set of values. Valid + operators are In, NotIn, Exists and + DoesNotExist. + type: string + values: + description: values is an array of string + values. If the operator is In or NotIn, + the values array must be non-empty. + If the operator is Exists or DoesNotExist, + the values array must be empty. This + array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} + pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, + whose key field is "key", the operator is + "In", and the values array contains only "value". + The requirements are ANDed. + type: object + type: object + namespaceSelector: + description: A label query over the set of namespaces + that the term applies to. The term is applied + to the union of the namespaces selected by this + field and the ones listed in the namespaces field. + null selector and null or empty namespaces list + means "this pod's namespace". An empty selector + ({}) matches all namespaces. This field is beta-level + and is only honored when PodAffinityNamespaceSelector + feature is enabled. + properties: + matchExpressions: + description: matchExpressions is a list of label + selector requirements. The requirements are + ANDed. + items: + description: A label selector requirement + is a selector that contains values, a key, + and an operator that relates the key and + values. + properties: + key: + description: key is the label key that + the selector applies to. + type: string + operator: + description: operator represents a key's + relationship to a set of values. Valid + operators are In, NotIn, Exists and + DoesNotExist. + type: string + values: + description: values is an array of string + values. If the operator is In or NotIn, + the values array must be non-empty. + If the operator is Exists or DoesNotExist, + the values array must be empty. This + array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} + pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, + whose key field is "key", the operator is + "In", and the values array contains only "value". + The requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies a static list + of namespace names that the term applies to. The + term is applied to the union of the namespaces + listed in this field and the ones selected by + namespaceSelector. null or empty namespaces list + and null namespaceSelector means "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) + or not co-located (anti-affinity) with the pods + matching the labelSelector in the specified namespaces, + where co-located is defined as running on a node + whose value of the label with key topologyKey + matches that of any node on which any of the selected + pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + weight: + description: weight associated with matching the corresponding + podAffinityTerm, in the range 1-100. + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the anti-affinity requirements specified by + this field are not met at scheduling time, the pod will + not be scheduled onto the node. If the anti-affinity requirements + specified by this field cease to be met at some point during + pod execution (e.g. due to a pod label update), the system + may or may not try to eventually evict the pod from its + node. When there are multiple elements, the lists of nodes + corresponding to each podAffinityTerm are intersected, i.e. + all terms must be satisfied. + items: + description: Defines a set of pods (namely those matching + the labelSelector relative to the given namespace(s)) + that this pod should be co-located (affinity) or not co-located + (anti-affinity) with, where co-located is defined as running + on a node whose value of the label with key + matches that of any node on which a pod of the set of + pods is running + properties: + labelSelector: + description: A label query over a set of resources, + in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label + selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a + selector that contains values, a key, and an + operator that relates the key and values. + properties: + key: + description: key is the label key that the + selector applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are + In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string + values. If the operator is In or NotIn, + the values array must be non-empty. If the + operator is Exists or DoesNotExist, the + values array must be empty. This array is + replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} + pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, + whose key field is "key", the operator is "In", + and the values array contains only "value". The + requirements are ANDed. + type: object + type: object + namespaceSelector: + description: A label query over the set of namespaces + that the term applies to. The term is applied to the + union of the namespaces selected by this field and + the ones listed in the namespaces field. null selector + and null or empty namespaces list means "this pod's + namespace". An empty selector ({}) matches all namespaces. + This field is beta-level and is only honored when + PodAffinityNamespaceSelector feature is enabled. + properties: + matchExpressions: + description: matchExpressions is a list of label + selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a + selector that contains values, a key, and an + operator that relates the key and values. + properties: + key: + description: key is the label key that the + selector applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are + In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string + values. If the operator is In or NotIn, + the values array must be non-empty. If the + operator is Exists or DoesNotExist, the + values array must be empty. This array is + replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} + pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, + whose key field is "key", the operator is "In", + and the values array contains only "value". The + requirements are ANDed. + type: object + type: object + namespaces: + description: namespaces specifies a static list of namespace + names that the term applies to. The term is applied + to the union of the namespaces listed in this field + and the ones selected by namespaceSelector. null or + empty namespaces list and null namespaceSelector means + "this pod's namespace" + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) + or not co-located (anti-affinity) with the pods matching + the labelSelector in the specified namespaces, where + co-located is defined as running on a node whose value + of the label with key topologyKey matches that of + any node on which any of the selected pods is running. + Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + type: array + type: object + type: object + apiServer: + description: APIServerConfig allows specifying a host and auth methods + to access the Kubernetes API server. If left empty, the Agent will + assume that it is running inside of the cluster and will discover + API servers automatically and use the pod's CA certificate and bearer + token file at /var/run/secrets/kubernetes.io/serviceaccount. + properties: + authorization: + description: Authorization section for accessing apiserver + properties: + credentials: + description: The secret's key that contains the credentials + of the request + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + credentialsFile: + description: File to read a secret from, mutually exclusive + with Credentials (from SafeAuthorization) + type: string + type: + description: Set the authentication type. Defaults to Bearer, + Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth allow an endpoint to authenticate over + basic authentication + properties: + password: + description: The secret in the service monitor namespace that + contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace that + contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + type: object + bearerToken: + description: Bearer token for accessing apiserver. + type: string + bearerTokenFile: + description: File to read bearer token for accessing apiserver. + type: string + host: + description: Host of apiserver. A valid string consisting of a + hostname or IP followed by an optional port number + type: string + tlsConfig: + description: TLS Config to use for accessing apiserver. + properties: + ca: + description: Struct containing the CA cert to use for the + targets. + properties: + configMap: + description: ConfigMap containing data to use for the + targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or its + key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container + to use for the targets. + type: string + cert: + description: Struct containing the client cert file for the + targets. + properties: + configMap: + description: ConfigMap containing data to use for the + targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or its + key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus + container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus + container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the + targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + required: + - host + type: object + configMaps: + description: ConfigMaps is a liset of config maps in the same namespace + as the GrafanaAgent object which will be mounted into each running + Grafana Agent pod. The ConfigMaps are mounted into /etc/grafana-agent/extra-configmaps/. + items: + type: string + type: array + containers: + description: 'Containers allows injecting additional containers or + modifying operator generated containers. This can be used to allow + adding an authentication proxy to a Grafana Agent pod or to change + the behavior of an operator-generated container. Containers described + here modify an operator generated container if they share the same + name and modifications are done via a strategic merge patch. The + current container names are: `grafana-agent` and `config-reloader`. + Overriding containers is entirely outside the scope of what the + Grafana Agent team will support and by doing so, you accept that + this behavior may break at any time without notice.' + items: + description: A single application container that you want to run + within a pod. + properties: + args: + description: 'Arguments to the entrypoint. The docker image''s + CMD is used if this is not provided. Variable references $(VAR_NAME) + are expanded using the container''s environment. If a variable + cannot be resolved, the reference in the input string will + be unchanged. Double $$ are reduced to a single $, which allows + for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will + produce the string literal "$(VAR_NAME)". Escaped references + will never be expanded, regardless of whether the variable + exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + command: + description: 'Entrypoint array. Not executed within a shell. + The docker image''s ENTRYPOINT is used if this is not provided. + Variable references $(VAR_NAME) are expanded using the container''s + environment. If a variable cannot be resolved, the reference + in the input string will be unchanged. Double $$ are reduced + to a single $, which allows for escaping the $(VAR_NAME) syntax: + i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". + Escaped references will never be expanded, regardless of whether + the variable exists or not. Cannot be updated. More info: + https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + env: + description: List of environment variables to set in the container. + Cannot be updated. + items: + description: EnvVar represents an environment variable present + in a Container. + properties: + name: + description: Name of the environment variable. Must be + a C_IDENTIFIER. + type: string + value: + description: 'Variable references $(VAR_NAME) are expanded + using the previously defined environment variables in + the container and any service environment variables. + If a variable cannot be resolved, the reference in the + input string will be unchanged. Double $$ are reduced + to a single $, which allows for escaping the $(VAR_NAME) + syntax: i.e. "$$(VAR_NAME)" will produce the string + literal "$(VAR_NAME)". Escaped references will never + be expanded, regardless of whether the variable exists + or not. Defaults to "".' + type: string + valueFrom: + description: Source for the environment variable's value. + Cannot be used if value is not empty. + properties: + configMapKeyRef: + description: Selects a key of a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or + its key must be defined + type: boolean + required: + - key + type: object + fieldRef: + description: 'Selects a field of the pod: supports + metadata.name, metadata.namespace, `metadata.labels['''']`, + `metadata.annotations['''']`, spec.nodeName, + spec.serviceAccountName, status.hostIP, status.podIP, + status.podIPs.' + properties: + apiVersion: + description: Version of the schema the FieldPath + is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the + specified API version. + type: string + required: + - fieldPath + type: object + resourceFieldRef: + description: 'Selects a resource of the container: + only resources limits and requests (limits.cpu, + limits.memory, limits.ephemeral-storage, requests.cpu, + requests.memory and requests.ephemeral-storage) + are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, + optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the + exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + secretKeyRef: + description: Selects a key of a secret in the pod's + namespace + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its + key must be defined + type: boolean + required: + - key + type: object + type: object + required: + - name + type: object + type: array + envFrom: + description: List of sources to populate environment variables + in the container. The keys defined within a source must be + a C_IDENTIFIER. All invalid keys will be reported as an event + when the container is starting. When a key exists in multiple + sources, the value associated with the last source will take + precedence. Values defined by an Env with a duplicate key + will take precedence. Cannot be updated. + items: + description: EnvFromSource represents the source of a set + of ConfigMaps + properties: + configMapRef: + description: The ConfigMap to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap must be + defined + type: boolean + type: object + prefix: + description: An optional identifier to prepend to each + key in the ConfigMap. Must be a C_IDENTIFIER. + type: string + secretRef: + description: The Secret to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret must be defined + type: boolean + type: object + type: object + type: array + image: + description: 'Docker image name. More info: https://kubernetes.io/docs/concepts/containers/images + This field is optional to allow higher level config management + to default or override container images in workload controllers + like Deployments and StatefulSets.' + type: string + imagePullPolicy: + description: 'Image pull policy. One of Always, Never, IfNotPresent. + Defaults to Always if :latest tag is specified, or IfNotPresent + otherwise. Cannot be updated. More info: https://kubernetes.io/docs/concepts/containers/images#updating-images' + type: string + lifecycle: + description: Actions that the management system should take + in response to container lifecycle events. Cannot be updated. + properties: + postStart: + description: 'PostStart is called immediately after a container + is created. If the handler fails, the container is terminated + and restarted according to its restart policy. Other management + of the container blocks until the hook completes. More + info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute + inside the container, the working directory for + the command is root ('/') in the container's + filesystem. The command is simply exec'd, it is + not run inside a shell, so traditional shell instructions + ('|', etc) won't work. To use a shell, you need + to explicitly call out to that shell. Exit status + of 0 is treated as live/healthy and non-zero is + unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to + the pod IP. You probably want to set "Host" in + httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. + HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access + on the container. Number must be in the range + 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the + host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: Deprecated. TCPSocket is NOT supported + as a LifecycleHandler and kept for the backward compatibility. + There are no validation of this field and lifecycle + hooks will fail in runtime when tcp handler is specified. + properties: + host: + description: 'Optional: Host name to connect to, + defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access + on the container. Number must be in the range + 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + description: 'PreStop is called immediately before a container + is terminated due to an API request or management event + such as liveness/startup probe failure, preemption, resource + contention, etc. The handler is not called if the container + crashes or exits. The Pod''s termination grace period + countdown begins before the PreStop hook is executed. + Regardless of the outcome of the handler, the container + will eventually terminate within the Pod''s termination + grace period (unless delayed by finalizers). Other management + of the container blocks until the hook completes or until + the termination grace period is reached. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute + inside the container, the working directory for + the command is root ('/') in the container's + filesystem. The command is simply exec'd, it is + not run inside a shell, so traditional shell instructions + ('|', etc) won't work. To use a shell, you need + to explicitly call out to that shell. Exit status + of 0 is treated as live/healthy and non-zero is + unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to + the pod IP. You probably want to set "Host" in + httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. + HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access + on the container. Number must be in the range + 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the + host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: Deprecated. TCPSocket is NOT supported + as a LifecycleHandler and kept for the backward compatibility. + There are no validation of this field and lifecycle + hooks will fail in runtime when tcp handler is specified. + properties: + host: + description: 'Optional: Host name to connect to, + defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access + on the container. Number must be in the range + 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + description: 'Periodic probe of container liveness. Container + will be restarted if the probe fails. Cannot be updated. More + info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute + inside the container, the working directory for the + command is root ('/') in the container's filesystem. + The command is simply exec'd, it is not run inside + a shell, so traditional shell instructions ('|', etc) + won't work. To use a shell, you need to explicitly + call out to that shell. Exit status of 0 is treated + as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe + to be considered failed after having succeeded. Defaults + to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + This is an alpha field and requires enabling GRPCContainerProbe + feature gate. + properties: + port: + description: Port number of the gRPC service. Number + must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to + place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). + \n If this is not specified, the default behavior + is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the + pod IP. You probably want to set "Host" in httpHeaders + instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP + allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on + the container. Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has + started before liveness probes are initiated. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe + to be considered successful after having failed. Defaults + to 1. Must be 1 for liveness and startup. Minimum value + is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP + port. + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on + the container. Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs + to terminate gracefully upon probe failure. The grace + period is the duration in seconds after the processes + running in the pod are sent a termination signal and the + time when the processes are forcibly halted with a kill + signal. Set this value longer than the expected cleanup + time for your process. If this value is nil, the pod's + terminationGracePeriodSeconds will be used. Otherwise, + this value overrides the value provided by the pod spec. + Value must be non-negative integer. The value zero indicates + stop immediately via the kill signal (no opportunity to + shut down). This is a beta field and requires enabling + ProbeTerminationGracePeriod feature gate. Minimum value + is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times + out. Defaults to 1 second. Minimum value is 1. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + name: + description: Name of the container specified as a DNS_LABEL. + Each container in a pod must have a unique name (DNS_LABEL). + Cannot be updated. + type: string + ports: + description: List of ports to expose from the container. Exposing + a port here gives the system additional information about + the network connections a container uses, but is primarily + informational. Not specifying a port here DOES NOT prevent + that port from being exposed. Any port which is listening + on the default "0.0.0.0" address inside a container will be + accessible from the network. Cannot be updated. + items: + description: ContainerPort represents a network port in a + single container. + properties: + containerPort: + description: Number of port to expose on the pod's IP + address. This must be a valid port number, 0 < x < 65536. + format: int32 + type: integer + hostIP: + description: What host IP to bind the external port to. + type: string + hostPort: + description: Number of port to expose on the host. If + specified, this must be a valid port number, 0 < x < + 65536. If HostNetwork is specified, this must match + ContainerPort. Most containers do not need this. + format: int32 + type: integer + name: + description: If specified, this must be an IANA_SVC_NAME + and unique within the pod. Each named port in a pod + must have a unique name. Name for the port that can + be referred to by services. + type: string + protocol: + default: TCP + description: Protocol for port. Must be UDP, TCP, or SCTP. + Defaults to "TCP". + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + description: 'Periodic probe of container service readiness. + Container will be removed from service endpoints if the probe + fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute + inside the container, the working directory for the + command is root ('/') in the container's filesystem. + The command is simply exec'd, it is not run inside + a shell, so traditional shell instructions ('|', etc) + won't work. To use a shell, you need to explicitly + call out to that shell. Exit status of 0 is treated + as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe + to be considered failed after having succeeded. Defaults + to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + This is an alpha field and requires enabling GRPCContainerProbe + feature gate. + properties: + port: + description: Port number of the gRPC service. Number + must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to + place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). + \n If this is not specified, the default behavior + is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the + pod IP. You probably want to set "Host" in httpHeaders + instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP + allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on + the container. Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has + started before liveness probes are initiated. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe + to be considered successful after having failed. Defaults + to 1. Must be 1 for liveness and startup. Minimum value + is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP + port. + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on + the container. Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs + to terminate gracefully upon probe failure. The grace + period is the duration in seconds after the processes + running in the pod are sent a termination signal and the + time when the processes are forcibly halted with a kill + signal. Set this value longer than the expected cleanup + time for your process. If this value is nil, the pod's + terminationGracePeriodSeconds will be used. Otherwise, + this value overrides the value provided by the pod spec. + Value must be non-negative integer. The value zero indicates + stop immediately via the kill signal (no opportunity to + shut down). This is a beta field and requires enabling + ProbeTerminationGracePeriod feature gate. Minimum value + is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times + out. Defaults to 1 second. Minimum value is 1. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + resources: + description: 'Compute Resources required by this container. + Cannot be updated. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute + resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute + resources required. If Requests is omitted for a container, + it defaults to Limits if that is explicitly specified, + otherwise to an implementation-defined value. More info: + https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + securityContext: + description: 'SecurityContext defines the security options the + container should be run with. If set, the fields of SecurityContext + override the equivalent fields of PodSecurityContext. More + info: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/' + properties: + allowPrivilegeEscalation: + description: 'AllowPrivilegeEscalation controls whether + a process can gain more privileges than its parent process. + This bool directly controls if the no_new_privs flag will + be set on the container process. AllowPrivilegeEscalation + is true always when the container is: 1) run as Privileged + 2) has CAP_SYS_ADMIN Note that this field cannot be set + when spec.os.name is windows.' + type: boolean + capabilities: + description: The capabilities to add/drop when running containers. + Defaults to the default set of capabilities granted by + the container runtime. Note that this field cannot be + set when spec.os.name is windows. + properties: + add: + description: Added capabilities + items: + description: Capability represent POSIX capabilities + type + type: string + type: array + drop: + description: Removed capabilities + items: + description: Capability represent POSIX capabilities + type + type: string + type: array + type: object + privileged: + description: Run container in privileged mode. Processes + in privileged containers are essentially equivalent to + root on the host. Defaults to false. Note that this field + cannot be set when spec.os.name is windows. + type: boolean + procMount: + description: procMount denotes the type of proc mount to + use for the containers. The default is DefaultProcMount + which uses the container runtime defaults for readonly + paths and masked paths. This requires the ProcMountType + feature flag to be enabled. Note that this field cannot + be set when spec.os.name is windows. + type: string + readOnlyRootFilesystem: + description: Whether this container has a read-only root + filesystem. Default is false. Note that this field cannot + be set when spec.os.name is windows. + type: boolean + runAsGroup: + description: The GID to run the entrypoint of the container + process. Uses runtime default if unset. May also be set + in PodSecurityContext. If set in both SecurityContext + and PodSecurityContext, the value specified in SecurityContext + takes precedence. Note that this field cannot be set when + spec.os.name is windows. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a + non-root user. If true, the Kubelet will validate the + image at runtime to ensure that it does not run as UID + 0 (root) and fail to start the container if it does. If + unset or false, no such validation will be performed. + May also be set in PodSecurityContext. If set in both + SecurityContext and PodSecurityContext, the value specified + in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container + process. Defaults to user specified in image metadata + if unspecified. May also be set in PodSecurityContext. If + set in both SecurityContext and PodSecurityContext, the + value specified in SecurityContext takes precedence. Note + that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to the container. + If unspecified, the container runtime will allocate a + random SELinux context for each container. May also be + set in PodSecurityContext. If set in both SecurityContext + and PodSecurityContext, the value specified in SecurityContext + takes precedence. Note that this field cannot be set when + spec.os.name is windows. + properties: + level: + description: Level is SELinux level label that applies + to the container. + type: string + role: + description: Role is a SELinux role label that applies + to the container. + type: string + type: + description: Type is a SELinux type label that applies + to the container. + type: string + user: + description: User is a SELinux user label that applies + to the container. + type: string + type: object + seccompProfile: + description: The seccomp options to use by this container. + If seccomp options are provided at both the pod & container + level, the container options override the pod options. + Note that this field cannot be set when spec.os.name is + windows. + properties: + localhostProfile: + description: localhostProfile indicates a profile defined + in a file on the node should be used. The profile + must be preconfigured on the node to work. Must be + a descending path, relative to the kubelet's configured + seccomp profile location. Must only be set if type + is "Localhost". + type: string + type: + description: "type indicates which kind of seccomp profile + will be applied. Valid options are: \n Localhost - + a profile defined in a file on the node should be + used. RuntimeDefault - the container runtime default + profile should be used. Unconfined - no profile should + be applied." + type: string + required: + - type + type: object + windowsOptions: + description: The Windows specific settings applied to all + containers. If unspecified, the options from the PodSecurityContext + will be used. If set in both SecurityContext and PodSecurityContext, + the value specified in SecurityContext takes precedence. + Note that this field cannot be set when spec.os.name is + linux. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission + webhook (https://github.com/kubernetes-sigs/windows-gmsa) + inlines the contents of the GMSA credential spec named + by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the + GMSA credential spec to use. + type: string + hostProcess: + description: HostProcess determines if a container should + be run as a 'Host Process' container. This field is + alpha-level and will only be honored by components + that enable the WindowsHostProcessContainers feature + flag. Setting this field without the feature flag + will result in errors when validating the Pod. All + of a Pod's containers must have the same effective + HostProcess value (it is not allowed to have a mix + of HostProcess containers and non-HostProcess containers). In + addition, if HostProcess is true then HostNetwork + must also be set to true. + type: boolean + runAsUserName: + description: The UserName in Windows to run the entrypoint + of the container process. Defaults to the user specified + in image metadata if unspecified. May also be set + in PodSecurityContext. If set in both SecurityContext + and PodSecurityContext, the value specified in SecurityContext + takes precedence. + type: string + type: object + type: object + startupProbe: + description: 'StartupProbe indicates that the Pod has successfully + initialized. If specified, no other probes are executed until + this completes successfully. If this probe fails, the Pod + will be restarted, just as if the livenessProbe failed. This + can be used to provide different probe parameters at the beginning + of a Pod''s lifecycle, when it might take a long time to load + data or warm a cache, than during steady-state operation. + This cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute + inside the container, the working directory for the + command is root ('/') in the container's filesystem. + The command is simply exec'd, it is not run inside + a shell, so traditional shell instructions ('|', etc) + won't work. To use a shell, you need to explicitly + call out to that shell. Exit status of 0 is treated + as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe + to be considered failed after having succeeded. Defaults + to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + This is an alpha field and requires enabling GRPCContainerProbe + feature gate. + properties: + port: + description: Port number of the gRPC service. Number + must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to + place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). + \n If this is not specified, the default behavior + is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the + pod IP. You probably want to set "Host" in httpHeaders + instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP + allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on + the container. Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has + started before liveness probes are initiated. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe + to be considered successful after having failed. Defaults + to 1. Must be 1 for liveness and startup. Minimum value + is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP + port. + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on + the container. Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs + to terminate gracefully upon probe failure. The grace + period is the duration in seconds after the processes + running in the pod are sent a termination signal and the + time when the processes are forcibly halted with a kill + signal. Set this value longer than the expected cleanup + time for your process. If this value is nil, the pod's + terminationGracePeriodSeconds will be used. Otherwise, + this value overrides the value provided by the pod spec. + Value must be non-negative integer. The value zero indicates + stop immediately via the kill signal (no opportunity to + shut down). This is a beta field and requires enabling + ProbeTerminationGracePeriod feature gate. Minimum value + is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times + out. Defaults to 1 second. Minimum value is 1. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + stdin: + description: Whether this container should allocate a buffer + for stdin in the container runtime. If this is not set, reads + from stdin in the container will always result in EOF. Default + is false. + type: boolean + stdinOnce: + description: Whether the container runtime should close the + stdin channel after it has been opened by a single attach. + When stdin is true the stdin stream will remain open across + multiple attach sessions. If stdinOnce is set to true, stdin + is opened on container start, is empty until the first client + attaches to stdin, and then remains open and accepts data + until the client disconnects, at which time stdin is closed + and remains closed until the container is restarted. If this + flag is false, a container processes that reads from stdin + will never receive an EOF. Default is false + type: boolean + terminationMessagePath: + description: 'Optional: Path at which the file to which the + container''s termination message will be written is mounted + into the container''s filesystem. Message written is intended + to be brief final status, such as an assertion failure message. + Will be truncated by the node if greater than 4096 bytes. + The total message length across all containers will be limited + to 12kb. Defaults to /dev/termination-log. Cannot be updated.' + type: string + terminationMessagePolicy: + description: Indicate how the termination message should be + populated. File will use the contents of terminationMessagePath + to populate the container status message on both success and + failure. FallbackToLogsOnError will use the last chunk of + container log output if the termination message file is empty + and the container exited with an error. The log output is + limited to 2048 bytes or 80 lines, whichever is smaller. Defaults + to File. Cannot be updated. + type: string + tty: + description: Whether this container should allocate a TTY for + itself, also requires 'stdin' to be true. Default is false. + type: boolean + volumeDevices: + description: volumeDevices is the list of block devices to be + used by the container. + items: + description: volumeDevice describes a mapping of a raw block + device within a container. + properties: + devicePath: + description: devicePath is the path inside of the container + that the device will be mapped to. + type: string + name: + description: name must match the name of a persistentVolumeClaim + in the pod + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + description: Pod volumes to mount into the container's filesystem. + Cannot be updated. + items: + description: VolumeMount describes a mounting of a Volume + within a container. + properties: + mountPath: + description: Path within the container at which the volume + should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are + propagated from the host to container and the other + way around. When not set, MountPropagationNone is used. + This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise + (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's + volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which + the container's volume should be mounted. Behaves similarly + to SubPath but environment variable references $(VAR_NAME) + are expanded using the container's environment. Defaults + to "" (volume's root). SubPathExpr and SubPath are mutually + exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + description: Container's working directory. If not specified, + the container runtime's default will be used, which might + be configured in the container image. Cannot be updated. + type: string + required: + - name + type: object + type: array + enableConfigReadAPI: + default: false + description: enableConfigReadAPI enables the read API for viewing + currently running config port 8080 on the agent. + type: boolean + image: + description: Image, when specified, overrides the image used to run + the Agent. It should be specified along with a tag. Version must + still be set to ensure the Grafana Agent Operator knows which version + of Grafana Agent is being configured. + type: string + imagePullSecrets: + description: 'ImagePullSecrets holds an optional list of references + to secrets within the same namespace to use for pulling the Grafana + Agent image from registries. More info: https://kubernetes.io/docs/user-guide/images#specifying-imagepullsecrets-on-a-pod' + items: + description: LocalObjectReference contains enough information to + let you locate the referenced object inside the same namespace. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + type: array + initContainers: + description: 'InitContainers allows adding initContainers to the pod + definition. These can be used to, for example, fetch secrets for + injection into the Grafana Agent configuration from external sources. + Any errors during the execution of an initContainer will lead to + a restart of the pod. More info: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/ + Using initContainers for any use case other than secret fetching + is entirely outside the scope of what the Grafana Agent maintainers + will support and by doing so, you accept that this behavior may + break at any time without notice.' + items: + description: A single application container that you want to run + within a pod. + properties: + args: + description: 'Arguments to the entrypoint. The docker image''s + CMD is used if this is not provided. Variable references $(VAR_NAME) + are expanded using the container''s environment. If a variable + cannot be resolved, the reference in the input string will + be unchanged. Double $$ are reduced to a single $, which allows + for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will + produce the string literal "$(VAR_NAME)". Escaped references + will never be expanded, regardless of whether the variable + exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + command: + description: 'Entrypoint array. Not executed within a shell. + The docker image''s ENTRYPOINT is used if this is not provided. + Variable references $(VAR_NAME) are expanded using the container''s + environment. If a variable cannot be resolved, the reference + in the input string will be unchanged. Double $$ are reduced + to a single $, which allows for escaping the $(VAR_NAME) syntax: + i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". + Escaped references will never be expanded, regardless of whether + the variable exists or not. Cannot be updated. More info: + https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + env: + description: List of environment variables to set in the container. + Cannot be updated. + items: + description: EnvVar represents an environment variable present + in a Container. + properties: + name: + description: Name of the environment variable. Must be + a C_IDENTIFIER. + type: string + value: + description: 'Variable references $(VAR_NAME) are expanded + using the previously defined environment variables in + the container and any service environment variables. + If a variable cannot be resolved, the reference in the + input string will be unchanged. Double $$ are reduced + to a single $, which allows for escaping the $(VAR_NAME) + syntax: i.e. "$$(VAR_NAME)" will produce the string + literal "$(VAR_NAME)". Escaped references will never + be expanded, regardless of whether the variable exists + or not. Defaults to "".' + type: string + valueFrom: + description: Source for the environment variable's value. + Cannot be used if value is not empty. + properties: + configMapKeyRef: + description: Selects a key of a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or + its key must be defined + type: boolean + required: + - key + type: object + fieldRef: + description: 'Selects a field of the pod: supports + metadata.name, metadata.namespace, `metadata.labels['''']`, + `metadata.annotations['''']`, spec.nodeName, + spec.serviceAccountName, status.hostIP, status.podIP, + status.podIPs.' + properties: + apiVersion: + description: Version of the schema the FieldPath + is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the + specified API version. + type: string + required: + - fieldPath + type: object + resourceFieldRef: + description: 'Selects a resource of the container: + only resources limits and requests (limits.cpu, + limits.memory, limits.ephemeral-storage, requests.cpu, + requests.memory and requests.ephemeral-storage) + are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, + optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the + exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + secretKeyRef: + description: Selects a key of a secret in the pod's + namespace + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its + key must be defined + type: boolean + required: + - key + type: object + type: object + required: + - name + type: object + type: array + envFrom: + description: List of sources to populate environment variables + in the container. The keys defined within a source must be + a C_IDENTIFIER. All invalid keys will be reported as an event + when the container is starting. When a key exists in multiple + sources, the value associated with the last source will take + precedence. Values defined by an Env with a duplicate key + will take precedence. Cannot be updated. + items: + description: EnvFromSource represents the source of a set + of ConfigMaps + properties: + configMapRef: + description: The ConfigMap to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap must be + defined + type: boolean + type: object + prefix: + description: An optional identifier to prepend to each + key in the ConfigMap. Must be a C_IDENTIFIER. + type: string + secretRef: + description: The Secret to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret must be defined + type: boolean + type: object + type: object + type: array + image: + description: 'Docker image name. More info: https://kubernetes.io/docs/concepts/containers/images + This field is optional to allow higher level config management + to default or override container images in workload controllers + like Deployments and StatefulSets.' + type: string + imagePullPolicy: + description: 'Image pull policy. One of Always, Never, IfNotPresent. + Defaults to Always if :latest tag is specified, or IfNotPresent + otherwise. Cannot be updated. More info: https://kubernetes.io/docs/concepts/containers/images#updating-images' + type: string + lifecycle: + description: Actions that the management system should take + in response to container lifecycle events. Cannot be updated. + properties: + postStart: + description: 'PostStart is called immediately after a container + is created. If the handler fails, the container is terminated + and restarted according to its restart policy. Other management + of the container blocks until the hook completes. More + info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute + inside the container, the working directory for + the command is root ('/') in the container's + filesystem. The command is simply exec'd, it is + not run inside a shell, so traditional shell instructions + ('|', etc) won't work. To use a shell, you need + to explicitly call out to that shell. Exit status + of 0 is treated as live/healthy and non-zero is + unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to + the pod IP. You probably want to set "Host" in + httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. + HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access + on the container. Number must be in the range + 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the + host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: Deprecated. TCPSocket is NOT supported + as a LifecycleHandler and kept for the backward compatibility. + There are no validation of this field and lifecycle + hooks will fail in runtime when tcp handler is specified. + properties: + host: + description: 'Optional: Host name to connect to, + defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access + on the container. Number must be in the range + 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + description: 'PreStop is called immediately before a container + is terminated due to an API request or management event + such as liveness/startup probe failure, preemption, resource + contention, etc. The handler is not called if the container + crashes or exits. The Pod''s termination grace period + countdown begins before the PreStop hook is executed. + Regardless of the outcome of the handler, the container + will eventually terminate within the Pod''s termination + grace period (unless delayed by finalizers). Other management + of the container blocks until the hook completes or until + the termination grace period is reached. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute + inside the container, the working directory for + the command is root ('/') in the container's + filesystem. The command is simply exec'd, it is + not run inside a shell, so traditional shell instructions + ('|', etc) won't work. To use a shell, you need + to explicitly call out to that shell. Exit status + of 0 is treated as live/healthy and non-zero is + unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to + the pod IP. You probably want to set "Host" in + httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. + HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access + on the container. Number must be in the range + 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the + host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: Deprecated. TCPSocket is NOT supported + as a LifecycleHandler and kept for the backward compatibility. + There are no validation of this field and lifecycle + hooks will fail in runtime when tcp handler is specified. + properties: + host: + description: 'Optional: Host name to connect to, + defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access + on the container. Number must be in the range + 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + description: 'Periodic probe of container liveness. Container + will be restarted if the probe fails. Cannot be updated. More + info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute + inside the container, the working directory for the + command is root ('/') in the container's filesystem. + The command is simply exec'd, it is not run inside + a shell, so traditional shell instructions ('|', etc) + won't work. To use a shell, you need to explicitly + call out to that shell. Exit status of 0 is treated + as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe + to be considered failed after having succeeded. Defaults + to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + This is an alpha field and requires enabling GRPCContainerProbe + feature gate. + properties: + port: + description: Port number of the gRPC service. Number + must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to + place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). + \n If this is not specified, the default behavior + is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the + pod IP. You probably want to set "Host" in httpHeaders + instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP + allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on + the container. Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has + started before liveness probes are initiated. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe + to be considered successful after having failed. Defaults + to 1. Must be 1 for liveness and startup. Minimum value + is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP + port. + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on + the container. Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs + to terminate gracefully upon probe failure. The grace + period is the duration in seconds after the processes + running in the pod are sent a termination signal and the + time when the processes are forcibly halted with a kill + signal. Set this value longer than the expected cleanup + time for your process. If this value is nil, the pod's + terminationGracePeriodSeconds will be used. Otherwise, + this value overrides the value provided by the pod spec. + Value must be non-negative integer. The value zero indicates + stop immediately via the kill signal (no opportunity to + shut down). This is a beta field and requires enabling + ProbeTerminationGracePeriod feature gate. Minimum value + is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times + out. Defaults to 1 second. Minimum value is 1. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + name: + description: Name of the container specified as a DNS_LABEL. + Each container in a pod must have a unique name (DNS_LABEL). + Cannot be updated. + type: string + ports: + description: List of ports to expose from the container. Exposing + a port here gives the system additional information about + the network connections a container uses, but is primarily + informational. Not specifying a port here DOES NOT prevent + that port from being exposed. Any port which is listening + on the default "0.0.0.0" address inside a container will be + accessible from the network. Cannot be updated. + items: + description: ContainerPort represents a network port in a + single container. + properties: + containerPort: + description: Number of port to expose on the pod's IP + address. This must be a valid port number, 0 < x < 65536. + format: int32 + type: integer + hostIP: + description: What host IP to bind the external port to. + type: string + hostPort: + description: Number of port to expose on the host. If + specified, this must be a valid port number, 0 < x < + 65536. If HostNetwork is specified, this must match + ContainerPort. Most containers do not need this. + format: int32 + type: integer + name: + description: If specified, this must be an IANA_SVC_NAME + and unique within the pod. Each named port in a pod + must have a unique name. Name for the port that can + be referred to by services. + type: string + protocol: + default: TCP + description: Protocol for port. Must be UDP, TCP, or SCTP. + Defaults to "TCP". + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + description: 'Periodic probe of container service readiness. + Container will be removed from service endpoints if the probe + fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute + inside the container, the working directory for the + command is root ('/') in the container's filesystem. + The command is simply exec'd, it is not run inside + a shell, so traditional shell instructions ('|', etc) + won't work. To use a shell, you need to explicitly + call out to that shell. Exit status of 0 is treated + as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe + to be considered failed after having succeeded. Defaults + to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + This is an alpha field and requires enabling GRPCContainerProbe + feature gate. + properties: + port: + description: Port number of the gRPC service. Number + must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to + place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). + \n If this is not specified, the default behavior + is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the + pod IP. You probably want to set "Host" in httpHeaders + instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP + allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on + the container. Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has + started before liveness probes are initiated. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe + to be considered successful after having failed. Defaults + to 1. Must be 1 for liveness and startup. Minimum value + is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP + port. + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on + the container. Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs + to terminate gracefully upon probe failure. The grace + period is the duration in seconds after the processes + running in the pod are sent a termination signal and the + time when the processes are forcibly halted with a kill + signal. Set this value longer than the expected cleanup + time for your process. If this value is nil, the pod's + terminationGracePeriodSeconds will be used. Otherwise, + this value overrides the value provided by the pod spec. + Value must be non-negative integer. The value zero indicates + stop immediately via the kill signal (no opportunity to + shut down). This is a beta field and requires enabling + ProbeTerminationGracePeriod feature gate. Minimum value + is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times + out. Defaults to 1 second. Minimum value is 1. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + resources: + description: 'Compute Resources required by this container. + Cannot be updated. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute + resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute + resources required. If Requests is omitted for a container, + it defaults to Limits if that is explicitly specified, + otherwise to an implementation-defined value. More info: + https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + securityContext: + description: 'SecurityContext defines the security options the + container should be run with. If set, the fields of SecurityContext + override the equivalent fields of PodSecurityContext. More + info: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/' + properties: + allowPrivilegeEscalation: + description: 'AllowPrivilegeEscalation controls whether + a process can gain more privileges than its parent process. + This bool directly controls if the no_new_privs flag will + be set on the container process. AllowPrivilegeEscalation + is true always when the container is: 1) run as Privileged + 2) has CAP_SYS_ADMIN Note that this field cannot be set + when spec.os.name is windows.' + type: boolean + capabilities: + description: The capabilities to add/drop when running containers. + Defaults to the default set of capabilities granted by + the container runtime. Note that this field cannot be + set when spec.os.name is windows. + properties: + add: + description: Added capabilities + items: + description: Capability represent POSIX capabilities + type + type: string + type: array + drop: + description: Removed capabilities + items: + description: Capability represent POSIX capabilities + type + type: string + type: array + type: object + privileged: + description: Run container in privileged mode. Processes + in privileged containers are essentially equivalent to + root on the host. Defaults to false. Note that this field + cannot be set when spec.os.name is windows. + type: boolean + procMount: + description: procMount denotes the type of proc mount to + use for the containers. The default is DefaultProcMount + which uses the container runtime defaults for readonly + paths and masked paths. This requires the ProcMountType + feature flag to be enabled. Note that this field cannot + be set when spec.os.name is windows. + type: string + readOnlyRootFilesystem: + description: Whether this container has a read-only root + filesystem. Default is false. Note that this field cannot + be set when spec.os.name is windows. + type: boolean + runAsGroup: + description: The GID to run the entrypoint of the container + process. Uses runtime default if unset. May also be set + in PodSecurityContext. If set in both SecurityContext + and PodSecurityContext, the value specified in SecurityContext + takes precedence. Note that this field cannot be set when + spec.os.name is windows. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a + non-root user. If true, the Kubelet will validate the + image at runtime to ensure that it does not run as UID + 0 (root) and fail to start the container if it does. If + unset or false, no such validation will be performed. + May also be set in PodSecurityContext. If set in both + SecurityContext and PodSecurityContext, the value specified + in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container + process. Defaults to user specified in image metadata + if unspecified. May also be set in PodSecurityContext. If + set in both SecurityContext and PodSecurityContext, the + value specified in SecurityContext takes precedence. Note + that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to the container. + If unspecified, the container runtime will allocate a + random SELinux context for each container. May also be + set in PodSecurityContext. If set in both SecurityContext + and PodSecurityContext, the value specified in SecurityContext + takes precedence. Note that this field cannot be set when + spec.os.name is windows. + properties: + level: + description: Level is SELinux level label that applies + to the container. + type: string + role: + description: Role is a SELinux role label that applies + to the container. + type: string + type: + description: Type is a SELinux type label that applies + to the container. + type: string + user: + description: User is a SELinux user label that applies + to the container. + type: string + type: object + seccompProfile: + description: The seccomp options to use by this container. + If seccomp options are provided at both the pod & container + level, the container options override the pod options. + Note that this field cannot be set when spec.os.name is + windows. + properties: + localhostProfile: + description: localhostProfile indicates a profile defined + in a file on the node should be used. The profile + must be preconfigured on the node to work. Must be + a descending path, relative to the kubelet's configured + seccomp profile location. Must only be set if type + is "Localhost". + type: string + type: + description: "type indicates which kind of seccomp profile + will be applied. Valid options are: \n Localhost - + a profile defined in a file on the node should be + used. RuntimeDefault - the container runtime default + profile should be used. Unconfined - no profile should + be applied." + type: string + required: + - type + type: object + windowsOptions: + description: The Windows specific settings applied to all + containers. If unspecified, the options from the PodSecurityContext + will be used. If set in both SecurityContext and PodSecurityContext, + the value specified in SecurityContext takes precedence. + Note that this field cannot be set when spec.os.name is + linux. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission + webhook (https://github.com/kubernetes-sigs/windows-gmsa) + inlines the contents of the GMSA credential spec named + by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the + GMSA credential spec to use. + type: string + hostProcess: + description: HostProcess determines if a container should + be run as a 'Host Process' container. This field is + alpha-level and will only be honored by components + that enable the WindowsHostProcessContainers feature + flag. Setting this field without the feature flag + will result in errors when validating the Pod. All + of a Pod's containers must have the same effective + HostProcess value (it is not allowed to have a mix + of HostProcess containers and non-HostProcess containers). In + addition, if HostProcess is true then HostNetwork + must also be set to true. + type: boolean + runAsUserName: + description: The UserName in Windows to run the entrypoint + of the container process. Defaults to the user specified + in image metadata if unspecified. May also be set + in PodSecurityContext. If set in both SecurityContext + and PodSecurityContext, the value specified in SecurityContext + takes precedence. + type: string + type: object + type: object + startupProbe: + description: 'StartupProbe indicates that the Pod has successfully + initialized. If specified, no other probes are executed until + this completes successfully. If this probe fails, the Pod + will be restarted, just as if the livenessProbe failed. This + can be used to provide different probe parameters at the beginning + of a Pod''s lifecycle, when it might take a long time to load + data or warm a cache, than during steady-state operation. + This cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute + inside the container, the working directory for the + command is root ('/') in the container's filesystem. + The command is simply exec'd, it is not run inside + a shell, so traditional shell instructions ('|', etc) + won't work. To use a shell, you need to explicitly + call out to that shell. Exit status of 0 is treated + as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe + to be considered failed after having succeeded. Defaults + to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + This is an alpha field and requires enabling GRPCContainerProbe + feature gate. + properties: + port: + description: Port number of the gRPC service. Number + must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to + place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). + \n If this is not specified, the default behavior + is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the + pod IP. You probably want to set "Host" in httpHeaders + instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP + allows repeated headers. + items: + description: HTTPHeader describes a custom header + to be used in HTTP probes + properties: + name: + description: The header field name + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on + the container. Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. + Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has + started before liveness probes are initiated. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. + Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe + to be considered successful after having failed. Defaults + to 1. Must be 1 for liveness and startup. Minimum value + is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP + port. + properties: + host: + description: 'Optional: Host name to connect to, defaults + to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on + the container. Number must be in the range 1 to 65535. + Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs + to terminate gracefully upon probe failure. The grace + period is the duration in seconds after the processes + running in the pod are sent a termination signal and the + time when the processes are forcibly halted with a kill + signal. Set this value longer than the expected cleanup + time for your process. If this value is nil, the pod's + terminationGracePeriodSeconds will be used. Otherwise, + this value overrides the value provided by the pod spec. + Value must be non-negative integer. The value zero indicates + stop immediately via the kill signal (no opportunity to + shut down). This is a beta field and requires enabling + ProbeTerminationGracePeriod feature gate. Minimum value + is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times + out. Defaults to 1 second. Minimum value is 1. More info: + https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + stdin: + description: Whether this container should allocate a buffer + for stdin in the container runtime. If this is not set, reads + from stdin in the container will always result in EOF. Default + is false. + type: boolean + stdinOnce: + description: Whether the container runtime should close the + stdin channel after it has been opened by a single attach. + When stdin is true the stdin stream will remain open across + multiple attach sessions. If stdinOnce is set to true, stdin + is opened on container start, is empty until the first client + attaches to stdin, and then remains open and accepts data + until the client disconnects, at which time stdin is closed + and remains closed until the container is restarted. If this + flag is false, a container processes that reads from stdin + will never receive an EOF. Default is false + type: boolean + terminationMessagePath: + description: 'Optional: Path at which the file to which the + container''s termination message will be written is mounted + into the container''s filesystem. Message written is intended + to be brief final status, such as an assertion failure message. + Will be truncated by the node if greater than 4096 bytes. + The total message length across all containers will be limited + to 12kb. Defaults to /dev/termination-log. Cannot be updated.' + type: string + terminationMessagePolicy: + description: Indicate how the termination message should be + populated. File will use the contents of terminationMessagePath + to populate the container status message on both success and + failure. FallbackToLogsOnError will use the last chunk of + container log output if the termination message file is empty + and the container exited with an error. The log output is + limited to 2048 bytes or 80 lines, whichever is smaller. Defaults + to File. Cannot be updated. + type: string + tty: + description: Whether this container should allocate a TTY for + itself, also requires 'stdin' to be true. Default is false. + type: boolean + volumeDevices: + description: volumeDevices is the list of block devices to be + used by the container. + items: + description: volumeDevice describes a mapping of a raw block + device within a container. + properties: + devicePath: + description: devicePath is the path inside of the container + that the device will be mapped to. + type: string + name: + description: name must match the name of a persistentVolumeClaim + in the pod + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + description: Pod volumes to mount into the container's filesystem. + Cannot be updated. + items: + description: VolumeMount describes a mounting of a Volume + within a container. + properties: + mountPath: + description: Path within the container at which the volume + should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are + propagated from the host to container and the other + way around. When not set, MountPropagationNone is used. + This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise + (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's + volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which + the container's volume should be mounted. Behaves similarly + to SubPath but environment variable references $(VAR_NAME) + are expanded using the container's environment. Defaults + to "" (volume's root). SubPathExpr and SubPath are mutually + exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + description: Container's working directory. If not specified, + the container runtime's default will be used, which might + be configured in the container image. Cannot be updated. + type: string + required: + - name + type: object + type: array + integrations: + description: Integrations controls the integration subsystem of the + Agent and settings unique to integration-specific pods that are + deployed. + properties: + namespaceSelector: + description: "Label selector for namespaces to search when discovering + integration resources. If nil, integration resources are only + discovered in the namespace of the GrafanaAgent resource. \n + Set to `{}` to search all namespaces." + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector + that contains values, a key, and an operator that relates + the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are In, NotIn, + Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If + the operator is In or NotIn, the values array must + be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced + during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A + single {key,value} in the matchLabels map is equivalent + to an element of matchExpressions, whose key field is "key", + the operator is "In", and the values array contains only + "value". The requirements are ANDed. + type: object + type: object + selector: + description: Label selector to find Integration resources to run. + When nil, no integration resources will be defined. + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector + that contains values, a key, and an operator that relates + the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are In, NotIn, + Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If + the operator is In or NotIn, the values array must + be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced + during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A + single {key,value} in the matchLabels map is equivalent + to an element of matchExpressions, whose key field is "key", + the operator is "In", and the values array contains only + "value". The requirements are ANDed. + type: object + type: object + type: object + logFormat: + description: LogFormat controls the logging format of the generated + pods. Defaults to "logfmt" if not set. + type: string + logLevel: + description: LogLevel controls the log level of the generated pods. + Defaults to "info" if not set. + type: string + logs: + description: Logs controls the logging subsystem of the Agent and + settings unique to logging-specific pods that are deployed. + properties: + clients: + description: Global set of clients to use when a discovered LogsInstance + does not have any clients defined. + items: + description: LogsClientSpec defines the client integration for + logs, indicating which Loki server to send logs to. + properties: + backoffConfig: + description: Configures how to retry requests to Loki when + a request fails. Defaults to a minPeriod of 500ms, maxPeriod + of 5m, and maxRetries of 10. + properties: + maxPeriod: + description: Maximum backoff time between retries. + type: string + maxRetries: + description: Maximum number of retries to perform before + giving up a request. + type: integer + minPeriod: + description: Initial backoff time between retries. Time + between retries is increased exponentially. + type: string + type: object + basicAuth: + description: BasicAuth for the Loki server. + properties: + password: + description: The secret in the service monitor namespace + that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace + that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + batchSize: + description: Maximum batch size (in bytes) of logs to accumulate + before sending the batch to Loki. + type: integer + batchWait: + description: Maximum amount of time to wait before sending + a batch, even if that batch isn't full. + type: string + bearerToken: + description: BearerToken used for remote_write. + type: string + bearerTokenFile: + description: BearerTokenFile used to read bearer token. + type: string + externalLabels: + additionalProperties: + type: string + description: ExternalLabels are labels to add to any time + series when sending data to Loki. + type: object + proxyUrl: + description: ProxyURL to proxy requests through. Optional. + type: string + tenantId: + description: Tenant ID used by default to push logs to Loki. + If omitted assumes remote Loki is running in single-tenant + mode or an authentication layer is used to inject an X-Scope-OrgID + header. + type: string + timeout: + description: Maximum time to wait for a server to respond + to a request. + type: string + tlsConfig: + description: TLSConfig to use for the client. Only used + when the protocol of the URL is https. + properties: + ca: + description: Struct containing the CA cert to use for + the targets. + properties: + configMap: + description: ConfigMap containing data to use for + the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, + kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or + its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the + targets. + properties: + key: + description: The key of the secret to select + from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, + kind, uid?' + type: string + optional: + description: Specify whether the Secret or its + key must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container + to use for the targets. + type: string + cert: + description: Struct containing the client cert file + for the targets. + properties: + configMap: + description: ConfigMap containing data to use for + the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, + kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or + its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the + targets. + properties: + key: + description: The key of the secret to select + from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, + kind, uid?' + type: string + optional: + description: Specify whether the Secret or its + key must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus + container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus + container for the targets. + type: string + keySecret: + description: Secret containing the client key file for + the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + url: + description: 'URL is the URL where Loki is listening. Must + be a full HTTP URL, including protocol. Required. Example: + https://logs-prod-us-central1.grafana.net/loki/api/v1/push.' + type: string + required: + - url + type: object + type: array + enforcedNamespaceLabel: + description: EnforcedNamespaceLabel enforces adding a namespace + label of origin for each metric that is user-created. The label + value will always be the namespace of the object that is being + created. + type: string + ignoreNamespaceSelectors: + description: IgnoreNamespaceSelectors, if true, will ignore NamespaceSelector + settings from the PodLogs configs, and they will only discover + endpoints within their current namespace. + type: boolean + instanceNamespaceSelector: + description: InstanceNamespaceSelector are the set of labels to + determine which namespaces to watch for LogInstances. If not + provided, only checks own namespace. + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector + that contains values, a key, and an operator that relates + the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are In, NotIn, + Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If + the operator is In or NotIn, the values array must + be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced + during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A + single {key,value} in the matchLabels map is equivalent + to an element of matchExpressions, whose key field is "key", + the operator is "In", and the values array contains only + "value". The requirements are ANDed. + type: object + type: object + instanceSelector: + description: InstanceSelector determines which LogInstances should + be selected for running. Each instance runs its own set of Prometheus + components, including service discovery, scraping, and remote_write. + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector + that contains values, a key, and an operator that relates + the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are In, NotIn, + Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If + the operator is In or NotIn, the values array must + be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced + during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A + single {key,value} in the matchLabels map is equivalent + to an element of matchExpressions, whose key field is "key", + the operator is "In", and the values array contains only + "value". The requirements are ANDed. + type: object + type: object + logsExternalLabelName: + description: LogsExternalLabelName is the name of the external + label used to denote Grafana Agent cluster. Defaults to "cluster." + External label will _not_ be added when value is set to the + empty string. + type: string + type: object + metrics: + description: Metrics controls the metrics subsystem of the Agent and + settings unique to metrics-specific pods that are deployed. + properties: + arbitraryFSAccessThroughSMs: + description: ArbitraryFSAccessThroughSMs configures whether configuration + based on a ServiceMonitor can access arbitrary files on the + file system of the Grafana Agent container e.g. bearer token + files. + properties: + deny: + type: boolean + type: object + enforcedNamespaceLabel: + description: EnforcedNamespaceLabel enforces adding a namespace + label of origin for each metric that is user-created. The label + value will always be the namespace of the object that is being + created. + type: string + enforcedSampleLimit: + description: EnforcedSampleLimit defines global limit on the number + of scraped samples that will be accepted. This overrides any + SampleLimit set per ServiceMonitor and/or PodMonitor. It is + meant to be used by admins to enforce the SampleLimit to keep + the overall number of samples and series under the desired limit. + Note that if a SampleLimit from a ServiceMonitor or PodMonitor + is lower, that value will be used instead. + format: int64 + type: integer + enforcedTargetLimit: + description: EnforcedTargetLimit defines a global limit on the + number of scraped targets. This overrides any TargetLimit set + per ServiceMonitor and/or PodMonitor. It is meant to be used + by admins to enforce the TargetLimit to keep the overall number + of targets under the desired limit. Note that if a TargetLimit + from a ServiceMonitor or PodMonitor is higher, that value will + be used instead. + format: int64 + type: integer + externalLabels: + additionalProperties: + type: string + description: ExternalLabels are labels to add to any time series + when sending data over remote_write. + type: object + ignoreNamespaceSelectors: + description: IgnoreNamespaceSelectors, if true, will ignore NamespaceSelector + settings from the PodMonitor and ServiceMonitor configs, and + they will only discover endpoints within their current namespace. + type: boolean + instanceNamespaceSelector: + description: InstanceNamespaceSelector are the set of labels to + determine which namespaces to watch for MetricsInstances. If + not provided, only checks own namespace. + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector + that contains values, a key, and an operator that relates + the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are In, NotIn, + Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If + the operator is In or NotIn, the values array must + be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced + during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A + single {key,value} in the matchLabels map is equivalent + to an element of matchExpressions, whose key field is "key", + the operator is "In", and the values array contains only + "value". The requirements are ANDed. + type: object + type: object + instanceSelector: + description: InstanceSelector determines which MetricsInstances + should be selected for running. Each instance runs its own set + of Metrics components, including service discovery, scraping, + and remote_write. + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector + that contains values, a key, and an operator that relates + the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are In, NotIn, + Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If + the operator is In or NotIn, the values array must + be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced + during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A + single {key,value} in the matchLabels map is equivalent + to an element of matchExpressions, whose key field is "key", + the operator is "In", and the values array contains only + "value". The requirements are ANDed. + type: object + type: object + metricsExternalLabelName: + description: MetricsExternalLabelName is the name of the external + label used to denote Grafana Agent cluster. Defaults to "cluster." + External label will _not_ be added when value is set to the + empty string. + type: string + overrideHonorLabels: + description: OverrideHonorLabels, if true, overrides all configured + honor_labels read from ServiceMonitor or PodMonitor to false. + type: boolean + overrideHonorTimestamps: + description: OverrideHonorTimestamps allows to globally enforce + honoring timestamps in all scrape configs. + type: boolean + remoteWrite: + description: RemoteWrite controls default remote_write settings + for all instances. If an instance does not provide its own remoteWrite + settings, these will be used instead. + items: + description: RemoteWriteSpec defines the remote_write configuration + for Prometheus. + properties: + basicAuth: + description: BasicAuth for the URL. + properties: + password: + description: The secret in the service monitor namespace + that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace + that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + bearerToken: + description: BearerToken used for remote_write. + type: string + bearerTokenFile: + description: BearerTokenFile used to read bearer token. + type: string + headers: + additionalProperties: + type: string + description: Headers is a set of custom HTTP headers to + be sent along with each remote_write request. Be aware + that any headers set by Grafana Agent itself can't be + overwritten. + type: object + metadataConfig: + description: MetadataConfig configures the sending of series + metadata to remote storage. + properties: + send: + description: Send enables metric metadata to be sent + to remote storage. + type: boolean + sendInterval: + description: SendInterval controls how frequently metric + metadata is sent to remote storage. + type: string + type: object + name: + description: Name of the remote_write queue. Must be unique + if specified. The name is used in metrics and logging + in order to differentiate queues. + type: string + proxyUrl: + description: ProxyURL to proxy requests through. Optional. + type: string + queueConfig: + description: QueueConfig allows tuning of the remote_write + queue parameters. + properties: + batchSendDeadline: + description: BatchSendDeadline is the maximum time a + sample will wait in buffer. + type: string + capacity: + description: Capacity is the number of samples to buffer + per shard before we start dropping them. + type: integer + maxBackoff: + description: MaxBackoff is the maximum retry delay. + type: string + maxRetries: + description: MaxRetries is the maximum number of times + to retry a batch on recoverable errors. + type: integer + maxSamplesPerSend: + description: MaxSamplesPerSend is the maximum number + of samples per send. + type: integer + maxShards: + description: MaxShards is the maximum number of shards, + i.e. amount of concurrency. + type: integer + minBackoff: + description: MinBackoff is the initial retry delay. + Gets doubled for every retry. + type: string + minShards: + description: MinShards is the minimum number of shards, + i.e. amount of concurrency. + type: integer + retryOnRateLimit: + description: RetryOnRateLimit retries requests when + encountering rate limits. + type: boolean + type: object + remoteTimeout: + description: RemoteTimeout is the timeout for requests to + the remote_write endpoint. + type: string + sigv4: + description: SigV4 configures SigV4-based authentication + to the remote_write endpoint. Will be used if SigV4 is + defined, even with an empty object. + properties: + accessKey: + description: AccessKey holds the secret of the AWS API + access key to use for signing. If not provided, The + environment variable AWS_ACCESS_KEY_ID is used. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + profile: + description: Profile is the named AWS profile to use + for authentication. + type: string + region: + description: Region of the AWS endpoint. If blank, the + region from the default credentials chain is used. + type: string + roleARN: + description: RoleARN is the AWS Role ARN to use for + authentication, as an alternative for using the AWS + API keys. + type: string + secretKey: + description: SecretKey of the AWS API to use for signing. + If blank, the environment variable AWS_SECRET_ACCESS_KEY + is used. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + tlsConfig: + description: TLSConfig to use for remote_write. + properties: + ca: + description: Struct containing the CA cert to use for + the targets. + properties: + configMap: + description: ConfigMap containing data to use for + the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, + kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or + its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the + targets. + properties: + key: + description: The key of the secret to select + from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, + kind, uid?' + type: string + optional: + description: Specify whether the Secret or its + key must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container + to use for the targets. + type: string + cert: + description: Struct containing the client cert file + for the targets. + properties: + configMap: + description: ConfigMap containing data to use for + the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, + kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or + its key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the + targets. + properties: + key: + description: The key of the secret to select + from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, + kind, uid?' + type: string + optional: + description: Specify whether the Secret or its + key must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus + container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus + container for the targets. + type: string + keySecret: + description: Secret containing the client key file for + the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + url: + description: URL of the endpoint to send samples to. + type: string + writeRelabelConfigs: + description: WriteRelabelConfigs holds relabel_configs to + relabel samples before they are sent to the remote_write + endpoint. + items: + description: 'RelabelConfig allows dynamic rewriting of + the label set, being applied to samples before ingestion. + It defines ``-section of Prometheus + configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. + Default is 'replace' + enum: + - replace + - keep + - drop + - hashmod + - labelmap + - labeldrop + - labelkeep + type: string + modulus: + description: Modulus to take of the hash of the source + label values. + format: int64 + type: integer + regex: + description: Regular expression against which the + extracted value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex + replace is performed if the regular expression matches. + Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated + source label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from + existing labels. Their content is concatenated using + the configured separator and matched against the + configured regular expression for the replace, keep, + and drop actions. + items: + description: LabelName is a valid Prometheus label + name which may only contain ASCII letters, numbers, + as well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is + written in a replace action. It is mandatory for + replace actions. Regex capture groups are available. + type: string + type: object + type: array + required: + - url + type: object + type: array + replicaExternalLabelName: + description: ReplicaExternalLabelName is the name of the metrics + external label used to denote replica name. Defaults to __replica__. + External label will _not_ be added when value is set to the + empty string. + type: string + replicas: + description: Replicas of each shard to deploy for metrics pods. + Number of replicas multiplied by the number of shards is the + total number of pods created. + format: int32 + type: integer + scrapeInterval: + description: ScrapeInterval is the time between consecutive scrapes. + type: string + scrapeTimeout: + description: ScrapeTimeout is the time to wait for a target to + respond before marking a scrape as failed. + type: string + shards: + description: Shards to distribute targets onto. Number of replicas + multiplied by the number of shards is the total number of pods + created. Note that scaling down shards will not reshard data + onto remaining instances, it must be manually moved. Increasing + shards will not reshard data either but it will continue to + be available from the same instances. Sharding is performed + on the content of the __address__ target meta-label. + format: int32 + type: integer + type: object + nodeSelector: + additionalProperties: + type: string + description: NodeSelector defines which nodes pods should be scheduling + on. + type: object + paused: + description: Paused prevents actions except for deletion to be performed + on the underlying managed objects. + type: boolean + podMetadata: + description: PodMetadata configures Labels and Annotations which are + propagated to created Grafana Agent pods. + properties: + annotations: + additionalProperties: + type: string + description: 'Annotations is an unstructured key value map stored + with a resource that may be set by external tools to store and + retrieve arbitrary metadata. They are not queryable and should + be preserved when modifying objects. More info: http://kubernetes.io/docs/user-guide/annotations' + type: object + labels: + additionalProperties: + type: string + description: 'Map of string keys and values that can be used to + organize and categorize (scope and select) objects. May match + selectors of replication controllers and services. More info: + http://kubernetes.io/docs/user-guide/labels' + type: object + name: + description: 'Name must be unique within a namespace. Is required + when creating resources, although some resources may allow a + client to request the generation of an appropriate name automatically. + Name is primarily intended for creation idempotence and configuration + definition. Cannot be updated. More info: http://kubernetes.io/docs/user-guide/identifiers#names' + type: string + type: object + portName: + description: Port name used for the pods and governing service. This + defaults to agent-metrics. + type: string + priorityClassName: + description: PriorityClassName is the priority class assigned to pods. + type: string + resources: + description: Resources holds requests and limits for individual pods. + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources + allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute + resources required. If Requests is omitted for a container, + it defaults to Limits if that is explicitly specified, otherwise + to an implementation-defined value. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + secrets: + description: Secrets is a list of secrets in the same namespace as + the GrafanaAgent object which will be mounted into each running + Grafana Agent pod. The secrets are mounted into /etc/grafana-agent/extra-secrets/. + items: + type: string + type: array + securityContext: + description: SecurityContext holds pod-level security attributes and + common container settings. When unspecified, defaults to the default + PodSecurityContext. + properties: + fsGroup: + description: "A special supplemental group that applies to all + containers in a pod. Some volume types allow the Kubelet to + change the ownership of that volume to be owned by the pod: + \n 1. The owning GID will be the FSGroup 2. The setgid bit is + set (new files created in the volume will be owned by FSGroup) + 3. The permission bits are OR'd with rw-rw---- \n If unset, + the Kubelet will not modify the ownership and permissions of + any volume. Note that this field cannot be set when spec.os.name + is windows." + format: int64 + type: integer + fsGroupChangePolicy: + description: 'fsGroupChangePolicy defines behavior of changing + ownership and permission of the volume before being exposed + inside Pod. This field will only apply to volume types which + support fsGroup based ownership(and permissions). It will have + no effect on ephemeral volume types such as: secret, configmaps + and emptydir. Valid values are "OnRootMismatch" and "Always". + If not specified, "Always" is used. Note that this field cannot + be set when spec.os.name is windows.' + type: string + runAsGroup: + description: The GID to run the entrypoint of the container process. + Uses runtime default if unset. May also be set in SecurityContext. If + set in both SecurityContext and PodSecurityContext, the value + specified in SecurityContext takes precedence for that container. + Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root + user. If true, the Kubelet will validate the image at runtime + to ensure that it does not run as UID 0 (root) and fail to start + the container if it does. If unset or false, no such validation + will be performed. May also be set in SecurityContext. If set + in both SecurityContext and PodSecurityContext, the value specified + in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. + Defaults to user specified in image metadata if unspecified. + May also be set in SecurityContext. If set in both SecurityContext + and PodSecurityContext, the value specified in SecurityContext + takes precedence for that container. Note that this field cannot + be set when spec.os.name is windows. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to all containers. + If unspecified, the container runtime will allocate a random + SELinux context for each container. May also be set in SecurityContext. If + set in both SecurityContext and PodSecurityContext, the value + specified in SecurityContext takes precedence for that container. + Note that this field cannot be set when spec.os.name is windows. + properties: + level: + description: Level is SELinux level label that applies to + the container. + type: string + role: + description: Role is a SELinux role label that applies to + the container. + type: string + type: + description: Type is a SELinux type label that applies to + the container. + type: string + user: + description: User is a SELinux user label that applies to + the container. + type: string + type: object + seccompProfile: + description: The seccomp options to use by the containers in this + pod. Note that this field cannot be set when spec.os.name is + windows. + properties: + localhostProfile: + description: localhostProfile indicates a profile defined + in a file on the node should be used. The profile must be + preconfigured on the node to work. Must be a descending + path, relative to the kubelet's configured seccomp profile + location. Must only be set if type is "Localhost". + type: string + type: + description: "type indicates which kind of seccomp profile + will be applied. Valid options are: \n Localhost - a profile + defined in a file on the node should be used. RuntimeDefault + - the container runtime default profile should be used. + Unconfined - no profile should be applied." + type: string + required: + - type + type: object + supplementalGroups: + description: A list of groups applied to the first process run + in each container, in addition to the container's primary GID. If + unspecified, no groups will be added to any container. Note + that this field cannot be set when spec.os.name is windows. + items: + format: int64 + type: integer + type: array + sysctls: + description: Sysctls hold a list of namespaced sysctls used for + the pod. Pods with unsupported sysctls (by the container runtime) + might fail to launch. Note that this field cannot be set when + spec.os.name is windows. + items: + description: Sysctl defines a kernel parameter to be set + properties: + name: + description: Name of a property to set + type: string + value: + description: Value of a property to set + type: string + required: + - name + - value + type: object + type: array + windowsOptions: + description: The Windows specific settings applied to all containers. + If unspecified, the options within a container's SecurityContext + will be used. If set in both SecurityContext and PodSecurityContext, + the value specified in SecurityContext takes precedence. Note + that this field cannot be set when spec.os.name is linux. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission + webhook (https://github.com/kubernetes-sigs/windows-gmsa) + inlines the contents of the GMSA credential spec named by + the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA + credential spec to use. + type: string + hostProcess: + description: HostProcess determines if a container should + be run as a 'Host Process' container. This field is alpha-level + and will only be honored by components that enable the WindowsHostProcessContainers + feature flag. Setting this field without the feature flag + will result in errors when validating the Pod. All of a + Pod's containers must have the same effective HostProcess + value (it is not allowed to have a mix of HostProcess containers + and non-HostProcess containers). In addition, if HostProcess + is true then HostNetwork must also be set to true. + type: boolean + runAsUserName: + description: The UserName in Windows to run the entrypoint + of the container process. Defaults to the user specified + in image metadata if unspecified. May also be set in PodSecurityContext. + If set in both SecurityContext and PodSecurityContext, the + value specified in SecurityContext takes precedence. + type: string + type: object + type: object + serviceAccountName: + description: ServiceAccountName is the name of the ServiceAccount + to use for running Grafana Agent pods. + type: string + storage: + description: Storage spec to specify how storage will be used. + properties: + disableMountSubPath: + description: 'Deprecated: subPath usage will be disabled by default + in a future release, this option will become unnecessary. DisableMountSubPath + allows to remove any subPath usage in volume mounts.' + type: boolean + emptyDir: + description: 'EmptyDirVolumeSource to be used by the Prometheus + StatefulSets. If specified, used in place of any volumeClaimTemplate. + More info: https://kubernetes.io/docs/concepts/storage/volumes/#emptydir' + properties: + medium: + description: 'What type of storage medium should back this + directory. The default is "" which means to use the node''s + default medium. Must be an empty string (default) or Memory. + More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + description: 'Total amount of local storage required for this + EmptyDir volume. The size limit is also applicable for memory + medium. The maximum usage on memory medium EmptyDir would + be the minimum value between the SizeLimit specified here + and the sum of memory limits of all containers in a pod. + The default is nil which means that the limit is undefined. + More info: http://kubernetes.io/docs/user-guide/volumes#emptydir' + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + ephemeral: + description: 'EphemeralVolumeSource to be used by the Prometheus + StatefulSets. This is a beta field in k8s 1.21, for lower versions, + starting with k8s 1.19, it requires enabling the GenericEphemeralVolume + feature gate. More info: https://kubernetes.io/docs/concepts/storage/ephemeral-volumes/#generic-ephemeral-volumes' + properties: + volumeClaimTemplate: + description: "Will be used to create a stand-alone PVC to + provision the volume. The pod in which this EphemeralVolumeSource + is embedded will be the owner of the PVC, i.e. the PVC will + be deleted together with the pod. The name of the PVC will + be `-` where `` is the + name from the `PodSpec.Volumes` array entry. Pod validation + will reject the pod if the concatenated name is not valid + for a PVC (for example, too long). \n An existing PVC with + that name that is not owned by the pod will *not* be used + for the pod to avoid using an unrelated volume by mistake. + Starting the pod is then blocked until the unrelated PVC + is removed. If such a pre-created PVC is meant to be used + by the pod, the PVC has to updated with an owner reference + to the pod once the pod exists. Normally this should not + be necessary, but it may be useful when manually reconstructing + a broken cluster. \n This field is read-only and no changes + will be made by Kubernetes to the PVC after it has been + created. \n Required, must not be nil." + properties: + metadata: + description: May contain labels and annotations that will + be copied into the PVC when creating it. No other fields + are allowed and will be rejected during validation. + type: object + spec: + description: The specification for the PersistentVolumeClaim. + The entire content is copied unchanged into the PVC + that gets created from this template. The same fields + as in a PersistentVolumeClaim are also valid here. + properties: + accessModes: + description: 'AccessModes contains the desired access + modes the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + dataSource: + description: 'This field can be used to specify either: + * An existing VolumeSnapshot object (snapshot.storage.k8s.io/VolumeSnapshot) + * An existing PVC (PersistentVolumeClaim) If the + provisioner or an external controller can support + the specified data source, it will create a new + volume based on the contents of the specified data + source. If the AnyVolumeDataSource feature gate + is enabled, this field will always have the same + contents as the DataSourceRef field.' + properties: + apiGroup: + description: APIGroup is the group for the resource + being referenced. If APIGroup is not specified, + the specified Kind must be in the core API group. + For any other third-party types, APIGroup is + required. + type: string + kind: + description: Kind is the type of resource being + referenced + type: string + name: + description: Name is the name of resource being + referenced + type: string + required: + - kind + - name + type: object + dataSourceRef: + description: 'Specifies the object from which to populate + the volume with data, if a non-empty volume is desired. + This may be any local object from a non-empty API + group (non core object) or a PersistentVolumeClaim + object. When this field is specified, volume binding + will only succeed if the type of the specified object + matches some installed volume populator or dynamic + provisioner. This field will replace the functionality + of the DataSource field and as such if both fields + are non-empty, they must have the same value. For + backwards compatibility, both fields (DataSource + and DataSourceRef) will be set to the same value + automatically if one of them is empty and the other + is non-empty. There are two important differences + between DataSource and DataSourceRef: * While DataSource + only allows two specific types of objects, DataSourceRef + allows any non-core object, as well as PersistentVolumeClaim + objects. * While DataSource ignores disallowed values + (dropping them), DataSourceRef preserves all values, + and generates an error if a disallowed value is + specified. (Alpha) Using this field requires the + AnyVolumeDataSource feature gate to be enabled.' + properties: + apiGroup: + description: APIGroup is the group for the resource + being referenced. If APIGroup is not specified, + the specified Kind must be in the core API group. + For any other third-party types, APIGroup is + required. + type: string + kind: + description: Kind is the type of resource being + referenced + type: string + name: + description: Name is the name of resource being + referenced + type: string + required: + - kind + - name + type: object + resources: + description: 'Resources represents the minimum resources + the volume should have. If RecoverVolumeExpansionFailure + feature is enabled users are allowed to specify + resource requirements that are lower than previous + value but must still be higher than capacity recorded + in the status field of the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#resources' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount + of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount + of compute resources required. If Requests is + omitted for a container, it defaults to Limits + if that is explicitly specified, otherwise to + an implementation-defined value. More info: + https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + selector: + description: A label query over volumes to consider + for binding. + properties: + matchExpressions: + description: matchExpressions is a list of label + selector requirements. The requirements are + ANDed. + items: + description: A label selector requirement is + a selector that contains values, a key, and + an operator that relates the key and values. + properties: + key: + description: key is the label key that the + selector applies to. + type: string + operator: + description: operator represents a key's + relationship to a set of values. Valid + operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string + values. If the operator is In or NotIn, + the values array must be non-empty. If + the operator is Exists or DoesNotExist, + the values array must be empty. This array + is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} + pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, + whose key field is "key", the operator is "In", + and the values array contains only "value". + The requirements are ANDed. + type: object + type: object + storageClassName: + description: 'Name of the StorageClass required by + the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#class-1' + type: string + volumeMode: + description: volumeMode defines what type of volume + is required by the claim. Value of Filesystem is + implied when not included in claim spec. + type: string + volumeName: + description: VolumeName is the binding reference to + the PersistentVolume backing this claim. + type: string + type: object + required: + - spec + type: object + type: object + volumeClaimTemplate: + description: A PVC spec to be used by the Prometheus StatefulSets. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this + representation of an object. Servers should convert recognized + schemas to the latest internal value, and may reject unrecognized + values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST + resource this object represents. Servers may infer this + from the endpoint the client submits requests to. Cannot + be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + description: EmbeddedMetadata contains metadata relevant to + an EmbeddedResource. + properties: + annotations: + additionalProperties: + type: string + description: 'Annotations is an unstructured key value + map stored with a resource that may be set by external + tools to store and retrieve arbitrary metadata. They + are not queryable and should be preserved when modifying + objects. More info: http://kubernetes.io/docs/user-guide/annotations' + type: object + labels: + additionalProperties: + type: string + description: 'Map of string keys and values that can be + used to organize and categorize (scope and select) objects. + May match selectors of replication controllers and services. + More info: http://kubernetes.io/docs/user-guide/labels' + type: object + name: + description: 'Name must be unique within a namespace. + Is required when creating resources, although some resources + may allow a client to request the generation of an appropriate + name automatically. Name is primarily intended for creation + idempotence and configuration definition. Cannot be + updated. More info: http://kubernetes.io/docs/user-guide/identifiers#names' + type: string + type: object + spec: + description: 'Spec defines the desired characteristics of + a volume requested by a pod author. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + accessModes: + description: 'AccessModes contains the desired access + modes the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + dataSource: + description: 'This field can be used to specify either: + * An existing VolumeSnapshot object (snapshot.storage.k8s.io/VolumeSnapshot) + * An existing PVC (PersistentVolumeClaim) If the provisioner + or an external controller can support the specified + data source, it will create a new volume based on the + contents of the specified data source. If the AnyVolumeDataSource + feature gate is enabled, this field will always have + the same contents as the DataSourceRef field.' + properties: + apiGroup: + description: APIGroup is the group for the resource + being referenced. If APIGroup is not specified, + the specified Kind must be in the core API group. + For any other third-party types, APIGroup is required. + type: string + kind: + description: Kind is the type of resource being referenced + type: string + name: + description: Name is the name of resource being referenced + type: string + required: + - kind + - name + type: object + dataSourceRef: + description: 'Specifies the object from which to populate + the volume with data, if a non-empty volume is desired. + This may be any local object from a non-empty API group + (non core object) or a PersistentVolumeClaim object. + When this field is specified, volume binding will only + succeed if the type of the specified object matches + some installed volume populator or dynamic provisioner. + This field will replace the functionality of the DataSource + field and as such if both fields are non-empty, they + must have the same value. For backwards compatibility, + both fields (DataSource and DataSourceRef) will be set + to the same value automatically if one of them is empty + and the other is non-empty. There are two important + differences between DataSource and DataSourceRef: * + While DataSource only allows two specific types of objects, + DataSourceRef allows any non-core object, as well as + PersistentVolumeClaim objects. * While DataSource ignores + disallowed values (dropping them), DataSourceRef preserves + all values, and generates an error if a disallowed value + is specified. (Alpha) Using this field requires the + AnyVolumeDataSource feature gate to be enabled.' + properties: + apiGroup: + description: APIGroup is the group for the resource + being referenced. If APIGroup is not specified, + the specified Kind must be in the core API group. + For any other third-party types, APIGroup is required. + type: string + kind: + description: Kind is the type of resource being referenced + type: string + name: + description: Name is the name of resource being referenced + type: string + required: + - kind + - name + type: object + resources: + description: 'Resources represents the minimum resources + the volume should have. If RecoverVolumeExpansionFailure + feature is enabled users are allowed to specify resource + requirements that are lower than previous value but + must still be higher than capacity recorded in the status + field of the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#resources' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount + of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount + of compute resources required. If Requests is omitted + for a container, it defaults to Limits if that is + explicitly specified, otherwise to an implementation-defined + value. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + selector: + description: A label query over volumes to consider for + binding. + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector + that contains values, a key, and an operator that + relates the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are In, + NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. + If the operator is In or NotIn, the values + array must be non-empty. If the operator is + Exists or DoesNotExist, the values array must + be empty. This array is replaced during a + strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. + A single {key,value} in the matchLabels map is equivalent + to an element of matchExpressions, whose key field + is "key", the operator is "In", and the values array + contains only "value". The requirements are ANDed. + type: object + type: object + storageClassName: + description: 'Name of the StorageClass required by the + claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#class-1' + type: string + volumeMode: + description: volumeMode defines what type of volume is + required by the claim. Value of Filesystem is implied + when not included in claim spec. + type: string + volumeName: + description: VolumeName is the binding reference to the + PersistentVolume backing this claim. + type: string + type: object + status: + description: 'Status represents the current information/status + of a persistent volume claim. Read-only. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + accessModes: + description: 'AccessModes contains the actual access modes + the volume backing the PVC has. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + allocatedResources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: The storage resource within AllocatedResources + tracks the capacity allocated to a PVC. It may be larger + than the actual capacity when a volume expansion operation + is requested. For storage quota, the larger value from + allocatedResources and PVC.spec.resources is used. If + allocatedResources is not set, PVC.spec.resources alone + is used for quota calculation. If a volume expansion + capacity request is lowered, allocatedResources is only + lowered if there are no expansion operations in progress + and if the actual volume capacity is equal or lower + than the requested capacity. This is an alpha field + and requires enabling RecoverVolumeExpansionFailure + feature. + type: object + capacity: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Represents the actual resources of the underlying + volume. + type: object + conditions: + description: Current Condition of persistent volume claim. + If underlying persistent volume is being resized then + the Condition will be set to 'ResizeStarted'. + items: + description: PersistentVolumeClaimCondition contails + details about state of pvc + properties: + lastProbeTime: + description: Last time we probed the condition. + format: date-time + type: string + lastTransitionTime: + description: Last time the condition transitioned + from one status to another. + format: date-time + type: string + message: + description: Human-readable message indicating details + about last transition. + type: string + reason: + description: Unique, this should be a short, machine + understandable string that gives the reason for + condition's last transition. If it reports "ResizeStarted" + that means the underlying persistent volume is + being resized. + type: string + status: + type: string + type: + description: PersistentVolumeClaimConditionType + is a valid value of PersistentVolumeClaimCondition.Type + type: string + required: + - status + - type + type: object + type: array + phase: + description: Phase represents the current phase of PersistentVolumeClaim. + type: string + resizeStatus: + description: ResizeStatus stores status of resize operation. + ResizeStatus is not set by default but when expansion + is complete resizeStatus is set to empty string by resize + controller or kubelet. This is an alpha field and requires + enabling RecoverVolumeExpansionFailure feature. + type: string + type: object + type: object + type: object + tolerations: + description: Tolerations, if specified, controls the pod's tolerations. + items: + description: The pod this Toleration is attached to tolerates any + taint that matches the triple using the matching + operator . + properties: + effect: + description: Effect indicates the taint effect to match. Empty + means match all taint effects. When specified, allowed values + are NoSchedule, PreferNoSchedule and NoExecute. + type: string + key: + description: Key is the taint key that the toleration applies + to. Empty means match all taint keys. If the key is empty, + operator must be Exists; this combination means to match all + values and all keys. + type: string + operator: + description: Operator represents a key's relationship to the + value. Valid operators are Exists and Equal. Defaults to Equal. + Exists is equivalent to wildcard for value, so that a pod + can tolerate all taints of a particular category. + type: string + tolerationSeconds: + description: TolerationSeconds represents the period of time + the toleration (which must be of effect NoExecute, otherwise + this field is ignored) tolerates the taint. By default, it + is not set, which means tolerate the taint forever (do not + evict). Zero and negative values will be treated as 0 (evict + immediately) by the system. + format: int64 + type: integer + value: + description: Value is the taint value the toleration matches + to. If the operator is Exists, the value should be empty, + otherwise just a regular string. + type: string + type: object + type: array + topologySpreadConstraints: + description: TopologySpreadConstraints, if specified, controls the + pod's topology spread constraints. + items: + description: TopologySpreadConstraint specifies how to spread matching + pods among the given topology. + properties: + labelSelector: + description: LabelSelector is used to find matching pods. Pods + that match this label selector are counted to determine the + number of pods in their corresponding topology domain. + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector + that contains values, a key, and an operator that relates + the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: operator represents a key's relationship + to a set of values. Valid operators are In, NotIn, + Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. + If the operator is In or NotIn, the values array + must be non-empty. If the operator is Exists or + DoesNotExist, the values array must be empty. This + array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. + A single {key,value} in the matchLabels map is equivalent + to an element of matchExpressions, whose key field is + "key", the operator is "In", and the values array contains + only "value". The requirements are ANDed. + type: object + type: object + maxSkew: + description: 'MaxSkew describes the degree to which pods may + be unevenly distributed. When `whenUnsatisfiable=DoNotSchedule`, + it is the maximum permitted difference between the number + of matching pods in the target topology and the global minimum. + For example, in a 3-zone cluster, MaxSkew is set to 1, and + pods with the same labelSelector spread as 1/1/0: | zone1 + | zone2 | zone3 | | P | P | | - if MaxSkew is + 1, incoming pod can only be scheduled to zone3 to become 1/1/1; + scheduling it onto zone1(zone2) would make the ActualSkew(2-0) + on zone1(zone2) violate MaxSkew(1). - if MaxSkew is 2, incoming + pod can be scheduled onto any zone. When `whenUnsatisfiable=ScheduleAnyway`, + it is used to give higher precedence to topologies that satisfy + it. It''s a required field. Default value is 1 and 0 is not + allowed.' + format: int32 + type: integer + topologyKey: + description: TopologyKey is the key of node labels. Nodes that + have a label with this key and identical values are considered + to be in the same topology. We consider each + as a "bucket", and try to put balanced number of pods into + each bucket. It's a required field. + type: string + whenUnsatisfiable: + description: 'WhenUnsatisfiable indicates how to deal with a + pod if it doesn''t satisfy the spread constraint. - DoNotSchedule + (default) tells the scheduler not to schedule it. - ScheduleAnyway + tells the scheduler to schedule the pod in any location, but + giving higher precedence to topologies that would help reduce + the skew. A constraint is considered "Unsatisfiable" for an + incoming pod if and only if every possible node assignment + for that pod would violate "MaxSkew" on some topology. For + example, in a 3-zone cluster, MaxSkew is set to 1, and pods + with the same labelSelector spread as 3/1/1: | zone1 | zone2 + | zone3 | | P P P | P | P | If WhenUnsatisfiable is + set to DoNotSchedule, incoming pod can only be scheduled to + zone2(zone3) to become 3/2/1(3/1/2) as ActualSkew(2-1) on + zone2(zone3) satisfies MaxSkew(1). In other words, the cluster + can still be imbalanced, but scheduler won''t make it *more* + imbalanced. It''s a required field.' + type: string + required: + - maxSkew + - topologyKey + - whenUnsatisfiable + type: object + type: array + version: + description: Version of Grafana Agent to be deployed. + type: string + volumeMounts: + description: VolumeMounts allows configuration of additional VolumeMounts + on the output StatefulSet definition. VolumEMounts specified will + be appended to other VolumeMounts in the Grafana Agent container + that are generated as a result of StorageSpec objects. + items: + description: VolumeMount describes a mounting of a Volume within + a container. + properties: + mountPath: + description: Path within the container at which the volume should + be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated + from the host to container and the other way around. When + not set, MountPropagationNone is used. This field is beta + in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise + (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's + volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the + container's volume should be mounted. Behaves similarly to + SubPath but environment variable references $(VAR_NAME) are + expanded using the container's environment. Defaults to "" + (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + volumes: + description: Volumes allows configuration of additional volumes on + the output StatefulSet definition. Volumes specified will be appended + to other volumes that are generated as a result of StorageSpec objects. + items: + description: Volume represents a named volume in a pod that may + be accessed by any container in the pod. + properties: + awsElasticBlockStore: + description: 'AWSElasticBlockStore represents an AWS Disk resource + that is attached to a kubelet''s host machine and then exposed + to the pod. More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + properties: + fsType: + description: 'Filesystem type of the volume that you want + to mount. Tip: Ensure that the filesystem type is supported + by the host operating system. Examples: "ext4", "xfs", + "ntfs". Implicitly inferred to be "ext4" if unspecified. + More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore + TODO: how do we prevent errors in the filesystem from + compromising the machine' + type: string + partition: + description: 'The partition in the volume that you want + to mount. If omitted, the default is to mount by volume + name. Examples: For volume /dev/sda1, you specify the + partition as "1". Similarly, the volume partition for + /dev/sda is "0" (or you can leave the property empty).' + format: int32 + type: integer + readOnly: + description: 'Specify "true" to force and set the ReadOnly + property in VolumeMounts to "true". If omitted, the default + is "false". More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + type: boolean + volumeID: + description: 'Unique ID of the persistent disk resource + in AWS (Amazon EBS volume). More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + type: string + required: + - volumeID + type: object + azureDisk: + description: AzureDisk represents an Azure Data Disk mount on + the host and bind mount to the pod. + properties: + cachingMode: + description: 'Host Caching mode: None, Read Only, Read Write.' + type: string + diskName: + description: The Name of the data disk in the blob storage + type: string + diskURI: + description: The URI the data disk in the blob storage + type: string + fsType: + description: Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + kind: + description: 'Expected values Shared: multiple blob disks + per storage account Dedicated: single blob disk per storage + account Managed: azure managed data disk (only in managed + availability set). defaults to shared' + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here + will force the ReadOnly setting in VolumeMounts. + type: boolean + required: + - diskName + - diskURI + type: object + azureFile: + description: AzureFile represents an Azure File Service mount + on the host and bind mount to the pod. + properties: + readOnly: + description: Defaults to false (read/write). ReadOnly here + will force the ReadOnly setting in VolumeMounts. + type: boolean + secretName: + description: the name of secret that contains Azure Storage + Account Name and Key + type: string + shareName: + description: Share Name + type: string + required: + - secretName + - shareName + type: object + cephfs: + description: CephFS represents a Ceph FS mount on the host that + shares a pod's lifetime + properties: + monitors: + description: 'Required: Monitors is a collection of Ceph + monitors More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + items: + type: string + type: array + path: + description: 'Optional: Used as the mounted root, rather + than the full Ceph tree, default is /' + type: string + readOnly: + description: 'Optional: Defaults to false (read/write). + ReadOnly here will force the ReadOnly setting in VolumeMounts. + More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: boolean + secretFile: + description: 'Optional: SecretFile is the path to key ring + for User, default is /etc/ceph/user.secret More info: + https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: string + secretRef: + description: 'Optional: SecretRef is reference to the authentication + secret for User, default is empty. More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + user: + description: 'Optional: User is the rados user name, default + is admin More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: string + required: + - monitors + type: object + cinder: + description: 'Cinder represents a cinder volume attached and + mounted on kubelets host machine. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + properties: + fsType: + description: 'Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Examples: + "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" + if unspecified. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: string + readOnly: + description: 'Optional: Defaults to false (read/write). + ReadOnly here will force the ReadOnly setting in VolumeMounts. + More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: boolean + secretRef: + description: 'Optional: points to a secret object containing + parameters used to connect to OpenStack.' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + volumeID: + description: 'volume id used to identify the volume in cinder. + More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: string + required: + - volumeID + type: object + configMap: + description: ConfigMap represents a configMap that should populate + this volume + properties: + defaultMode: + description: 'Optional: mode bits used to set permissions + on created files by default. Must be an octal value between + 0000 and 0777 or a decimal value between 0 and 511. YAML + accepts both octal and decimal values, JSON requires decimal + values for mode bits. Defaults to 0644. Directories within + the path are not affected by this setting. This might + be in conflict with other options that affect the file + mode, like fsGroup, and the result can be other mode bits + set.' + format: int32 + type: integer + items: + description: If unspecified, each key-value pair in the + Data field of the referenced ConfigMap will be projected + into the volume as a file whose name is the key and content + is the value. If specified, the listed keys will be projected + into the specified paths, and unlisted keys will not be + present. If a key is specified which is not present in + the ConfigMap, the volume setup will error unless it is + marked optional. Paths must be relative and may not contain + the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits used to set permissions + on this file. Must be an octal value between 0000 + and 0777 or a decimal value between 0 and 511. YAML + accepts both octal and decimal values, JSON requires + decimal values for mode bits. If not specified, + the volume defaultMode will be used. This might + be in conflict with other options that affect the + file mode, like fsGroup, and the result can be other + mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map + the key to. May not be an absolute path. May not + contain the path element '..'. May not start with + the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its keys must + be defined + type: boolean + type: object + csi: + description: CSI (Container Storage Interface) represents ephemeral + storage that is handled by certain external CSI drivers (Beta + feature). + properties: + driver: + description: Driver is the name of the CSI driver that handles + this volume. Consult with your admin for the correct name + as registered in the cluster. + type: string + fsType: + description: Filesystem type to mount. Ex. "ext4", "xfs", + "ntfs". If not provided, the empty value is passed to + the associated CSI driver which will determine the default + filesystem to apply. + type: string + nodePublishSecretRef: + description: NodePublishSecretRef is a reference to the + secret object containing sensitive information to pass + to the CSI driver to complete the CSI NodePublishVolume + and NodeUnpublishVolume calls. This field is optional, + and may be empty if no secret is required. If the secret + object contains more than one secret, all secret references + are passed. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + readOnly: + description: Specifies a read-only configuration for the + volume. Defaults to false (read/write). + type: boolean + volumeAttributes: + additionalProperties: + type: string + description: VolumeAttributes stores driver-specific properties + that are passed to the CSI driver. Consult your driver's + documentation for supported values. + type: object + required: + - driver + type: object + downwardAPI: + description: DownwardAPI represents downward API about the pod + that should populate this volume + properties: + defaultMode: + description: 'Optional: mode bits to use on created files + by default. Must be a Optional: mode bits used to set + permissions on created files by default. Must be an octal + value between 0000 and 0777 or a decimal value between + 0 and 511. YAML accepts both octal and decimal values, + JSON requires decimal values for mode bits. Defaults to + 0644. Directories within the path are not affected by + this setting. This might be in conflict with other options + that affect the file mode, like fsGroup, and the result + can be other mode bits set.' + format: int32 + type: integer + items: + description: Items is a list of downward API volume file + items: + description: DownwardAPIVolumeFile represents information + to create the file containing the pod field + properties: + fieldRef: + description: 'Required: Selects a field of the pod: + only annotations, labels, name and namespace are + supported.' + properties: + apiVersion: + description: Version of the schema the FieldPath + is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the + specified API version. + type: string + required: + - fieldPath + type: object + mode: + description: 'Optional: mode bits used to set permissions + on this file, must be an octal value between 0000 + and 0777 or a decimal value between 0 and 511. YAML + accepts both octal and decimal values, JSON requires + decimal values for mode bits. If not specified, + the volume defaultMode will be used. This might + be in conflict with other options that affect the + file mode, like fsGroup, and the result can be other + mode bits set.' + format: int32 + type: integer + path: + description: 'Required: Path is the relative path + name of the file to be created. Must not be absolute + or contain the ''..'' path. Must be utf-8 encoded. + The first item of the relative path must not start + with ''..''' + type: string + resourceFieldRef: + description: 'Selects a resource of the container: + only resources limits and requests (limits.cpu, + limits.memory, requests.cpu and requests.memory) + are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, + optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the + exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + required: + - path + type: object + type: array + type: object + emptyDir: + description: 'EmptyDir represents a temporary directory that + shares a pod''s lifetime. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + properties: + medium: + description: 'What type of storage medium should back this + directory. The default is "" which means to use the node''s + default medium. Must be an empty string (default) or Memory. + More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + description: 'Total amount of local storage required for + this EmptyDir volume. The size limit is also applicable + for memory medium. The maximum usage on memory medium + EmptyDir would be the minimum value between the SizeLimit + specified here and the sum of memory limits of all containers + in a pod. The default is nil which means that the limit + is undefined. More info: http://kubernetes.io/docs/user-guide/volumes#emptydir' + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + ephemeral: + description: "Ephemeral represents a volume that is handled + by a cluster storage driver. The volume's lifecycle is tied + to the pod that defines it - it will be created before the + pod starts, and deleted when the pod is removed. \n Use this + if: a) the volume is only needed while the pod runs, b) features + of normal volumes like restoring from snapshot or capacity + tracking are needed, c) the storage driver is specified through + a storage class, and d) the storage driver supports dynamic + volume provisioning through a PersistentVolumeClaim (see EphemeralVolumeSource + for more information on the connection between this volume + type and PersistentVolumeClaim). \n Use PersistentVolumeClaim + or one of the vendor-specific APIs for volumes that persist + for longer than the lifecycle of an individual pod. \n Use + CSI for light-weight local ephemeral volumes if the CSI driver + is meant to be used that way - see the documentation of the + driver for more information. \n A pod can use both types of + ephemeral volumes and persistent volumes at the same time." + properties: + volumeClaimTemplate: + description: "Will be used to create a stand-alone PVC to + provision the volume. The pod in which this EphemeralVolumeSource + is embedded will be the owner of the PVC, i.e. the PVC + will be deleted together with the pod. The name of the + PVC will be `-` where `` is the name from the `PodSpec.Volumes` array entry. + Pod validation will reject the pod if the concatenated + name is not valid for a PVC (for example, too long). \n + An existing PVC with that name that is not owned by the + pod will *not* be used for the pod to avoid using an unrelated + volume by mistake. Starting the pod is then blocked until + the unrelated PVC is removed. If such a pre-created PVC + is meant to be used by the pod, the PVC has to updated + with an owner reference to the pod once the pod exists. + Normally this should not be necessary, but it may be useful + when manually reconstructing a broken cluster. \n This + field is read-only and no changes will be made by Kubernetes + to the PVC after it has been created. \n Required, must + not be nil." + properties: + metadata: + description: May contain labels and annotations that + will be copied into the PVC when creating it. No other + fields are allowed and will be rejected during validation. + type: object + spec: + description: The specification for the PersistentVolumeClaim. + The entire content is copied unchanged into the PVC + that gets created from this template. The same fields + as in a PersistentVolumeClaim are also valid here. + properties: + accessModes: + description: 'AccessModes contains the desired access + modes the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + dataSource: + description: 'This field can be used to specify + either: * An existing VolumeSnapshot object (snapshot.storage.k8s.io/VolumeSnapshot) + * An existing PVC (PersistentVolumeClaim) If the + provisioner or an external controller can support + the specified data source, it will create a new + volume based on the contents of the specified + data source. If the AnyVolumeDataSource feature + gate is enabled, this field will always have the + same contents as the DataSourceRef field.' + properties: + apiGroup: + description: APIGroup is the group for the resource + being referenced. If APIGroup is not specified, + the specified Kind must be in the core API + group. For any other third-party types, APIGroup + is required. + type: string + kind: + description: Kind is the type of resource being + referenced + type: string + name: + description: Name is the name of resource being + referenced + type: string + required: + - kind + - name + type: object + dataSourceRef: + description: 'Specifies the object from which to + populate the volume with data, if a non-empty + volume is desired. This may be any local object + from a non-empty API group (non core object) or + a PersistentVolumeClaim object. When this field + is specified, volume binding will only succeed + if the type of the specified object matches some + installed volume populator or dynamic provisioner. + This field will replace the functionality of the + DataSource field and as such if both fields are + non-empty, they must have the same value. For + backwards compatibility, both fields (DataSource + and DataSourceRef) will be set to the same value + automatically if one of them is empty and the + other is non-empty. There are two important differences + between DataSource and DataSourceRef: * While + DataSource only allows two specific types of objects, + DataSourceRef allows any non-core object, as well + as PersistentVolumeClaim objects. * While DataSource + ignores disallowed values (dropping them), DataSourceRef + preserves all values, and generates an error if + a disallowed value is specified. (Alpha) Using + this field requires the AnyVolumeDataSource feature + gate to be enabled.' + properties: + apiGroup: + description: APIGroup is the group for the resource + being referenced. If APIGroup is not specified, + the specified Kind must be in the core API + group. For any other third-party types, APIGroup + is required. + type: string + kind: + description: Kind is the type of resource being + referenced + type: string + name: + description: Name is the name of resource being + referenced + type: string + required: + - kind + - name + type: object + resources: + description: 'Resources represents the minimum resources + the volume should have. If RecoverVolumeExpansionFailure + feature is enabled users are allowed to specify + resource requirements that are lower than previous + value but must still be higher than capacity recorded + in the status field of the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#resources' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount + of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum + amount of compute resources required. If Requests + is omitted for a container, it defaults to + Limits if that is explicitly specified, otherwise + to an implementation-defined value. More info: + https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + selector: + description: A label query over volumes to consider + for binding. + properties: + matchExpressions: + description: matchExpressions is a list of label + selector requirements. The requirements are + ANDed. + items: + description: A label selector requirement + is a selector that contains values, a key, + and an operator that relates the key and + values. + properties: + key: + description: key is the label key that + the selector applies to. + type: string + operator: + description: operator represents a key's + relationship to a set of values. Valid + operators are In, NotIn, Exists and + DoesNotExist. + type: string + values: + description: values is an array of string + values. If the operator is In or NotIn, + the values array must be non-empty. + If the operator is Exists or DoesNotExist, + the values array must be empty. This + array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} + pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, + whose key field is "key", the operator is + "In", and the values array contains only "value". + The requirements are ANDed. + type: object + type: object + storageClassName: + description: 'Name of the StorageClass required + by the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#class-1' + type: string + volumeMode: + description: volumeMode defines what type of volume + is required by the claim. Value of Filesystem + is implied when not included in claim spec. + type: string + volumeName: + description: VolumeName is the binding reference + to the PersistentVolume backing this claim. + type: string + type: object + required: + - spec + type: object + type: object + fc: + description: FC represents a Fibre Channel resource that is + attached to a kubelet's host machine and then exposed to the + pod. + properties: + fsType: + description: 'Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + TODO: how do we prevent errors in the filesystem from + compromising the machine' + type: string + lun: + description: 'Optional: FC target lun number' + format: int32 + type: integer + readOnly: + description: 'Optional: Defaults to false (read/write). + ReadOnly here will force the ReadOnly setting in VolumeMounts.' + type: boolean + targetWWNs: + description: 'Optional: FC target worldwide names (WWNs)' + items: + type: string + type: array + wwids: + description: 'Optional: FC volume world wide identifiers + (wwids) Either wwids or combination of targetWWNs and + lun must be set, but not both simultaneously.' + items: + type: string + type: array + type: object + flexVolume: + description: FlexVolume represents a generic volume resource + that is provisioned/attached using an exec based plugin. + properties: + driver: + description: Driver is the name of the driver to use for + this volume. + type: string + fsType: + description: Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". The default filesystem depends on FlexVolume + script. + type: string + options: + additionalProperties: + type: string + description: 'Optional: Extra command options if any.' + type: object + readOnly: + description: 'Optional: Defaults to false (read/write). + ReadOnly here will force the ReadOnly setting in VolumeMounts.' + type: boolean + secretRef: + description: 'Optional: SecretRef is reference to the secret + object containing sensitive information to pass to the + plugin scripts. This may be empty if no secret object + is specified. If the secret object contains more than + one secret, all secrets are passed to the plugin scripts.' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + required: + - driver + type: object + flocker: + description: Flocker represents a Flocker volume attached to + a kubelet's host machine. This depends on the Flocker control + service being running + properties: + datasetName: + description: Name of the dataset stored as metadata -> name + on the dataset for Flocker should be considered as deprecated + type: string + datasetUUID: + description: UUID of the dataset. This is unique identifier + of a Flocker dataset + type: string + type: object + gcePersistentDisk: + description: 'GCEPersistentDisk represents a GCE Disk resource + that is attached to a kubelet''s host machine and then exposed + to the pod. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + properties: + fsType: + description: 'Filesystem type of the volume that you want + to mount. Tip: Ensure that the filesystem type is supported + by the host operating system. Examples: "ext4", "xfs", + "ntfs". Implicitly inferred to be "ext4" if unspecified. + More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk + TODO: how do we prevent errors in the filesystem from + compromising the machine' + type: string + partition: + description: 'The partition in the volume that you want + to mount. If omitted, the default is to mount by volume + name. Examples: For volume /dev/sda1, you specify the + partition as "1". Similarly, the volume partition for + /dev/sda is "0" (or you can leave the property empty). + More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + format: int32 + type: integer + pdName: + description: 'Unique name of the PD resource in GCE. Used + to identify the disk in GCE. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + type: string + readOnly: + description: 'ReadOnly here will force the ReadOnly setting + in VolumeMounts. Defaults to false. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + type: boolean + required: + - pdName + type: object + gitRepo: + description: 'GitRepo represents a git repository at a particular + revision. DEPRECATED: GitRepo is deprecated. To provision + a container with a git repo, mount an EmptyDir into an InitContainer + that clones the repo using git, then mount the EmptyDir into + the Pod''s container.' + properties: + directory: + description: Target directory name. Must not contain or + start with '..'. If '.' is supplied, the volume directory + will be the git repository. Otherwise, if specified, + the volume will contain the git repository in the subdirectory + with the given name. + type: string + repository: + description: Repository URL + type: string + revision: + description: Commit hash for the specified revision. + type: string + required: + - repository + type: object + glusterfs: + description: 'Glusterfs represents a Glusterfs mount on the + host that shares a pod''s lifetime. More info: https://examples.k8s.io/volumes/glusterfs/README.md' + properties: + endpoints: + description: 'EndpointsName is the endpoint name that details + Glusterfs topology. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: string + path: + description: 'Path is the Glusterfs volume path. More info: + https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: string + readOnly: + description: 'ReadOnly here will force the Glusterfs volume + to be mounted with read-only permissions. Defaults to + false. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: boolean + required: + - endpoints + - path + type: object + hostPath: + description: 'HostPath represents a pre-existing file or directory + on the host machine that is directly exposed to the container. + This is generally used for system agents or other privileged + things that are allowed to see the host machine. Most containers + will NOT need this. More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath + --- TODO(jonesdl) We need to restrict who can use host directory + mounts and who can/can not mount host directories as read/write.' + properties: + path: + description: 'Path of the directory on the host. If the + path is a symlink, it will follow the link to the real + path. More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath' + type: string + type: + description: 'Type for HostPath Volume Defaults to "" More + info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath' + type: string + required: + - path + type: object + iscsi: + description: 'ISCSI represents an ISCSI Disk resource that is + attached to a kubelet''s host machine and then exposed to + the pod. More info: https://examples.k8s.io/volumes/iscsi/README.md' + properties: + chapAuthDiscovery: + description: whether support iSCSI Discovery CHAP authentication + type: boolean + chapAuthSession: + description: whether support iSCSI Session CHAP authentication + type: boolean + fsType: + description: 'Filesystem type of the volume that you want + to mount. Tip: Ensure that the filesystem type is supported + by the host operating system. Examples: "ext4", "xfs", + "ntfs". Implicitly inferred to be "ext4" if unspecified. + More info: https://kubernetes.io/docs/concepts/storage/volumes#iscsi + TODO: how do we prevent errors in the filesystem from + compromising the machine' + type: string + initiatorName: + description: Custom iSCSI Initiator Name. If initiatorName + is specified with iscsiInterface simultaneously, new iSCSI + interface : will be created + for the connection. + type: string + iqn: + description: Target iSCSI Qualified Name. + type: string + iscsiInterface: + description: iSCSI Interface Name that uses an iSCSI transport. + Defaults to 'default' (tcp). + type: string + lun: + description: iSCSI Target Lun number. + format: int32 + type: integer + portals: + description: iSCSI Target Portal List. The portal is either + an IP or ip_addr:port if the port is other than default + (typically TCP ports 860 and 3260). + items: + type: string + type: array + readOnly: + description: ReadOnly here will force the ReadOnly setting + in VolumeMounts. Defaults to false. + type: boolean + secretRef: + description: CHAP Secret for iSCSI target and initiator + authentication + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + targetPortal: + description: iSCSI Target Portal. The Portal is either an + IP or ip_addr:port if the port is other than default (typically + TCP ports 860 and 3260). + type: string + required: + - iqn + - lun + - targetPortal + type: object + name: + description: 'Volume''s name. Must be a DNS_LABEL and unique + within the pod. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + nfs: + description: 'NFS represents an NFS mount on the host that shares + a pod''s lifetime More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + properties: + path: + description: 'Path that is exported by the NFS server. More + info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: string + readOnly: + description: 'ReadOnly here will force the NFS export to + be mounted with read-only permissions. Defaults to false. + More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: boolean + server: + description: 'Server is the hostname or IP address of the + NFS server. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: string + required: + - path + - server + type: object + persistentVolumeClaim: + description: 'PersistentVolumeClaimVolumeSource represents a + reference to a PersistentVolumeClaim in the same namespace. + More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + claimName: + description: 'ClaimName is the name of a PersistentVolumeClaim + in the same namespace as the pod using this volume. More + info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + type: string + readOnly: + description: Will force the ReadOnly setting in VolumeMounts. + Default false. + type: boolean + required: + - claimName + type: object + photonPersistentDisk: + description: PhotonPersistentDisk represents a PhotonController + persistent disk attached and mounted on kubelets host machine + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + pdID: + description: ID that identifies Photon Controller persistent + disk + type: string + required: + - pdID + type: object + portworxVolume: + description: PortworxVolume represents a portworx volume attached + and mounted on kubelets host machine + properties: + fsType: + description: FSType represents the filesystem type to mount + Must be a filesystem type supported by the host operating + system. Ex. "ext4", "xfs". Implicitly inferred to be "ext4" + if unspecified. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here + will force the ReadOnly setting in VolumeMounts. + type: boolean + volumeID: + description: VolumeID uniquely identifies a Portworx volume + type: string + required: + - volumeID + type: object + projected: + description: Items for all in one resources secrets, configmaps, + and downward API + properties: + defaultMode: + description: Mode bits used to set permissions on created + files by default. Must be an octal value between 0000 + and 0777 or a decimal value between 0 and 511. YAML accepts + both octal and decimal values, JSON requires decimal values + for mode bits. Directories within the path are not affected + by this setting. This might be in conflict with other + options that affect the file mode, like fsGroup, and the + result can be other mode bits set. + format: int32 + type: integer + sources: + description: list of volume projections + items: + description: Projection that may be projected along with + other supported volume types + properties: + configMap: + description: information about the configMap data + to project + properties: + items: + description: If unspecified, each key-value pair + in the Data field of the referenced ConfigMap + will be projected into the volume as a file + whose name is the key and content is the value. + If specified, the listed keys will be projected + into the specified paths, and unlisted keys + will not be present. If a key is specified which + is not present in the ConfigMap, the volume + setup will error unless it is marked optional. + Paths must be relative and may not contain the + '..' path or start with '..'. + items: + description: Maps a string key to a path within + a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits used to + set permissions on this file. Must be + an octal value between 0000 and 0777 or + a decimal value between 0 and 511. YAML + accepts both octal and decimal values, + JSON requires decimal values for mode + bits. If not specified, the volume defaultMode + will be used. This might be in conflict + with other options that affect the file + mode, like fsGroup, and the result can + be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file + to map the key to. May not be an absolute + path. May not contain the path element + '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or + its keys must be defined + type: boolean + type: object + downwardAPI: + description: information about the downwardAPI data + to project + properties: + items: + description: Items is a list of DownwardAPIVolume + file + items: + description: DownwardAPIVolumeFile represents + information to create the file containing + the pod field + properties: + fieldRef: + description: 'Required: Selects a field + of the pod: only annotations, labels, + name and namespace are supported.' + properties: + apiVersion: + description: Version of the schema the + FieldPath is written in terms of, + defaults to "v1". + type: string + fieldPath: + description: Path of the field to select + in the specified API version. + type: string + required: + - fieldPath + type: object + mode: + description: 'Optional: mode bits used to + set permissions on this file, must be + an octal value between 0000 and 0777 or + a decimal value between 0 and 511. YAML + accepts both octal and decimal values, + JSON requires decimal values for mode + bits. If not specified, the volume defaultMode + will be used. This might be in conflict + with other options that affect the file + mode, like fsGroup, and the result can + be other mode bits set.' + format: int32 + type: integer + path: + description: 'Required: Path is the relative + path name of the file to be created. Must + not be absolute or contain the ''..'' + path. Must be utf-8 encoded. The first + item of the relative path must not start + with ''..''' + type: string + resourceFieldRef: + description: 'Selects a resource of the + container: only resources limits and requests + (limits.cpu, limits.memory, requests.cpu + and requests.memory) are currently supported.' + properties: + containerName: + description: 'Container name: required + for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format + of the exposed resources, defaults + to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to + select' + type: string + required: + - resource + type: object + required: + - path + type: object + type: array + type: object + secret: + description: information about the secret data to + project + properties: + items: + description: If unspecified, each key-value pair + in the Data field of the referenced Secret will + be projected into the volume as a file whose + name is the key and content is the value. If + specified, the listed keys will be projected + into the specified paths, and unlisted keys + will not be present. If a key is specified which + is not present in the Secret, the volume setup + will error unless it is marked optional. Paths + must be relative and may not contain the '..' + path or start with '..'. + items: + description: Maps a string key to a path within + a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits used to + set permissions on this file. Must be + an octal value between 0000 and 0777 or + a decimal value between 0 and 511. YAML + accepts both octal and decimal values, + JSON requires decimal values for mode + bits. If not specified, the volume defaultMode + will be used. This might be in conflict + with other options that affect the file + mode, like fsGroup, and the result can + be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file + to map the key to. May not be an absolute + path. May not contain the path element + '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its + key must be defined + type: boolean + type: object + serviceAccountToken: + description: information about the serviceAccountToken + data to project + properties: + audience: + description: Audience is the intended audience + of the token. A recipient of a token must identify + itself with an identifier specified in the audience + of the token, and otherwise should reject the + token. The audience defaults to the identifier + of the apiserver. + type: string + expirationSeconds: + description: ExpirationSeconds is the requested + duration of validity of the service account + token. As the token approaches expiration, the + kubelet volume plugin will proactively rotate + the service account token. The kubelet will + start trying to rotate the token if the token + is older than 80 percent of its time to live + or if the token is older than 24 hours.Defaults + to 1 hour and must be at least 10 minutes. + format: int64 + type: integer + path: + description: Path is the path relative to the + mount point of the file to project the token + into. + type: string + required: + - path + type: object + type: object + type: array + type: object + quobyte: + description: Quobyte represents a Quobyte mount on the host + that shares a pod's lifetime + properties: + group: + description: Group to map volume access to Default is no + group + type: string + readOnly: + description: ReadOnly here will force the Quobyte volume + to be mounted with read-only permissions. Defaults to + false. + type: boolean + registry: + description: Registry represents a single or multiple Quobyte + Registry services specified as a string as host:port pair + (multiple entries are separated with commas) which acts + as the central registry for volumes + type: string + tenant: + description: Tenant owning the given Quobyte volume in the + Backend Used with dynamically provisioned Quobyte volumes, + value is set by the plugin + type: string + user: + description: User to map volume access to Defaults to serivceaccount + user + type: string + volume: + description: Volume is a string that references an already + created Quobyte volume by name. + type: string + required: + - registry + - volume + type: object + rbd: + description: 'RBD represents a Rados Block Device mount on the + host that shares a pod''s lifetime. More info: https://examples.k8s.io/volumes/rbd/README.md' + properties: + fsType: + description: 'Filesystem type of the volume that you want + to mount. Tip: Ensure that the filesystem type is supported + by the host operating system. Examples: "ext4", "xfs", + "ntfs". Implicitly inferred to be "ext4" if unspecified. + More info: https://kubernetes.io/docs/concepts/storage/volumes#rbd + TODO: how do we prevent errors in the filesystem from + compromising the machine' + type: string + image: + description: 'The rados image name. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + keyring: + description: 'Keyring is the path to key ring for RBDUser. + Default is /etc/ceph/keyring. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + monitors: + description: 'A collection of Ceph monitors. More info: + https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + items: + type: string + type: array + pool: + description: 'The rados pool name. Default is rbd. More + info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + readOnly: + description: 'ReadOnly here will force the ReadOnly setting + in VolumeMounts. Defaults to false. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: boolean + secretRef: + description: 'SecretRef is name of the authentication secret + for RBDUser. If provided overrides keyring. Default is + nil. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + user: + description: 'The rados user name. Default is admin. More + info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + required: + - image + - monitors + type: object + scaleIO: + description: ScaleIO represents a ScaleIO persistent volume + attached and mounted on Kubernetes nodes. + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". Default is "xfs". + type: string + gateway: + description: The host address of the ScaleIO API Gateway. + type: string + protectionDomain: + description: The name of the ScaleIO Protection Domain for + the configured storage. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here + will force the ReadOnly setting in VolumeMounts. + type: boolean + secretRef: + description: SecretRef references to the secret for ScaleIO + user and other sensitive information. If this is not provided, + Login operation will fail. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + sslEnabled: + description: Flag to enable/disable SSL communication with + Gateway, default false + type: boolean + storageMode: + description: Indicates whether the storage for a volume + should be ThickProvisioned or ThinProvisioned. Default + is ThinProvisioned. + type: string + storagePool: + description: The ScaleIO Storage Pool associated with the + protection domain. + type: string + system: + description: The name of the storage system as configured + in ScaleIO. + type: string + volumeName: + description: The name of a volume already created in the + ScaleIO system that is associated with this volume source. + type: string + required: + - gateway + - secretRef + - system + type: object + secret: + description: 'Secret represents a secret that should populate + this volume. More info: https://kubernetes.io/docs/concepts/storage/volumes#secret' + properties: + defaultMode: + description: 'Optional: mode bits used to set permissions + on created files by default. Must be an octal value between + 0000 and 0777 or a decimal value between 0 and 511. YAML + accepts both octal and decimal values, JSON requires decimal + values for mode bits. Defaults to 0644. Directories within + the path are not affected by this setting. This might + be in conflict with other options that affect the file + mode, like fsGroup, and the result can be other mode bits + set.' + format: int32 + type: integer + items: + description: If unspecified, each key-value pair in the + Data field of the referenced Secret will be projected + into the volume as a file whose name is the key and content + is the value. If specified, the listed keys will be projected + into the specified paths, and unlisted keys will not be + present. If a key is specified which is not present in + the Secret, the volume setup will error unless it is marked + optional. Paths must be relative and may not contain the + '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits used to set permissions + on this file. Must be an octal value between 0000 + and 0777 or a decimal value between 0 and 511. YAML + accepts both octal and decimal values, JSON requires + decimal values for mode bits. If not specified, + the volume defaultMode will be used. This might + be in conflict with other options that affect the + file mode, like fsGroup, and the result can be other + mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map + the key to. May not be an absolute path. May not + contain the path element '..'. May not start with + the string '..'. + type: string + required: + - key + - path + type: object + type: array + optional: + description: Specify whether the Secret or its keys must + be defined + type: boolean + secretName: + description: 'Name of the secret in the pod''s namespace + to use. More info: https://kubernetes.io/docs/concepts/storage/volumes#secret' + type: string + type: object + storageos: + description: StorageOS represents a StorageOS volume attached + and mounted on Kubernetes nodes. + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here + will force the ReadOnly setting in VolumeMounts. + type: boolean + secretRef: + description: SecretRef specifies the secret to use for obtaining + the StorageOS API credentials. If not specified, default + values will be attempted. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + volumeName: + description: VolumeName is the human-readable name of the + StorageOS volume. Volume names are only unique within + a namespace. + type: string + volumeNamespace: + description: VolumeNamespace specifies the scope of the + volume within StorageOS. If no namespace is specified + then the Pod's namespace will be used. This allows the + Kubernetes name scoping to be mirrored within StorageOS + for tighter integration. Set VolumeName to any name to + override the default behaviour. Set to "default" if you + are not using namespaces within StorageOS. Namespaces + that do not pre-exist within StorageOS will be created. + type: string + type: object + vsphereVolume: + description: VsphereVolume represents a vSphere volume attached + and mounted on kubelets host machine + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + storagePolicyID: + description: Storage Policy Based Management (SPBM) profile + ID associated with the StoragePolicyName. + type: string + storagePolicyName: + description: Storage Policy Based Management (SPBM) profile + name. + type: string + volumePath: + description: Path that identifies vSphere volume vmdk + type: string + required: + - volumePath + type: object + required: + - name + type: object + type: array + type: object + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_integrations.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_integrations.yaml new file mode 100644 index 0000000..18bd037 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_integrations.yaml @@ -0,0 +1,1657 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.8.0 + creationTimestamp: null + name: integrations.monitoring.grafana.com +spec: + group: monitoring.grafana.com + names: + categories: + - agent-operator + kind: Integration + listKind: IntegrationList + plural: integrations + singular: integration + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: "Integration runs a single Grafana Agent integration. Integrations + that generate telemetry must be configured to send that telemetry somewhere; + such as autoscrape for exporter-based integrations. \n Integrations have + access to the LogsInstances and MetricsInstances in the same GrafanaAgent + resource set, referenced by the / of the *Instance resource. + \n For example, if there is a default/production MetricsInstance, you can + configure a supported integration's autoscrape block with: \n autoscrape: + enable: true metrics_instance: default/production \n There is currently + no way for telemetry created by an Operator-managed integration to be collected + from outside of the integration itself." + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation + of an object. Servers should convert recognized schemas to the latest + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this + object represents. Servers may infer this from the endpoint the client + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Specifies the desired behavior of the Integration. + properties: + config: + description: "The configuration for the named integration. Note that + integrations are deployed with the integrations-next feature flag, + which has different common settings: \n https://grafana.com/docs/agent/latest/configuration/integrations/integrations-next/" + type: object + x-kubernetes-preserve-unknown-fields: true + configMaps: + description: "An extra list of keys from ConfigMaps in the same namespace + as the Integration which will be mounted into the Grafana Agent + pod running this integration. \n ConfigMaps will be mounted at /etc/grafana-agent/integrations/configMaps///." + items: + description: Selects a key from a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be + defined + type: boolean + required: + - key + type: object + type: array + name: + description: Name of the integration to run (e.g., "node_exporter", + "mysqld_exporter"). + type: string + secrets: + description: "An extra list of keys from Secrets in the same namespace + as the Integration which will be mounted into the Grafana Agent + pod running this integration. \n Secrets will be mounted at /etc/grafana-agent/integrations/secrets///." + items: + description: SecretKeySelector selects a key of a Secret. + properties: + key: + description: The key of the secret to select from. Must be + a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: array + type: + description: Type informs Grafana Agent Operator how to manage the + integration being configured. + properties: + allNodes: + description: When true, the configured integration should be run + on every Node in the cluster. This is required for integrations + that generate Node-specific metrics like node_exporter, otherwise + it must be false to avoid generating duplicate metrics. + type: boolean + unique: + description: Whether this integration can only be defined once + for a Grafana Agent process, such as statsd_exporter. It is + invalid for a GrafanaAgent to discover multiple unique Integrations + with the same integration name (i.e., a single GrafanaAgent + cannot deploy two statsd_exporters). + type: boolean + type: object + volumeMounts: + description: "An extra list of VolumeMounts to be associated with + the Grafana Agent pods running this integration. VolumeMount names + will be mutated to be unique across all used IntegrationSpecs. \n + Mount paths should include the namespace/name of the Integration + CR to avoid potentially colliding with other resources." + items: + description: VolumeMount describes a mounting of a Volume within + a container. + properties: + mountPath: + description: Path within the container at which the volume should + be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated + from the host to container and the other way around. When + not set, MountPropagationNone is used. This field is beta + in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise + (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's + volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the + container's volume should be mounted. Behaves similarly to + SubPath but environment variable references $(VAR_NAME) are + expanded using the container's environment. Defaults to "" + (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + volumes: + description: "An extra list of Volumes to be associated with the Grafana + Agent pods running this integration. Volume names will be mutated + to be unique across all Integrations. Note that the specified volumes + should be able to tolerate existing on multiple pods at once when + type is daemonset. \n Don't use volumes for loading secrets/configMaps + from the same namespace as the Integration; use the secrets and + configMaps fields instead." + items: + description: Volume represents a named volume in a pod that may + be accessed by any container in the pod. + properties: + awsElasticBlockStore: + description: 'AWSElasticBlockStore represents an AWS Disk resource + that is attached to a kubelet''s host machine and then exposed + to the pod. More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + properties: + fsType: + description: 'Filesystem type of the volume that you want + to mount. Tip: Ensure that the filesystem type is supported + by the host operating system. Examples: "ext4", "xfs", + "ntfs". Implicitly inferred to be "ext4" if unspecified. + More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore + TODO: how do we prevent errors in the filesystem from + compromising the machine' + type: string + partition: + description: 'The partition in the volume that you want + to mount. If omitted, the default is to mount by volume + name. Examples: For volume /dev/sda1, you specify the + partition as "1". Similarly, the volume partition for + /dev/sda is "0" (or you can leave the property empty).' + format: int32 + type: integer + readOnly: + description: 'Specify "true" to force and set the ReadOnly + property in VolumeMounts to "true". If omitted, the default + is "false". More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + type: boolean + volumeID: + description: 'Unique ID of the persistent disk resource + in AWS (Amazon EBS volume). More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + type: string + required: + - volumeID + type: object + azureDisk: + description: AzureDisk represents an Azure Data Disk mount on + the host and bind mount to the pod. + properties: + cachingMode: + description: 'Host Caching mode: None, Read Only, Read Write.' + type: string + diskName: + description: The Name of the data disk in the blob storage + type: string + diskURI: + description: The URI the data disk in the blob storage + type: string + fsType: + description: Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + kind: + description: 'Expected values Shared: multiple blob disks + per storage account Dedicated: single blob disk per storage + account Managed: azure managed data disk (only in managed + availability set). defaults to shared' + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here + will force the ReadOnly setting in VolumeMounts. + type: boolean + required: + - diskName + - diskURI + type: object + azureFile: + description: AzureFile represents an Azure File Service mount + on the host and bind mount to the pod. + properties: + readOnly: + description: Defaults to false (read/write). ReadOnly here + will force the ReadOnly setting in VolumeMounts. + type: boolean + secretName: + description: the name of secret that contains Azure Storage + Account Name and Key + type: string + shareName: + description: Share Name + type: string + required: + - secretName + - shareName + type: object + cephfs: + description: CephFS represents a Ceph FS mount on the host that + shares a pod's lifetime + properties: + monitors: + description: 'Required: Monitors is a collection of Ceph + monitors More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + items: + type: string + type: array + path: + description: 'Optional: Used as the mounted root, rather + than the full Ceph tree, default is /' + type: string + readOnly: + description: 'Optional: Defaults to false (read/write). + ReadOnly here will force the ReadOnly setting in VolumeMounts. + More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: boolean + secretFile: + description: 'Optional: SecretFile is the path to key ring + for User, default is /etc/ceph/user.secret More info: + https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: string + secretRef: + description: 'Optional: SecretRef is reference to the authentication + secret for User, default is empty. More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + user: + description: 'Optional: User is the rados user name, default + is admin More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: string + required: + - monitors + type: object + cinder: + description: 'Cinder represents a cinder volume attached and + mounted on kubelets host machine. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + properties: + fsType: + description: 'Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Examples: + "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" + if unspecified. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: string + readOnly: + description: 'Optional: Defaults to false (read/write). + ReadOnly here will force the ReadOnly setting in VolumeMounts. + More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: boolean + secretRef: + description: 'Optional: points to a secret object containing + parameters used to connect to OpenStack.' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + volumeID: + description: 'volume id used to identify the volume in cinder. + More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: string + required: + - volumeID + type: object + configMap: + description: ConfigMap represents a configMap that should populate + this volume + properties: + defaultMode: + description: 'Optional: mode bits used to set permissions + on created files by default. Must be an octal value between + 0000 and 0777 or a decimal value between 0 and 511. YAML + accepts both octal and decimal values, JSON requires decimal + values for mode bits. Defaults to 0644. Directories within + the path are not affected by this setting. This might + be in conflict with other options that affect the file + mode, like fsGroup, and the result can be other mode bits + set.' + format: int32 + type: integer + items: + description: If unspecified, each key-value pair in the + Data field of the referenced ConfigMap will be projected + into the volume as a file whose name is the key and content + is the value. If specified, the listed keys will be projected + into the specified paths, and unlisted keys will not be + present. If a key is specified which is not present in + the ConfigMap, the volume setup will error unless it is + marked optional. Paths must be relative and may not contain + the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits used to set permissions + on this file. Must be an octal value between 0000 + and 0777 or a decimal value between 0 and 511. YAML + accepts both octal and decimal values, JSON requires + decimal values for mode bits. If not specified, + the volume defaultMode will be used. This might + be in conflict with other options that affect the + file mode, like fsGroup, and the result can be other + mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map + the key to. May not be an absolute path. May not + contain the path element '..'. May not start with + the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its keys must + be defined + type: boolean + type: object + csi: + description: CSI (Container Storage Interface) represents ephemeral + storage that is handled by certain external CSI drivers (Beta + feature). + properties: + driver: + description: Driver is the name of the CSI driver that handles + this volume. Consult with your admin for the correct name + as registered in the cluster. + type: string + fsType: + description: Filesystem type to mount. Ex. "ext4", "xfs", + "ntfs". If not provided, the empty value is passed to + the associated CSI driver which will determine the default + filesystem to apply. + type: string + nodePublishSecretRef: + description: NodePublishSecretRef is a reference to the + secret object containing sensitive information to pass + to the CSI driver to complete the CSI NodePublishVolume + and NodeUnpublishVolume calls. This field is optional, + and may be empty if no secret is required. If the secret + object contains more than one secret, all secret references + are passed. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + readOnly: + description: Specifies a read-only configuration for the + volume. Defaults to false (read/write). + type: boolean + volumeAttributes: + additionalProperties: + type: string + description: VolumeAttributes stores driver-specific properties + that are passed to the CSI driver. Consult your driver's + documentation for supported values. + type: object + required: + - driver + type: object + downwardAPI: + description: DownwardAPI represents downward API about the pod + that should populate this volume + properties: + defaultMode: + description: 'Optional: mode bits to use on created files + by default. Must be a Optional: mode bits used to set + permissions on created files by default. Must be an octal + value between 0000 and 0777 or a decimal value between + 0 and 511. YAML accepts both octal and decimal values, + JSON requires decimal values for mode bits. Defaults to + 0644. Directories within the path are not affected by + this setting. This might be in conflict with other options + that affect the file mode, like fsGroup, and the result + can be other mode bits set.' + format: int32 + type: integer + items: + description: Items is a list of downward API volume file + items: + description: DownwardAPIVolumeFile represents information + to create the file containing the pod field + properties: + fieldRef: + description: 'Required: Selects a field of the pod: + only annotations, labels, name and namespace are + supported.' + properties: + apiVersion: + description: Version of the schema the FieldPath + is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the + specified API version. + type: string + required: + - fieldPath + type: object + mode: + description: 'Optional: mode bits used to set permissions + on this file, must be an octal value between 0000 + and 0777 or a decimal value between 0 and 511. YAML + accepts both octal and decimal values, JSON requires + decimal values for mode bits. If not specified, + the volume defaultMode will be used. This might + be in conflict with other options that affect the + file mode, like fsGroup, and the result can be other + mode bits set.' + format: int32 + type: integer + path: + description: 'Required: Path is the relative path + name of the file to be created. Must not be absolute + or contain the ''..'' path. Must be utf-8 encoded. + The first item of the relative path must not start + with ''..''' + type: string + resourceFieldRef: + description: 'Selects a resource of the container: + only resources limits and requests (limits.cpu, + limits.memory, requests.cpu and requests.memory) + are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, + optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the + exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + required: + - path + type: object + type: array + type: object + emptyDir: + description: 'EmptyDir represents a temporary directory that + shares a pod''s lifetime. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + properties: + medium: + description: 'What type of storage medium should back this + directory. The default is "" which means to use the node''s + default medium. Must be an empty string (default) or Memory. + More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + description: 'Total amount of local storage required for + this EmptyDir volume. The size limit is also applicable + for memory medium. The maximum usage on memory medium + EmptyDir would be the minimum value between the SizeLimit + specified here and the sum of memory limits of all containers + in a pod. The default is nil which means that the limit + is undefined. More info: http://kubernetes.io/docs/user-guide/volumes#emptydir' + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + ephemeral: + description: "Ephemeral represents a volume that is handled + by a cluster storage driver. The volume's lifecycle is tied + to the pod that defines it - it will be created before the + pod starts, and deleted when the pod is removed. \n Use this + if: a) the volume is only needed while the pod runs, b) features + of normal volumes like restoring from snapshot or capacity + tracking are needed, c) the storage driver is specified through + a storage class, and d) the storage driver supports dynamic + volume provisioning through a PersistentVolumeClaim (see EphemeralVolumeSource + for more information on the connection between this volume + type and PersistentVolumeClaim). \n Use PersistentVolumeClaim + or one of the vendor-specific APIs for volumes that persist + for longer than the lifecycle of an individual pod. \n Use + CSI for light-weight local ephemeral volumes if the CSI driver + is meant to be used that way - see the documentation of the + driver for more information. \n A pod can use both types of + ephemeral volumes and persistent volumes at the same time." + properties: + volumeClaimTemplate: + description: "Will be used to create a stand-alone PVC to + provision the volume. The pod in which this EphemeralVolumeSource + is embedded will be the owner of the PVC, i.e. the PVC + will be deleted together with the pod. The name of the + PVC will be `-` where `` is the name from the `PodSpec.Volumes` array entry. + Pod validation will reject the pod if the concatenated + name is not valid for a PVC (for example, too long). \n + An existing PVC with that name that is not owned by the + pod will *not* be used for the pod to avoid using an unrelated + volume by mistake. Starting the pod is then blocked until + the unrelated PVC is removed. If such a pre-created PVC + is meant to be used by the pod, the PVC has to updated + with an owner reference to the pod once the pod exists. + Normally this should not be necessary, but it may be useful + when manually reconstructing a broken cluster. \n This + field is read-only and no changes will be made by Kubernetes + to the PVC after it has been created. \n Required, must + not be nil." + properties: + metadata: + description: May contain labels and annotations that + will be copied into the PVC when creating it. No other + fields are allowed and will be rejected during validation. + type: object + spec: + description: The specification for the PersistentVolumeClaim. + The entire content is copied unchanged into the PVC + that gets created from this template. The same fields + as in a PersistentVolumeClaim are also valid here. + properties: + accessModes: + description: 'AccessModes contains the desired access + modes the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + dataSource: + description: 'This field can be used to specify + either: * An existing VolumeSnapshot object (snapshot.storage.k8s.io/VolumeSnapshot) + * An existing PVC (PersistentVolumeClaim) If the + provisioner or an external controller can support + the specified data source, it will create a new + volume based on the contents of the specified + data source. If the AnyVolumeDataSource feature + gate is enabled, this field will always have the + same contents as the DataSourceRef field.' + properties: + apiGroup: + description: APIGroup is the group for the resource + being referenced. If APIGroup is not specified, + the specified Kind must be in the core API + group. For any other third-party types, APIGroup + is required. + type: string + kind: + description: Kind is the type of resource being + referenced + type: string + name: + description: Name is the name of resource being + referenced + type: string + required: + - kind + - name + type: object + dataSourceRef: + description: 'Specifies the object from which to + populate the volume with data, if a non-empty + volume is desired. This may be any local object + from a non-empty API group (non core object) or + a PersistentVolumeClaim object. When this field + is specified, volume binding will only succeed + if the type of the specified object matches some + installed volume populator or dynamic provisioner. + This field will replace the functionality of the + DataSource field and as such if both fields are + non-empty, they must have the same value. For + backwards compatibility, both fields (DataSource + and DataSourceRef) will be set to the same value + automatically if one of them is empty and the + other is non-empty. There are two important differences + between DataSource and DataSourceRef: * While + DataSource only allows two specific types of objects, + DataSourceRef allows any non-core object, as well + as PersistentVolumeClaim objects. * While DataSource + ignores disallowed values (dropping them), DataSourceRef + preserves all values, and generates an error if + a disallowed value is specified. (Alpha) Using + this field requires the AnyVolumeDataSource feature + gate to be enabled.' + properties: + apiGroup: + description: APIGroup is the group for the resource + being referenced. If APIGroup is not specified, + the specified Kind must be in the core API + group. For any other third-party types, APIGroup + is required. + type: string + kind: + description: Kind is the type of resource being + referenced + type: string + name: + description: Name is the name of resource being + referenced + type: string + required: + - kind + - name + type: object + resources: + description: 'Resources represents the minimum resources + the volume should have. If RecoverVolumeExpansionFailure + feature is enabled users are allowed to specify + resource requirements that are lower than previous + value but must still be higher than capacity recorded + in the status field of the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#resources' + properties: + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount + of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum + amount of compute resources required. If Requests + is omitted for a container, it defaults to + Limits if that is explicitly specified, otherwise + to an implementation-defined value. More info: + https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + selector: + description: A label query over volumes to consider + for binding. + properties: + matchExpressions: + description: matchExpressions is a list of label + selector requirements. The requirements are + ANDed. + items: + description: A label selector requirement + is a selector that contains values, a key, + and an operator that relates the key and + values. + properties: + key: + description: key is the label key that + the selector applies to. + type: string + operator: + description: operator represents a key's + relationship to a set of values. Valid + operators are In, NotIn, Exists and + DoesNotExist. + type: string + values: + description: values is an array of string + values. If the operator is In or NotIn, + the values array must be non-empty. + If the operator is Exists or DoesNotExist, + the values array must be empty. This + array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} + pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, + whose key field is "key", the operator is + "In", and the values array contains only "value". + The requirements are ANDed. + type: object + type: object + storageClassName: + description: 'Name of the StorageClass required + by the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#class-1' + type: string + volumeMode: + description: volumeMode defines what type of volume + is required by the claim. Value of Filesystem + is implied when not included in claim spec. + type: string + volumeName: + description: VolumeName is the binding reference + to the PersistentVolume backing this claim. + type: string + type: object + required: + - spec + type: object + type: object + fc: + description: FC represents a Fibre Channel resource that is + attached to a kubelet's host machine and then exposed to the + pod. + properties: + fsType: + description: 'Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + TODO: how do we prevent errors in the filesystem from + compromising the machine' + type: string + lun: + description: 'Optional: FC target lun number' + format: int32 + type: integer + readOnly: + description: 'Optional: Defaults to false (read/write). + ReadOnly here will force the ReadOnly setting in VolumeMounts.' + type: boolean + targetWWNs: + description: 'Optional: FC target worldwide names (WWNs)' + items: + type: string + type: array + wwids: + description: 'Optional: FC volume world wide identifiers + (wwids) Either wwids or combination of targetWWNs and + lun must be set, but not both simultaneously.' + items: + type: string + type: array + type: object + flexVolume: + description: FlexVolume represents a generic volume resource + that is provisioned/attached using an exec based plugin. + properties: + driver: + description: Driver is the name of the driver to use for + this volume. + type: string + fsType: + description: Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". The default filesystem depends on FlexVolume + script. + type: string + options: + additionalProperties: + type: string + description: 'Optional: Extra command options if any.' + type: object + readOnly: + description: 'Optional: Defaults to false (read/write). + ReadOnly here will force the ReadOnly setting in VolumeMounts.' + type: boolean + secretRef: + description: 'Optional: SecretRef is reference to the secret + object containing sensitive information to pass to the + plugin scripts. This may be empty if no secret object + is specified. If the secret object contains more than + one secret, all secrets are passed to the plugin scripts.' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + required: + - driver + type: object + flocker: + description: Flocker represents a Flocker volume attached to + a kubelet's host machine. This depends on the Flocker control + service being running + properties: + datasetName: + description: Name of the dataset stored as metadata -> name + on the dataset for Flocker should be considered as deprecated + type: string + datasetUUID: + description: UUID of the dataset. This is unique identifier + of a Flocker dataset + type: string + type: object + gcePersistentDisk: + description: 'GCEPersistentDisk represents a GCE Disk resource + that is attached to a kubelet''s host machine and then exposed + to the pod. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + properties: + fsType: + description: 'Filesystem type of the volume that you want + to mount. Tip: Ensure that the filesystem type is supported + by the host operating system. Examples: "ext4", "xfs", + "ntfs". Implicitly inferred to be "ext4" if unspecified. + More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk + TODO: how do we prevent errors in the filesystem from + compromising the machine' + type: string + partition: + description: 'The partition in the volume that you want + to mount. If omitted, the default is to mount by volume + name. Examples: For volume /dev/sda1, you specify the + partition as "1". Similarly, the volume partition for + /dev/sda is "0" (or you can leave the property empty). + More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + format: int32 + type: integer + pdName: + description: 'Unique name of the PD resource in GCE. Used + to identify the disk in GCE. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + type: string + readOnly: + description: 'ReadOnly here will force the ReadOnly setting + in VolumeMounts. Defaults to false. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + type: boolean + required: + - pdName + type: object + gitRepo: + description: 'GitRepo represents a git repository at a particular + revision. DEPRECATED: GitRepo is deprecated. To provision + a container with a git repo, mount an EmptyDir into an InitContainer + that clones the repo using git, then mount the EmptyDir into + the Pod''s container.' + properties: + directory: + description: Target directory name. Must not contain or + start with '..'. If '.' is supplied, the volume directory + will be the git repository. Otherwise, if specified, + the volume will contain the git repository in the subdirectory + with the given name. + type: string + repository: + description: Repository URL + type: string + revision: + description: Commit hash for the specified revision. + type: string + required: + - repository + type: object + glusterfs: + description: 'Glusterfs represents a Glusterfs mount on the + host that shares a pod''s lifetime. More info: https://examples.k8s.io/volumes/glusterfs/README.md' + properties: + endpoints: + description: 'EndpointsName is the endpoint name that details + Glusterfs topology. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: string + path: + description: 'Path is the Glusterfs volume path. More info: + https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: string + readOnly: + description: 'ReadOnly here will force the Glusterfs volume + to be mounted with read-only permissions. Defaults to + false. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: boolean + required: + - endpoints + - path + type: object + hostPath: + description: 'HostPath represents a pre-existing file or directory + on the host machine that is directly exposed to the container. + This is generally used for system agents or other privileged + things that are allowed to see the host machine. Most containers + will NOT need this. More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath + --- TODO(jonesdl) We need to restrict who can use host directory + mounts and who can/can not mount host directories as read/write.' + properties: + path: + description: 'Path of the directory on the host. If the + path is a symlink, it will follow the link to the real + path. More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath' + type: string + type: + description: 'Type for HostPath Volume Defaults to "" More + info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath' + type: string + required: + - path + type: object + iscsi: + description: 'ISCSI represents an ISCSI Disk resource that is + attached to a kubelet''s host machine and then exposed to + the pod. More info: https://examples.k8s.io/volumes/iscsi/README.md' + properties: + chapAuthDiscovery: + description: whether support iSCSI Discovery CHAP authentication + type: boolean + chapAuthSession: + description: whether support iSCSI Session CHAP authentication + type: boolean + fsType: + description: 'Filesystem type of the volume that you want + to mount. Tip: Ensure that the filesystem type is supported + by the host operating system. Examples: "ext4", "xfs", + "ntfs". Implicitly inferred to be "ext4" if unspecified. + More info: https://kubernetes.io/docs/concepts/storage/volumes#iscsi + TODO: how do we prevent errors in the filesystem from + compromising the machine' + type: string + initiatorName: + description: Custom iSCSI Initiator Name. If initiatorName + is specified with iscsiInterface simultaneously, new iSCSI + interface : will be created + for the connection. + type: string + iqn: + description: Target iSCSI Qualified Name. + type: string + iscsiInterface: + description: iSCSI Interface Name that uses an iSCSI transport. + Defaults to 'default' (tcp). + type: string + lun: + description: iSCSI Target Lun number. + format: int32 + type: integer + portals: + description: iSCSI Target Portal List. The portal is either + an IP or ip_addr:port if the port is other than default + (typically TCP ports 860 and 3260). + items: + type: string + type: array + readOnly: + description: ReadOnly here will force the ReadOnly setting + in VolumeMounts. Defaults to false. + type: boolean + secretRef: + description: CHAP Secret for iSCSI target and initiator + authentication + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + targetPortal: + description: iSCSI Target Portal. The Portal is either an + IP or ip_addr:port if the port is other than default (typically + TCP ports 860 and 3260). + type: string + required: + - iqn + - lun + - targetPortal + type: object + name: + description: 'Volume''s name. Must be a DNS_LABEL and unique + within the pod. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + nfs: + description: 'NFS represents an NFS mount on the host that shares + a pod''s lifetime More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + properties: + path: + description: 'Path that is exported by the NFS server. More + info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: string + readOnly: + description: 'ReadOnly here will force the NFS export to + be mounted with read-only permissions. Defaults to false. + More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: boolean + server: + description: 'Server is the hostname or IP address of the + NFS server. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: string + required: + - path + - server + type: object + persistentVolumeClaim: + description: 'PersistentVolumeClaimVolumeSource represents a + reference to a PersistentVolumeClaim in the same namespace. + More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + claimName: + description: 'ClaimName is the name of a PersistentVolumeClaim + in the same namespace as the pod using this volume. More + info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + type: string + readOnly: + description: Will force the ReadOnly setting in VolumeMounts. + Default false. + type: boolean + required: + - claimName + type: object + photonPersistentDisk: + description: PhotonPersistentDisk represents a PhotonController + persistent disk attached and mounted on kubelets host machine + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + pdID: + description: ID that identifies Photon Controller persistent + disk + type: string + required: + - pdID + type: object + portworxVolume: + description: PortworxVolume represents a portworx volume attached + and mounted on kubelets host machine + properties: + fsType: + description: FSType represents the filesystem type to mount + Must be a filesystem type supported by the host operating + system. Ex. "ext4", "xfs". Implicitly inferred to be "ext4" + if unspecified. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here + will force the ReadOnly setting in VolumeMounts. + type: boolean + volumeID: + description: VolumeID uniquely identifies a Portworx volume + type: string + required: + - volumeID + type: object + projected: + description: Items for all in one resources secrets, configmaps, + and downward API + properties: + defaultMode: + description: Mode bits used to set permissions on created + files by default. Must be an octal value between 0000 + and 0777 or a decimal value between 0 and 511. YAML accepts + both octal and decimal values, JSON requires decimal values + for mode bits. Directories within the path are not affected + by this setting. This might be in conflict with other + options that affect the file mode, like fsGroup, and the + result can be other mode bits set. + format: int32 + type: integer + sources: + description: list of volume projections + items: + description: Projection that may be projected along with + other supported volume types + properties: + configMap: + description: information about the configMap data + to project + properties: + items: + description: If unspecified, each key-value pair + in the Data field of the referenced ConfigMap + will be projected into the volume as a file + whose name is the key and content is the value. + If specified, the listed keys will be projected + into the specified paths, and unlisted keys + will not be present. If a key is specified which + is not present in the ConfigMap, the volume + setup will error unless it is marked optional. + Paths must be relative and may not contain the + '..' path or start with '..'. + items: + description: Maps a string key to a path within + a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits used to + set permissions on this file. Must be + an octal value between 0000 and 0777 or + a decimal value between 0 and 511. YAML + accepts both octal and decimal values, + JSON requires decimal values for mode + bits. If not specified, the volume defaultMode + will be used. This might be in conflict + with other options that affect the file + mode, like fsGroup, and the result can + be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file + to map the key to. May not be an absolute + path. May not contain the path element + '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or + its keys must be defined + type: boolean + type: object + downwardAPI: + description: information about the downwardAPI data + to project + properties: + items: + description: Items is a list of DownwardAPIVolume + file + items: + description: DownwardAPIVolumeFile represents + information to create the file containing + the pod field + properties: + fieldRef: + description: 'Required: Selects a field + of the pod: only annotations, labels, + name and namespace are supported.' + properties: + apiVersion: + description: Version of the schema the + FieldPath is written in terms of, + defaults to "v1". + type: string + fieldPath: + description: Path of the field to select + in the specified API version. + type: string + required: + - fieldPath + type: object + mode: + description: 'Optional: mode bits used to + set permissions on this file, must be + an octal value between 0000 and 0777 or + a decimal value between 0 and 511. YAML + accepts both octal and decimal values, + JSON requires decimal values for mode + bits. If not specified, the volume defaultMode + will be used. This might be in conflict + with other options that affect the file + mode, like fsGroup, and the result can + be other mode bits set.' + format: int32 + type: integer + path: + description: 'Required: Path is the relative + path name of the file to be created. Must + not be absolute or contain the ''..'' + path. Must be utf-8 encoded. The first + item of the relative path must not start + with ''..''' + type: string + resourceFieldRef: + description: 'Selects a resource of the + container: only resources limits and requests + (limits.cpu, limits.memory, requests.cpu + and requests.memory) are currently supported.' + properties: + containerName: + description: 'Container name: required + for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format + of the exposed resources, defaults + to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to + select' + type: string + required: + - resource + type: object + required: + - path + type: object + type: array + type: object + secret: + description: information about the secret data to + project + properties: + items: + description: If unspecified, each key-value pair + in the Data field of the referenced Secret will + be projected into the volume as a file whose + name is the key and content is the value. If + specified, the listed keys will be projected + into the specified paths, and unlisted keys + will not be present. If a key is specified which + is not present in the Secret, the volume setup + will error unless it is marked optional. Paths + must be relative and may not contain the '..' + path or start with '..'. + items: + description: Maps a string key to a path within + a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits used to + set permissions on this file. Must be + an octal value between 0000 and 0777 or + a decimal value between 0 and 511. YAML + accepts both octal and decimal values, + JSON requires decimal values for mode + bits. If not specified, the volume defaultMode + will be used. This might be in conflict + with other options that affect the file + mode, like fsGroup, and the result can + be other mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file + to map the key to. May not be an absolute + path. May not contain the path element + '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: + https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its + key must be defined + type: boolean + type: object + serviceAccountToken: + description: information about the serviceAccountToken + data to project + properties: + audience: + description: Audience is the intended audience + of the token. A recipient of a token must identify + itself with an identifier specified in the audience + of the token, and otherwise should reject the + token. The audience defaults to the identifier + of the apiserver. + type: string + expirationSeconds: + description: ExpirationSeconds is the requested + duration of validity of the service account + token. As the token approaches expiration, the + kubelet volume plugin will proactively rotate + the service account token. The kubelet will + start trying to rotate the token if the token + is older than 80 percent of its time to live + or if the token is older than 24 hours.Defaults + to 1 hour and must be at least 10 minutes. + format: int64 + type: integer + path: + description: Path is the path relative to the + mount point of the file to project the token + into. + type: string + required: + - path + type: object + type: object + type: array + type: object + quobyte: + description: Quobyte represents a Quobyte mount on the host + that shares a pod's lifetime + properties: + group: + description: Group to map volume access to Default is no + group + type: string + readOnly: + description: ReadOnly here will force the Quobyte volume + to be mounted with read-only permissions. Defaults to + false. + type: boolean + registry: + description: Registry represents a single or multiple Quobyte + Registry services specified as a string as host:port pair + (multiple entries are separated with commas) which acts + as the central registry for volumes + type: string + tenant: + description: Tenant owning the given Quobyte volume in the + Backend Used with dynamically provisioned Quobyte volumes, + value is set by the plugin + type: string + user: + description: User to map volume access to Defaults to serivceaccount + user + type: string + volume: + description: Volume is a string that references an already + created Quobyte volume by name. + type: string + required: + - registry + - volume + type: object + rbd: + description: 'RBD represents a Rados Block Device mount on the + host that shares a pod''s lifetime. More info: https://examples.k8s.io/volumes/rbd/README.md' + properties: + fsType: + description: 'Filesystem type of the volume that you want + to mount. Tip: Ensure that the filesystem type is supported + by the host operating system. Examples: "ext4", "xfs", + "ntfs". Implicitly inferred to be "ext4" if unspecified. + More info: https://kubernetes.io/docs/concepts/storage/volumes#rbd + TODO: how do we prevent errors in the filesystem from + compromising the machine' + type: string + image: + description: 'The rados image name. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + keyring: + description: 'Keyring is the path to key ring for RBDUser. + Default is /etc/ceph/keyring. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + monitors: + description: 'A collection of Ceph monitors. More info: + https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + items: + type: string + type: array + pool: + description: 'The rados pool name. Default is rbd. More + info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + readOnly: + description: 'ReadOnly here will force the ReadOnly setting + in VolumeMounts. Defaults to false. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: boolean + secretRef: + description: 'SecretRef is name of the authentication secret + for RBDUser. If provided overrides keyring. Default is + nil. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + user: + description: 'The rados user name. Default is admin. More + info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + required: + - image + - monitors + type: object + scaleIO: + description: ScaleIO represents a ScaleIO persistent volume + attached and mounted on Kubernetes nodes. + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". Default is "xfs". + type: string + gateway: + description: The host address of the ScaleIO API Gateway. + type: string + protectionDomain: + description: The name of the ScaleIO Protection Domain for + the configured storage. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here + will force the ReadOnly setting in VolumeMounts. + type: boolean + secretRef: + description: SecretRef references to the secret for ScaleIO + user and other sensitive information. If this is not provided, + Login operation will fail. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + sslEnabled: + description: Flag to enable/disable SSL communication with + Gateway, default false + type: boolean + storageMode: + description: Indicates whether the storage for a volume + should be ThickProvisioned or ThinProvisioned. Default + is ThinProvisioned. + type: string + storagePool: + description: The ScaleIO Storage Pool associated with the + protection domain. + type: string + system: + description: The name of the storage system as configured + in ScaleIO. + type: string + volumeName: + description: The name of a volume already created in the + ScaleIO system that is associated with this volume source. + type: string + required: + - gateway + - secretRef + - system + type: object + secret: + description: 'Secret represents a secret that should populate + this volume. More info: https://kubernetes.io/docs/concepts/storage/volumes#secret' + properties: + defaultMode: + description: 'Optional: mode bits used to set permissions + on created files by default. Must be an octal value between + 0000 and 0777 or a decimal value between 0 and 511. YAML + accepts both octal and decimal values, JSON requires decimal + values for mode bits. Defaults to 0644. Directories within + the path are not affected by this setting. This might + be in conflict with other options that affect the file + mode, like fsGroup, and the result can be other mode bits + set.' + format: int32 + type: integer + items: + description: If unspecified, each key-value pair in the + Data field of the referenced Secret will be projected + into the volume as a file whose name is the key and content + is the value. If specified, the listed keys will be projected + into the specified paths, and unlisted keys will not be + present. If a key is specified which is not present in + the Secret, the volume setup will error unless it is marked + optional. Paths must be relative and may not contain the + '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: The key to project. + type: string + mode: + description: 'Optional: mode bits used to set permissions + on this file. Must be an octal value between 0000 + and 0777 or a decimal value between 0 and 511. YAML + accepts both octal and decimal values, JSON requires + decimal values for mode bits. If not specified, + the volume defaultMode will be used. This might + be in conflict with other options that affect the + file mode, like fsGroup, and the result can be other + mode bits set.' + format: int32 + type: integer + path: + description: The relative path of the file to map + the key to. May not be an absolute path. May not + contain the path element '..'. May not start with + the string '..'. + type: string + required: + - key + - path + type: object + type: array + optional: + description: Specify whether the Secret or its keys must + be defined + type: boolean + secretName: + description: 'Name of the secret in the pod''s namespace + to use. More info: https://kubernetes.io/docs/concepts/storage/volumes#secret' + type: string + type: object + storageos: + description: StorageOS represents a StorageOS volume attached + and mounted on Kubernetes nodes. + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + readOnly: + description: Defaults to false (read/write). ReadOnly here + will force the ReadOnly setting in VolumeMounts. + type: boolean + secretRef: + description: SecretRef specifies the secret to use for obtaining + the StorageOS API credentials. If not specified, default + values will be attempted. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + volumeName: + description: VolumeName is the human-readable name of the + StorageOS volume. Volume names are only unique within + a namespace. + type: string + volumeNamespace: + description: VolumeNamespace specifies the scope of the + volume within StorageOS. If no namespace is specified + then the Pod's namespace will be used. This allows the + Kubernetes name scoping to be mirrored within StorageOS + for tighter integration. Set VolumeName to any name to + override the default behaviour. Set to "default" if you + are not using namespaces within StorageOS. Namespaces + that do not pre-exist within StorageOS will be created. + type: string + type: object + vsphereVolume: + description: VsphereVolume represents a vSphere volume attached + and mounted on kubelets host machine + properties: + fsType: + description: Filesystem type to mount. Must be a filesystem + type supported by the host operating system. Ex. "ext4", + "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + storagePolicyID: + description: Storage Policy Based Management (SPBM) profile + ID associated with the StoragePolicyName. + type: string + storagePolicyName: + description: Storage Policy Based Management (SPBM) profile + name. + type: string + volumePath: + description: Path that identifies vSphere volume vmdk + type: string + required: + - volumePath + type: object + required: + - name + type: object + type: array + required: + - config + - name + - type + type: object + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_logsinstances.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_logsinstances.yaml new file mode 100644 index 0000000..0546c2a --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_logsinstances.yaml @@ -0,0 +1,411 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.8.0 + creationTimestamp: null + name: logsinstances.monitoring.grafana.com +spec: + group: monitoring.grafana.com + names: + categories: + - agent-operator + kind: LogsInstance + listKind: LogsInstanceList + plural: logsinstances + singular: logsinstance + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: LogsInstance controls an individual logs instance within a Grafana + Agent deployment. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation + of an object. Servers should convert recognized schemas to the latest + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this + object represents. Servers may infer this from the endpoint the client + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Spec holds the specification of the desired behavior for + the logs instance. + properties: + additionalScrapeConfigs: + description: "AdditionalScrapeConfigs allows specifying a key of a + Secret containing additional Grafana Agent logging scrape configurations. + Scrape configurations specified are appended to the configurations + generated by the Grafana Agent Operator. \n Job configurations specified + must have the form as specified in the official Promtail documentation: + \n https://grafana.com/docs/loki/latest/clients/promtail/configuration/#scrape_configs + \n As scrape configs are appended, the user is responsible to make + sure it is valid. Note that using this feature may expose the possibility + to break upgrades of Grafana Agent. It is advised to review both + Grafana Agent and Promtail release notes to ensure that no incompatible + scrape configs are going to break Grafana Agent after the upgrade." + properties: + key: + description: The key of the secret to select from. Must be a + valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + clients: + description: Clients controls where logs are written to for this instance. + items: + description: LogsClientSpec defines the client integration for logs, + indicating which Loki server to send logs to. + properties: + backoffConfig: + description: Configures how to retry requests to Loki when a + request fails. Defaults to a minPeriod of 500ms, maxPeriod + of 5m, and maxRetries of 10. + properties: + maxPeriod: + description: Maximum backoff time between retries. + type: string + maxRetries: + description: Maximum number of retries to perform before + giving up a request. + type: integer + minPeriod: + description: Initial backoff time between retries. Time + between retries is increased exponentially. + type: string + type: object + basicAuth: + description: BasicAuth for the Loki server. + properties: + password: + description: The secret in the service monitor namespace + that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace + that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + type: object + batchSize: + description: Maximum batch size (in bytes) of logs to accumulate + before sending the batch to Loki. + type: integer + batchWait: + description: Maximum amount of time to wait before sending a + batch, even if that batch isn't full. + type: string + bearerToken: + description: BearerToken used for remote_write. + type: string + bearerTokenFile: + description: BearerTokenFile used to read bearer token. + type: string + externalLabels: + additionalProperties: + type: string + description: ExternalLabels are labels to add to any time series + when sending data to Loki. + type: object + proxyUrl: + description: ProxyURL to proxy requests through. Optional. + type: string + tenantId: + description: Tenant ID used by default to push logs to Loki. + If omitted assumes remote Loki is running in single-tenant + mode or an authentication layer is used to inject an X-Scope-OrgID + header. + type: string + timeout: + description: Maximum time to wait for a server to respond to + a request. + type: string + tlsConfig: + description: TLSConfig to use for the client. Only used when + the protocol of the URL is https. + properties: + ca: + description: Struct containing the CA cert to use for the + targets. + properties: + configMap: + description: ConfigMap containing data to use for the + targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or its + key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container + to use for the targets. + type: string + cert: + description: Struct containing the client cert file for + the targets. + properties: + configMap: + description: ConfigMap containing data to use for the + targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or its + key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus + container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus + container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the + targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + url: + description: 'URL is the URL where Loki is listening. Must be + a full HTTP URL, including protocol. Required. Example: https://logs-prod-us-central1.grafana.net/loki/api/v1/push.' + type: string + required: + - url + type: object + type: array + podLogsNamespaceSelector: + description: Set of labels to determine which namespaces should be + watched for PodLogs. If not provided, checks only namespace of the + instance. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: A label selector requirement is a selector that + contains values, a key, and an operator that relates the key + and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: operator represents a key's relationship to + a set of values. Valid operators are In, NotIn, Exists + and DoesNotExist. + type: string + values: + description: values is an array of string values. If the + operator is In or NotIn, the values array must be non-empty. + If the operator is Exists or DoesNotExist, the values + array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single + {key,value} in the matchLabels map is equivalent to an element + of matchExpressions, whose key field is "key", the operator + is "In", and the values array contains only "value". The requirements + are ANDed. + type: object + type: object + podLogsSelector: + description: Determines which PodLogs should be selected for including + in this instance. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: A label selector requirement is a selector that + contains values, a key, and an operator that relates the key + and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: operator represents a key's relationship to + a set of values. Valid operators are In, NotIn, Exists + and DoesNotExist. + type: string + values: + description: values is an array of string values. If the + operator is In or NotIn, the values array must be non-empty. + If the operator is Exists or DoesNotExist, the values + array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single + {key,value} in the matchLabels map is equivalent to an element + of matchExpressions, whose key field is "key", the operator + is "In", and the values array contains only "value". The requirements + are ANDed. + type: object + type: object + targetConfig: + description: Configures how tailed targets will be watched. + properties: + syncPeriod: + description: Period to resync directories being watched and files + being tailed to discover new ones or stop watching removed ones. + type: string + type: object + type: object + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_metricsinstances.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_metricsinstances.yaml new file mode 100644 index 0000000..648ae96 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_metricsinstances.yaml @@ -0,0 +1,751 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.8.0 + creationTimestamp: null + name: metricsinstances.monitoring.grafana.com +spec: + group: monitoring.grafana.com + names: + categories: + - agent-operator + kind: MetricsInstance + listKind: MetricsInstanceList + plural: metricsinstances + singular: metricsinstance + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: MetricsInstance controls an individual Metrics instance within + a Grafana Agent deployment. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation + of an object. Servers should convert recognized schemas to the latest + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this + object represents. Servers may infer this from the endpoint the client + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Spec holds the specification of the desired behavior for + the Metrics instance. + properties: + additionalScrapeConfigs: + description: 'AdditionalScrapeConfigs allows specifying a key of a + Secret containing additional Grafana Agent Prometheus scrape configurations. + SCrape configurations specified are appended to the configurations + generated by the Grafana Agent Operator. Job configurations specified + must have the form as specified in the official Prometheus documentation: + https://prometheus.io/docs/prometheus/latest/configuration/configuration/#scrape_config. + As scrape configs are appended, the user is responsible to make + sure it is valid. Note that using this feature may expose the possibility + to break upgrades of Grafana Agent. It is advised to review both + Grafana Agent and Prometheus release notes to ensure that no incompatible + scrape configs are going to break Grafana Agent after the upgrade.' + properties: + key: + description: The key of the secret to select from. Must be a + valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + maxWALTime: + description: MaxWALTime is the maximum amount of time series and asmples + may exist in the WAL before being forcibly deleted. + type: string + minWALTime: + description: MinWALTime is the minimum amount of time series and samples + may exist in the WAL before being considered for deletion. + type: string + podMonitorNamespaceSelector: + description: PodMonitorNamespaceSelector are the set of labels to + determine which namespaces to watch for PodMonitor discovery. If + nil, only checks own namespace. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: A label selector requirement is a selector that + contains values, a key, and an operator that relates the key + and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: operator represents a key's relationship to + a set of values. Valid operators are In, NotIn, Exists + and DoesNotExist. + type: string + values: + description: values is an array of string values. If the + operator is In or NotIn, the values array must be non-empty. + If the operator is Exists or DoesNotExist, the values + array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single + {key,value} in the matchLabels map is equivalent to an element + of matchExpressions, whose key field is "key", the operator + is "In", and the values array contains only "value". The requirements + are ANDed. + type: object + type: object + podMonitorSelector: + description: PodMonitorSelector determines which PodMonitors should + be selected for target discovery. Experimental. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: A label selector requirement is a selector that + contains values, a key, and an operator that relates the key + and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: operator represents a key's relationship to + a set of values. Valid operators are In, NotIn, Exists + and DoesNotExist. + type: string + values: + description: values is an array of string values. If the + operator is In or NotIn, the values array must be non-empty. + If the operator is Exists or DoesNotExist, the values + array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single + {key,value} in the matchLabels map is equivalent to an element + of matchExpressions, whose key field is "key", the operator + is "In", and the values array contains only "value". The requirements + are ANDed. + type: object + type: object + probeNamespaceSelector: + description: ProbeNamespaceSelector are the set of labels to determine + which namespaces to watch for Probe discovery. If nil, only checks + own namespace. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: A label selector requirement is a selector that + contains values, a key, and an operator that relates the key + and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: operator represents a key's relationship to + a set of values. Valid operators are In, NotIn, Exists + and DoesNotExist. + type: string + values: + description: values is an array of string values. If the + operator is In or NotIn, the values array must be non-empty. + If the operator is Exists or DoesNotExist, the values + array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single + {key,value} in the matchLabels map is equivalent to an element + of matchExpressions, whose key field is "key", the operator + is "In", and the values array contains only "value". The requirements + are ANDed. + type: object + type: object + probeSelector: + description: ProbeSelector determines which Probes should be selected + for target discovery. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: A label selector requirement is a selector that + contains values, a key, and an operator that relates the key + and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: operator represents a key's relationship to + a set of values. Valid operators are In, NotIn, Exists + and DoesNotExist. + type: string + values: + description: values is an array of string values. If the + operator is In or NotIn, the values array must be non-empty. + If the operator is Exists or DoesNotExist, the values + array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single + {key,value} in the matchLabels map is equivalent to an element + of matchExpressions, whose key field is "key", the operator + is "In", and the values array contains only "value". The requirements + are ANDed. + type: object + type: object + remoteFlushDeadline: + description: RemoteFlushDeadline is the deadline for flushing data + when an instance shuts down. + type: string + remoteWrite: + description: RemoteWrite controls remote_write settings for this instance. + items: + description: RemoteWriteSpec defines the remote_write configuration + for Prometheus. + properties: + basicAuth: + description: BasicAuth for the URL. + properties: + password: + description: The secret in the service monitor namespace + that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + username: + description: The secret in the service monitor namespace + that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + type: object + bearerToken: + description: BearerToken used for remote_write. + type: string + bearerTokenFile: + description: BearerTokenFile used to read bearer token. + type: string + headers: + additionalProperties: + type: string + description: Headers is a set of custom HTTP headers to be sent + along with each remote_write request. Be aware that any headers + set by Grafana Agent itself can't be overwritten. + type: object + metadataConfig: + description: MetadataConfig configures the sending of series + metadata to remote storage. + properties: + send: + description: Send enables metric metadata to be sent to + remote storage. + type: boolean + sendInterval: + description: SendInterval controls how frequently metric + metadata is sent to remote storage. + type: string + type: object + name: + description: Name of the remote_write queue. Must be unique + if specified. The name is used in metrics and logging in order + to differentiate queues. + type: string + proxyUrl: + description: ProxyURL to proxy requests through. Optional. + type: string + queueConfig: + description: QueueConfig allows tuning of the remote_write queue + parameters. + properties: + batchSendDeadline: + description: BatchSendDeadline is the maximum time a sample + will wait in buffer. + type: string + capacity: + description: Capacity is the number of samples to buffer + per shard before we start dropping them. + type: integer + maxBackoff: + description: MaxBackoff is the maximum retry delay. + type: string + maxRetries: + description: MaxRetries is the maximum number of times to + retry a batch on recoverable errors. + type: integer + maxSamplesPerSend: + description: MaxSamplesPerSend is the maximum number of + samples per send. + type: integer + maxShards: + description: MaxShards is the maximum number of shards, + i.e. amount of concurrency. + type: integer + minBackoff: + description: MinBackoff is the initial retry delay. Gets + doubled for every retry. + type: string + minShards: + description: MinShards is the minimum number of shards, + i.e. amount of concurrency. + type: integer + retryOnRateLimit: + description: RetryOnRateLimit retries requests when encountering + rate limits. + type: boolean + type: object + remoteTimeout: + description: RemoteTimeout is the timeout for requests to the + remote_write endpoint. + type: string + sigv4: + description: SigV4 configures SigV4-based authentication to + the remote_write endpoint. Will be used if SigV4 is defined, + even with an empty object. + properties: + accessKey: + description: AccessKey holds the secret of the AWS API access + key to use for signing. If not provided, The environment + variable AWS_ACCESS_KEY_ID is used. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + profile: + description: Profile is the named AWS profile to use for + authentication. + type: string + region: + description: Region of the AWS endpoint. If blank, the region + from the default credentials chain is used. + type: string + roleARN: + description: RoleARN is the AWS Role ARN to use for authentication, + as an alternative for using the AWS API keys. + type: string + secretKey: + description: SecretKey of the AWS API to use for signing. + If blank, the environment variable AWS_SECRET_ACCESS_KEY + is used. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + type: object + tlsConfig: + description: TLSConfig to use for remote_write. + properties: + ca: + description: Struct containing the CA cert to use for the + targets. + properties: + configMap: + description: ConfigMap containing data to use for the + targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or its + key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + caFile: + description: Path to the CA cert in the Prometheus container + to use for the targets. + type: string + cert: + description: Struct containing the client cert file for + the targets. + properties: + configMap: + description: ConfigMap containing data to use for the + targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the ConfigMap or its + key must be defined + type: boolean + required: + - key + type: object + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, + uid?' + type: string + optional: + description: Specify whether the Secret or its key + must be defined + type: boolean + required: + - key + type: object + type: object + certFile: + description: Path to the client cert file in the Prometheus + container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus + container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the + targets. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + url: + description: URL of the endpoint to send samples to. + type: string + writeRelabelConfigs: + description: WriteRelabelConfigs holds relabel_configs to relabel + samples before they are sent to the remote_write endpoint. + items: + description: 'RelabelConfig allows dynamic rewriting of the + label set, being applied to samples before ingestion. It + defines ``-section of Prometheus + configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. + Default is 'replace' + enum: + - replace + - keep + - drop + - hashmod + - labelmap + - labeldrop + - labelkeep + type: string + modulus: + description: Modulus to take of the hash of the source + label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted + value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace + is performed if the regular expression matches. Regex + capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source + label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing + labels. Their content is concatenated using the configured + separator and matched against the configured regular + expression for the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label name + which may only contain ASCII letters, numbers, as + well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written + in a replace action. It is mandatory for replace actions. + Regex capture groups are available. + type: string + type: object + type: array + required: + - url + type: object + type: array + serviceMonitorNamespaceSelector: + description: ServiceMonitorNamespaceSelector are the set of labels + to determine which namespaces to watch for ServiceMonitor discovery. + If nil, only checks own namespace. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: A label selector requirement is a selector that + contains values, a key, and an operator that relates the key + and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: operator represents a key's relationship to + a set of values. Valid operators are In, NotIn, Exists + and DoesNotExist. + type: string + values: + description: values is an array of string values. If the + operator is In or NotIn, the values array must be non-empty. + If the operator is Exists or DoesNotExist, the values + array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single + {key,value} in the matchLabels map is equivalent to an element + of matchExpressions, whose key field is "key", the operator + is "In", and the values array contains only "value". The requirements + are ANDed. + type: object + type: object + serviceMonitorSelector: + description: ServiceMonitorSelector determines which ServiceMonitors + should be selected for target discovery. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: A label selector requirement is a selector that + contains values, a key, and an operator that relates the key + and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: operator represents a key's relationship to + a set of values. Valid operators are In, NotIn, Exists + and DoesNotExist. + type: string + values: + description: values is an array of string values. If the + operator is In or NotIn, the values array must be non-empty. + If the operator is Exists or DoesNotExist, the values + array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single + {key,value} in the matchLabels map is equivalent to an element + of matchExpressions, whose key field is "key", the operator + is "In", and the values array contains only "value". The requirements + are ANDed. + type: object + type: object + walTruncateFrequency: + description: WALTruncateFrequency specifies how frequently the WAL + truncation process should run. Higher values causes the WAL to increase + and for old series to stay in the WAL for longer, but reduces the + chances of data loss when remote_write is failing for longer than + the given frequency. + type: string + writeStaleOnShutdown: + description: WriteStaleOnShutdown writes staleness markers on shutdown + for all series. + type: boolean + type: object + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_podlogs.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_podlogs.yaml new file mode 100644 index 0000000..533e336 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/crds/monitoring.grafana.com_podlogs.yaml @@ -0,0 +1,554 @@ +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.8.0 + creationTimestamp: null + name: podlogs.monitoring.grafana.com +spec: + group: monitoring.grafana.com + names: + categories: + - agent-operator + kind: PodLogs + listKind: PodLogsList + plural: podlogs + singular: podlogs + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: PodLogs defines how to collect logs for a pod. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation + of an object. Servers should convert recognized schemas to the latest + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this + object represents. Servers may infer this from the endpoint the client + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Spec holds the specification of the desired behavior for + the PodLogs. + properties: + jobLabel: + description: The label to use to retrieve the job name from. + type: string + namespaceSelector: + description: Selector to select which namespaces the Pod objects are + discovered from. + properties: + any: + description: Boolean describing whether all namespaces are selected + in contrast to a list restricting them. + type: boolean + matchNames: + description: List of namespace names to select from. + items: + type: string + type: array + type: object + pipelineStages: + description: Pipeline stages for this pod. Pipeline stages allow for + transforming and filtering log lines. + items: + description: "PipelineStageSpec defines an individual pipeline stage. + Each stage type is mutually exclusive and no more than one may + be set per stage. \n More information on pipelines can be found + in the Promtail documentation: https://grafana.com/docs/loki/latest/clients/promtail/pipelines/" + properties: + cri: + description: 'CRI is a parsing stage that reads log lines using + the standard CRI logging format. Supply cri: {} to enable.' + type: object + docker: + description: 'Docker is a parsing stage that reads log lines + using the standard Docker logging format. Supply docker: {} + to enable.' + type: object + drop: + description: Drop is a filtering stage that lets you drop certain + logs. + properties: + dropCounterReason: + description: Every time a log line is dropped the metric + logentry_dropped_lines_total will be incremented. A "reason" + label is added, and can be customized by providing a custom + value here. Defaults to "drop_stage." + type: string + expression: + description: "RE2 regular exprssion. \n If source is provided, + the regex will attempt to match the source. \n If no source + is provided, then the regex will attempt to attach the + log line. \n If the provided regex matches the log line + or a provided source, the line will be dropped." + type: string + longerThan: + description: LongerThan will drop a log line if it its content + is longer than this value (in bytes). Can be expressed + as an integer (8192) or a number with a suffix (8kb). + type: string + olderThan: + description: OlderThan will be parsed as a Go duration. + If the log line's timestamp is older than the current + time minus the provided duration it will be dropped. + type: string + source: + description: Name from the extract data to parse. If empty, + uses the log message. + type: string + value: + description: "Value can only be specified when source is + specified. If the value provided is an exact match for + the given source then the line will be dropped. \n Mutually + exclusive with expression." + type: string + type: object + json: + description: "JSON is a parsing stage that reads the log line + as JSON and accepts JMESPath expressions to extract data. + \n Information on JMESPath: http://jmespath.org/" + properties: + expressions: + additionalProperties: + type: string + description: "Set of the key/value pairs of JMESPath expressions. + The key will be the key in the extracted data while the + expression will be the value, evaluated as a JMESPath + from the source data. \n Literal JMESPath exprssions can + be done by wrapping a key in double quotes, which then + must be wrapped again in single quotes in YAML so they + get passed to the JMESPath parser." + type: object + source: + description: Name from the extracted data to parse as JSON. + If empty, uses entire log message. + type: string + type: object + labelAllow: + description: LabelAllow is an action stage that only allows + the provided labels to be included in the label set that is + sent to Loki with the log entry. + items: + type: string + type: array + labelDrop: + description: LabelDrop is an action stage that drops labels + from the label set that is sent to Loki with the log entry. + items: + type: string + type: array + labels: + additionalProperties: + type: string + description: "Labels is an action stage that takes data from + the extracted map and modifies the label set that is sent + to Loki with the log entry. \n The key is REQUIRED and represents + the name for the label that will be created. Value is optional + and will be the name from extracted data to use for the value + of the label. If the value is not provided, it defaults to + match the key." + type: object + match: + description: Match is a filtering stage that conditionally applies + a set of stages or drop entries when a log entry matches a + configurable LogQL stream selector and filter expressions. + properties: + action: + description: Determines what action is taken when the selector + matches the log line. Can be keep or drop. Defaults to + keep. When set to drop, entries will be dropped and no + later metrics will be recorded. Stages must be empty when + dropping metrics. + type: string + dropCounterReason: + description: Every time a log line is dropped the metric + logentry_dropped_lines_total will be incremented. A "reason" + label is added, and can be customized by providing a custom + value here. Defaults to "match_stage." + type: string + pipelineName: + description: Names the pipeline. When defined, creates an + additional label in the pipeline_duration_seconds histogram, + where the value is concatenated with job_name using an + underscore. + type: string + selector: + description: LogQL stream selector and filter expressions. + Required. + type: string + stages: + description: "Nested set of pipeline stages to execute when + action: keep and the log line matches selector. \n An + example value for stages may be: \n stages: | - json: + {} - labelAllow: [foo, bar] \n Note that stages is a string + because SIG API Machinery does not support recursive types, + and so it cannot be validated for correctness. Be careful + not to mistype anything." + type: string + required: + - selector + type: object + metrics: + additionalProperties: + description: MetricsStageSpec is an action stage that allows + for defining and updating metrics based on data from the + extracted map. Created metrics are not pushed to Loki or + Prometheus and are instead exposed via the /metrics endpoint + of the Grafana Agent pod. The Grafana Agent Operator should + be configured with a MetricsInstance that discovers the + logging DaemonSet to collect metrics created by this stage. + properties: + action: + description: "The action to take against the metric. Required. + \n Must be either \"inc\" or \"add\" for type: counter + or type: histogram. When type: gauge, must be one of + \"set\", \"inc\", \"dec\", \"add\", or \"sub\". \n \"add\", + \"set\", or \"sub\" requires the extracted value to + be convertible to a positive float." + type: string + buckets: + description: 'Buckets to create. Bucket values must be + convertible to float64s. Extremely large or small numbers + are subject to some loss of precision. Only valid for + type: histogram.' + items: + type: string + type: array + countEntryBytes: + description: "If true all log line bytes will be counted. + Can only be set with matchAll: true and action: add. + \n Only valid for type: counter." + type: boolean + description: + description: Sets the description for the created metric. + type: string + matchAll: + description: "If true all log lines will be counted without + attempting to match the source to the extracted map. + Mutually exclusive with value. \n Only valid for type: + counter." + type: boolean + maxIdleDuration: + description: "Label values on metrics are dynamic which + can cause exported metrics to go stale. To prevent unbounded + cardinality, any metrics not updated within MaxIdleDuration + will be removed. \n Must be greater or equal to 1s. + Defaults to 5m." + type: string + prefix: + description: Sets the custom prefix name for the metric. + Defaults to "promtail_custom_". + type: string + source: + description: Key from the extracted data map to use for + the metric. Defaults to the metrics name if not present. + type: string + type: + description: The metric type to create. Must be one of + counter, gauge, histogram. Required. + type: string + value: + description: Filters down source data and only changes + the metric if the targeted value exactly matches the + provided string. If not present, all data will match. + type: string + required: + - action + - type + type: object + description: Metrics is an action stage that allows for defining + and updating metrics based on data from the extracted map. + Created metrics are not pushed to Loki or Prometheus and are + instead exposed via the /metrics endpoint of the Grafana Agent + pod. The Grafana Agent Operator should be configured with + a MetricsInstance that discovers the logging DaemonSet to + collect metrics created by this stage. + type: object + multiline: + description: Multiline stage merges multiple lines into a multiline + block before passing it on to the next stage in the pipeline. + properties: + firstLine: + description: RE2 regular expression. Creates a new multiline + block when matched. Required. + type: string + maxLines: + description: Maximum number of lines a block can have. A + new block is started if the number of lines surpasses + this value. Defaults to 128. + type: integer + maxWaitTime: + description: Maximum time to wait before passing on the + multiline block to the next stage if no new lines are + received. Defaults to 3s. + type: string + required: + - firstLine + type: object + output: + description: Output stage is an action stage that takes data + from the extracted map and changes the log line that will + be sent to Loki. + properties: + source: + description: Name from extract data to use for the log entry. + Required. + type: string + required: + - source + type: object + pack: + description: Pack is a transform stage that lets you embed extracted + values and labels into the log line by packing the log line + and labels inside of a JSON object. + properties: + ingestTimestamp: + description: If the resulting log line should use any existing + timestamp or use time.Now() when the line was created. + Set to true when combining several log streams from different + containers to avoid out of order errors. + type: boolean + labels: + description: Name from extracted data or line labels. Requiried. + Labels provided here are automatically removed from output + labels. + items: + type: string + type: array + required: + - labels + type: object + regex: + description: Regex is a parsing stage that parses a log line + using a regular expression. Named capture groups in the regex + allows for adding data into the extracted map. + properties: + expression: + description: RE2 regular expression. Each capture group + MUST be named. Required. + type: string + source: + description: Name from extracted data to parse. If empty, + defaults to using the log message. + type: string + required: + - expression + type: object + replace: + description: Replace is a parsing stage that parses a log line + using a regular expression and replaces the log line. Named + capture groups in the regex allows for adding data into the + extracted map. + properties: + expression: + description: RE2 regular expression. Each capture group + MUST be named. Required. + type: string + replace: + description: Value to replace the captured group with. + type: string + source: + description: Name from extracted data to parse. If empty, + defaults to using the log message. + type: string + required: + - expression + type: object + template: + description: Template is a transform stage that manipulates + the values in the extracted map using Go's template syntax. + properties: + source: + description: Name from extracted data to parse. Required. + If empty, defaults to using the log message. + type: string + template: + description: Go template string to use. Required. In additional + to normal template functions, ToLower, ToUpper, Replace, + Trim, TrimLeft, TrimRight, TrimPrefix, and TrimSpace are + also available. + type: string + required: + - source + - template + type: object + tenant: + description: Tenant is an action stage that sets the tenant + ID for the log entry picking it from a field in the extracted + data map. If the field is missing, the default LogsClientSpec.tenantId + will be used. + properties: + source: + description: Name from extracted data to use as the tenant + ID. Mutually exclusive with value. + type: string + value: + description: Value to use for the template ID. Useful when + this stage is used within a conditional pipeline such + as match. Mutually exclusive with source. + type: string + type: object + timestamp: + description: Timestamp is an action stage that can change the + timestamp of a log line before it is sent to Loki. If not + present, the timestamp of a log line defaults to the time + when the log line was read. + properties: + actionOnFailure: + description: Action to take when the timestamp can't be + extracted or parsed. Can be skip or fudge. Defaults to + fudge. + type: string + fallbackFormats: + description: Fallback formats to try if format fails. + items: + type: string + type: array + format: + description: 'Determines format of the time string. Required. + Can be one of: ANSIC, UnixDate, RubyDate, RFC822, RFC822Z, + RFC850, RFC1123, RFC1123Z, RFC3339, RFC3339Nano, Unix, + UnixMs, UnixUs, UnixNs.' + type: string + location: + description: IANA Timezone Database string. + type: string + source: + description: Name from extracted data to use as the timestamp. + Required. + type: string + required: + - format + - source + type: object + type: object + type: array + podTargetLabels: + description: PodTargetLabels transfers labels on the Kubernetes Pod + onto the target. + items: + type: string + type: array + relabelings: + description: "RelabelConfigs to apply to logs before delivering. Grafana + Agent Operator automatically adds relabelings for a few standard + Kubernetes fields and replaces original scrape job name with __tmp_logs_job_name. + \n More info: https://grafana.com/docs/loki/latest/clients/promtail/configuration/#relabel_configs" + items: + description: 'RelabelConfig allows dynamic rewriting of the label + set, being applied to samples before ingestion. It defines ``-section + of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. Default + is 'replace' + enum: + - replace + - keep + - drop + - hashmod + - labelmap + - labeldrop + - labelkeep + type: string + modulus: + description: Modulus to take of the hash of the source label + values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted + value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace + is performed if the regular expression matches. Regex capture + groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label + values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. + Their content is concatenated using the configured separator + and matched against the configured regular expression for + the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label name which + may only contain ASCII letters, numbers, as well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in + a replace action. It is mandatory for replace actions. Regex + capture groups are available. + type: string + type: object + type: array + selector: + description: Selector to select Pod objects. Required. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: A label selector requirement is a selector that + contains values, a key, and an operator that relates the key + and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: operator represents a key's relationship to + a set of values. Valid operators are In, NotIn, Exists + and DoesNotExist. + type: string + values: + description: values is an array of string values. If the + operator is In or NotIn, the values array must be non-empty. + If the operator is Exists or DoesNotExist, the values + array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single + {key,value} in the matchLabels map is equivalent to an element + of matchExpressions, whose key field is "key", the operator + is "In", and the values array contains only "value". The requirements + are ANDed. + type: object + type: object + required: + - selector + type: object + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/_helpers.tpl b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/_helpers.tpl new file mode 100644 index 0000000..f464671 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/_helpers.tpl @@ -0,0 +1,67 @@ +{{/* +Expand the name of the chart. +*/}} +{{- define "ga-operator.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "ga-operator.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default .Chart.Name .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "ga-operator.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "ga-operator.labels" -}} +{{ include "ga-operator.selectorLabels" . }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +app.kubernetes.io/component: operator +helm.sh/chart: {{ include "ga-operator.chart" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +{{- if .Values.customLabels }} +{{ toYaml .Values.customLabels }} +{{- end }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "ga-operator.selectorLabels" -}} +app.kubernetes.io/name: {{ include "ga-operator.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Create the name of the service account to use +*/}} +{{- define "ga-operator.serviceAccountName" -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "ga-operator.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} + diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/operator-clusterrole.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/operator-clusterrole.yaml new file mode 100644 index 0000000..aad0c89 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/operator-clusterrole.yaml @@ -0,0 +1,55 @@ +{{- if .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ include "ga-operator.fullname" . }} + labels: +{{ include "ga-operator.labels" . | indent 4 }} +rules: +- apiGroups: [monitoring.grafana.com] + resources: + - grafanaagents + - metricsinstances + - logsinstances + - podlogs + - integrations + verbs: [get, list, watch] +- apiGroups: [monitoring.grafana.com] + resources: + - grafanaagents/finalizers + - metricsinstances/finalizers + - logsinstances/finalizers + - podlogs/finalizers + - integrations/finalizers + verbs: [get, list, watch, update] +- apiGroups: [monitoring.coreos.com] + resources: + - podmonitors + - probes + - servicemonitors + verbs: [get, list, watch] +- apiGroups: [monitoring.coreos.com] + resources: + - podmonitors/finalizers + - probes/finalizers + - servicemonitors/finalizers + verbs: [get, list, watch, update] +- apiGroups: [""] + resources: + - namespaces + - nodes + verbs: [get, list, watch] +- apiGroups: [""] + resources: + - secrets + - services + - configmaps + - endpoints + verbs: [get, list, watch, create, update, patch, delete] +- apiGroups: ["apps"] + resources: + - statefulsets + - daemonsets + - deployments + verbs: [get, list, watch, create, update, patch, delete] +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/operator-clusterrolebinding.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/operator-clusterrolebinding.yaml new file mode 100644 index 0000000..372d310 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/operator-clusterrolebinding.yaml @@ -0,0 +1,17 @@ +{{- if .Values.rbac.create -}} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "ga-operator.fullname" . }} + labels: +{{ include "ga-operator.labels" . | indent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "ga-operator.fullname" . }} +subjects: +- kind: ServiceAccount + name: {{ template "ga-operator.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} +{{- end -}} + diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/operator-deployment.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/operator-deployment.yaml new file mode 100644 index 0000000..d83087c --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/operator-deployment.yaml @@ -0,0 +1,67 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "ga-operator.fullname" . }} + labels: +{{ include "ga-operator.labels" . | indent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: 1 + selector: + matchLabels: +{{ include "ga-operator.selectorLabels" . | indent 6 }} + template: + metadata: + labels: +{{ include "ga-operator.selectorLabels" . | indent 8 }} +{{- with .Values.podLabels }} +{{- toYaml . | nindent 8 }} +{{- end }} +{{- with .Values.podAnnotations }} + annotations: +{{ toYaml . | indent 8 }} +{{- end }} + spec: + serviceAccountName: {{ template "ga-operator.serviceAccountName" . }} + {{- with .Values.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: {{ include "ga-operator.name" . }} + image: "{{ .Values.image.registry }}/{{ .Values.image.repository }}:{{ .Values.image.tag }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + {{- with .Values.resources }} + resources: + {{- toYaml . | nindent 10 }} + {{- end }} + {{- if or (and .Values.kubeletService.namespace .Values.kubeletService.serviceName) (.Values.extraArgs) }} + args: + {{- if and .Values.kubeletService.namespace .Values.kubeletService.serviceName }} + - --kubelet-service={{ .Values.kubeletService.namespace }}/{{ .Values.kubeletService.serviceName }} + {{- end }} + {{- if .Values.extraArgs }} + {{- range .Values.extraArgs }} + - {{ . }} + {{- end }} + {{- end }} + {{- end }} + {{- with .Values.image.pullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/operator-serviceaccount.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/operator-serviceaccount.yaml new file mode 100644 index 0000000..f8125e8 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/operator-serviceaccount.yaml @@ -0,0 +1,9 @@ +{{- if .Values.serviceAccount.create -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ template "ga-operator.serviceAccountName" . }} + labels: +{{ include "ga-operator.labels" . | indent 4 }} +{{- end -}} + diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/tests/test-grafanaagent.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/tests/test-grafanaagent.yaml new file mode 100644 index 0000000..9e9d913 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/templates/tests/test-grafanaagent.yaml @@ -0,0 +1,118 @@ +apiVersion: monitoring.grafana.com/v1alpha1 +kind: GrafanaAgent +metadata: + name: grafana-agent-test + labels: + app: grafana-agent-test + annotations: + "helm.sh/hook": test + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded,hook-failed +spec: + image: "{{ .Values.image.registry }}/grafana/agent:{{ .Values.image.tag }}" + logLevel: info + serviceAccountName: grafana-agent-test-sa + metrics: + instanceSelector: + matchLabels: + agent: grafana-agent-test + +--- + +apiVersion: v1 +kind: ServiceAccount +metadata: + name: grafana-agent-test-sa + annotations: + "helm.sh/hook": test + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded,hook-failed + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: grafana-agent-test-cr + annotations: + "helm.sh/hook": test + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded,hook-failed +rules: +- apiGroups: + - "" + resources: + - nodes + - nodes/proxy + - nodes/metrics + - services + - endpoints + - pods + verbs: + - get + - list + - watch +- apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch +- nonResourceURLs: + - /metrics + - /metrics/cadvisor + verbs: + - get + +--- + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: grafana-agent-test-crb + annotations: + "helm.sh/hook": test + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded,hook-failed +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: grafana-agent-test-cr +subjects: +- kind: ServiceAccount + name: grafana-agent-test-sa + namespace: {{ .Release.Namespace }} + +--- + +apiVersion: monitoring.grafana.com/v1alpha1 +kind: MetricsInstance +metadata: + name: primary-test + annotations: + "helm.sh/hook": test + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded,hook-failed + labels: + agent: grafana-agent-test +spec: {} + +--- + +apiVersion: v1 +kind: Pod +metadata: + name: grafana-agent-test-probe + annotations: + "helm.sh/hook": test + "helm.sh/hook-weight": "1" + "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded,hook-failed +spec: + containers: + - name: busybox + image: busybox + command: ['wget'] + args: ['grafana-agent-test-operated:8080/-/healthy'] + # Wait for GrafanaAgent CR + initContainers: + - name: sleep + image: busybox + command: ['sleep', '60'] + restartPolicy: Never diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/values.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/values.yaml new file mode 100644 index 0000000..3d69c60 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/grafana-agent-operator/values.yaml @@ -0,0 +1,60 @@ +# -- Overrides the chart's name +nameOverride: "" + +# -- Overrides the chart's computed fullname +fullnameOverride: "" + +# -- Annotations for the Deployment +annotations: {} + +# -- Annotations for the Deployment Pods +podAnnotations: {} + +# -- Annotations for the Deployment Pods +podLabels: {} + +# -- Pod security context (runAsUser, etc.) +podSecurityContext: {} + +# -- Toggle to create ClusterRole and ClusterRoleBinding +rbac: + create: true + +serviceAccount: + # -- Toggle to create ServiceAccount + create: true + # -- Service account name + name: + +image: + # -- Image registry + registry: docker.io + # -- Image repo + repository: grafana/agent-operator + # -- Image tag + tag: v0.25.1 + # -- Image pull policy + pullPolicy: IfNotPresent + # -- Image pull secrets + pullSecrets: [] + +# -- If both are set, Agent Operator will create and maintain a service for scraping kubelets +# https://grafana.com/docs/agent/latest/operator/getting-started/#monitor-kubelets +kubeletService: + namespace: default + serviceName: kubelet + +# -- List of additional cli arguments to configure agent-operator (example: `--log.level`) +extraArgs: [] + +# -- Resource limits and requests config +resources: {} + +# -- nodeSelector configuration +nodeSelector: {} + +# -- Tolerations applied to Pods +tolerations: [] + +# -- Pod affinity configuration +affinity: {} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/.helmignore b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/.helmignore new file mode 100644 index 0000000..a9fe727 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/.helmignore @@ -0,0 +1,23 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj +# OWNERS file for Kubernetes +OWNERS \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/Chart.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/Chart.yaml new file mode 100644 index 0000000..67824a4 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/Chart.yaml @@ -0,0 +1,18 @@ +apiVersion: v1 +appVersion: RELEASE.2022-08-13T21-54-44Z +description: Multi-Cloud Object Storage +home: https://min.io +icon: https://min.io/resources/img/logo/MINIO_wordmark.png +keywords: +- minio +- storage +- object-storage +- s3 +- cluster +maintainers: +- email: dev@minio.io + name: MinIO, Inc +name: minio +sources: +- https://github.com/minio/minio +version: 4.0.12 diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/README.md b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/README.md new file mode 100644 index 0000000..898dcfa --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/README.md @@ -0,0 +1,236 @@ +# MinIO Helm Chart + +[![Slack](https://slack.min.io/slack?type=svg)](https://slack.min.io) [![license](https://img.shields.io/badge/license-AGPL%20V3-blue)](https://github.com/minio/minio/blob/master/LICENSE) + +MinIO is a High Performance Object Storage released under GNU Affero General Public License v3.0. It is API compatible with Amazon S3 cloud storage service. Use MinIO to build high performance infrastructure for machine learning, analytics and application data workloads. + +For more detailed documentation please visit [here](https://docs.minio.io/) + +## Introduction + +This chart bootstraps MinIO Cluster on [Kubernetes](http://kubernetes.io) using the [Helm](https://helm.sh) package manager. + +## Prerequisites + +- Helm cli with Kubernetes cluster configured. +- PV provisioner support in the underlying infrastructure. (We recommend using ) +- Use Kubernetes version v1.19 and later for best experience. + +## Configure MinIO Helm repo + +```bash +helm repo add minio https://charts.min.io/ +``` + +### Installing the Chart + +Install this chart using: + +```bash +helm install --namespace minio --set rootUser=rootuser,rootPassword=rootpass123 --generate-name minio/minio +``` + +The command deploys MinIO on the Kubernetes cluster in the default configuration. The [configuration](#configuration) section lists the parameters that can be configured during installation. + +### Upgrading the Chart + +You can use Helm to update MinIO version in a live release. Assuming your release is named as `my-release`, get the values using the command: + +```bash +helm get values my-release > old_values.yaml +``` + +Then change the field `image.tag` in `old_values.yaml` file with MinIO image tag you want to use. Now update the chart using + +```bash +helm upgrade -f old_values.yaml my-release minio/minio +``` + +Default upgrade strategies are specified in the `values.yaml` file. Update these fields if you'd like to use a different strategy. + +### Configuration + +Refer the [Values file](./values.yaml) for all the possible config fields. + +You can specify each parameter using the `--set key=value[,key=value]` argument to `helm install`. For example, + +```bash +helm install --name my-release --set persistence.size=1Ti minio/minio +``` + +The above command deploys MinIO server with a 1Ti backing persistent volume. + +Alternately, you can provide a YAML file that specifies parameter values while installing the chart. For example, + +```bash +helm install --name my-release -f values.yaml minio/minio +``` + +### Persistence + +This chart provisions a PersistentVolumeClaim and mounts corresponding persistent volume to default location `/export`. You'll need physical storage available in the Kubernetes cluster for this to work. If you'd rather use `emptyDir`, disable PersistentVolumeClaim by: + +```bash +helm install --set persistence.enabled=false minio/minio +``` + +> *"An emptyDir volume is first created when a Pod is assigned to a Node, and exists as long as that Pod is running on that node. When a Pod is removed from a node for any reason, the data in the emptyDir is deleted forever."* + +### Existing PersistentVolumeClaim + +If a Persistent Volume Claim already exists, specify it during installation. + +1. Create the PersistentVolume +2. Create the PersistentVolumeClaim +3. Install the chart + +```bash +helm install --set persistence.existingClaim=PVC_NAME minio/minio +``` + +### NetworkPolicy + +To enable network policy for MinIO, +install [a networking plugin that implements the Kubernetes +NetworkPolicy spec](https://kubernetes.io/docs/tasks/administer-cluster/declare-network-policy#before-you-begin), +and set `networkPolicy.enabled` to `true`. + +For Kubernetes v1.5 & v1.6, you must also turn on NetworkPolicy by setting +the DefaultDeny namespace annotation. Note: this will enforce policy for *all* pods in the namespace: + +``` +kubectl annotate namespace default "net.beta.kubernetes.io/network-policy={\"ingress\":{\"isolation\":\"DefaultDeny\"}}" +``` + +With NetworkPolicy enabled, traffic will be limited to just port 9000. + +For more precise policy, set `networkPolicy.allowExternal=true`. This will +only allow pods with the generated client label to connect to MinIO. +This label will be displayed in the output of a successful install. + +### Existing secret + +Instead of having this chart create the secret for you, you can supply a preexisting secret, much +like an existing PersistentVolumeClaim. + +First, create the secret: + +```bash +kubectl create secret generic my-minio-secret --from-literal=rootUser=foobarbaz --from-literal=rootPassword=foobarbazqux +``` + +Then install the chart, specifying that you want to use an existing secret: + +```bash +helm install --set existingSecret=my-minio-secret minio/minio +``` + +The following fields are expected in the secret: + +| .data.\ in Secret | Corresponding variable | Description | Required | +|:------------------------|:-----------------------|:---------------|:---------| +| `rootUser` | `rootUser` | Root user. | yes | +| `rootPassword` | `rootPassword` | Root password. | yes | + +All corresponding variables will be ignored in values file. + +### Configure TLS + +To enable TLS for MinIO containers, acquire TLS certificates from a CA or create self-signed certificates. While creating / acquiring certificates ensure the corresponding domain names are set as per the standard [DNS naming conventions](https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#pod-identity) in a Kubernetes StatefulSet (for a distributed MinIO setup). Then create a secret using + +```bash +kubectl create secret generic tls-ssl-minio --from-file=path/to/private.key --from-file=path/to/public.crt +``` + +Then install the chart, specifying that you want to use the TLS secret: + +```bash +helm install --set tls.enabled=true,tls.certSecret=tls-ssl-minio minio/minio +``` + +### Installing certificates from third party CAs + +MinIO can connect to other servers, including MinIO nodes or other server types such as NATs and Redis. If these servers use certificates that were not registered with a known CA, add trust for these certificates to MinIO Server by bundling these certificates into a Kubernetes secret and providing it to Helm via the `trustedCertsSecret` value. If `.Values.tls.enabled` is `true` and you're installing certificates for third party CAs, remember to include MinIO's own certificate with key `public.crt`, if it also needs to be trusted. + +For instance, given that TLS is enabled and you need to add trust for MinIO's own CA and for the CA of a Keycloak server, a Kubernetes secret can be created from the certificate files using `kubectl`: + +``` +kubectl -n minio create secret generic minio-trusted-certs --from-file=public.crt --from-file=keycloak.crt +``` + +If TLS is not enabled, you would need only the third party CA: + +``` +kubectl -n minio create secret generic minio-trusted-certs --from-file=keycloak.crt +``` + +The name of the generated secret can then be passed to Helm using a values file or the `--set` parameter: + +``` +trustedCertsSecret: "minio-trusted-certs" + +or + +--set trustedCertsSecret=minio-trusted-certs +``` + +### Create buckets after install + +Install the chart, specifying the buckets you want to create after install: + +```bash +helm install --set buckets[0].name=bucket1,buckets[0].policy=none,buckets[0].purge=false minio/minio +``` + +Description of the configuration parameters used above - + +- `buckets[].name` - name of the bucket to create, must be a string with length > 0 +- `buckets[].policy` - can be one of none|download|upload|public +- `buckets[].purge` - purge if bucket exists already + +### Create policies after install + +Install the chart, specifying the policies you want to create after install: + +```bash +helm install --set policies[0].name=mypolicy,policies[0].statements[0].resources[0]='arn:aws:s3:::bucket1',policies[0].statements[0].actions[0]='s3:ListBucket',policies[0].statements[0].actions[1]='s3:GetObject' minio/minio +``` + +Description of the configuration parameters used above - + +- `policies[].name` - name of the policy to create, must be a string with length > 0 +- `policies[].statements[]` - list of statements, includes actions and resources +- `policies[].statements[].resources[]` - list of resources that applies the statement +- `policies[].statements[].actions[]` - list of actions granted + +### Create user after install + +Install the chart, specifying the users you want to create after install: + +```bash +helm install --set users[0].accessKey=accessKey,users[0].secretKey=secretKey,users[0].policy=none,users[1].accessKey=accessKey2,users[1].secretRef=existingSecret,users[1].secretKey=password,users[1].policy=none minio/minio +``` + +Description of the configuration parameters used above - + +- `users[].accessKey` - accessKey of user +- `users[].secretKey` - secretKey of usersecretRef +- `users[].existingSecret` - secret name that contains the secretKey of user +- `users[].existingSecretKey` - data key in existingSecret secret containing the secretKey +- `users[].policy` - name of the policy to assign to user + +## Uninstalling the Chart + +Assuming your release is named as `my-release`, delete it using the command: + +```bash +helm delete my-release +``` + +or + +```bash +helm uninstall my-release +``` + +The command removes all the Kubernetes components associated with the chart and deletes the release. diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/NOTES.txt b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/NOTES.txt new file mode 100644 index 0000000..9337196 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/NOTES.txt @@ -0,0 +1,43 @@ +{{- if eq .Values.service.type "ClusterIP" "NodePort" }} +MinIO can be accessed via port {{ .Values.service.port }} on the following DNS name from within your cluster: +{{ template "minio.fullname" . }}.{{ .Release.Namespace }}.svc.cluster.local + +To access MinIO from localhost, run the below commands: + + 1. export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "release={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}") + + 2. kubectl port-forward $POD_NAME 9000 --namespace {{ .Release.Namespace }} + +Read more about port forwarding here: http://kubernetes.io/docs/user-guide/kubectl/kubectl_port-forward/ + +You can now access MinIO server on http://localhost:9000. Follow the below steps to connect to MinIO server with mc client: + + 1. Download the MinIO mc client - https://docs.minio.io/docs/minio-client-quickstart-guide + + 2. export MC_HOST_{{ template "minio.fullname" . }}-local=http://$(kubectl get secret --namespace {{ .Release.Namespace }} {{ template "minio.secretName" . }} -o jsonpath="{.data.rootUser}" | base64 --decode):$(kubectl get secret --namespace {{ .Release.Namespace }} {{ template "minio.secretName" . }} -o jsonpath="{.data.rootPassword}" | base64 --decode)@localhost:{{ .Values.service.port }} + + 3. mc ls {{ template "minio.fullname" . }}-local + +{{- end }} +{{- if eq .Values.service.type "LoadBalancer" }} +MinIO can be accessed via port {{ .Values.service.port }} on an external IP address. Get the service external IP address by: +kubectl get svc --namespace {{ .Release.Namespace }} -l app={{ template "minio.fullname" . }} + +Note that the public IP may take a couple of minutes to be available. + +You can now access MinIO server on http://:9000. Follow the below steps to connect to MinIO server with mc client: + + 1. Download the MinIO mc client - https://docs.minio.io/docs/minio-client-quickstart-guide + + 2. export MC_HOST_{{ template "minio.fullname" . }}-local=http://$(kubectl get secret {{ template "minio.secretName" . }} --namespace {{ .Release.Namespace }} -o jsonpath="{.data.rootUser}" | base64 --decode):$(kubectl get secret {{ template "minio.secretName" . }} -o jsonpath="{.data.rootPassword}" | base64 --decode)@:{{ .Values.service.port }} + + 3. mc ls {{ template "minio.fullname" . }} + +Alternately, you can use your browser or the MinIO SDK to access the server - https://docs.minio.io/categories/17 +{{- end }} + +{{ if and (.Values.networkPolicy.enabled) (not .Values.networkPolicy.allowExternal) }} +Note: Since NetworkPolicy is enabled, only pods with label +{{ template "minio.fullname" . }}-client=true" +will be able to connect to this minio cluster. +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_create_bucket.txt b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_create_bucket.txt new file mode 100644 index 0000000..ced600d --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_create_bucket.txt @@ -0,0 +1,123 @@ +#!/bin/sh +set -e ; # Have script exit in the event of a failed command. + +{{- if .Values.configPathmc }} +MC_CONFIG_DIR="{{ .Values.configPathmc }}" +MC="/usr/bin/mc --insecure --config-dir ${MC_CONFIG_DIR}" +{{- else }} +MC="/usr/bin/mc --insecure" +{{- end }} + +# connectToMinio +# Use a check-sleep-check loop to wait for MinIO service to be available +connectToMinio() { + SCHEME=$1 + ATTEMPTS=0 ; LIMIT=29 ; # Allow 30 attempts + set -e ; # fail if we can't read the keys. + ACCESS=$(cat /config/rootUser) ; SECRET=$(cat /config/rootPassword) ; + set +e ; # The connections to minio are allowed to fail. + echo "Connecting to MinIO server: $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT" ; + MC_COMMAND="${MC} alias set myminio $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT $ACCESS $SECRET" ; + $MC_COMMAND ; + STATUS=$? ; + until [ $STATUS = 0 ] + do + ATTEMPTS=`expr $ATTEMPTS + 1` ; + echo \"Failed attempts: $ATTEMPTS\" ; + if [ $ATTEMPTS -gt $LIMIT ]; then + exit 1 ; + fi ; + sleep 2 ; # 1 second intervals between attempts + $MC_COMMAND ; + STATUS=$? ; + done ; + set -e ; # reset `e` as active + return 0 +} + +# checkBucketExists ($bucket) +# Check if the bucket exists, by using the exit code of `mc ls` +checkBucketExists() { + BUCKET=$1 + CMD=$(${MC} ls myminio/$BUCKET > /dev/null 2>&1) + return $? +} + +# createBucket ($bucket, $policy, $purge) +# Ensure bucket exists, purging if asked to +createBucket() { + BUCKET=$1 + POLICY=$2 + PURGE=$3 + VERSIONING=$4 + OBJECTLOCKING=$5 + + # Purge the bucket, if set & exists + # Since PURGE is user input, check explicitly for `true` + if [ $PURGE = true ]; then + if checkBucketExists $BUCKET ; then + echo "Purging bucket '$BUCKET'." + set +e ; # don't exit if this fails + ${MC} rm -r --force myminio/$BUCKET + set -e ; # reset `e` as active + else + echo "Bucket '$BUCKET' does not exist, skipping purge." + fi + fi + +# Create the bucket if it does not exist and set objectlocking if enabled (NOTE: versioning will be not changed if OBJECTLOCKING is set because it enables versioning to the Buckets created) +if ! checkBucketExists $BUCKET ; then + if [ ! -z $OBJECTLOCKING ] ; then + if [ $OBJECTLOCKING = true ] ; then + echo "Creating bucket with OBJECTLOCKING '$BUCKET'" + ${MC} mb --with-lock myminio/$BUCKET + elif [ $OBJECTLOCKING = false ] ; then + echo "Creating bucket '$BUCKET'" + ${MC} mb myminio/$BUCKET + fi + elif [ -z $OBJECTLOCKING ] ; then + echo "Creating bucket '$BUCKET'" + ${MC} mb myminio/$BUCKET + else + echo "Bucket '$BUCKET' already exists." + fi + fi + + + # set versioning for bucket if objectlocking is disabled or not set + if [ -z $OBJECTLOCKING ] ; then + if [ ! -z $VERSIONING ] ; then + if [ $VERSIONING = true ] ; then + echo "Enabling versioning for '$BUCKET'" + ${MC} version enable myminio/$BUCKET + elif [ $VERSIONING = false ] ; then + echo "Suspending versioning for '$BUCKET'" + ${MC} version suspend myminio/$BUCKET + fi + fi + else + echo "Bucket '$BUCKET' versioning unchanged." + fi + + + # At this point, the bucket should exist, skip checking for existence + # Set policy on the bucket + echo "Setting policy of bucket '$BUCKET' to '$POLICY'." + ${MC} policy set $POLICY myminio/$BUCKET +} + +# Try connecting to MinIO instance +{{- if .Values.tls.enabled }} +scheme=https +{{- else }} +scheme=http +{{- end }} +connectToMinio $scheme + +{{ if .Values.buckets }} +{{ $global := . }} +# Create the buckets +{{- range .Values.buckets }} +createBucket {{ tpl .name $global }} {{ .policy }} {{ .purge }} {{ .versioning }} {{ .objectlocking }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_create_policy.txt b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_create_policy.txt new file mode 100644 index 0000000..d565b16 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_create_policy.txt @@ -0,0 +1,75 @@ +#!/bin/sh +set -e ; # Have script exit in the event of a failed command. + +{{- if .Values.configPathmc }} +MC_CONFIG_DIR="{{ .Values.configPathmc }}" +MC="/usr/bin/mc --insecure --config-dir ${MC_CONFIG_DIR}" +{{- else }} +MC="/usr/bin/mc --insecure" +{{- end }} + +# connectToMinio +# Use a check-sleep-check loop to wait for MinIO service to be available +connectToMinio() { + SCHEME=$1 + ATTEMPTS=0 ; LIMIT=29 ; # Allow 30 attempts + set -e ; # fail if we can't read the keys. + ACCESS=$(cat /config/rootUser) ; SECRET=$(cat /config/rootPassword) ; + set +e ; # The connections to minio are allowed to fail. + echo "Connecting to MinIO server: $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT" ; + MC_COMMAND="${MC} alias set myminio $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT $ACCESS $SECRET" ; + $MC_COMMAND ; + STATUS=$? ; + until [ $STATUS = 0 ] + do + ATTEMPTS=`expr $ATTEMPTS + 1` ; + echo \"Failed attempts: $ATTEMPTS\" ; + if [ $ATTEMPTS -gt $LIMIT ]; then + exit 1 ; + fi ; + sleep 2 ; # 1 second intervals between attempts + $MC_COMMAND ; + STATUS=$? ; + done ; + set -e ; # reset `e` as active + return 0 +} + +# checkPolicyExists ($policy) +# Check if the policy exists, by using the exit code of `mc admin policy info` +checkPolicyExists() { + POLICY=$1 + CMD=$(${MC} admin policy info myminio $POLICY > /dev/null 2>&1) + return $? +} + +# createPolicy($name, $filename) +createPolicy () { + NAME=$1 + FILENAME=$2 + + # Create the name if it does not exist + echo "Checking policy: $NAME (in /config/$FILENAME.json)" + if ! checkPolicyExists $NAME ; then + echo "Creating policy '$NAME'" + else + echo "Policy '$NAME' already exists." + fi + ${MC} admin policy add myminio $NAME /config/$FILENAME.json + +} + +# Try connecting to MinIO instance +{{- if .Values.tls.enabled }} +scheme=https +{{- else }} +scheme=http +{{- end }} +connectToMinio $scheme + +{{ if .Values.policies }} +# Create the policies +{{- range $idx, $policy := .Values.policies }} +createPolicy {{ $policy.name }} policy_{{ $idx }} +{{- end }} +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_create_user.txt b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_create_user.txt new file mode 100644 index 0000000..ea2b3b6 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_create_user.txt @@ -0,0 +1,105 @@ +#!/bin/sh +set -e ; # Have script exit in the event of a failed command. + +{{- if .Values.configPathmc }} +MC_CONFIG_DIR="{{ .Values.configPathmc }}" +MC="/usr/bin/mc --insecure --config-dir ${MC_CONFIG_DIR}" +{{- else }} +MC="/usr/bin/mc --insecure" +{{- end }} + +# AccessKey and secretkey credentials file are added to prevent shell execution errors caused by special characters. +# Special characters for example : ',",<,>,{,} +MINIO_ACCESSKEY_SECRETKEY_TMP="/tmp/accessKey_and_secretKey_tmp" + +# connectToMinio +# Use a check-sleep-check loop to wait for MinIO service to be available +connectToMinio() { + SCHEME=$1 + ATTEMPTS=0 ; LIMIT=29 ; # Allow 30 attempts + set -e ; # fail if we can't read the keys. + ACCESS=$(cat /config/rootUser) ; SECRET=$(cat /config/rootPassword) ; + set +e ; # The connections to minio are allowed to fail. + echo "Connecting to MinIO server: $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT" ; + MC_COMMAND="${MC} alias set myminio $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT $ACCESS $SECRET" ; + $MC_COMMAND ; + STATUS=$? ; + until [ $STATUS = 0 ] + do + ATTEMPTS=`expr $ATTEMPTS + 1` ; + echo \"Failed attempts: $ATTEMPTS\" ; + if [ $ATTEMPTS -gt $LIMIT ]; then + exit 1 ; + fi ; + sleep 2 ; # 1 second intervals between attempts + $MC_COMMAND ; + STATUS=$? ; + done ; + set -e ; # reset `e` as active + return 0 +} + +# checkUserExists () +# Check if the user exists, by using the exit code of `mc admin user info` +checkUserExists() { + CMD=$(${MC} admin user info myminio $(head -1 $MINIO_ACCESSKEY_SECRETKEY_TMP) > /dev/null 2>&1) + return $? +} + +# createUser ($policy) +createUser() { + POLICY=$1 + #check accessKey_and_secretKey_tmp file + if [[ ! -f $MINIO_ACCESSKEY_SECRETKEY_TMP ]];then + echo "credentials file does not exist" + return 1 + fi + if [[ $(cat $MINIO_ACCESSKEY_SECRETKEY_TMP|wc -l) -ne 2 ]];then + echo "credentials file is invalid" + rm -f $MINIO_ACCESSKEY_SECRETKEY_TMP + return 1 + fi + USER=$(head -1 $MINIO_ACCESSKEY_SECRETKEY_TMP) + # Create the user if it does not exist + if ! checkUserExists ; then + echo "Creating user '$USER'" + cat $MINIO_ACCESSKEY_SECRETKEY_TMP | ${MC} admin user add myminio + else + echo "User '$USER' already exists." + fi + #clean up credentials files. + rm -f $MINIO_ACCESSKEY_SECRETKEY_TMP + + # set policy for user + if [ ! -z $POLICY -a $POLICY != " " ] ; then + echo "Adding policy '$POLICY' for '$USER'" + ${MC} admin policy set myminio $POLICY user=$USER + else + echo "User '$USER' has no policy attached." + fi +} + +# Try connecting to MinIO instance +{{- if .Values.tls.enabled }} +scheme=https +{{- else }} +scheme=http +{{- end }} +connectToMinio $scheme + +{{ if .Values.users }} +{{ $global := . }} +# Create the users +{{- range .Values.users }} +echo {{ tpl .accessKey $global }} > $MINIO_ACCESSKEY_SECRETKEY_TMP +{{- if .existingSecret }} +cat /config/secrets/{{ tpl .existingSecretKey $global }} >> $MINIO_ACCESSKEY_SECRETKEY_TMP +# Add a new line if it doesn't exist +sed -i '$a\' $MINIO_ACCESSKEY_SECRETKEY_TMP +createUser {{ .policy }} +{{ else }} +echo {{ .secretKey }} >> $MINIO_ACCESSKEY_SECRETKEY_TMP +createUser {{ .policy }} +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_custom_command.txt b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_custom_command.txt new file mode 100644 index 0000000..b583a77 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_custom_command.txt @@ -0,0 +1,58 @@ +#!/bin/sh +set -e ; # Have script exit in the event of a failed command. + +{{- if .Values.configPathmc }} +MC_CONFIG_DIR="{{ .Values.configPathmc }}" +MC="/usr/bin/mc --insecure --config-dir ${MC_CONFIG_DIR}" +{{- else }} +MC="/usr/bin/mc --insecure" +{{- end }} + +# connectToMinio +# Use a check-sleep-check loop to wait for MinIO service to be available +connectToMinio() { + SCHEME=$1 + ATTEMPTS=0 ; LIMIT=29 ; # Allow 30 attempts + set -e ; # fail if we can't read the keys. + ACCESS=$(cat /config/rootUser) ; SECRET=$(cat /config/rootPassword) ; + set +e ; # The connections to minio are allowed to fail. + echo "Connecting to MinIO server: $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT" ; + MC_COMMAND="${MC} alias set myminio $SCHEME://$MINIO_ENDPOINT:$MINIO_PORT $ACCESS $SECRET" ; + $MC_COMMAND ; + STATUS=$? ; + until [ $STATUS = 0 ] + do + ATTEMPTS=`expr $ATTEMPTS + 1` ; + echo \"Failed attempts: $ATTEMPTS\" ; + if [ $ATTEMPTS -gt $LIMIT ]; then + exit 1 ; + fi ; + sleep 2 ; # 1 second intervals between attempts + $MC_COMMAND ; + STATUS=$? ; + done ; + set -e ; # reset `e` as active + return 0 +} + +# runCommand ($@) +# Run custom mc command +runCommand() { + ${MC} "$@" + return $? +} + +# Try connecting to MinIO instance +{{- if .Values.tls.enabled }} +scheme=https +{{- else }} +scheme=http +{{- end }} +connectToMinio $scheme + +{{ if .Values.customCommands }} +# Run custom commands +{{- range .Values.customCommands }} +runCommand {{ .command }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_policy.tpl b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_policy.tpl new file mode 100644 index 0000000..83a2e15 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helper_policy.tpl @@ -0,0 +1,18 @@ +{{- $statements_length := len .statements -}} +{{- $statements_length := sub $statements_length 1 -}} +{ + "Version": "2012-10-17", + "Statement": [ +{{- range $i, $statement := .statements }} + { + "Effect": "Allow", + "Action": [ +"{{ $statement.actions | join "\",\n\"" }}" + ]{{ if $statement.resources }}, + "Resource": [ +"{{ $statement.resources | join "\",\n\"" }}" + ]{{ end }} + }{{ if lt $i $statements_length }},{{end }} +{{- end }} + ] +} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helpers.tpl b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helpers.tpl new file mode 100644 index 0000000..4e38194 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/_helpers.tpl @@ -0,0 +1,218 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "minio.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "minio.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default .Chart.Name .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "minio.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for networkpolicy. +*/}} +{{- define "minio.networkPolicy.apiVersion" -}} +{{- if semverCompare ">=1.4-0, <1.7-0" .Capabilities.KubeVersion.Version -}} +{{- print "extensions/v1beta1" -}} +{{- else if semverCompare ">=1.7-0, <1.16-0" .Capabilities.KubeVersion.Version -}} +{{- print "networking.k8s.io/v1beta1" -}} +{{- else if semverCompare "^1.16-0" .Capabilities.KubeVersion.Version -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for deployment. +*/}} +{{- define "minio.deployment.apiVersion" -}} +{{- if semverCompare "<1.9-0" .Capabilities.KubeVersion.Version -}} +{{- print "apps/v1beta2" -}} +{{- else -}} +{{- print "apps/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for statefulset. +*/}} +{{- define "minio.statefulset.apiVersion" -}} +{{- if semverCompare "<1.16-0" .Capabilities.KubeVersion.Version -}} +{{- print "apps/v1beta2" -}} +{{- else -}} +{{- print "apps/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "minio.ingress.apiVersion" -}} +{{- if semverCompare "<1.14-0" .Capabilities.KubeVersion.GitVersion -}} +{{- print "extensions/v1beta1" -}} +{{- else if semverCompare "<1.19-0" .Capabilities.KubeVersion.GitVersion -}} +{{- print "networking.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for console ingress. +*/}} +{{- define "minio.consoleIngress.apiVersion" -}} +{{- if semverCompare "<1.14-0" .Capabilities.KubeVersion.GitVersion -}} +{{- print "extensions/v1beta1" -}} +{{- else if semverCompare "<1.19-0" .Capabilities.KubeVersion.GitVersion -}} +{{- print "networking.k8s.io/v1beta1" -}} +{{- else -}} +{{- print "networking.k8s.io/v1" -}} +{{- end -}} +{{- end -}} + +{{/* +Determine secret name. +*/}} +{{- define "minio.secretName" -}} +{{- if .Values.existingSecret -}} +{{- .Values.existingSecret }} +{{- else -}} +{{- include "minio.fullname" . -}} +{{- end -}} +{{- end -}} + +{{/* +Determine name for scc role and rolebinding +*/}} +{{- define "minio.sccRoleName" -}} +{{- printf "%s-%s" "scc" (include "minio.fullname" .) | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Properly format optional additional arguments to MinIO binary +*/}} +{{- define "minio.extraArgs" -}} +{{- range .Values.extraArgs -}} +{{ " " }}{{ . }} +{{- end -}} +{{- end -}} + +{{/* +Return the proper Docker Image Registry Secret Names +*/}} +{{- define "minio.imagePullSecrets" -}} +{{/* +Helm 2.11 supports the assignment of a value to a variable defined in a different scope, +but Helm 2.9 and 2.10 does not support it, so we need to implement this if-else logic. +Also, we can not use a single if because lazy evaluation is not an option +*/}} +{{- if .Values.global }} +{{- if .Values.global.imagePullSecrets }} +imagePullSecrets: +{{- range .Values.global.imagePullSecrets }} + - name: {{ . }} +{{- end }} +{{- else if .Values.imagePullSecrets }} +imagePullSecrets: + {{ toYaml .Values.imagePullSecrets }} +{{- end -}} +{{- else if .Values.imagePullSecrets }} +imagePullSecrets: + {{ toYaml .Values.imagePullSecrets }} +{{- end -}} +{{- end -}} + +{{/* +Formats volumeMount for MinIO TLS keys and trusted certs +*/}} +{{- define "minio.tlsKeysVolumeMount" -}} +{{- if .Values.tls.enabled }} +- name: cert-secret-volume + mountPath: {{ .Values.certsPath }} +{{- end }} +{{- if or .Values.tls.enabled (ne .Values.trustedCertsSecret "") }} +{{- $casPath := printf "%s/CAs" .Values.certsPath | clean }} +- name: trusted-cert-secret-volume + mountPath: {{ $casPath }} +{{- end }} +{{- end -}} + +{{/* +Formats volume for MinIO TLS keys and trusted certs +*/}} +{{- define "minio.tlsKeysVolume" -}} +{{- if .Values.tls.enabled }} +- name: cert-secret-volume + secret: + secretName: {{ .Values.tls.certSecret }} + items: + - key: {{ .Values.tls.publicCrt }} + path: public.crt + - key: {{ .Values.tls.privateKey }} + path: private.key +{{- end }} +{{- if or .Values.tls.enabled (ne .Values.trustedCertsSecret "") }} +{{- $certSecret := eq .Values.trustedCertsSecret "" | ternary .Values.tls.certSecret .Values.trustedCertsSecret }} +{{- $publicCrt := eq .Values.trustedCertsSecret "" | ternary .Values.tls.publicCrt "" }} +- name: trusted-cert-secret-volume + secret: + secretName: {{ $certSecret }} + {{- if ne $publicCrt "" }} + items: + - key: {{ $publicCrt }} + path: public.crt + {{- end }} +{{- end }} +{{- end -}} + +{{/* +Returns the available value for certain key in an existing secret (if it exists), +otherwise it generates a random value. +*/}} +{{- define "minio.getValueFromSecret" }} + {{- $len := (default 16 .Length) | int -}} + {{- $obj := (lookup "v1" "Secret" .Namespace .Name).data -}} + {{- if $obj }} + {{- index $obj .Key | b64dec -}} + {{- else -}} + {{- randAlphaNum $len -}} + {{- end -}} +{{- end }} + +{{- define "minio.root.username" -}} + {{- if .Values.rootUser }} + {{- .Values.rootUser | toString }} + {{- else }} + {{- include "minio.getValueFromSecret" (dict "Namespace" .Release.Namespace "Name" (include "minio.fullname" .) "Length" 20 "Key" "rootUser") }} + {{- end }} +{{- end -}} + +{{- define "minio.root.password" -}} + {{- if .Values.rootPassword }} + {{- .Values.rootPassword | toString }} + {{- else }} + {{- include "minio.getValueFromSecret" (dict "Namespace" .Release.Namespace "Name" (include "minio.fullname" .) "Length" 40 "Key" "rootPassword") }} + {{- end }} +{{- end -}} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/configmap.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/configmap.yaml new file mode 100644 index 0000000..95a7c60 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/configmap.yaml @@ -0,0 +1,24 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ template "minio.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +data: + initialize: |- +{{ include (print $.Template.BasePath "/_helper_create_bucket.txt") . | indent 4 }} + add-user: |- +{{ include (print $.Template.BasePath "/_helper_create_user.txt") . | indent 4 }} + add-policy: |- +{{ include (print $.Template.BasePath "/_helper_create_policy.txt") . | indent 4 }} +{{- range $idx, $policy := .Values.policies }} + # {{ $policy.name }} + policy_{{ $idx }}.json: |- +{{ include (print $.Template.BasePath "/_helper_policy.tpl") . | indent 4 }} +{{ end }} + custom-command: |- +{{ include (print $.Template.BasePath "/_helper_custom_command.txt") . | indent 4 }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/console-ingress.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/console-ingress.yaml new file mode 100644 index 0000000..2ce9a93 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/console-ingress.yaml @@ -0,0 +1,58 @@ +{{- if .Values.consoleIngress.enabled -}} +{{- $fullName := printf "%s-console" (include "minio.fullname" .) -}} +{{- $servicePort := .Values.consoleService.port -}} +{{- $ingressPath := .Values.consoleIngress.path -}} +apiVersion: {{ template "minio.consoleIngress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ $fullName }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +{{- with .Values.consoleIngress.labels }} +{{ toYaml . | indent 4 }} +{{- end }} + +{{- with .Values.consoleIngress.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} +spec: +{{- if .Values.consoleIngress.ingressClassName }} + ingressClassName: {{ .Values.consoleIngress.ingressClassName }} +{{- end }} +{{- if .Values.consoleIngress.tls }} + tls: + {{- range .Values.consoleIngress.tls }} + - hosts: + {{- range .hosts }} + - {{ . | quote }} + {{- end }} + secretName: {{ .secretName }} + {{- end }} +{{- end }} + rules: + {{- range .Values.consoleIngress.hosts }} + - http: + paths: + - path: {{ $ingressPath }} + {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }} + pathType: Prefix + backend: + service: + name: {{ $fullName }} + port: + number: {{ $servicePort }} + {{- else }} + backend: + serviceName: {{ $fullName }} + servicePort: {{ $servicePort }} + {{- end }} + {{- if . }} + host: {{ . | quote }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/console-service.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/console-service.yaml new file mode 100644 index 0000000..46da359 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/console-service.yaml @@ -0,0 +1,48 @@ +{{ $scheme := "http" }} +{{- if .Values.tls.enabled }} +{{ $scheme = "https" }} +{{ end }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "minio.fullname" . }}-console + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +{{- if .Values.consoleService.annotations }} + annotations: +{{ toYaml .Values.consoleService.annotations | indent 4 }} +{{- end }} +spec: +{{- if (or (eq .Values.consoleService.type "ClusterIP" "") (empty .Values.consoleService.type)) }} + type: ClusterIP + {{- if not (empty .Values.consoleService.clusterIP) }} + clusterIP: {{ .Values.consoleService.clusterIP }} + {{end}} +{{- else if eq .Values.consoleService.type "LoadBalancer" }} + type: {{ .Values.consoleService.type }} + loadBalancerIP: {{ default "" .Values.consoleService.loadBalancerIP }} +{{- else }} + type: {{ .Values.consoleService.type }} +{{- end }} + ports: + - name: {{ $scheme }} + port: {{ .Values.consoleService.port }} + protocol: TCP +{{- if (and (eq .Values.consoleService.type "NodePort") ( .Values.consoleService.nodePort)) }} + nodePort: {{ .Values.consoleService.nodePort }} +{{- else }} + targetPort: {{ .Values.minioConsolePort }} +{{- end}} +{{- if .Values.consoleService.externalIPs }} + externalIPs: +{{- range $i , $ip := .Values.consoleService.externalIPs }} + - {{ $ip }} +{{- end }} +{{- end }} + selector: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/deployment.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/deployment.yaml new file mode 100644 index 0000000..062d141 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/deployment.yaml @@ -0,0 +1,195 @@ +{{- if eq .Values.mode "standalone" }} +{{ $scheme := "http" }} +{{- if .Values.tls.enabled }} +{{ $scheme = "https" }} +{{ end }} +{{ $bucketRoot := or ($.Values.bucketRoot) ($.Values.mountPath) }} +apiVersion: {{ template "minio.deployment.apiVersion" . }} +kind: Deployment +metadata: + name: {{ template "minio.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +{{- if .Values.additionalLabels }} +{{ toYaml .Values.additionalLabels | trimSuffix "\n" | indent 4 }} +{{- end }} +{{- if .Values.additionalAnnotations }} + annotations: +{{ toYaml .Values.additionalAnnotations | trimSuffix "\n" | indent 4 }} +{{- end }} +spec: + strategy: + type: {{ .Values.DeploymentUpdate.type }} + {{- if eq .Values.DeploymentUpdate.type "RollingUpdate" }} + rollingUpdate: + maxSurge: {{ .Values.DeploymentUpdate.maxSurge }} + maxUnavailable: {{ .Values.DeploymentUpdate.maxUnavailable }} + {{- end}} + replicas: 1 + selector: + matchLabels: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} + template: + metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} +{{- if .Values.podLabels }} +{{ toYaml .Values.podLabels | indent 8 }} +{{- end }} + annotations: +{{- if not .Values.ignoreChartChecksums }} + checksum/secrets: {{ include (print $.Template.BasePath "/secrets.yaml") . | sha256sum }} + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} +{{- end }} +{{- if .Values.podAnnotations }} +{{ toYaml .Values.podAnnotations | trimSuffix "\n" | indent 8 }} +{{- end }} + spec: + {{- if .Values.priorityClassName }} + priorityClassName: "{{ .Values.priorityClassName }}" + {{- end }} + {{- if .Values.runtimeClassName }} + runtimeClassName: "{{ .Values.runtimeClassName }}" + {{- end }} +{{- if and .Values.securityContext.enabled .Values.persistence.enabled }} + securityContext: + runAsUser: {{ .Values.securityContext.runAsUser }} + runAsGroup: {{ .Values.securityContext.runAsGroup }} + fsGroup: {{ .Values.securityContext.fsGroup }} + {{- if and (ge .Capabilities.KubeVersion.Major "1") (ge .Capabilities.KubeVersion.Minor "20") }} + fsGroupChangePolicy: {{ .Values.securityContext.fsGroupChangePolicy }} + {{- end }} +{{- end }} +{{ if .Values.serviceAccount.create }} + serviceAccountName: {{ .Values.serviceAccount.name }} +{{- end }} + containers: + - name: {{ .Chart.Name }} + image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + command: + - "/bin/sh" + - "-ce" + - "/usr/bin/docker-entrypoint.sh minio server {{ $bucketRoot }} -S {{ .Values.certsPath }} --address :{{ .Values.minioAPIPort }} --console-address :{{ .Values.minioConsolePort }} {{- template "minio.extraArgs" . }}" + volumeMounts: + - name: minio-user + mountPath: "/tmp/credentials" + readOnly: true + {{- if .Values.persistence.enabled }} + - name: export + mountPath: {{ .Values.mountPath }} + {{- if .Values.persistence.subPath }} + subPath: "{{ .Values.persistence.subPath }}" + {{- end }} + {{- end }} + {{- if .Values.extraSecret }} + - name: extra-secret + mountPath: "/tmp/minio-config-env" + {{- end }} + {{- include "minio.tlsKeysVolumeMount" . | indent 12 }} + ports: + - name: {{ $scheme }} + containerPort: {{ .Values.minioAPIPort }} + - name: {{ $scheme }}-console + containerPort: {{ .Values.minioConsolePort }} + env: + - name: MINIO_ROOT_USER + valueFrom: + secretKeyRef: + name: {{ template "minio.secretName" . }} + key: rootUser + - name: MINIO_ROOT_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "minio.secretName" . }} + key: rootPassword + {{- if .Values.extraSecret }} + - name: MINIO_CONFIG_ENV_FILE + value: "/tmp/minio-config-env/config.env" + {{- end}} + {{- if .Values.metrics.serviceMonitor.public }} + - name: MINIO_PROMETHEUS_AUTH_TYPE + value: "public" + {{- end}} + {{- if .Values.oidc.enabled }} + - name: MINIO_IDENTITY_OPENID_CONFIG_URL + value: {{ .Values.oidc.configUrl }} + - name: MINIO_IDENTITY_OPENID_CLIENT_ID + value: {{ .Values.oidc.clientId }} + - name: MINIO_IDENTITY_OPENID_CLIENTs_SECRET + value: {{ .Values.oidc.clientSecret }} + - name: MINIO_IDENTITY_OPENID_CLAIM_NAME + value: {{ .Values.oidc.claimName }} + - name: MINIO_IDENTITY_OPENID_CLAIM_PREFIX + value: {{ .Values.oidc.claimPrefix }} + - name: MINIO_IDENTITY_OPENID_SCOPES + value: {{ .Values.oidc.scopes }} + - name: MINIO_IDENTITY_OPENID_REDIRECT_URI + value: {{ .Values.oidc.redirectUri }} + - name: MINIO_IDENTITY_OPENID_COMMENT + value: {{ .Values.oidc.comment }} + {{- end}} + {{- if .Values.etcd.endpoints }} + - name: MINIO_ETCD_ENDPOINTS + value: {{ join "," .Values.etcd.endpoints | quote }} + {{- if .Values.etcd.clientCert }} + - name: MINIO_ETCD_CLIENT_CERT + value: "/tmp/credentials/etcd_client_cert.pem" + {{- end }} + {{- if .Values.etcd.clientCertKey }} + - name: MINIO_ETCD_CLIENT_CERT_KEY + value: "/tmp/credentials/etcd_client_cert_key.pem" + {{- end }} + {{- if .Values.etcd.pathPrefix }} + - name: MINIO_ETCD_PATH_PREFIX + value: {{ .Values.etcd.pathPrefix }} + {{- end }} + {{- if .Values.etcd.corednsPathPrefix }} + - name: MINIO_ETCD_COREDNS_PATH + value: {{ .Values.etcd.corednsPathPrefix }} + {{- end }} + {{- end }} + {{- range $key, $val := .Values.environment }} + - name: {{ $key }} + value: {{ $val | quote }} + {{- end}} + resources: +{{ toYaml .Values.resources | indent 12 }} +{{- with .Values.nodeSelector }} + nodeSelector: +{{ toYaml . | indent 8 }} +{{- end }} +{{- include "minio.imagePullSecrets" . | indent 6 }} +{{- with .Values.affinity }} + affinity: +{{ toYaml . | indent 8 }} +{{- end }} +{{- with .Values.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} +{{- end }} + volumes: + - name: export + {{- if .Values.persistence.enabled }} + persistentVolumeClaim: + claimName: {{ .Values.persistence.existingClaim | default (include "minio.fullname" .) }} + {{- else }} + emptyDir: {} + {{- end }} + {{- if .Values.extraSecret }} + - name: extra-secret + secret: + secretName: {{ .Values.extraSecret }} + {{- end }} + - name: minio-user + secret: + secretName: {{ template "minio.secretName" . }} + {{- include "minio.tlsKeysVolume" . | indent 8 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/gateway-deployment.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/gateway-deployment.yaml new file mode 100644 index 0000000..b14f86b --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/gateway-deployment.yaml @@ -0,0 +1,173 @@ +{{- if eq .Values.mode "gateway" }} +{{ $scheme := "http" }} +{{- if .Values.tls.enabled }} +{{ $scheme = "https" }} +{{ end }} +{{ $bucketRoot := or ($.Values.bucketRoot) ($.Values.mountPath) }} +apiVersion: {{ template "minio.deployment.apiVersion" . }} +kind: Deployment +metadata: + name: {{ template "minio.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +{{- if .Values.additionalLabels }} +{{ toYaml .Values.additionalLabels | trimSuffix "\n" | indent 4 }} +{{- end }} +{{- if .Values.additionalAnnotations }} + annotations: +{{ toYaml .Values.additionalAnnotations | trimSuffix "\n" | indent 4 }} +{{- end }} +spec: + strategy: + type: {{ .Values.DeploymentUpdate.type }} + {{- if eq .Values.DeploymentUpdate.type "RollingUpdate" }} + rollingUpdate: + maxSurge: {{ .Values.DeploymentUpdate.maxSurge }} + maxUnavailable: {{ .Values.DeploymentUpdate.maxUnavailable }} + {{- end}} + replicas: {{ .Values.gateway.replicas }} + selector: + matchLabels: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} + template: + metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} +{{- if .Values.podLabels }} +{{ toYaml .Values.podLabels | indent 8 }} +{{- end }} + annotations: +{{- if not .Values.ignoreChartChecksums }} + checksum/secrets: {{ include (print $.Template.BasePath "/secrets.yaml") . | sha256sum }} + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} +{{- end }} +{{- if .Values.podAnnotations }} +{{ toYaml .Values.podAnnotations | trimSuffix "\n" | indent 8 }} +{{- end }} + spec: + {{- if .Values.priorityClassName }} + priorityClassName: "{{ .Values.priorityClassName }}" + {{- end }} +{{- if and .Values.securityContext.enabled .Values.persistence.enabled }} + securityContext: + runAsUser: {{ .Values.securityContext.runAsUser }} + runAsGroup: {{ .Values.securityContext.runAsGroup }} + fsGroup: {{ .Values.securityContext.fsGroup }} +{{- end }} +{{ if .Values.serviceAccount.create }} + serviceAccountName: {{ .Values.serviceAccount.name }} +{{- end }} + containers: + - name: {{ .Chart.Name }} + image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + command: + - "/bin/sh" + - "-ce" + {{- if eq .Values.gateway.type "nas" }} + - "/usr/bin/docker-entrypoint.sh minio gateway nas {{ $bucketRoot }} -S {{ .Values.certsPath }} --address :{{ .Values.minioAPIPort }} --console-address :{{ .Values.minioConsolePort }} {{- template "minio.extraArgs" . }} " + {{- end }} + volumeMounts: + - name: minio-user + mountPath: "/tmp/credentials" + readOnly: true + {{- if .Values.persistence.enabled }} + - name: export + mountPath: {{ .Values.mountPath }} + {{- if .Values.persistence.subPath }} + subPath: "{{ .Values.persistence.subPath }}" + {{- end }} + {{- end }} + {{- if .Values.extraSecret }} + - name: extra-secret + mountPath: "/tmp/minio-config-env" + {{- end }} + {{- include "minio.tlsKeysVolumeMount" . | indent 12 }} + ports: + - name: {{ $scheme }} + containerPort: {{ .Values.minioAPIPort }} + - name: {{ $scheme }}-console + containerPort: {{ .Values.minioConsolePort }} + env: + - name: MINIO_ROOT_USER + valueFrom: + secretKeyRef: + name: {{ template "minio.secretName" . }} + key: rootUser + - name: MINIO_ROOT_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "minio.secretName" . }} + key: rootPassword + {{- if .Values.extraSecret }} + - name: MINIO_CONFIG_ENV_FILE + value: "/tmp/minio-config-env/config.env" + {{- end}} + {{- if .Values.metrics.serviceMonitor.public }} + - name: MINIO_PROMETHEUS_AUTH_TYPE + value: "public" + {{- end}} + {{- if .Values.etcd.endpoints }} + - name: MINIO_ETCD_ENDPOINTS + value: {{ join "," .Values.etcd.endpoints | quote }} + {{- if .Values.etcd.clientCert }} + - name: MINIO_ETCD_CLIENT_CERT + value: "/tmp/credentials/etcd_client.crt" + {{- end }} + {{- if .Values.etcd.clientCertKey }} + - name: MINIO_ETCD_CLIENT_CERT_KEY + value: "/tmp/credentials/etcd_client.key" + {{- end }} + {{- if .Values.etcd.pathPrefix }} + - name: MINIO_ETCD_PATH_PREFIX + value: {{ .Values.etcd.pathPrefix }} + {{- end }} + {{- if .Values.etcd.corednsPathPrefix }} + - name: MINIO_ETCD_COREDNS_PATH + value: {{ .Values.etcd.corednsPathPrefix }} + {{- end }} + {{- end }} + {{- range $key, $val := .Values.environment }} + - name: {{ $key }} + value: {{ $val | quote }} + {{- end}} + resources: +{{ toYaml .Values.resources | indent 12 }} +{{- with .Values.nodeSelector }} + nodeSelector: +{{ toYaml . | indent 8 }} +{{- end }} +{{- include "minio.imagePullSecrets" . | indent 6 }} +{{- with .Values.affinity }} + affinity: +{{ toYaml . | indent 8 }} +{{- end }} +{{- with .Values.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} +{{- end }} + volumes: + - name: export + {{- if .Values.persistence.enabled }} + persistentVolumeClaim: + claimName: {{ .Values.persistence.existingClaim | default (include "minio.fullname" .) }} + {{- else }} + emptyDir: {} + {{- end }} + - name: minio-user + secret: + secretName: {{ template "minio.secretName" . }} + {{- if .Values.extraSecret }} + - name: extra-secret + secret: + secretName: {{ .Values.extraSecret }} + {{- end }} + {{- include "minio.tlsKeysVolume" . | indent 8 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/ingress.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/ingress.yaml new file mode 100644 index 0000000..8d9a837 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/ingress.yaml @@ -0,0 +1,58 @@ +{{- if .Values.ingress.enabled -}} +{{- $fullName := include "minio.fullname" . -}} +{{- $servicePort := .Values.service.port -}} +{{- $ingressPath := .Values.ingress.path -}} +apiVersion: {{ template "minio.ingress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ $fullName }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +{{- with .Values.ingress.labels }} +{{ toYaml . | indent 4 }} +{{- end }} + +{{- with .Values.ingress.annotations }} + annotations: +{{ toYaml . | indent 4 }} +{{- end }} +spec: +{{- if .Values.ingress.ingressClassName }} + ingressClassName: {{ .Values.ingress.ingressClassName }} +{{- end }} +{{- if .Values.ingress.tls }} + tls: + {{- range .Values.ingress.tls }} + - hosts: + {{- range .hosts }} + - {{ . | quote }} + {{- end }} + secretName: {{ .secretName }} + {{- end }} +{{- end }} + rules: + {{- range .Values.ingress.hosts }} + - http: + paths: + - path: {{ $ingressPath }} + {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }} + pathType: Prefix + backend: + service: + name: {{ $fullName }} + port: + number: {{ $servicePort }} + {{- else }} + backend: + serviceName: {{ $fullName }} + servicePort: {{ $servicePort }} + {{- end }} + {{- if . }} + host: {{ . | quote }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/networkpolicy.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/networkpolicy.yaml new file mode 100644 index 0000000..ac219b9 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/networkpolicy.yaml @@ -0,0 +1,27 @@ +{{- if .Values.networkPolicy.enabled }} +kind: NetworkPolicy +apiVersion: {{ template "minio.networkPolicy.apiVersion" . }} +metadata: + name: {{ template "minio.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +spec: + podSelector: + matchLabels: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} + ingress: + - ports: + - port: {{ .Values.minioAPIPort }} + - port: {{ .Values.minioConsolePort }} + {{- if not .Values.networkPolicy.allowExternal }} + from: + - podSelector: + matchLabels: + {{ template "minio.name" . }}-client: "true" + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/poddisruptionbudget.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/poddisruptionbudget.yaml new file mode 100644 index 0000000..8037eb7 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/poddisruptionbudget.yaml @@ -0,0 +1,14 @@ +{{- if .Values.podDisruptionBudget.enabled }} +apiVersion: policy/v1beta1 +kind: PodDisruptionBudget +metadata: + name: minio + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} +spec: + maxUnavailable: {{ .Values.podDisruptionBudget.maxUnavailable }} + selector: + matchLabels: + app: {{ template "minio.name" . }} +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/post-install-create-bucket-job.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/post-install-create-bucket-job.yaml new file mode 100644 index 0000000..37d4f6b --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/post-install-create-bucket-job.yaml @@ -0,0 +1,92 @@ +{{- if .Values.buckets }} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ template "minio.fullname" . }}-make-bucket-job + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }}-make-bucket-job + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + annotations: + "helm.sh/hook": post-install,post-upgrade + "helm.sh/hook-delete-policy": hook-succeeded,before-hook-creation +{{- with .Values.makeBucketJob.annotations }} +{{ toYaml . | indent 4 }} +{{- end }} +spec: + template: + metadata: + labels: + app: {{ template "minio.name" . }}-job + release: {{ .Release.Name }} +{{- if .Values.podLabels }} +{{ toYaml .Values.podLabels | indent 8 }} +{{- end }} +{{- if .Values.makeBucketJob.podAnnotations }} + annotations: +{{ toYaml .Values.makeBucketJob.podAnnotations | indent 8 }} +{{- end }} + spec: + restartPolicy: OnFailure +{{- include "minio.imagePullSecrets" . | indent 6 }} +{{- if .Values.nodeSelector }} + nodeSelector: +{{ toYaml .Values.makeBucketJob.nodeSelector | indent 8 }} +{{- end }} +{{- with .Values.makeBucketJob.affinity }} + affinity: +{{ toYaml . | indent 8 }} +{{- end }} +{{- with .Values.makeBucketJob.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} +{{- end }} +{{- if .Values.makeBucketJob.securityContext.enabled }} + securityContext: + runAsUser: {{ .Values.makeBucketJob.securityContext.runAsUser }} + runAsGroup: {{ .Values.makeBucketJob.securityContext.runAsGroup }} + fsGroup: {{ .Values.makeBucketJob.securityContext.fsGroup }} +{{- end }} + volumes: + - name: minio-configuration + projected: + sources: + - configMap: + name: {{ template "minio.fullname" . }} + - secret: + name: {{ template "minio.secretName" . }} + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + secret: + secretName: {{ .Values.tls.certSecret }} + items: + - key: {{ .Values.tls.publicCrt }} + path: CAs/public.crt + {{ end }} + containers: + - name: minio-mc + image: "{{ .Values.mcImage.repository }}:{{ .Values.mcImage.tag }}" + imagePullPolicy: {{ .Values.mcImage.pullPolicy }} + {{- if .Values.makeBucketJob.exitCommand }} + command: ["/bin/sh", "-c"] + args: ["/bin/sh /config/initialize; x=$(echo $?); {{ .Values.makeBucketJob.exitCommand }} && exit $x" ] + {{- else }} + command: ["/bin/sh", "/config/initialize"] + {{- end }} + env: + - name: MINIO_ENDPOINT + value: {{ template "minio.fullname" . }} + - name: MINIO_PORT + value: {{ .Values.service.port | quote }} + volumeMounts: + - name: minio-configuration + mountPath: /config + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + mountPath: {{ .Values.configPathmc }}certs + {{ end }} + resources: +{{ toYaml .Values.makeBucketJob.resources | indent 10 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/post-install-create-policy-job.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/post-install-create-policy-job.yaml new file mode 100644 index 0000000..cf3c660 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/post-install-create-policy-job.yaml @@ -0,0 +1,92 @@ +{{- if .Values.policies }} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ template "minio.fullname" . }}-make-policies-job + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }}-make-policies-job + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + annotations: + "helm.sh/hook": post-install,post-upgrade + "helm.sh/hook-delete-policy": hook-succeeded,before-hook-creation +{{- with .Values.makePolicyJob.annotations }} +{{ toYaml . | indent 4 }} +{{- end }} +spec: + template: + metadata: + labels: + app: {{ template "minio.name" . }}-job + release: {{ .Release.Name }} +{{- if .Values.podLabels }} +{{ toYaml .Values.podLabels | indent 8 }} +{{- end }} +{{- if .Values.makePolicyJob.podAnnotations }} + annotations: +{{ toYaml .Values.makePolicyJob.podAnnotations | indent 8 }} +{{- end }} + spec: + restartPolicy: OnFailure +{{- include "minio.imagePullSecrets" . | indent 6 }} +{{- if .Values.nodeSelector }} + nodeSelector: +{{ toYaml .Values.makePolicyJob.nodeSelector | indent 8 }} +{{- end }} +{{- with .Values.makePolicyJob.affinity }} + affinity: +{{ toYaml . | indent 8 }} +{{- end }} +{{- with .Values.makePolicyJob.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} +{{- end }} +{{- if .Values.makePolicyJob.securityContext.enabled }} + securityContext: + runAsUser: {{ .Values.makePolicyJob.securityContext.runAsUser }} + runAsGroup: {{ .Values.makePolicyJob.securityContext.runAsGroup }} + fsGroup: {{ .Values.makePolicyJob.securityContext.fsGroup }} +{{- end }} + volumes: + - name: minio-configuration + projected: + sources: + - configMap: + name: {{ template "minio.fullname" . }} + - secret: + name: {{ template "minio.secretName" . }} + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + secret: + secretName: {{ .Values.tls.certSecret }} + items: + - key: {{ .Values.tls.publicCrt }} + path: CAs/public.crt + {{ end }} + containers: + - name: minio-mc + image: "{{ .Values.mcImage.repository }}:{{ .Values.mcImage.tag }}" + imagePullPolicy: {{ .Values.mcImage.pullPolicy }} + {{- if .Values.makePolicyJob.exitCommand }} + command: ["/bin/sh", "-c"] + args: ["/bin/sh /config/add-policy; x=$(echo $?); {{ .Values.makePolicyJob.exitCommand }} && exit $x" ] + {{- else }} + command: ["/bin/sh", "/config/add-policy"] + {{- end }} + env: + - name: MINIO_ENDPOINT + value: {{ template "minio.fullname" . }} + - name: MINIO_PORT + value: {{ .Values.service.port | quote }} + volumeMounts: + - name: minio-configuration + mountPath: /config + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + mountPath: {{ .Values.configPathmc }}certs + {{ end }} + resources: +{{ toYaml .Values.makePolicyJob.resources | indent 10 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/post-install-create-user-job.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/post-install-create-user-job.yaml new file mode 100644 index 0000000..7d7f6dd --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/post-install-create-user-job.yaml @@ -0,0 +1,102 @@ +{{- $global := . -}} +{{- if .Values.users }} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ template "minio.fullname" . }}-make-user-job + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }}-make-user-job + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + annotations: + "helm.sh/hook": post-install,post-upgrade + "helm.sh/hook-delete-policy": hook-succeeded,before-hook-creation +{{- with .Values.makeUserJob.annotations }} +{{ toYaml . | indent 4 }} +{{- end }} +spec: + template: + metadata: + labels: + app: {{ template "minio.name" . }}-job + release: {{ .Release.Name }} +{{- if .Values.podLabels }} +{{ toYaml .Values.podLabels | indent 8 }} +{{- end }} +{{- if .Values.makeUserJob.podAnnotations }} + annotations: +{{ toYaml .Values.makeUserJob.podAnnotations | indent 8 }} +{{- end }} + spec: + restartPolicy: OnFailure +{{- include "minio.imagePullSecrets" . | indent 6 }} +{{- if .Values.nodeSelector }} + nodeSelector: +{{ toYaml .Values.makeUserJob.nodeSelector | indent 8 }} +{{- end }} +{{- with .Values.makeUserJob.affinity }} + affinity: +{{ toYaml . | indent 8 }} +{{- end }} +{{- with .Values.makeUserJob.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} +{{- end }} +{{- if .Values.makeUserJob.securityContext.enabled }} + securityContext: + runAsUser: {{ .Values.makeUserJob.securityContext.runAsUser }} + runAsGroup: {{ .Values.makeUserJob.securityContext.runAsGroup }} + fsGroup: {{ .Values.makeUserJob.securityContext.fsGroup }} +{{- end }} + volumes: + - name: minio-configuration + projected: + sources: + - configMap: + name: {{ template "minio.fullname" . }} + - secret: + name: {{ template "minio.secretName" . }} + {{- range .Values.users }} + {{- if .existingSecret }} + - secret: + name: {{ tpl .existingSecret $global }} + items: + - key: {{ .existingSecretKey }} + path: secrets/{{ tpl .existingSecretKey $global }} + {{- end }} + {{- end }} + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + secret: + secretName: {{ .Values.tls.certSecret }} + items: + - key: {{ .Values.tls.publicCrt }} + path: CAs/public.crt + {{ end }} + containers: + - name: minio-mc + image: "{{ .Values.mcImage.repository }}:{{ .Values.mcImage.tag }}" + imagePullPolicy: {{ .Values.mcImage.pullPolicy }} + {{- if .Values.makeUserJob.exitCommand }} + command: ["/bin/sh", "-c"] + args: ["/bin/sh /config/add-user; x=$(echo $?); {{ .Values.makeUserJob.exitCommand }} && exit $x" ] + {{- else }} + command: ["/bin/sh", "/config/add-user"] + {{- end }} + env: + - name: MINIO_ENDPOINT + value: {{ template "minio.fullname" . }} + - name: MINIO_PORT + value: {{ .Values.service.port | quote }} + volumeMounts: + - name: minio-configuration + mountPath: /config + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + mountPath: {{ .Values.configPathmc }}certs + {{ end }} + resources: +{{ toYaml .Values.makeUserJob.resources | indent 10 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/post-install-custom-command.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/post-install-custom-command.yaml new file mode 100644 index 0000000..48cbd75 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/post-install-custom-command.yaml @@ -0,0 +1,92 @@ +{{- if .Values.customCommands }} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ template "minio.fullname" . }}-custom-command-job + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }}-custom-command-job + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + annotations: + "helm.sh/hook": post-install,post-upgrade + "helm.sh/hook-delete-policy": hook-succeeded,before-hook-creation +{{- with .Values.customCommandJob.annotations }} +{{ toYaml . | indent 4 }} +{{- end }} +spec: + template: + metadata: + labels: + app: {{ template "minio.name" . }}-job + release: {{ .Release.Name }} +{{- if .Values.podLabels }} +{{ toYaml .Values.podLabels | indent 8 }} +{{- end }} +{{- if .Values.customCommandJob.podAnnotations }} + annotations: +{{ toYaml .Values.customCommandJob.podAnnotations | indent 8 }} +{{- end }} + spec: + restartPolicy: OnFailure +{{- include "minio.imagePullSecrets" . | indent 6 }} +{{- if .Values.nodeSelector }} + nodeSelector: +{{ toYaml .Values.customCommandJob.nodeSelector | indent 8 }} +{{- end }} +{{- with .Values.customCommandJob.affinity }} + affinity: +{{ toYaml . | indent 8 }} +{{- end }} +{{- with .Values.customCommandJob.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} +{{- end }} +{{- if .Values.customCommandJob.securityContext.enabled }} + securityContext: + runAsUser: {{ .Values.customCommandJob.securityContext.runAsUser }} + runAsGroup: {{ .Values.customCommandJob.securityContext.runAsGroup }} + fsGroup: {{ .Values.customCommandJob.securityContext.fsGroup }} +{{- end }} + volumes: + - name: minio-configuration + projected: + sources: + - configMap: + name: {{ template "minio.fullname" . }} + - secret: + name: {{ template "minio.secretName" . }} + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + secret: + secretName: {{ .Values.tls.certSecret }} + items: + - key: {{ .Values.tls.publicCrt }} + path: CAs/public.crt + {{ end }} + containers: + - name: minio-mc + image: "{{ .Values.mcImage.repository }}:{{ .Values.mcImage.tag }}" + imagePullPolicy: {{ .Values.mcImage.pullPolicy }} + {{- if .Values.customCommandJob.exitCommand }} + command: ["/bin/sh", "-c"] + args: ["/bin/sh /config/custom-command; x=$(echo $?); {{ .Values.customCommandJob.exitCommand }} && exit $x" ] + {{- else }} + command: ["/bin/sh", "/config/custom-command"] + {{- end }} + env: + - name: MINIO_ENDPOINT + value: {{ template "minio.fullname" . }} + - name: MINIO_PORT + value: {{ .Values.service.port | quote }} + volumeMounts: + - name: minio-configuration + mountPath: /config + {{- if .Values.tls.enabled }} + - name: cert-secret-volume-mc + mountPath: {{ .Values.configPathmc }}certs + {{ end }} + resources: +{{ toYaml .Values.customCommandJob.resources | indent 10 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/pvc.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/pvc.yaml new file mode 100644 index 0000000..369aade --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/pvc.yaml @@ -0,0 +1,35 @@ +{{- if eq .Values.mode "standalone" }} +{{- if and .Values.persistence.enabled (not .Values.persistence.existingClaim) }} +apiVersion: v1 +kind: PersistentVolumeClaim +metadata: + name: {{ template "minio.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +{{- if .Values.persistence.annotations }} + annotations: +{{ toYaml .Values.persistence.annotations | trimSuffix "\n" | indent 4 }} +{{- end }} +spec: + accessModes: + - {{ .Values.persistence.accessMode | quote }} + resources: + requests: + storage: {{ .Values.persistence.size | quote }} + +{{- if .Values.persistence.storageClass }} +{{- if (eq "-" .Values.persistence.storageClass) }} + storageClassName: "" +{{- else }} + storageClassName: "{{ .Values.persistence.storageClass }}" +{{- end }} +{{- end }} +{{- if .Values.persistence.VolumeName }} + volumeName: "{{ .Values.persistence.VolumeName }}" +{{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/secrets.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/secrets.yaml new file mode 100644 index 0000000..da2ecab --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/secrets.yaml @@ -0,0 +1,22 @@ +{{- if not .Values.existingSecret }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ template "minio.secretName" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +type: Opaque +data: + rootUser: {{ include "minio.root.username" . | b64enc | quote }} + rootPassword: {{ include "minio.root.password" . | b64enc | quote }} + {{- if .Values.etcd.clientCert }} + etcd_client.crt: {{ .Values.etcd.clientCert | toString | b64enc | quote }} + {{- end }} + {{- if .Values.etcd.clientCertKey }} + etcd_client.key: {{ .Values.etcd.clientCertKey | toString | b64enc | quote }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/securitycontextconstraints.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/securitycontextconstraints.yaml new file mode 100644 index 0000000..4bac7e3 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/securitycontextconstraints.yaml @@ -0,0 +1,45 @@ +{{- if and .Values.securityContext.enabled .Values.persistence.enabled (.Capabilities.APIVersions.Has "security.openshift.io/v1") }} +apiVersion: security.openshift.io/v1 +kind: SecurityContextConstraints +metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +allowHostDirVolumePlugin: false +allowHostIPC: false +allowHostNetwork: false +allowHostPID: false +allowHostPorts: false +allowPrivilegeEscalation: true +allowPrivilegedContainer: false +allowedCapabilities: [] +readOnlyRootFilesystem: false +defaultAddCapabilities: [] +requiredDropCapabilities: +- KILL +- MKNOD +- SETUID +- SETGID +fsGroup: + type: MustRunAs + ranges: + - max: {{ .Values.securityContext.fsGroup }} + min: {{ .Values.securityContext.fsGroup }} +runAsUser: + type: MustRunAs + uid: {{ .Values.securityContext.runAsUser }} +seLinuxContext: + type: MustRunAs +supplementalGroups: + type: RunAsAny +volumes: +- configMap +- downwardAPI +- emptyDir +- persistentVolumeClaim +- projected +- secret +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/service.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/service.yaml new file mode 100644 index 0000000..741528d --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/service.yaml @@ -0,0 +1,49 @@ +{{ $scheme := "http" }} +{{- if .Values.tls.enabled }} +{{ $scheme = "https" }} +{{ end }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "minio.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + monitoring: "true" +{{- if .Values.service.annotations }} + annotations: +{{ toYaml .Values.service.annotations | indent 4 }} +{{- end }} +spec: +{{- if (or (eq .Values.service.type "ClusterIP" "") (empty .Values.service.type)) }} + type: ClusterIP + {{- if not (empty .Values.service.clusterIP) }} + clusterIP: {{ .Values.service.clusterIP }} + {{end}} +{{- else if eq .Values.service.type "LoadBalancer" }} + type: {{ .Values.service.type }} + loadBalancerIP: {{ default "" .Values.service.loadBalancerIP }} +{{- else }} + type: {{ .Values.service.type }} +{{- end }} + ports: + - name: {{ $scheme }} + port: {{ .Values.service.port }} + protocol: TCP +{{- if (and (eq .Values.service.type "NodePort") ( .Values.service.nodePort)) }} + nodePort: {{ .Values.service.nodePort }} +{{- else }} + targetPort: {{ .Values.minioAPIPort }} +{{- end}} +{{- if .Values.service.externalIPs }} + externalIPs: +{{- range $i , $ip := .Values.service.externalIPs }} + - {{ $ip }} +{{- end }} +{{- end }} + selector: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/serviceaccount.yaml new file mode 100644 index 0000000..6a4bd94 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/serviceaccount.yaml @@ -0,0 +1,7 @@ +{{- if .Values.serviceAccount.create -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ .Values.serviceAccount.name | quote }} + namespace: {{ .Release.Namespace | quote }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/servicemonitor.yaml new file mode 100644 index 0000000..d3fb629 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/servicemonitor.yaml @@ -0,0 +1,61 @@ +{{- if .Values.metrics.serviceMonitor.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ template "minio.fullname" . }} + {{- if .Values.metrics.serviceMonitor.namespace }} + namespace: {{ .Values.metrics.serviceMonitor.namespace }} + {{ else }} + namespace: {{ .Release.Namespace | quote }} + {{- end }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} + {{- if .Values.metrics.serviceMonitor.additionalLabels }} +{{ toYaml .Values.metrics.serviceMonitor.additionalLabels | indent 4 }} + {{- end }} +{{- if .Values.metrics.serviceMonitor.annotations }} + annotations: +{{ toYaml .Values.metrics.serviceMonitor.annotations | trimSuffix "\n" | indent 4 }} +{{- end }} +spec: + endpoints: + {{- if .Values.tls.enabled }} + - port: https + scheme: https + tlsConfig: + ca: + secret: + name: {{ .Values.tls.certSecret }} + key: {{ .Values.tls.publicCrt }} + serverName: {{ template "minio.fullname" . }} + {{ else }} + - port: http + scheme: http + {{- end }} + path: /minio/v2/metrics/cluster + {{- if .Values.metrics.serviceMonitor.interval }} + interval: {{ .Values.metrics.serviceMonitor.interval }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ .Values.metrics.serviceMonitor.scrapeTimeout }} + {{- end }} + {{- if .Values.metrics.serviceMonitor.relabelConfigs }} +{{ toYaml .Values.metrics.serviceMonitor.relabelConfigs | indent 6 }} + {{- end }} + {{- if not .Values.metrics.serviceMonitor.public }} + bearerTokenSecret: + name: {{ template "minio.fullname" . }}-prometheus + key: token + {{- end }} + namespaceSelector: + matchNames: + - {{ .Release.Namespace | quote }} + selector: + matchLabels: + app: {{ include "minio.name" . }} + release: {{ .Release.Name }} + monitoring: "true" +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/statefulset.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/statefulset.yaml new file mode 100644 index 0000000..6d695dd --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/templates/statefulset.yaml @@ -0,0 +1,246 @@ +{{- if eq .Values.mode "distributed" }} +{{ $poolCount := .Values.pools | int }} +{{ $nodeCount := .Values.replicas | int }} +{{ $replicas := mul $poolCount $nodeCount }} +{{ $drivesPerNode := .Values.drivesPerNode | int }} +{{ $scheme := "http" }} +{{- if .Values.tls.enabled }} +{{ $scheme = "https" }} +{{ end }} +{{ $mountPath := .Values.mountPath }} +{{ $bucketRoot := or ($.Values.bucketRoot) ($.Values.mountPath) }} +{{ $subPath := .Values.persistence.subPath }} +{{ $penabled := .Values.persistence.enabled }} +{{ $accessMode := .Values.persistence.accessMode }} +{{ $storageClass := .Values.persistence.storageClass }} +{{ $psize := .Values.persistence.size }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "minio.fullname" . }}-svc + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: "{{ .Release.Name }}" + heritage: "{{ .Release.Service }}" +spec: + publishNotReadyAddresses: true + clusterIP: None + ports: + - name: {{ $scheme }} + port: {{ .Values.service.port }} + protocol: TCP + targetPort: {{ .Values.minioAPIPort }} + selector: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} +--- +apiVersion: {{ template "minio.statefulset.apiVersion" . }} +kind: StatefulSet +metadata: + name: {{ template "minio.fullname" . }} + namespace: {{ .Release.Namespace | quote }} + labels: + app: {{ template "minio.name" . }} + chart: {{ template "minio.chart" . }} + release: {{ .Release.Name }} + heritage: {{ .Release.Service }} +{{- if .Values.additionalLabels }} +{{ toYaml .Values.additionalLabels | trimSuffix "\n" | indent 4 }} +{{- end }} +{{- if .Values.additionalAnnotations }} + annotations: +{{ toYaml .Values.additionalAnnotations | trimSuffix "\n" | indent 4 }} +{{- end }} +spec: + updateStrategy: + type: {{ .Values.StatefulSetUpdate.updateStrategy }} + podManagementPolicy: "Parallel" + serviceName: {{ template "minio.fullname" . }}-svc + replicas: {{ $replicas }} + selector: + matchLabels: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} + template: + metadata: + name: {{ template "minio.fullname" . }} + labels: + app: {{ template "minio.name" . }} + release: {{ .Release.Name }} +{{- if .Values.podLabels }} +{{ toYaml .Values.podLabels | indent 8 }} +{{- end }} + annotations: +{{- if not .Values.ignoreChartChecksums }} + checksum/secrets: {{ include (print $.Template.BasePath "/secrets.yaml") . | sha256sum }} + checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }} +{{- end }} +{{- if .Values.podAnnotations }} +{{ toYaml .Values.podAnnotations | trimSuffix "\n" | indent 8 }} +{{- end }} + spec: + {{- if .Values.priorityClassName }} + priorityClassName: "{{ .Values.priorityClassName }}" + {{- end }} + {{- if .Values.runtimeClassName }} + runtimeClassName: "{{ .Values.runtimeClassName }}" + {{- end }} +{{- if and .Values.securityContext.enabled .Values.persistence.enabled }} + securityContext: + runAsUser: {{ .Values.securityContext.runAsUser }} + runAsGroup: {{ .Values.securityContext.runAsGroup }} + fsGroup: {{ .Values.securityContext.fsGroup }} + {{- if and (ge .Capabilities.KubeVersion.Major "1") (ge .Capabilities.KubeVersion.Minor "20") }} + fsGroupChangePolicy: {{ .Values.securityContext.fsGroupChangePolicy }} + {{- end }} +{{- end }} +{{ if .Values.serviceAccount.create }} + serviceAccountName: {{ .Values.serviceAccount.name }} +{{- end }} + containers: + - name: {{ .Chart.Name }} + image: {{ .Values.image.repository }}:{{ .Values.image.tag }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + + command: [ "/bin/sh", + "-ce", + "/usr/bin/docker-entrypoint.sh minio server {{- range $i := until $poolCount }}{{ $factor := mul $i $nodeCount }}{{ $endIndex := add $factor $nodeCount }}{{ $beginIndex := mul $i $nodeCount }} {{ $scheme }}://{{ template `minio.fullname` $ }}-{{ `{` }}{{ $beginIndex }}...{{ sub $endIndex 1 }}{{ `}`}}.{{ template `minio.fullname` $ }}-svc.{{ $.Release.Namespace }}.svc.{{ $.Values.clusterDomain }}{{if (gt $drivesPerNode 1)}}{{ $bucketRoot }}-{{ `{` }}0...{{ sub $drivesPerNode 1 }}{{ `}` }}{{else}}{{ $bucketRoot }}{{end}}{{- end}} -S {{ .Values.certsPath }} --address :{{ .Values.minioAPIPort }} --console-address :{{ .Values.minioConsolePort }} {{- template `minio.extraArgs` . }}" ] + volumeMounts: + {{- if $penabled }} + {{- if (gt $drivesPerNode 1) }} + {{- range $i := until $drivesPerNode }} + - name: export-{{ $i }} + mountPath: {{ $mountPath }}-{{ $i }} + {{- if and $penabled $subPath }} + subPath: {{ $subPath }} + {{- end }} + {{- end }} + {{- else }} + - name: export + mountPath: {{ $mountPath }} + {{- if and $penabled $subPath }} + subPath: {{ $subPath }} + {{- end }} + {{- end }} + {{- end }} + {{- if .Values.extraSecret }} + - name: extra-secret + mountPath: "/tmp/minio-config-env" + {{- end }} + {{- include "minio.tlsKeysVolumeMount" . | indent 12 }} + ports: + - name: {{ $scheme }} + containerPort: {{ .Values.minioAPIPort }} + - name: {{ $scheme }}-console + containerPort: {{ .Values.minioConsolePort }} + env: + - name: MINIO_ROOT_USER + valueFrom: + secretKeyRef: + name: {{ template "minio.secretName" . }} + key: rootUser + - name: MINIO_ROOT_PASSWORD + valueFrom: + secretKeyRef: + name: {{ template "minio.secretName" . }} + key: rootPassword + {{- if .Values.extraSecret }} + - name: MINIO_CONFIG_ENV_FILE + value: "/tmp/minio-config-env/config.env" + {{- end}} + {{- if .Values.metrics.serviceMonitor.public }} + - name: MINIO_PROMETHEUS_AUTH_TYPE + value: "public" + {{- end}} + {{- if .Values.oidc.enabled }} + - name: MINIO_IDENTITY_OPENID_CONFIG_URL + value: {{ .Values.oidc.configUrl }} + - name: MINIO_IDENTITY_OPENID_CLIENT_ID + value: {{ .Values.oidc.clientId }} + - name: MINIO_IDENTITY_OPENID_CLIENT_SECRET + value: {{ .Values.oidc.clientSecret }} + - name: MINIO_IDENTITY_OPENID_CLAIM_NAME + value: {{ .Values.oidc.claimName }} + - name: MINIO_IDENTITY_OPENID_CLAIM_PREFIX + value: {{ .Values.oidc.claimPrefix }} + - name: MINIO_IDENTITY_OPENID_SCOPES + value: {{ .Values.oidc.scopes }} + - name: MINIO_IDENTITY_OPENID_REDIRECT_URI + value: {{ .Values.oidc.redirectUri }} + - name: MINIO_IDENTITY_OPENID_COMMENT + value: {{ .Values.oidc.comment }} + {{- end}} + {{- range $key, $val := .Values.environment }} + - name: {{ $key }} + value: {{ $val | quote }} + {{- end}} + resources: +{{ toYaml .Values.resources | indent 12 }} + {{- with .Values.nodeSelector }} + nodeSelector: +{{ toYaml . | indent 8 }} + {{- end }} +{{- include "minio.imagePullSecrets" . | indent 6 }} + {{- with .Values.affinity }} + affinity: +{{ toYaml . | indent 8 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: +{{ toYaml . | indent 8 }} + {{- end }} + {{- if and (gt $replicas 1) (ge .Capabilities.KubeVersion.Major "1") (ge .Capabilities.KubeVersion.Minor "19") }} + {{- with .Values.topologySpreadConstraints }} + topologySpreadConstraints: +{{ toYaml . | indent 8 }} + {{- end }} + {{- end }} + volumes: + - name: minio-user + secret: + secretName: {{ template "minio.secretName" . }} + {{- if .Values.extraSecret }} + - name: extra-secret + secret: + secretName: {{ .Values.extraSecret }} + {{- end }} + {{- include "minio.tlsKeysVolume" . | indent 8 }} +{{- if .Values.persistence.enabled }} + volumeClaimTemplates: + {{- if gt $drivesPerNode 1 }} + {{- range $diskId := until $drivesPerNode}} + - metadata: + name: export-{{ $diskId }} + {{- if $.Values.persistence.annotations }} + annotations: +{{ toYaml $.Values.persistence.annotations | trimSuffix "\n" | indent 10 }} + {{- end }} + spec: + accessModes: [ {{ $accessMode | quote }} ] + {{- if $storageClass }} + storageClassName: {{ $storageClass }} + {{- end }} + resources: + requests: + storage: {{ $psize }} + {{- end }} + {{- else }} + - metadata: + name: export + {{- if $.Values.persistence.annotations }} + annotations: +{{ toYaml $.Values.persistence.annotations | trimSuffix "\n" | indent 10 }} + {{- end }} + spec: + accessModes: [ {{ $accessMode | quote }} ] + {{- if $storageClass }} + storageClassName: {{ $storageClass }} + {{- end }} + resources: + requests: + storage: {{ $psize }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/values.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/values.yaml new file mode 100644 index 0000000..457d647 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/minio/values.yaml @@ -0,0 +1,482 @@ +## Provide a name in place of minio for `app:` labels +## +nameOverride: "" + +## Provide a name to substitute for the full names of resources +## +fullnameOverride: "" + +## set kubernetes cluster domain where minio is running +## +clusterDomain: cluster.local + +## Set default image, imageTag, and imagePullPolicy. mode is used to indicate the +## +image: + repository: quay.io/minio/minio + tag: RELEASE.2022-08-13T21-54-44Z + pullPolicy: IfNotPresent + +imagePullSecrets: [] +# - name: "image-pull-secret" + +## Set default image, imageTag, and imagePullPolicy for the `mc` (the minio +## client used to create a default bucket). +## +mcImage: + repository: quay.io/minio/mc + tag: RELEASE.2022-08-11T00-30-48Z + pullPolicy: IfNotPresent + +## minio mode, i.e. standalone or distributed or gateway. +mode: distributed ## other supported values are "standalone", "gateway" + +## Additional labels to include with deployment or statefulset +additionalLabels: [] + +## Additional annotations to include with deployment or statefulset +additionalAnnotations: [] + +## Typically the deployment/statefulset includes checksums of secrets/config, +## So that when these change on a subsequent helm install, the deployment/statefulset +## is restarted. This can result in unnecessary restarts under GitOps tooling such as +## flux, so set to "true" to disable this behaviour. +ignoreChartChecksums: false + +## Additional arguments to pass to minio binary +extraArgs: [] + +## Internal port number for MinIO S3 API container +## Change service.port to change external port number +minioAPIPort: "9000" + +## Internal port number for MinIO Browser Console container +## Change consoleService.port to change external port number +minioConsolePort: "9001" + +## Update strategy for Deployments +DeploymentUpdate: + type: RollingUpdate + maxUnavailable: 0 + maxSurge: 100% + +## Update strategy for StatefulSets +StatefulSetUpdate: + updateStrategy: RollingUpdate + +## Pod priority settings +## ref: https://kubernetes.io/docs/concepts/configuration/pod-priority-preemption/ +## +priorityClassName: "" + +## Pod runtime class name +## ref https://kubernetes.io/docs/concepts/containers/runtime-class/ +## +runtimeClassName: "" + +## Set default rootUser, rootPassword +## AccessKey and secretKey is generated when not set +## Distributed MinIO ref: https://docs.minio.io/docs/distributed-minio-quickstart-guide +## +rootUser: "" +rootPassword: "" + +## Use existing Secret that store following variables: +## +## | Chart var | .data. in Secret | +## |:----------------------|:-------------------------| +## | rootUser | rootUser | +## | rootPassword | rootPassword | +## +## All mentioned variables will be ignored in values file. +## .data.rootUser and .data.rootPassword are mandatory, +## others depend on enabled status of corresponding sections. +existingSecret: "" + +## Directory on the MinIO pof +certsPath: "/etc/minio/certs/" +configPathmc: "/etc/minio/mc/" + +## Path where PV would be mounted on the MinIO Pod +mountPath: "/export" +## Override the root directory which the minio server should serve from. +## If left empty, it defaults to the value of {{ .Values.mountPath }} +## If defined, it must be a sub-directory of the path specified in {{ .Values.mountPath }} +## +bucketRoot: "" + +# Number of drives attached to a node +drivesPerNode: 1 +# Number of MinIO containers running +replicas: 16 +# Number of expanded MinIO clusters +pools: 1 + +# Deploy if 'mode == gateway' - 4 replicas. +gateway: + type: "nas" # currently only "nas" are supported. + replicas: 4 + +## TLS Settings for MinIO +tls: + enabled: false + ## Create a secret with private.key and public.crt files and pass that here. Ref: https://github.com/minio/minio/tree/master/docs/tls/kubernetes#2-create-kubernetes-secret + certSecret: "" + publicCrt: public.crt + privateKey: private.key + +## Trusted Certificates Settings for MinIO. Ref: https://docs.minio.io/docs/how-to-secure-access-to-minio-server-with-tls#install-certificates-from-third-party-cas +## Bundle multiple trusted certificates into one secret and pass that here. Ref: https://github.com/minio/minio/tree/master/docs/tls/kubernetes#2-create-kubernetes-secret +## When using self-signed certificates, remember to include MinIO's own certificate in the bundle with key public.crt. +## If certSecret is left empty and tls is enabled, this chart installs the public certificate from .Values.tls.certSecret. +trustedCertsSecret: "" + +## Enable persistence using Persistent Volume Claims +## ref: http://kubernetes.io/docs/user-guide/persistent-volumes/ +## +persistence: + enabled: true + annotations: {} + + ## A manually managed Persistent Volume and Claim + ## Requires persistence.enabled: true + ## If defined, PVC must be created manually before volume will be bound + existingClaim: "" + + ## minio data Persistent Volume Storage Class + ## If defined, storageClassName: + ## If set to "-", storageClassName: "", which disables dynamic provisioning + ## If undefined (the default) or set to null, no storageClassName spec is + ## set, choosing the default provisioner. (gp2 on AWS, standard on + ## GKE, AWS & OpenStack) + ## + ## Storage class of PV to bind. By default it looks for standard storage class. + ## If the PV uses a different storage class, specify that here. + storageClass: "" + VolumeName: "" + accessMode: ReadWriteOnce + size: 500Gi + + ## If subPath is set mount a sub folder of a volume instead of the root of the volume. + ## This is especially handy for volume plugins that don't natively support sub mounting (like glusterfs). + ## + subPath: "" + +## Expose the MinIO service to be accessed from outside the cluster (LoadBalancer service). +## or access it from within the cluster (ClusterIP service). Set the service type and the port to serve it. +## ref: http://kubernetes.io/docs/user-guide/services/ +## +service: + type: ClusterIP + clusterIP: ~ + port: "9000" + nodePort: 32000 + +## Configure Ingress based on the documentation here: https://kubernetes.io/docs/concepts/services-networking/ingress/ +## + +ingress: + enabled: false + # ingressClassName: "" + labels: {} + # node-role.kubernetes.io/ingress: platform + + annotations: {} + # kubernetes.io/ingress.class: nginx + # kubernetes.io/tls-acme: "true" + # kubernetes.io/ingress.allow-http: "false" + # kubernetes.io/ingress.global-static-ip-name: "" + # nginx.ingress.kubernetes.io/secure-backends: "true" + # nginx.ingress.kubernetes.io/backend-protocol: "HTTPS" + # nginx.ingress.kubernetes.io/whitelist-source-range: 0.0.0.0/0 + path: / + hosts: + - minio-example.local + tls: [] + # - secretName: chart-example-tls + # hosts: + # - chart-example.local + +consoleService: + type: ClusterIP + clusterIP: ~ + port: "9001" + nodePort: 32001 + +consoleIngress: + enabled: false + # ingressClassName: "" + labels: {} + # node-role.kubernetes.io/ingress: platform + + annotations: {} + # kubernetes.io/ingress.class: nginx + # kubernetes.io/tls-acme: "true" + # kubernetes.io/ingress.allow-http: "false" + # kubernetes.io/ingress.global-static-ip-name: "" + # nginx.ingress.kubernetes.io/secure-backends: "true" + # nginx.ingress.kubernetes.io/backend-protocol: "HTTPS" + # nginx.ingress.kubernetes.io/whitelist-source-range: 0.0.0.0/0 + path: / + hosts: + - console.minio-example.local + tls: [] + # - secretName: chart-example-tls + # hosts: + # - chart-example.local + +## Node labels for pod assignment +## Ref: https://kubernetes.io/docs/user-guide/node-selection/ +## +nodeSelector: {} +tolerations: [] +affinity: {} +topologySpreadConstraints: [] + +## Add stateful containers to have security context, if enabled MinIO will run as this +## user and group NOTE: securityContext is only enabled if persistence.enabled=true +securityContext: + enabled: true + runAsUser: 1000 + runAsGroup: 1000 + fsGroup: 1000 + fsGroupChangePolicy: "OnRootMismatch" + +# Additational pod annotations +podAnnotations: {} + +# Additional pod labels +podLabels: {} + +## Configure resource requests and limits +## ref: http://kubernetes.io/docs/user-guide/compute-resources/ +## +resources: + requests: + memory: 16Gi + +## List of policies to be created after minio install +## +## In addition to default policies [readonly|readwrite|writeonly|consoleAdmin|diagnostics] +## you can define additional policies with custom supported actions and resources +policies: [] +## writeexamplepolicy policy grants creation or deletion of buckets with name +## starting with example. In addition, grants objects write permissions on buckets starting with +## example. +# - name: writeexamplepolicy +# statements: +# - resources: +# - 'arn:aws:s3:::example*/*' +# actions: +# - "s3:AbortMultipartUpload" +# - "s3:GetObject" +# - "s3:DeleteObject" +# - "s3:PutObject" +# - "s3:ListMultipartUploadParts" +# - resources: +# - 'arn:aws:s3:::example*' +# actions: +# - "s3:CreateBucket" +# - "s3:DeleteBucket" +# - "s3:GetBucketLocation" +# - "s3:ListBucket" +# - "s3:ListBucketMultipartUploads" +## readonlyexamplepolicy policy grants access to buckets with name starting with example. +## In addition, grants objects read permissions on buckets starting with example. +# - name: readonlyexamplepolicy +# statements: +# - resources: +# - 'arn:aws:s3:::example*/*' +# actions: +# - "s3:GetObject" +# - resources: +# - 'arn:aws:s3:::example*' +# actions: +# - "s3:GetBucketLocation" +# - "s3:ListBucket" +# - "s3:ListBucketMultipartUploads" +## Additional Annotations for the Kubernetes Job makePolicyJob +makePolicyJob: + podAnnotations: + annotations: + securityContext: + enabled: false + runAsUser: 1000 + runAsGroup: 1000 + fsGroup: 1000 + resources: + requests: + memory: 128Mi + nodeSelector: {} + tolerations: [] + affinity: {} + # Command to run after the main command on exit + exitCommand: "" + +## List of users to be created after minio install +## +users: + ## Username, password and policy to be assigned to the user + ## Default policies are [readonly|readwrite|writeonly|consoleAdmin|diagnostics] + ## Add new policies as explained here https://docs.min.io/docs/minio-multi-user-quickstart-guide.html + ## NOTE: this will fail if LDAP is enabled in your MinIO deployment + ## make sure to disable this if you are using LDAP. + - accessKey: console + secretKey: console123 + policy: consoleAdmin + # Or you can refer to specific secret + #- accessKey: externalSecret + # existingSecret: my-secret + # existingSecretKey: password + # policy: readonly + + +## Additional Annotations for the Kubernetes Job makeUserJob +makeUserJob: + podAnnotations: + annotations: + securityContext: + enabled: false + runAsUser: 1000 + runAsGroup: 1000 + fsGroup: 1000 + resources: + requests: + memory: 128Mi + nodeSelector: {} + tolerations: [] + affinity: {} + # Command to run after the main command on exit + exitCommand: "" + +## List of buckets to be created after minio install +## +buckets: + # # Name of the bucket + # - name: bucket1 + # # Policy to be set on the + # # bucket [none|download|upload|public] + # policy: none + # # Purge if bucket exists already + # purge: false + # # set versioning for + # # bucket [true|false] + # versioning: false + # # set objectlocking for + # # bucket [true|false] NOTE: versioning is enabled by default if you use locking + # objectlocking: false + # - name: bucket2 + # policy: none + # purge: false + # versioning: true + # # set objectlocking for + # # bucket [true|false] NOTE: versioning is enabled by default if you use locking + # objectlocking: false + +## Additional Annotations for the Kubernetes Job makeBucketJob +makeBucketJob: + podAnnotations: + annotations: + securityContext: + enabled: false + runAsUser: 1000 + runAsGroup: 1000 + fsGroup: 1000 + resources: + requests: + memory: 128Mi + nodeSelector: {} + tolerations: [] + affinity: {} + # Command to run after the main command on exit + exitCommand: "" + +## List of command to run after minio install +## NOTE: the mc command TARGET is always "myminio" +customCommands: + # - command: "admin policy set myminio consoleAdmin group='cn=ops,cn=groups,dc=example,dc=com'" + +## Additional Annotations for the Kubernetes Job customCommandJob +customCommandJob: + podAnnotations: + annotations: + securityContext: + enabled: false + runAsUser: 1000 + runAsGroup: 1000 + fsGroup: 1000 + resources: + requests: + memory: 128Mi + nodeSelector: {} + tolerations: [] + affinity: {} + # Command to run after the main command on exit + exitCommand: "" + +## Use this field to add environment variables relevant to MinIO server. These fields will be passed on to MinIO container(s) +## when Chart is deployed +environment: + ## Please refer for comprehensive list https://docs.min.io/minio/baremetal/reference/minio-server/minio-server.html + ## MINIO_SUBNET_LICENSE: "License key obtained from https://subnet.min.io" + ## MINIO_BROWSER: "off" + +## The name of a secret in the same kubernetes namespace which contain secret values +## This can be useful for LDAP password, etc +## The key in the secret must be 'config.env' +## +# extraSecret: minio-extraenv + +## OpenID Identity Management +## The following section documents environment variables for enabling external identity management using an OpenID Connect (OIDC)-compatible provider. +## See https://docs.min.io/minio/baremetal/security/openid-external-identity-management/external-authentication-with-openid-identity-provider.html#minio-external-identity-management-openid for a tutorial on using these variables. +oidc: + enabled: false + configUrl: "https://identity-provider-url/.well-known/openid-configuration" + clientId: "minio" + clientSecret: "" + claimName: "policy" + scopes: "openid,profile,email" + redirectUri: "https://console-endpoint-url/oauth_callback" + # Can leave empty + claimPrefix: "" + comment: "" + +networkPolicy: + enabled: false + allowExternal: true + +## PodDisruptionBudget settings +## ref: https://kubernetes.io/docs/concepts/workloads/pods/disruptions/ +## +podDisruptionBudget: + enabled: false + maxUnavailable: 1 + +## Specify the service account to use for the MinIO pods. If 'create' is set to 'false' +## and 'name' is left unspecified, the account 'default' will be used. +serviceAccount: + create: true + ## The name of the service account to use. If 'create' is 'true', a service account with that name + ## will be created. + name: "minio-sa" + +metrics: + serviceMonitor: + enabled: false + public: true + additionalLabels: {} + annotations: {} + relabelConfigs: {} + # namespace: monitoring + # interval: 30s + # scrapeTimeout: 10s + +## ETCD settings: https://github.com/minio/minio/blob/master/docs/sts/etcd.md +## Define endpoints to enable this section. +etcd: + endpoints: [] + pathPrefix: "" + corednsPathPrefix: "" + clientCert: "" + clientCertKey: "" diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/.helmignore b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/.helmignore new file mode 100644 index 0000000..0e8a0eb --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/.helmignore @@ -0,0 +1,23 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*.orig +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/Chart.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/Chart.yaml new file mode 100644 index 0000000..51db3a3 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/Chart.yaml @@ -0,0 +1,8 @@ +apiVersion: v2 +appVersion: v0.14.0 +description: Grafana rollout-operator +home: https://github.com/grafana/rollout-operator +kubeVersion: ^1.10.0-0 +name: rollout-operator +type: application +version: 0.15.0 diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/README.md b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/README.md new file mode 100644 index 0000000..360e462 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/README.md @@ -0,0 +1,71 @@ +# Grafana rollout-operator Helm Chart + +Helm chart for deploying [Grafana rollout-operator](https://github.com/grafana/rollout-operator) to Kubernetes. + +# rollout-operator + +![Version: 0.15.0](https://img.shields.io/badge/Version-0.15.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: v0.14.0](https://img.shields.io/badge/AppVersion-v0.14.0-informational?style=flat-square) + +Grafana rollout-operator + +## Requirements + +Kubernetes: `^1.10.0-0` + +## Installation + +This section describes various use cases for installation, upgrade and migration from different systems and versions. + +### Preparation + +These are the common tasks to perform before any of the use cases. + +```bash +# Add the repository +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update +``` + +### Installation of Grafana Rollout Operator + +```bash +helm install -n grafana/rollout-operator +``` + +The Grafana rollout-operator should be installed in the same namespace as the statefulsets it is operating upon. +It is not a highly available application and runs as a single pod. + +## Values + +| Key | Type | Default | Description | +|-----|------|---------|-------------| +| affinity | object | `{}` | | +| fullnameOverride | string | `""` | | +| hostAliases | list | `[]` | hostAliases to add | +| image.pullPolicy | string | `"IfNotPresent"` | | +| image.repository | string | `"grafana/rollout-operator"` | | +| image.tag | string | `""` | Overrides the image tag whose default is the chart appVersion. | +| imagePullSecrets | list | `[]` | | +| minReadySeconds | int | `10` | | +| nameOverride | string | `""` | | +| nodeSelector | object | `{}` | | +| podAnnotations | object | `{}` | Pod Annotations | +| podLabels | object | `{}` | Pod (extra) Labels | +| podSecurityContext | object | `{}` | | +| priorityClassName | string | `""` | | +| resources.limits.memory | string | `"200Mi"` | | +| resources.requests.cpu | string | `"100m"` | | +| resources.requests.memory | string | `"100Mi"` | | +| securityContext | object | `{}` | | +| serviceAccount.annotations | object | `{}` | Annotations to add to the service account | +| serviceAccount.create | bool | `true` | Specifies whether a service account should be created | +| serviceAccount.name | string | `""` | The name of the service account to use. If not set and create is true, a name is generated using the fullname template | +| serviceMonitor.annotations | object | `{}` | ServiceMonitor annotations | +| serviceMonitor.enabled | bool | `false` | Create ServiceMonitor to scrape metrics for Prometheus | +| serviceMonitor.interval | string | `nil` | ServiceMonitor scrape interval | +| serviceMonitor.labels | object | `{}` | Additional ServiceMonitor labels | +| serviceMonitor.namespace | string | `nil` | Alternative namespace for ServiceMonitor resources | +| serviceMonitor.namespaceSelector | object | `{}` | Namespace selector for ServiceMonitor resources | +| serviceMonitor.relabelings | list | `[]` | ServiceMonitor relabel configs to apply to samples before scraping https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig | +| serviceMonitor.scrapeTimeout | string | `nil` | ServiceMonitor scrape timeout in Go duration format (e.g. 15s) | +| tolerations | list | `[]` | | diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/README.md.gotmpl b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/README.md.gotmpl new file mode 100644 index 0000000..0ac2d47 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/README.md.gotmpl @@ -0,0 +1,38 @@ +# Grafana rollout-operator Helm Chart + +Helm chart for deploying [Grafana rollout-operator]({{ template "chart.homepage" . }}) to Kubernetes. + +{{ template "chart.header" . }} + +{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }} + +{{ template "chart.description" . }} + +{{ template "chart.sourcesSection" . }} + +{{ template "chart.requirementsSection" . }} + +## Installation + +This section describes various use cases for installation, upgrade and migration from different systems and versions. + +### Preparation + +These are the common tasks to perform before any of the use cases. + +```bash +# Add the repository +helm repo add grafana https://grafana.github.io/helm-charts +helm repo update +``` + +### Installation of Grafana Rollout Operator + +```bash +helm install -n grafana/rollout-operator +``` + +The Grafana rollout-operator should be installed in the same namespace as the statefulsets it is operating upon. +It is not a highly available application and runs as a single pod. + +{{ template "chart.valuesSection" . }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/NOTES.txt b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/NOTES.txt new file mode 100644 index 0000000..a76e5ba --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/NOTES.txt @@ -0,0 +1,10 @@ +Repo : {{ .Chart.Home }} + +Validation: + +Check the logs of the pod and ensure messages for reconcilliation of the statefulsets are present. +``` +kubectl logs -n {{ .Release.Namespace }} -l {{ include "cli.labels" . }} +``` +Example log line: +level=debug ts=2022-04-20T13:59:52.783051541Z msg="reconciling StatefulSet" statefulset=mimir-store-gateway-zone-a diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/_helpers.tpl b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/_helpers.tpl new file mode 100644 index 0000000..bf3553a --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/_helpers.tpl @@ -0,0 +1,79 @@ +{{/* +Expand the name of the chart. +*/}} +{{- define "rollout-operator.name" -}} +{{- default (include "rollout-operator.chartName" .) .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "rollout-operator.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default (include "rollout-operator.chartName" .) .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Recalculate the chart name, because it may be sub-chart included as rollout_operator, +and _ is not valid in resource names. +*/}} +{{- define "rollout-operator.chartName" -}} +{{- print .Chart.Name | replace "_" "-" -}} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "rollout-operator.chart" -}} +{{- printf "%s-%s" (include "rollout-operator.chartName" .) .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "rollout-operator.labels" -}} +helm.sh/chart: {{ include "rollout-operator.chart" . }} +{{ include "rollout-operator.selectorLabels" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "rollout-operator.selectorLabels" -}} +app.kubernetes.io/name: {{ include "rollout-operator.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Create the name of the service account to use +*/}} +{{- define "rollout-operator.serviceAccountName" -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "rollout-operator.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} + + +{{- define "cli.labels" -}} +{{- $list := list -}} +{{- range $k, $v := ( include "rollout-operator.selectorLabels" . | fromYaml ) -}} +{{- $list = append $list (printf "%s=%s" $k $v) -}} +{{- end -}} +{{ join "," $list }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/deployment.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/deployment.yaml new file mode 100644 index 0000000..d35b866 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/deployment.yaml @@ -0,0 +1,74 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "rollout-operator.fullname" . }} + labels: + {{- include "rollout-operator.labels" . | nindent 4 }} +spec: + replicas: 1 + minReadySeconds: {{ .Values.minReadySeconds }} + selector: + matchLabels: + {{- include "rollout-operator.selectorLabels" . | nindent 6 }} + strategy: + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + template: + metadata: + {{- with .Values.podAnnotations }} + annotations: + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "rollout-operator.selectorLabels" . | nindent 8 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- with .Values.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "rollout-operator.serviceAccountName" . }} + securityContext: + {{- toYaml .Values.podSecurityContext | nindent 8 }} + containers: + - name: rollout-operator + securityContext: + {{- toYaml .Values.securityContext | nindent 12 }} + image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - -kubernetes.namespace={{ .Release.Namespace }} + ports: + - name: http-metrics + containerPort: 8001 + protocol: TCP + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 5 + timeoutSeconds: 1 + resources: + {{- toYaml .Values.resources | nindent 12 }} + {{- with .Values.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/role.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/role.yaml new file mode 100644 index 0000000..210c456 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/role.yaml @@ -0,0 +1,28 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ include "rollout-operator.fullname" . }} +rules: +- apiGroups: + - "" + resources: + - pods + verbs: + - list + - get + - watch + - delete +- apiGroups: + - apps + resources: + - statefulsets + verbs: + - list + - get + - watch +- apiGroups: + - apps + resources: + - statefulsets/status + verbs: + - update diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/rolebinding.yaml new file mode 100644 index 0000000..24fcd72 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/rolebinding.yaml @@ -0,0 +1,11 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "rollout-operator.fullname" . }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "rollout-operator.fullname" . }} +subjects: +- kind: ServiceAccount + name: {{ include "rollout-operator.serviceAccountName" . }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/service.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/service.yaml new file mode 100644 index 0000000..60ce5b1 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/service.yaml @@ -0,0 +1,18 @@ +{{- if .Values.serviceMonitor.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "rollout-operator.fullname" . }} + labels: + {{- include "rollout-operator.labels" . | nindent 4 }} +spec: + type: ClusterIP + clusterIP: None + ports: + - port: 8001 + targetPort: http-metrics + protocol: TCP + name: http-metrics + selector: + {{- include "rollout-operator.selectorLabels" . | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/serviceaccount.yaml new file mode 100644 index 0000000..37698a4 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/serviceaccount.yaml @@ -0,0 +1,12 @@ +{{- if .Values.serviceAccount.create -}} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "rollout-operator.serviceAccountName" . }} + labels: + {{- include "rollout-operator.labels" . | nindent 4 }} + {{- with .Values.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/servicemonitor.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/servicemonitor.yaml new file mode 100644 index 0000000..7810843 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/templates/servicemonitor.yaml @@ -0,0 +1,36 @@ +{{- if .Values.serviceMonitor.enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "rollout-operator.fullname" . }} + {{- with .Values.serviceMonitor.namespace }} + namespace: {{ . }} + {{- end }} + labels: + {{- include "rollout-operator.labels" . | nindent 4 }} + {{- with .Values.serviceMonitor.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .Values.serviceMonitor.namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "rollout-operator.selectorLabels" . | nindent 6 }} + endpoints: + - port: http-metrics + {{- with .Values.serviceMonitor.interval }} + interval: {{ . }} + {{- end }} + {{- with .Values.serviceMonitor.scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + relabelings: + {{- with .Values.serviceMonitor.relabelings }} + {{- toYaml . | nindent 8 }} + {{- end }} + scheme: http +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/values.yaml b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/values.yaml new file mode 100644 index 0000000..66f9486 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/charts/rollout-operator/values.yaml @@ -0,0 +1,83 @@ +# Default values for rollout-operator. +# This is a YAML-formatted file. +# Declare variables to be passed into your templates. + +image: + repository: grafana/rollout-operator + pullPolicy: IfNotPresent + # -- Overrides the image tag whose default is the chart appVersion. + tag: "" + +imagePullSecrets: [] + +# -- hostAliases to add +hostAliases: [] +# - ip: 1.2.3.4 +# hostnames: +# - domain.tld + +nameOverride: "" +fullnameOverride: "" + +serviceAccount: + # -- Specifies whether a service account should be created + create: true + # -- Annotations to add to the service account + annotations: {} + # -- The name of the service account to use. + # If not set and create is true, a name is generated using the fullname template + name: "" + +# -- Pod Annotations +podAnnotations: {} + +# -- Pod (extra) Labels +podLabels: {} + +podSecurityContext: {} + # fsGroup: 2000 + +securityContext: {} + # capabilities: + # drop: + # - ALL + # readOnlyRootFilesystem: true + # runAsNonRoot: true + # runAsUser: 1000 + +resources: + limits: + # cpu: "1" + memory: 200Mi + requests: + cpu: 100m + memory: 100Mi + +minReadySeconds: 10 + +nodeSelector: {} + +tolerations: [] + +affinity: {} + +priorityClassName: "" + +serviceMonitor: + # -- Create ServiceMonitor to scrape metrics for Prometheus + enabled: false + # -- Alternative namespace for ServiceMonitor resources + namespace: null + # -- Namespace selector for ServiceMonitor resources + namespaceSelector: {} + # -- ServiceMonitor annotations + annotations: {} + # -- Additional ServiceMonitor labels + labels: {} + # -- ServiceMonitor scrape interval + interval: null + # -- ServiceMonitor scrape timeout in Go duration format (e.g. 15s) + scrapeTimeout: null + # -- ServiceMonitor relabel configs to apply to samples before scraping + # https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig + relabelings: [] diff --git a/observability/lgtm-distributed/charts/tempo-distributed/ci/parquet-dedicated-columns.yaml b/observability/lgtm-distributed/charts/tempo-distributed/ci/parquet-dedicated-columns.yaml new file mode 100644 index 0000000..5878f37 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/ci/parquet-dedicated-columns.yaml @@ -0,0 +1,11 @@ +storage: + trace: + block: + version: vParquet3 + dedicated_columns: + - name: cluster + type: string + scope: resource + - name: service.name + type: string + scope: resource diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/NOTES.txt b/observability/lgtm-distributed/charts/tempo-distributed/templates/NOTES.txt new file mode 100644 index 0000000..22b5fbc --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/NOTES.txt @@ -0,0 +1,21 @@ +*********************************************************************** + Welcome to Grafana Tempo + Chart version: {{ .Chart.Version }} + Tempo version: {{ .Chart.AppVersion }} +*********************************************************************** + +Installed components: +* ingester +* distributor +* querier +* query-frontend +{{- if .Values.enterpriseFederationFrontend.enabled }} +* federation-frontend +{{- end }} +* compactor +{{- if .Values.memcached.enabled }} +* memcached +{{- end }} +{{- if .Values.gateway.enabled }} +* gateway +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/_helpers.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/_helpers.tpl new file mode 100644 index 0000000..cabad97 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/_helpers.tpl @@ -0,0 +1,299 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "tempo.name" -}} +{{- default "tempo" .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "tempo.fullname" -}} +{{- if .Values.fullnameOverride -}} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- $name := default "tempo" .Values.nameOverride -}} +{{- if contains $name .Release.Name -}} +{{- .Release.Name | trunc 63 | trimSuffix "-" -}} +{{- else -}} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}} +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +Docker image selector for Tempo. Hierachy based on global, component, and tempo values. +*/}} +{{- define "tempo.tempoImage" -}} +{{- $registry := coalesce .global.registry .component.registry .tempo.registry -}} +{{- $repository := coalesce .component.repository .tempo.repository -}} +{{- $tag := coalesce .component.tag .tempo.tag .defaultVersion | toString -}} +{{- printf "%s/%s:%s" $registry $repository $tag -}} +{{- end -}} + +{{/* +Optional list of imagePullSecrets for Tempo docker images +*/}} +{{- define "tempo.imagePullSecrets" -}} +{{- $imagePullSecrets := coalesce .global.pullSecrets .component.pullSecrets .tempo.pullSecrets -}} +{{- if $imagePullSecrets -}} +imagePullSecrets: +{{- range $imagePullSecrets }} + - name: {{ . }} +{{ end }} +{{- end }} +{{- end -}} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "tempo.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Calculate image name based on whether enterprise features are requested. Fallback to hierarchy handling in `tempo.tempoImage`. +*/}} +{{- define "tempo.imageReference" -}} +{{ $tempo := "" }} +{{- if .ctx.Values.enterprise.enabled -}} +{{ $tempo = merge .ctx.Values.enterprise.image .ctx.Values.tempo.image }} +{{- else -}} +{{ $tempo = .ctx.Values.tempo.image }} +{{- end -}} +{{- $componentSection := include "tempo.componentSectionFromName" . }} +{{- if not (hasKey .ctx.Values $componentSection) }} +{{- print "Component section " $componentSection " does not exist" | fail }} +{{- end }} +{{- $component := (index .ctx.Values $componentSection).image | default dict }} +{{- $dict := dict "tempo" $tempo "component" $component "global" .ctx.Values.global.image "defaultVersion" .ctx.Chart.AppVersion -}} +{{- include "tempo.tempoImage" $dict -}} +{{- end -}} + +{{/* +Simple resource labels +*/}} +{{- define "tempo.labels" -}} +helm.sh/chart: {{ include "tempo.chart" .ctx }} +app.kubernetes.io/name: {{ include "tempo.name" .ctx }} +app.kubernetes.io/instance: {{ .ctx.Release.Name }} +{{- if .component }} +app.kubernetes.io/component: {{ .component }} +{{- end }} +{{- if .memberlist }} +app.kubernetes.io/part-of: memberlist +{{- end }} +{{- if .ctx.Chart.AppVersion }} +app.kubernetes.io/version: {{ .ctx.Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .ctx.Release.Service }} +{{- end -}} + +{{/* +Simple service selector labels +*/}} +{{- define "tempo.selectorLabels" -}} +app.kubernetes.io/name: {{ include "tempo.name" .ctx }} +app.kubernetes.io/instance: {{ .ctx.Release.Name }} +{{- if .component }} +app.kubernetes.io/component: {{ .component }} +{{- end -}} +{{- end -}} + +{{/* +Create the name of the service account to use +*/}} +{{- define "tempo.serviceAccountName" -}} +{{- if .Values.serviceAccount.create -}} + {{ default (include "tempo.fullname" .) .Values.serviceAccount.name }} +{{- else -}} + {{ default "default" .Values.serviceAccount.name }} +{{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "tempo.ingress.apiVersion" -}} + {{- if and (.Capabilities.APIVersions.Has "networking.k8s.io/v1") (semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version) -}} + {{- print "networking.k8s.io/v1" -}} + {{- else if .Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" -}} + {{- print "networking.k8s.io/v1beta1" -}} + {{- else -}} + {{- print "extensions/v1beta1" -}} + {{- end -}} +{{- end -}} + +{{/* +Return if ingress is stable. +*/}} +{{- define "tempo.ingress.isStable" -}} + {{- eq (include "tempo.ingress.apiVersion" .) "networking.k8s.io/v1" -}} +{{- end -}} + +{{/* +Return if ingress supports ingressClassName. +*/}} +{{- define "tempo.ingress.supportsIngressClassName" -}} + {{- or (eq (include "tempo.ingress.isStable" .) "true") (and (eq (include "tempo.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) -}} +{{- end -}} + +{{/* +Return if ingress supports pathType. +*/}} +{{- define "tempo.ingress.supportsPathType" -}} + {{- or (eq (include "tempo.ingress.isStable" .) "true") (and (eq (include "tempo.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for PodDisruptionBudget. +*/}} +{{- define "tempo.pdb.apiVersion" -}} + {{- if and (.Capabilities.APIVersions.Has "policy/v1") (semverCompare ">=1.21-0" .Capabilities.KubeVersion.Version) -}} + {{- print "policy/v1" -}} + {{- else -}} + {{- print "policy/v1beta1" -}} + {{- end -}} +{{- end -}} + +{{/* +Return the appropriate apiVersion for HorizontalPodAutoscaler. +*/}} +{{- define "tempo.hpa.apiVersion" -}} + {{- if and (.Capabilities.APIVersions.Has "autoscaling/v2") (semverCompare ">=1.23-0" .Capabilities.KubeVersion.Version) -}} + {{- print "autoscaling/v2" -}} + {{- else -}} + {{- print "autoscaling/v2beta1" -}} + {{- end -}} +{{- end -}} + +{{/* +Resource name template +*/}} +{{- define "tempo.resourceName" -}} +{{ include "tempo.fullname" .ctx }}{{- if .component -}}-{{ .component }}{{- end -}} +{{- end -}} + +{{/* +Calculate the config from structured and unstructured text input +*/}} +{{- define "tempo.calculatedConfig" -}} +{{ tpl (mergeOverwrite (tpl .Values.config . | fromYaml) .Values.tempo.structuredConfig | toYaml) . }} +{{- end -}} + +{{/* +Renders the overrides config +*/}} +{{- define "tempo.overridesConfig" -}} +{{ tpl .Values.overrides . }} +{{- end -}} + +{{/* +The volume to mount for tempo configuration +*/}} +{{- define "tempo.configVolume" -}} +{{- if eq .Values.configStorageType "Secret" -}} +secret: + secretName: {{ tpl .Values.externalConfigSecretName . }} +{{- else if eq .Values.configStorageType "ConfigMap" -}} +configMap: + name: {{ tpl .Values.externalConfigSecretName . }} + items: + - key: "tempo.yaml" + path: "tempo.yaml" +{{- if .Values.queryFrontend.query.enabled }} + - key: "tempo-query.yaml" + path: "tempo-query.yaml" +{{- end -}} +{{- end -}} +{{- end -}} + +{{/* +The volume to mount for tempo runtime configuration +*/}} +{{- define "tempo.runtimeVolume" -}} +configMap: + name: {{ tpl .Values.externalRuntimeConfigName . }} + items: + - key: "overrides.yaml" + path: "overrides.yaml" +{{- end -}} + +{{/* +Internal servers http listen port - derived from Loki default +*/}} +{{- define "tempo.serverHttpListenPort" -}} +{{ (((.Values.tempo).structuredConfig).server).http_listen_port | default "3100" }} +{{- end -}} + +{{/* +Internal servers grpc listen port - derived from Tempo default +*/}} +{{- define "tempo.serverGrpcListenPort" -}} +{{ (((.Values.tempo).structuredConfig).server).grpc_listen_port | default "9095" }} +{{- end -}} + +{{/* +Memberlist bind port +*/}} +{{- define "tempo.memberlistBindPort" -}} +{{ (((.Values.tempo).structuredConfig).memberlist).bind_port | default "7946" }} +{{- end -}} + +{{/* +Calculate values.yaml section name from component name +Expects the component name in .component on the passed context +*/}} +{{- define "tempo.componentSectionFromName" -}} +{{- .component | replace "-" "_" | camelcase | untitle -}} +{{- end -}} + +{{/* +POD labels +*/}} +{{- define "tempo.podLabels" -}} +helm.sh/chart: {{ include "tempo.chart" .ctx }} +app.kubernetes.io/name: {{ include "tempo.name" .ctx }} +app.kubernetes.io/instance: {{ .ctx.Release.Name }} +app.kubernetes.io/version: {{ .ctx.Chart.AppVersion | quote }} +app.kubernetes.io/managed-by: {{ .ctx.Release.Service }} +{{- if .component }} +app.kubernetes.io/component: {{ .component }} +{{- end }} +{{- if .memberlist }} +app.kubernetes.io/part-of: memberlist +{{- end -}} +{{- end -}} + +{{/* +POD annotations +*/}} +{{- define "tempo.podAnnotations" -}} +{{- if .ctx.Values.useExternalConfig }} +checksum/config: {{ .ctx.Values.externalConfigVersion }} +{{- else -}} +checksum/config: {{ include (print .ctx.Template.BasePath "/configmap-tempo.yaml") .ctx | sha256sum }} +{{- end }} +{{- with .ctx.Values.global.podAnnotations }} +{{ toYaml . }} +{{- end }} +{{- if .component }} +{{- $componentSection := include "tempo.componentSectionFromName" . }} +{{- if not (hasKey .ctx.Values $componentSection) }} +{{- print "Component section " $componentSection " does not exist" | fail }} +{{- end }} +{{- with (index .ctx.Values $componentSection).podAnnotations }} +{{ toYaml . }} +{{- end }} +{{- end }} +{{- end -}} + +{{/* +Cluster name that shows up in dashboard metrics +*/}} +{{- define "tempo.clusterName" -}} +{{ (include "tempo.calculatedConfig" . | fromYaml).cluster_name | default .Release.Name }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/_helpers.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/_helpers.tpl new file mode 100644 index 0000000..3b72a66 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/_helpers.tpl @@ -0,0 +1,7 @@ +{{/* +adminApi imagePullSecrets +*/}} +{{- define "tempo.adminApiImagePullSecrets" -}} +{{- $dict := dict "tempo" .Values.tempo.image "component" .Values.adminApi.image "global" .Values.global.image -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/admin-api-dep.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/admin-api-dep.yaml new file mode 100644 index 0000000..ae0d733 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/admin-api-dep.yaml @@ -0,0 +1,131 @@ +{{- if .Values.enterprise.enabled -}} +{{ $dict := dict "ctx" . "component" "admin-api" "memberlist" true }} +apiVersion: apps/v1 +kind: Deployment +metadata: + annotations: + {{- toYaml .Values.adminApi.annotations | nindent 4 }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace | quote }} +spec: + replicas: {{ .Values.adminApi.replicas }} + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + strategy: + {{- toYaml .Values.adminApi.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "tempo.podLabels" $dict | nindent 8 }} + {{- with .Values.adminApi.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + {{- include "tempo.podAnnotations" $dict | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "tempo.serviceAccountName" . }} + {{- if .Values.adminApi.priorityClassName }} + priorityClassName: {{ .Values.adminApi.priorityClassName }} + {{- end }} + securityContext: + {{- toYaml .Values.adminApi.securityContext | nindent 8 }} + initContainers: + {{- with .Values.adminApi.initContainers }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- include "tempo.adminApiImagePullSecrets" . | nindent 6 -}} + {{- with .Values.adminApi.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: admin-api + image: "{{ include "tempo.imageReference" $dict }}" + imagePullPolicy: {{ .Values.tempo.image.pullPolicy }} + args: + - "-target=admin-api" + - "-config.expand-env=true" + - "-config.file=/conf/tempo.yaml" + {{- range $key, $value := .Values.adminApi.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + - mountPath: /conf + name: config + - name: license + mountPath: /license + - name: storage + mountPath: "/data" + subPath: {{ .Values.adminApi.persistence.subPath }} + {{- if .Values.adminApi.extraVolumeMounts }} + {{ toYaml .Values.adminApi.extraVolumeMounts | nindent 12}} + {{- end }} + ports: + - name: http-metrics + containerPort: {{ include "tempo.serverHttpListenPort" . }} + protocol: TCP + - name: grpc + containerPort: {{ include "tempo.serverGrpcListenPort" . }} + protocol: TCP + - name: memberlist + containerPort: {{ include "tempo.memberlistBindPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.adminApi.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.adminApi.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.adminApi.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.adminApi.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.adminApi.env }} + {{ toYaml . | nindent 12 }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.adminApi.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.adminApi.extraContainers }} + {{ toYaml . | nindent 8 }} + {{- end }} + nodeSelector: + {{- toYaml .Values.adminApi.nodeSelector | nindent 8 }} + {{- if semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version }} + {{- with .Values.adminApi.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.adminApi.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + tolerations: + {{- toYaml .Values.adminApi.tolerations | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.adminApi.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "tempo.configVolume" . | nindent 10 }} + - name: runtime-config + configMap: + name: {{ template "tempo.fullname" . }}-runtime + {{- if .Values.adminApi.extraVolumes }} + {{ toYaml .Values.adminApi.extraVolumes | nindent 8}} + {{- end }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + - name: storage + emptyDir: {} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/admin-api-pdb.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/admin-api-pdb.yaml new file mode 100644 index 0000000..5fbeb11 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/admin-api-pdb.yaml @@ -0,0 +1,3 @@ +{{- if .Values.enterprise.enabled -}} +{{- include "tempo.lib.podDisruptionBudget" (dict "ctx" $ "component" "admin-api" "memberlist" true) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/admin-api-servmon.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/admin-api-servmon.yaml new file mode 100644 index 0000000..c00bda5 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/admin-api-servmon.yaml @@ -0,0 +1,3 @@ +{{- if .Values.enterprise.enabled -}} +{{- include "tempo.lib.serviceMonitor" (dict "ctx" . "component" "admin-api" "memberlist" true) }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/admin-api-svc.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/admin-api-svc.yaml new file mode 100644 index 0000000..6d49cbe --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/admin-api/admin-api-svc.yaml @@ -0,0 +1,27 @@ +{{- if .Values.enterprise.enabled -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "admin-api") }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "admin-api" "memberlist" true) | nindent 4 }} + {{- with .Values.adminApi.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.adminApi.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: ClusterIP + ports: + - port: {{ include "tempo.serverHttpListenPort" . }} + protocol: TCP + name: http-metrics + targetPort: http-metrics + - port: {{ include "tempo.serverGrpcListenPort" . }} + protocol: TCP + name: grpc + targetPort: grpc + selector: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "admin-api" "memberlist" true) | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/_helpers-compactor.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/_helpers-compactor.tpl new file mode 100644 index 0000000..b984c9e --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/_helpers-compactor.tpl @@ -0,0 +1,7 @@ +{{/* +compactor imagePullSecrets +*/}} +{{- define "tempo.compactorImagePullSecrets" -}} +{{- $dict := dict "tempo" .Values.tempo.image "component" .Values.compactor.image "global" .Values.global.image -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/deployment-compactor.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/deployment-compactor.yaml new file mode 100644 index 0000000..e0f397a --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/deployment-compactor.yaml @@ -0,0 +1,140 @@ +{{ $dict := dict "ctx" . "component" "compactor" "memberlist" true }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ template "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.compactor.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + minReadySeconds: 10 + replicas: {{ .Values.compactor.replicas }} + revisionHistoryLimit: 10 + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + strategy: + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + template: + metadata: + labels: + {{- include "tempo.podLabels" $dict | nindent 8 }} + {{- with .Values.tempo.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.compactor.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap-tempo.yaml") . | sha256sum }} + {{- with .Values.tempo.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.compactor.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if or (.Values.compactor.priorityClassName) (.Values.global.priorityClassName) }} + priorityClassName: {{ default .Values.compactor.priorityClassName .Values.global.priorityClassName }} + {{- end }} + serviceAccountName: {{ include "tempo.serviceAccountName" . }} + {{- with .Values.tempo.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + enableServiceLinks: false + {{- include "tempo.compactorImagePullSecrets" . | nindent 6 -}} + {{- with .Values.compactor.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - args: + - -target=compactor + - -config.file=/conf/tempo.yaml + - -mem-ballast-size-mbs=1024 + {{- with .Values.compactor.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + image: {{ include "tempo.imageReference" $dict }} + imagePullPolicy: {{ .Values.tempo.image.pullPolicy }} + name: compactor + ports: + - containerPort: 3100 + name: http-metrics + - containerPort: 7946 + name: http-memberlist + {{- with .Values.compactor.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.compactor.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.compactor.resources | nindent 12 }} + {{- with .Values.tempo.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - mountPath: /conf + name: config + - mountPath: /runtime-config + name: runtime-config + - mountPath: /var/tempo + name: tempo-compactor-store + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + {{- with .Values.compactor.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.compactor.terminationGracePeriodSeconds }} + {{- if semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version }} + {{- with .Values.compactor.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.compactor.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.compactor.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.compactor.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.compactor.dnsConfigOverides.enabled }} + {{- with .Values.compactor.dnsConfigOverides.dnsConfig }} + dnsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + volumes: + - name: config + {{- include "tempo.configVolume" . | nindent 10 }} + - name: runtime-config + {{- include "tempo.runtimeVolume" . | nindent 10 }} + - name: tempo-compactor-store + emptyDir: {} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + {{- with .Values.compactor.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/poddisruptionbudget-compactor.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/poddisruptionbudget-compactor.yaml new file mode 100644 index 0000000..780caab --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/poddisruptionbudget-compactor.yaml @@ -0,0 +1,14 @@ +{{- if gt (int .Values.compactor.replicas) 1 }} +{{ $dict := dict "ctx" . "component" "compactor" "memberlist" true }} +apiVersion: {{ include "tempo.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "tempo.resourceName" $dict }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + maxUnavailable: 1 +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/service-compactor.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/service-compactor.yaml new file mode 100644 index 0000000..d280df9 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/service-compactor.yaml @@ -0,0 +1,19 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ template "tempo.resourceName" (dict "ctx" . "component" "compactor") }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "compactor") | nindent 4 }} + {{- with .Values.compactor.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + ports: + - name: http-metrics + port: 3100 + targetPort: 3100 + protocol: TCP + selector: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "compactor") | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/servicemonitor-compactor.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/servicemonitor-compactor.yaml new file mode 100644 index 0000000..5712b2c --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/compactor/servicemonitor-compactor.yaml @@ -0,0 +1 @@ +{{- include "tempo.lib.serviceMonitor" (dict "ctx" $ "component" "compactor" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/configmap-runtime.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/configmap-runtime.yaml new file mode 100644 index 0000000..c0801b5 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/configmap-runtime.yaml @@ -0,0 +1,12 @@ +{{- if not .Values.useExternalConfig }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ tpl .Values.externalRuntimeConfigName . }} + labels: + {{- include "tempo.labels" (dict "ctx" .) | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +data: + overrides.yaml: | + {{ include "tempo.overridesConfig" . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/configmap-tempo.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/configmap-tempo.yaml new file mode 100644 index 0000000..cc3aa59 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/configmap-tempo.yaml @@ -0,0 +1,24 @@ +{{- if not .Values.useExternalConfig }} +apiVersion: v1 +{{- if eq .Values.configStorageType "Secret" }} +kind: Secret +{{- else }} +kind: ConfigMap +{{- end }} +metadata: + name: {{ tpl .Values.externalConfigSecretName . }} + labels: + {{- include "tempo.labels" (dict "ctx" .) | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +{{- if eq .Values.configStorageType "Secret" }} +data: + tempo-query.yaml: {{ tpl .Values.queryFrontend.query.config . | b64enc }} + tempo.yaml: {{ include "tempo.calculatedConfig" . | b64enc }} +{{- else }} +data: + tempo-query.yaml: | + {{- tpl .Values.queryFrontend.query.config . | nindent 4 }} + tempo.yaml: | + {{ include "tempo.calculatedConfig" . | nindent 4 }} +{{- end -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/_helpers-distributor.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/_helpers-distributor.tpl new file mode 100644 index 0000000..95fc752 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/_helpers-distributor.tpl @@ -0,0 +1,7 @@ +{{/* +distributor imagePullSecrets +*/}} +{{- define "tempo.distributorImagePullSecrets" -}} +{{- $dict := dict "tempo" .Values.tempo.image "component" .Values.distributor.image "global" .Values.global.image -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/deployment-distributor.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/deployment-distributor.yaml new file mode 100644 index 0000000..8ec4c41 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/deployment-distributor.yaml @@ -0,0 +1,175 @@ +{{ $dict := dict "ctx" . "component" "distributor" "memberlist" true }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.distributor.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + minReadySeconds: 10 +{{- if not .Values.distributor.autoscaling.enabled }} + replicas: {{ .Values.distributor.replicas }} +{{- end }} + revisionHistoryLimit: 10 + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + template: + metadata: + labels: + {{- include "tempo.podLabels" $dict | nindent 8 }} + {{- with .Values.tempo.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.distributor.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap-tempo.yaml") . | sha256sum }} + {{- with .Values.tempo.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.distributor.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if or (.Values.distributor.priorityClassName) (.Values.global.priorityClassName) }} + priorityClassName: {{ default .Values.distributor.priorityClassName .Values.global.priorityClassName }} + {{- end }} + serviceAccountName: {{ include "tempo.serviceAccountName" . }} + {{- with .Values.tempo.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + enableServiceLinks: false + {{- include "tempo.distributorImagePullSecrets" . | nindent 6 -}} + {{- with .Values.distributor.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - args: + - -target=distributor + - -config.file=/conf/tempo.yaml + - -mem-ballast-size-mbs=1024 + {{- with .Values.distributor.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + image: {{ include "tempo.imageReference" $dict }} + imagePullPolicy: {{ .Values.tempo.image.pullPolicy }} + name: distributor + ports: + - containerPort: 7946 + name: http-memberlist + protocol: TCP + - containerPort: 3100 + name: http-metrics + {{- if .Values.traces.jaeger.thriftCompact.enabled }} + - containerPort: 6831 + name: jaeger-compact + protocol: UDP + {{- end }} + {{- if .Values.traces.jaeger.thriftBinary.enabled }} + - containerPort: 6832 + name: jaeger-binary + protocol: UDP + {{- end }} + {{- if .Values.traces.jaeger.thriftHttp.enabled }} + - containerPort: 14268 + name: jaeger-http + protocol: TCP + {{- end }} + {{- if .Values.traces.jaeger.grpc.enabled }} + - containerPort: 14250 + name: grpc-jaeger + protocol: TCP + {{- end }} + {{- if .Values.traces.zipkin.enabled }} + - containerPort: 9411 + name: zipkin + protocol: TCP + {{- end }} + {{- if .Values.traces.otlp.http.enabled }} + - containerPort: 4318 + name: otlp-http + protocol: TCP + {{- end }} + {{- if .Values.traces.otlp.grpc.enabled }} + - containerPort: 4317 + name: grpc-otlp + protocol: TCP + {{- end }} + {{- if .Values.traces.opencensus.enabled }} + - containerPort: 55678 + name: opencensus + protocol: TCP + {{- end }} + {{- with .Values.distributor.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.distributor.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + readinessProbe: + {{- toYaml .Values.tempo.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.distributor.resources | nindent 12 }} + {{- with .Values.tempo.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - mountPath: /conf + name: config + - mountPath: /runtime-config + name: runtime-config + - mountPath: /var/tempo + name: tempo-distributor-store + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + {{- with .Values.distributor.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.distributor.terminationGracePeriodSeconds }} + {{- if semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version }} + {{- with .Values.distributor.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.distributor.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.distributor.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.distributor.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- include "tempo.configVolume" . | nindent 10 }} + - name: runtime-config + {{- include "tempo.runtimeVolume" . | nindent 10 }} + - name: tempo-distributor-store + emptyDir: {} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + {{- with .Values.distributor.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/hpa.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/hpa.yaml new file mode 100644 index 0000000..8f3ad36 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/hpa.yaml @@ -0,0 +1,45 @@ +{{- if .Values.distributor.autoscaling.enabled }} +{{- $apiVersion := include "tempo.hpa.apiVersion" . -}} +apiVersion: {{ $apiVersion }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "distributor") }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "distributor") | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "distributor") }} + minReplicas: {{ .Values.distributor.autoscaling.minReplicas }} + maxReplicas: {{ .Values.distributor.autoscaling.maxReplicas }} + {{- with .Values.distributor.autoscaling.behavior }} + behavior: + {{- toYaml . | nindent 4 }} + {{- end }} + metrics: + {{- with .Values.distributor.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.distributor.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/poddisruptionbudget-distributor.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/poddisruptionbudget-distributor.yaml new file mode 100644 index 0000000..30b542b --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/poddisruptionbudget-distributor.yaml @@ -0,0 +1,14 @@ +{{- if gt (int .Values.distributor.replicas) 1 }} +{{ $dict := dict "ctx" . "component" "distributor" "memberlist" true }} +apiVersion: {{ include "tempo.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "tempo.resourceName" $dict }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + maxUnavailable: 1 +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/service-distributor-discovery.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/service-distributor-discovery.yaml new file mode 100644 index 0000000..d15797c --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/service-distributor-discovery.yaml @@ -0,0 +1,86 @@ +{{- $dict := dict "ctx" . "component" "distributor" }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "tempo.resourceName" $dict }}-discovery + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.distributor.serviceDiscovery.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + prometheus.io/service-monitor: "false" + {{- with .Values.distributor.serviceDiscovery.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: http-metrics + port: 3100 + targetPort: http-metrics + {{- if .Values.traces.jaeger.thriftCompact.enabled }} + - name: distributor-jaeger-thrift-compact + port: 6831 + protocol: UDP + targetPort: jaeger-compact + {{- end }} + {{- if .Values.traces.jaeger.thriftBinary.enabled }} + - name: distributor-jaeger-thrift-binary + port: 6832 + protocol: UDP + targetPort: jaeger-binary + {{- end }} + {{- if .Values.traces.jaeger.thriftHttp.enabled }} + - name: distributor-jaeger-thrift-http + port: 14268 + protocol: TCP + targetPort: jaeger-http + {{- end }} + {{- if .Values.traces.jaeger.grpc.enabled }} + - name: grpc-distributor-jaeger + port: 14250 + protocol: TCP + targetPort: grpc-jaeger + {{- if .Values.distributor.appProtocol.grpc }} + appProtocol: {{ .Values.distributor.appProtocol.grpc }} + {{- end }} + {{- end }} + {{- if .Values.traces.zipkin.enabled }} + - name: distributor-zipkin + port: 9411 + protocol: TCP + targetPort: zipkin + {{- end }} + {{- if .Values.traces.otlp.http.enabled }} + - name: distributor-otlp-http + port: 4318 + protocol: TCP + targetPort: otlp-http + {{- end }} + {{- if .Values.traces.otlp.grpc.enabled }} + - name: grpc-distributor-otlp + port: 4317 + protocol: TCP + targetPort: grpc-otlp + {{- if .Values.distributor.appProtocol.grpc }} + appProtocol: {{ .Values.distributor.appProtocol.grpc }} + {{- end }} + - name: distributor-otlp-legacy + port: 55680 + protocol: TCP + targetPort: grpc-otlp + {{- if .Values.distributor.appProtocol.grpc }} + appProtocol: {{ .Values.distributor.appProtocol.grpc }} + {{- end }} + {{- end }} + {{- if .Values.traces.opencensus.enabled }} + - name: distributor-opencensus + port: 55678 + protocol: TCP + targetPort: opencensus + {{- end }} + selector: + {{- include "tempo.selectorLabels" $dict | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/service-distributor.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/service-distributor.yaml new file mode 100644 index 0000000..3e5a812 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/service-distributor.yaml @@ -0,0 +1,99 @@ +{{- $dict := dict "ctx" . "component" "distributor" }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.distributor.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.distributor.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.distributor.service.type }} + ports: + - name: http-metrics + port: 3100 + targetPort: http-metrics + - name: grpc + port: 9095 + protocol: TCP + targetPort: 9095 + {{- if .Values.distributor.appProtocol.grpc }} + appProtocol: {{ .Values.distributor.appProtocol.grpc }} + {{- end }} + {{- if .Values.traces.jaeger.thriftCompact.enabled }} + - name: distributor-jaeger-thrift-compact + port: 6831 + protocol: UDP + targetPort: jaeger-compact + {{- end }} + {{- if .Values.traces.jaeger.thriftBinary.enabled }} + - name: distributor-jaeger-thrift-binary + port: 6832 + protocol: UDP + targetPort: jaeger-binary + {{- end }} + {{- if .Values.traces.jaeger.thriftHttp.enabled }} + - name: distributor-jaeger-thrift-http + port: 14268 + protocol: TCP + targetPort: jaeger-http + {{- end }} + {{- if .Values.traces.jaeger.grpc.enabled }} + - name: grpc-distributor-jaeger + port: 14250 + protocol: TCP + targetPort: grpc-jaeger + {{- if .Values.distributor.appProtocol.grpc }} + appProtocol: {{ .Values.distributor.appProtocol.grpc }} + {{- end }} + {{- end }} + {{- if .Values.traces.zipkin.enabled }} + - name: distributor-zipkin + port: 9411 + protocol: TCP + targetPort: zipkin + {{- end }} + {{- if .Values.traces.otlp.http.enabled }} + - name: distributor-otlp-http + port: 4318 + protocol: TCP + targetPort: otlp-http + {{- end }} + {{- if .Values.traces.otlp.grpc.enabled }} + - name: grpc-distributor-otlp + port: 4317 + protocol: TCP + targetPort: grpc-otlp + {{- if .Values.distributor.appProtocol.grpc }} + appProtocol: {{ .Values.distributor.appProtocol.grpc }} + {{- end }} + - name: distributor-otlp-legacy + port: 55680 + protocol: TCP + targetPort: grpc-otlp + {{- if .Values.distributor.appProtocol.grpc }} + appProtocol: {{ .Values.distributor.appProtocol.grpc }} + {{- end }} + {{- end }} + {{- if .Values.traces.opencensus.enabled }} + - name: distributor-opencensus + port: 55678 + protocol: TCP + targetPort: opencensus + {{- end }} + {{- if .Values.distributor.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.distributor.service.loadBalancerIP }} + {{- end }} + {{- with .Values.distributor.service.loadBalancerSourceRanges}} + loadBalancerSourceRanges: + {{ toYaml . | nindent 4 }} + {{- end }} + selector: + {{- include "tempo.selectorLabels" $dict | nindent 4 }} + diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/servicemonitor-distributor.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/servicemonitor-distributor.yaml new file mode 100644 index 0000000..6987dea --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/distributor/servicemonitor-distributor.yaml @@ -0,0 +1 @@ +{{- include "tempo.lib.serviceMonitor" (dict "ctx" $ "component" "distributor" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/_helpers-federation-frontend.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/_helpers-federation-frontend.tpl new file mode 100644 index 0000000..817e85e --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/_helpers-federation-frontend.tpl @@ -0,0 +1,7 @@ +{{/* +enterpriseFederationFrontend imagePullSecrets +*/}} +{{- define "tempo.enterpriseFederationFrontendImagePullSecrets" -}} +{{- $dict := dict "tempo" .Values.tempo.image "component" .Values.enterpriseFederationFrontend.image "global" .Values.global.image -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/deployment-federation-frontend.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/deployment-federation-frontend.yaml new file mode 100644 index 0000000..552bbd8 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/deployment-federation-frontend.yaml @@ -0,0 +1,132 @@ +{{- if and .Values.enterprise.enabled .Values.enterpriseFederationFrontend.enabled }} +{{ $dict := dict "ctx" . "component" "enterprise-federation-frontend" }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.enterpriseFederationFrontend.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + minReadySeconds: 10 +{{- if not .Values.enterpriseFederationFrontend.autoscaling.enabled }} + replicas: {{ .Values.enterpriseFederationFrontend.replicas }} +{{- end }} + revisionHistoryLimit: 10 + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + strategy: + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + template: + metadata: + labels: + {{- include "tempo.podLabels" $dict | nindent 8 }} + {{- with .Values.tempo.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.enterpriseFederationFrontend.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap-tempo.yaml") . | sha256sum }} + {{- with .Values.tempo.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.enterpriseFederationFrontend.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if or (.Values.enterpriseFederationFrontend.priorityClassName) (.Values.global.priorityClassName) }} + priorityClassName: {{ default .Values.enterpriseFederationFrontend.priorityClassName .Values.global.priorityClassName }} + {{- end }} + serviceAccountName: {{ include "tempo.serviceAccountName" . }} + {{- with .Values.tempo.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + enableServiceLinks: false + {{- include "tempo.enterpriseFederationFrontendImagePullSecrets" . | nindent 6 -}} + {{- with .Values.enterpriseFederationFrontend.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - args: + - -target=federation-frontend + - -config.file=/conf/tempo.yaml + - -mem-ballast-size-mbs=1024 + {{- with .Values.enterpriseFederationFrontend.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + image: {{ include "tempo.imageReference" $dict }} + imagePullPolicy: {{ .Values.tempo.image.pullPolicy }} + name: federation-frontend + ports: + - containerPort: 3100 + name: http-metrics + {{- with .Values.enterpriseFederationFrontend.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.enterpriseFederationFrontend.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.enterpriseFederationFrontend.resources | nindent 12 }} + {{- with .Values.tempo.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - mountPath: /conf + name: config + - mountPath: /var/tempo + name: tempo-federation-frontend-store + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + {{- with .Values.enterpriseFederationFrontend.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.enterpriseFederationFrontend.terminationGracePeriodSeconds }} + {{- if ge (.Capabilities.KubeVersion.Minor|int) 19 }} + {{- with .Values.enterpriseFederationFrontend.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.enterpriseFederationFrontend.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.enterpriseFederationFrontend.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.enterpriseFederationFrontend.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- include "tempo.configVolume" . | nindent 10 }} + - name: tempo-federation-frontend-store + emptyDir: {} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + {{- with .Values.enterpriseFederationFrontend.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/hpa.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/hpa.yaml new file mode 100644 index 0000000..8a84c9d --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/hpa.yaml @@ -0,0 +1,41 @@ +{{- if and .Values.enterprise.enabled .Values.enterpriseFederationFrontend.enabled .Values.enterpriseFederationFrontend.autoscaling.enabled }} +{{- $apiVersion := include "tempo.hpa.apiVersion" . -}} +apiVersion: {{ $apiVersion }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "enterprise-federation-frontend") }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "enterprise-federation-frontend") | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "enterprise-federation-frontend") }} + minReplicas: {{ .Values.enterpriseFederationFrontend.autoscaling.minReplicas }} + maxReplicas: {{ .Values.enterpriseFederationFrontend.autoscaling.maxReplicas }} + metrics: + {{- with .Values.enterpriseFederationFrontend.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.enterpriseFederationFrontend.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/poddisruptionbudget-federation-frontend.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/poddisruptionbudget-federation-frontend.yaml new file mode 100644 index 0000000..08b9a8f --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/poddisruptionbudget-federation-frontend.yaml @@ -0,0 +1,16 @@ +{{- if and .Values.enterprise.enabled .Values.enterpriseFederationFrontend.enabled -}} +{{- if gt (int .Values.enterpriseFederationFrontend.replicas) 1 }} +{{ $dict := dict "ctx" . "component" "enterprise-federation-frontend" }} +apiVersion: {{ include "tempo.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "tempo.resourceName" $dict }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + maxUnavailable: 1 +{{- end }} +{{- end -}} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/service-federation-frontend.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/service-federation-frontend.yaml new file mode 100644 index 0000000..8eb0804 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/service-federation-frontend.yaml @@ -0,0 +1,28 @@ +{{- if .Values.enterprise.enabled -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "enterprise-federation-frontend") }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "enterprise-federation-frontend") | nindent 4 }} + {{- with .Values.enterpriseFederationFrontend.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.enterpriseFederationFrontend.service.type }} + ports: + - name: http-metrics + port: 3100 + targetPort: 3100 + {{- if .Values.enterpriseFederationFrontend.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.enterpriseFederationFrontend.service.loadBalancerIP }} + {{- end }} + {{- with .Values.enterpriseFederationFrontend.service.loadBalancerSourceRanges}} + loadBalancerSourceRanges: + {{ toYaml . | nindent 4 }} + {{- end }} + selector: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "enterprise-federation-frontend") | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/servicemonitor-federation-frontend.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/servicemonitor-federation-frontend.yaml new file mode 100644 index 0000000..996ebf4 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-federation-frontend/servicemonitor-federation-frontend.yaml @@ -0,0 +1,3 @@ +{{- if and .Values.enterprise.enabled .Values.enterpriseFederationFrontend.enabled }} +{{- include "tempo.lib.serviceMonitor" (dict "ctx" $ "component" "enterprise-federation-frontend") }} +{{- end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/_helpers.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/_helpers.tpl new file mode 100644 index 0000000..cb030ee --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/_helpers.tpl @@ -0,0 +1,41 @@ +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "tempo.ingress.apiVersion" -}} + {{- if and (.Capabilities.APIVersions.Has "networking.k8s.io/v1") (semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version) -}} + {{- print "networking.k8s.io/v1" -}} + {{- else if .Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" -}} + {{- print "networking.k8s.io/v1beta1" -}} + {{- else -}} + {{- print "extensions/v1beta1" -}} + {{- end -}} +{{- end -}} + +{{/* +Return if ingress is stable. +*/}} +{{- define "tempo.ingress.isStable" -}} + {{- eq (include "tempo.ingress.apiVersion" .) "networking.k8s.io/v1" -}} +{{- end -}} + +{{/* +Return if ingress supports ingressClassName. +*/}} +{{- define "tempo.ingress.supportsIngressClassName" -}} + {{- or (eq (include "tempo.ingress.isStable" .) "true") (and (eq (include "tempo.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) -}} +{{- end -}} + +{{/* +Return if ingress supports pathType. +*/}} +{{- define "tempo.ingress.supportsPathType" -}} + {{- or (eq (include "tempo.ingress.isStable" .) "true") (and (eq (include "tempo.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) -}} +{{- end -}} + +{{/* +enterpriseGateway imagePullSecrets +*/}} +{{- define "tempo.enterpriseGatewayImagePullSecrets" -}} +{{- $dict := dict "tempo" .Values.tempo.image "component" .Values.enterpriseGateway.image "global" .Values.global.image -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-dep.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-dep.yaml new file mode 100644 index 0000000..0da57a1 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-dep.yaml @@ -0,0 +1,123 @@ +{{- if .Values.enterprise.enabled -}} +{{ $dict := dict "ctx" . "component" "enterprise-gateway" }} +apiVersion: apps/v1 +kind: Deployment +metadata: + annotations: + {{- toYaml .Values.enterpriseGateway.annotations | nindent 4 }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace | quote }} +spec: + replicas: {{ .Values.enterpriseGateway.replicas }} + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + strategy: + {{- toYaml .Values.enterpriseGateway.strategy | nindent 4 }} + template: + metadata: + labels: + {{- include "tempo.podLabels" $dict | nindent 8 }} + {{- with .Values.enterpriseGateway.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + {{- include "tempo.podAnnotations" $dict | nindent 8 }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "tempo.serviceAccountName" . }} + {{- if .Values.enterpriseGateway.priorityClassName }} + priorityClassName: {{ .Values.enterpriseGateway.priorityClassName }} + {{- end }} + securityContext: + {{- toYaml .Values.enterpriseGateway.securityContext | nindent 8 }} + initContainers: + {{- toYaml .Values.enterpriseGateway.initContainers | nindent 8 }} + {{- include "tempo.enterpriseGatewayImagePullSecrets" . | nindent 6 -}} + {{- with .Values.enterpriseGateway.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: gateway + image: "{{ include "tempo.imageReference" $dict }}" + imagePullPolicy: {{ .Values.tempo.image.pullPolicy }} + args: + - "-target=gateway" + - "-config.expand-env=true" + - "-config.file=/conf/tempo.yaml" + {{- range $key, $value := .Values.enterpriseGateway.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + {{- if .Values.enterpriseGateway.extraVolumeMounts }} + {{ toYaml .Values.enterpriseGateway.extraVolumeMounts | nindent 12}} + {{- end }} + - name: config + mountPath: /conf + - name: license + mountPath: /license + - name: storage + mountPath: "/data" + subPath: {{ .Values.enterpriseGateway.persistence.subPath }} + ports: + - name: http-metrics + containerPort: {{ include "tempo.serverHttpListenPort" . }} + protocol: TCP + livenessProbe: + {{- toYaml .Values.enterpriseGateway.livenessProbe | nindent 12 }} + readinessProbe: + {{- toYaml .Values.enterpriseGateway.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.enterpriseGateway.resources | nindent 12 }} + securityContext: + {{- toYaml .Values.enterpriseGateway.containerSecurityContext | nindent 12 }} + env: + {{- with .Values.global.extraEnv }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.enterpriseGateway.env }} + {{ toYaml . | nindent 12 }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.enterpriseGateway.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.enterpriseGateway.extraContainers }} + {{ toYaml . | nindent 8 }} + {{- end }} + nodeSelector: + {{- toYaml .Values.enterpriseGateway.nodeSelector | nindent 8 }} + {{- if semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version }} + {{- with .Values.enterpriseGateway.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.enterpriseGateway.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + tolerations: + {{- toYaml .Values.enterpriseGateway.tolerations | nindent 8 }} + terminationGracePeriodSeconds: {{ .Values.enterpriseGateway.terminationGracePeriodSeconds }} + volumes: + - name: config + {{- include "tempo.configVolume" . | nindent 10 }} + - name: runtime-config + configMap: + name: {{ template "tempo.fullname" . }}-runtime + {{- if .Values.enterpriseGateway.extraVolumes }} + {{ toYaml .Values.enterpriseGateway.extraVolumes | nindent 8}} + {{- end }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + - name: storage + emptyDir: {} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-ingress.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-ingress.yaml new file mode 100644 index 0000000..ea45a3f --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-ingress.yaml @@ -0,0 +1,57 @@ +{{- if .Values.enterprise.enabled -}} +{{ $dict := dict "ctx" . "component" "enterprise-gateway" }} +{{- if .Values.enterpriseGateway.ingress.enabled -}} +{{- $ingressApiIsStable := eq (include "tempo.ingress.isStable" .) "true" -}} +{{- $ingressSupportsIngressClassName := eq (include "tempo.ingress.supportsIngressClassName" .) "true" -}} +{{- $ingressSupportsPathType := eq (include "tempo.ingress.supportsPathType" .) "true" -}} +apiVersion: {{ include "tempo.ingress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ include "tempo.resourceName" $dict }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.enterpriseGateway.ingress.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + namespace: {{ .Release.Namespace | quote }} +spec: + {{- if and $ingressSupportsIngressClassName .Values.enterpriseGateway.ingress.ingressClassName }} + ingressClassName: {{ .Values.enterpriseGateway.ingress.ingressClassName }} + {{- end -}} + {{- if .Values.enterpriseGateway.ingress.tls }} + tls: + {{- range .Values.enterpriseGateway.ingress.tls }} + - hosts: + {{- range .hosts }} + - {{ . | quote }} + {{- end }} + {{- with .secretName }} + secretName: {{ . }} + {{- end }} + {{- end }} + {{- end }} + rules: + {{- range .Values.enterpriseGateway.ingress.hosts }} + - host: {{ .host | quote }} + http: + paths: + {{- range .paths }} + - path: {{ .path }} + {{- if $ingressSupportsPathType }} + pathType: {{ .pathType }} + {{- end }} + backend: + {{- if $ingressApiIsStable }} + service: + name: {{ include "tempo.resourceName" $dict }} + port: + number: {{ $.Values.enterpriseGateway.service.port | default (include "tempo.serverHttpListenPort" $ ) }} + {{- else }} + serviceName: {{ include "tempo.resourceName" $dict }} + servicePort: {{ $.Values.enterpriseGateway.service.port | default (include "tempo.serverHttpListenPort" $ ) }} + {{- end }} + {{- end }} + {{- end }} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-pdb.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-pdb.yaml new file mode 100644 index 0000000..b17c002 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-pdb.yaml @@ -0,0 +1,3 @@ +{{- if .Values.enterprise.enabled -}} +{{- include "tempo.lib.podDisruptionBudget" (dict "ctx" $ "component" "enterprise-gateway") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-servmon.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-servmon.yaml new file mode 100644 index 0000000..29d4e00 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-servmon.yaml @@ -0,0 +1,3 @@ +{{- if .Values.enterprise.enabled -}} +{{- include "tempo.lib.serviceMonitor" (dict "ctx" $ "component" "enterprise-gateway") }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-svc.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-svc.yaml new file mode 100644 index 0000000..1c5c37b --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/enterprise-gateway/gateway-svc.yaml @@ -0,0 +1,30 @@ +{{- if .Values.enterprise.enabled -}} +{{ $dict := dict "ctx" . "component" "enterprise-gateway" }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "tempo.resourceName" $dict }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.enterpriseGateway.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- toYaml .Values.enterpriseGateway.service.annotations | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +spec: + type: {{ .Values.enterpriseGateway.service.type }} + {{- with .Values.enterpriseGateway.service.clusterIP }} + clusterIP: {{ . }} + {{- end }} + {{- if and (eq "LoadBalancer" .Values.enterpriseGateway.service.type) .Values.enterpriseGateway.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.enterpriseGateway.service.loadBalancerIP }} + {{- end }} + ports: + - port: {{ .Values.enterpriseGateway.service.port | default (include "tempo.serverHttpListenPort" . ) }} + protocol: TCP + name: http-metrics + targetPort: http-metrics + selector: + {{- include "tempo.selectorLabels" $dict | nindent 4 }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/extra-manifests.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/extra-manifests.yaml new file mode 100644 index 0000000..2855904 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/extra-manifests.yaml @@ -0,0 +1,4 @@ +{{ range .Values.extraObjects }} +--- +{{ tpl (toYaml .) $ }} +{{ end }} \ No newline at end of file diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/_helpers-gateway.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/_helpers-gateway.tpl new file mode 100644 index 0000000..f5dffcc --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/_helpers-gateway.tpl @@ -0,0 +1,23 @@ +{{/* +gateway auth secret name +*/}} +{{- define "tempo.gatewayAuthSecret" -}} +{{ .Values.gateway.basicAuth.existingSecret | default (include "tempo.resourceName" (dict "ctx" . "component" "gateway")) }} +{{- end }} + + +{{/* +gateway image +*/}} +{{- define "tempo.gatewayImage" -}} +{{- $dict := dict "tempo" (dict) "service" .Values.gateway.image "global" .Values.global.image -}} +{{- include "tempo.tempoImage" $dict -}} +{{- end }} + +{{/* +gateway imagePullSecrets +*/}} +{{- define "tempo.gatewayImagePullSecrets" -}} +{{- $dict := dict "component" .Values.gateway.image "global" .Values.global.image "tempo" (dict) -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/configmap-gateway.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/configmap-gateway.yaml new file mode 100644 index 0000000..aaecf02 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/configmap-gateway.yaml @@ -0,0 +1,12 @@ +{{- if .Values.gateway.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "gateway") }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "gateway") | nindent 4 }} +data: + nginx.conf: | + {{- tpl .Values.gateway.nginxConfig.file . | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/deployment-gateway.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/deployment-gateway.yaml new file mode 100644 index 0000000..468e777 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/deployment-gateway.yaml @@ -0,0 +1,134 @@ +{{- if .Values.gateway.enabled }} +{{ $dict := dict "ctx" . "component" "gateway" }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} +spec: + minReadySeconds: 10 +{{- if not .Values.gateway.autoscaling.enabled }} + replicas: {{ .Values.gateway.replicas }} +{{- end }} + revisionHistoryLimit: 10 + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + template: + metadata: + annotations: + checksum/config: {{ include (print .Template.BasePath "/gateway/configmap-gateway.yaml") . | sha256sum }} + {{- with .Values.tempo.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.gateway.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + labels: + {{- include "tempo.selectorLabels" $dict | nindent 8 }} + {{- with .Values.tempo.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.gateway.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if or (.Values.gateway.priorityClassName) (.Values.global.priorityClassName) }} + priorityClassName: {{ default .Values.gateway.priorityClassName .Values.global.priorityClassName }} + {{- end }} + serviceAccountName: {{ include "tempo.serviceAccountName" . }} + {{- with .Values.tempo.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.gateway.terminationGracePeriodSeconds }} + enableServiceLinks: false + {{- include "tempo.gatewayImagePullSecrets" . | nindent 6 -}} + {{- with .Values.gateway.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - name: nginx + image: "{{ include "tempo.imageReference" $dict }}" + imagePullPolicy: {{ .Values.gateway.image.pullPolicy }} + ports: + - name: http-metrics + containerPort: 8080 + protocol: TCP + {{- with .Values.gateway.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.gateway.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + readinessProbe: + {{- toYaml .Values.gateway.readinessProbe | nindent 12 }} + volumeMounts: + - name: config + mountPath: /etc/nginx + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + {{- if .Values.gateway.basicAuth.enabled }} + - name: auth + mountPath: /etc/nginx/secrets + {{- end }} + - name: tmp + mountPath: /tmp + - name: docker-entrypoint-d-override + mountPath: /docker-entrypoint.d + {{- if .Values.gateway.extraVolumeMounts }} + {{- toYaml .Values.gateway.extraVolumeMounts | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.gateway.resources | nindent 12 }} + {{- with .Values.tempo.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version }} + {{- with .Values.gateway.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.gateway.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.gateway.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.gateway.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + configMap: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "gateway") }} + {{- if .Values.enterprise.enabled -}} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + {{- if .Values.gateway.basicAuth.enabled }} + - name: auth + secret: + secretName: {{ include "tempo.gatewayAuthSecret" . }} + {{- end }} + - name: tmp + emptyDir: {} + - name: docker-entrypoint-d-override + emptyDir: {} + {{- if .Values.gateway.extraVolumes }} + {{- toYaml .Values.gateway.extraVolumes | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/hpa.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/hpa.yaml new file mode 100644 index 0000000..dcccb2d --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/hpa.yaml @@ -0,0 +1,46 @@ +{{- if .Values.gateway.autoscaling.enabled }} +{{- $apiVersion := include "tempo.hpa.apiVersion" . -}} +apiVersion: {{ $apiVersion }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "gateway") }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "gateway") | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "gateway") }} + minReplicas: {{ .Values.gateway.autoscaling.minReplicas }} + maxReplicas: {{ .Values.gateway.autoscaling.maxReplicas }} + {{- with .Values.gateway.autoscaling.behavior }} + behavior: + {{- toYaml . | nindent 4 }} + {{- end }} + metrics: + {{- with .Values.gateway.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.gateway.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/ingress-gateway.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/ingress-gateway.yaml new file mode 100644 index 0000000..f38d63c --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/ingress-gateway.yaml @@ -0,0 +1,60 @@ +{{- if .Values.gateway.enabled -}} +{{- if .Values.gateway.ingress.enabled -}} +{{ $dict := dict "ctx" . "component" "gateway" }} +{{- $ingressApiIsStable := eq (include "tempo.ingress.isStable" .) "true" -}} +{{- $ingressSupportsIngressClassName := eq (include "tempo.ingress.supportsIngressClassName" .) "true" -}} +{{- $ingressSupportsPathType := eq (include "tempo.ingress.supportsPathType" .) "true" -}} +apiVersion: {{ include "tempo.ingress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "gateway") | nindent 4 }} + {{- with .Values.gateway.ingress.labels }} + {{- toYaml . | nindent 4}} + {{- end}} + {{- with .Values.gateway.ingress.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if and $ingressSupportsIngressClassName .Values.gateway.ingress.ingressClassName }} + ingressClassName: {{ .Values.gateway.ingress.ingressClassName }} + {{- end -}} + {{- if .Values.gateway.ingress.tls }} + tls: + {{- range .Values.gateway.ingress.tls }} + - hosts: + {{- range .hosts }} + - {{ . | quote }} + {{- end }} + {{- with .secretName }} + secretName: {{ . }} + {{- end }} + {{- end }} + {{- end }} + rules: + {{- range .Values.gateway.ingress.hosts }} + - host: {{ .host | quote }} + http: + paths: + {{- range .paths }} + - path: {{ .path }} + {{- if $ingressSupportsPathType }} + pathType: {{ .pathType }} + {{- end }} + backend: + {{- if $ingressApiIsStable }} + service: + name: {{ include "tempo.resourceName" $dict }} + port: + number: {{ $.Values.gateway.service.port }} + {{- else }} + serviceName: {{ include "tempo.resourceName" $dict }} + servicePort: {{ $.Values.gateway.service.port }} + {{- end }} + {{- end }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/poddisruptionbudget-gateway.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/poddisruptionbudget-gateway.yaml new file mode 100644 index 0000000..025584b --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/poddisruptionbudget-gateway.yaml @@ -0,0 +1,15 @@ +{{- if gt (int .Values.gateway.replicas) 1 }} +{{ $dict := dict "ctx" . "component" "gateway" }} +apiVersion: {{ include "tempo.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + maxUnavailable: 1 +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/secret-gateway.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/secret-gateway.yaml new file mode 100644 index 0000000..ed25c43 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/secret-gateway.yaml @@ -0,0 +1,16 @@ +{{- $root := . -}} +{{- $dict := dict "ctx" . "component" "gateway" -}} +{{- with .Values.gateway }} +{{- if and .enabled .basicAuth.enabled (not .basicAuth.existingSecret) }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ $root.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} +stringData: + .htpasswd: | + {{- tpl .basicAuth.htpasswd $dict.ctx | nindent 4 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/service-gateway.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/service-gateway.yaml new file mode 100644 index 0000000..6270cf7 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/gateway/service-gateway.yaml @@ -0,0 +1,40 @@ +{{- if .Values.gateway.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "gateway") }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "gateway") | nindent 4 }} + {{- with .Values.gateway.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.gateway.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.gateway.service.type }} + {{- with .Values.gateway.service.clusterIP }} + clusterIP: {{ . }} + {{- end }} + {{- if and (eq "LoadBalancer" .Values.gateway.service.type) .Values.gateway.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.gateway.service.loadBalancerIP }} + {{- end }} + ports: + - name: http-metrics + port: {{ .Values.gateway.service.port }} + targetPort: http-metrics + {{- if and (eq "NodePort" .Values.gateway.service.type) .Values.gateway.service.nodePort }} + nodePort: {{ .Values.gateway.service.nodePort }} + {{- end }} + protocol: TCP + {{ range .Values.gateway.service.additionalPorts }} + - name: {{ .name }} + port: {{ .port }} + targetPort: {{ .targetPort }} + protocol: {{ .protocol }} + {{ end }} + selector: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "gateway") | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/gossip-ring/_helpers.gossip-ring.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/gossip-ring/_helpers.gossip-ring.tpl new file mode 100644 index 0000000..5766952 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/gossip-ring/_helpers.gossip-ring.tpl @@ -0,0 +1,8 @@ +{{/* +gossip-ring selector labels +*/}} +{{- define "tempo.gossipRingSelectorLabels" -}} +{{ include "tempo.selectorLabels" . }} +app.kubernetes.io/part-of: memberlist +{{- end -}} + diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/gossip-ring/service-gossip-ring.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/gossip-ring/service-gossip-ring.yaml new file mode 100644 index 0000000..5f6b822 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/gossip-ring/service-gossip-ring.yaml @@ -0,0 +1,21 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "gossip-ring") }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "gossip-ring") | nindent 4 }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: gossip-ring + port: 7946 + protocol: TCP + targetPort: http-memberlist + {{- if .Values.tempo.memberlist.appProtocol }} + appProtocol: {{ .Values.tempo.memberlist.appProtocol }} + {{- end }} + publishNotReadyAddresses: true + selector: + {{- include "tempo.gossipRingSelectorLabels" (dict "ctx" .) | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/_helpers-ingester.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/_helpers-ingester.tpl new file mode 100644 index 0000000..fc89667 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/_helpers-ingester.tpl @@ -0,0 +1,182 @@ +{{- define "tempo.ingesterImagePullSecrets" -}} +{{- $dict := dict "tempo" .Values.tempo.image "component" .Values.ingester.image "global" .Values.global.image -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} +{{- define "ingester.zoneAwareReplicationMap" -}} +{{- $zonesMap := (dict) -}} +{{- $defaultZone := (dict "affinity" .ctx.Values.ingester.affinity "nodeSelector" .ctx.Values.ingester.nodeSelector "replicas" .ctx.Values.ingester.replicas "storageClass" .ctx.Values.ingester.storageClass) -}} +{{- if .ctx.Values.ingester.zoneAwareReplication.enabled -}} +{{- $numberOfZones := len .ctx.Values.ingester.zoneAwareReplication.zones -}} +{{- if lt $numberOfZones 3 -}} +{{- fail "When zone-awareness is enabled, you must have at least 3 zones defined." -}} +{{- end -}} +{{- $requestedReplicas := .ctx.Values.ingester.replicas -}} +{{- $replicaPerZone := div (add $requestedReplicas $numberOfZones -1) $numberOfZones -}} +{{- range $idx, $rolloutZone := .ctx.Values.ingester.zoneAwareReplication.zones -}} +{{- $_ := set $zonesMap $rolloutZone.name (dict +"affinity" (($rolloutZone.extraAffinity | default (dict)) | mergeOverwrite (include "ingester.zoneAntiAffinity" (dict "rolloutZoneName" $rolloutZone.name "topologyKey" $.ctx.Values.ingester.zoneAwareReplication.topologyKey) | fromYaml)) +"nodeSelector" ($rolloutZone.nodeSelector | default (dict) ) +"replicas" $replicaPerZone +"storageClass" $rolloutZone.storageClass +) -}} +{{- end -}} +{{- else -}} +{{- $_ := set $zonesMap "" $defaultZone -}} +{{- end -}} +{{- $zonesMap | toYaml }} +{{- end -}} +{{/* +Calculate anti-affinity for a zone +Params: + rolloutZoneName = name of the rollout zone + topologyKey = topology key +*/}} +{{- define "ingester.zoneAntiAffinity" -}} +{{- if .topologyKey -}} + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchExpressions: + - key: rollout-group + operator: In + values: + - ingester + - key: zone + operator: NotIn + values: + - {{ .rolloutZoneName }} + topologyKey: {{ .topologyKey | quote }} +{{- else -}} +{} +{{- end -}} +{{- end -}} + +{{/* +Calculate annotations with zone-awareness +Params: + ctx = . context + component = component name + rolloutZoneName = rollout zone name (optional) +*/}} +{{- define "ingester.Annotations" -}} +{{- if and .ctx.Values.ingester.zoneAwareReplication.maxUnavailable .rolloutZoneName }} +{{- $map := dict "rollout-max-unavailable" (.ctx.Values.ingester.zoneAwareReplication.maxUnavailable | toString) -}} +{{- toYaml (deepCopy $map | mergeOverwrite .ctx.Values.ingester.annotations) }} +{{- else -}} +{{ toYaml .ctx.Values.ingester.annotations }} +{{- end -}} +{{- end -}} + +{{/* +ingester labels +*/}} +{{- define "ingester.labels" -}} +{{- if and .ctx.Values.ingester.zoneAwareReplication.enabled .rolloutZoneName }} +name: {{ printf "%s-%s" .component .rolloutZoneName }} +rollout-group: {{ .component }} +zone: {{ .rolloutZoneName }} +{{- end }} +helm.sh/chart: {{ include "tempo.chart" .ctx }} +app.kubernetes.io/name: {{ include "tempo.name" .ctx }} +app.kubernetes.io/instance: {{ .ctx.Release.Name }} +{{- if .component }} +app.kubernetes.io/component: {{ .component }} +{{- end }} +{{- if .memberlist }} +app.kubernetes.io/part-of: memberlist +{{- end }} +{{- if .ctx.Chart.AppVersion }} +app.kubernetes.io/version: {{ .ctx.Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .ctx.Release.Service }} +{{- end -}} +{{/* +Resource name template +*/}} +{{- define "ingester.resourceName" -}} +{{- $resourceName := include "tempo.fullname" .ctx -}} +{{- if .component -}}{{- $resourceName = printf "%s-%s" $resourceName .component -}}{{- end -}} +{{- if .rolloutZoneName -}}{{- $resourceName = printf "%s-%s" $resourceName .rolloutZoneName -}}{{- end -}} +{{- $resourceName -}} +{{- end -}} + + +{{/* +ingester selector labels +Params: + ctx = . context + component = name of the component + rolloutZoneName = rollout zone name (optional) +*/}} +{{- define "ingester.selectorLabels" -}} +{{- if .ctx.Values.enterprise.legacyLabels }} +{{- if .component -}} +app: {{ include "tempo.name" .ctx }}-{{ .component }} +{{- end }} +release: {{ .ctx.Release.Name }} +{{- else -}} +app.kubernetes.io/name: {{ include "tempo.name" .ctx }} +app.kubernetes.io/instance: {{ .ctx.Release.Name }} +{{- if .component }} +app.kubernetes.io/component: {{ .component }} +{{- end }} +{{- end -}} +{{- if .rolloutZoneName }} +{{- if not .component }} +{{- printf "Component name cannot be empty if rolloutZoneName (%s) is set" .rolloutZoneName | fail }} +{{- end }} +rollout-group: {{ .component }} +zone: {{ .rolloutZoneName }} +{{- end }} +{{- end -}} + +{{/* +ingester POD labels +Params: + ctx = . context + component = name of the component + memberlist = true if part of memberlist gossip ring + rolloutZoneName = rollout zone name (optional) +*/}} +{{- define "ingester.podLabels" -}} +{{ with .ctx.Values.global.podLabels -}} +{{ toYaml . }} +{{ end }} +{{- if .ctx.Values.enterprise.legacyLabels }} +{{- if .component -}} +app: {{ include "tempo.name" .ctx }}-{{ .component }} +{{- if not .rolloutZoneName }} +name: {{ .component }} +{{- end }} +{{- end }} +{{- if .memberlist }} +gossip_ring_member: "true" +{{- end -}} +{{- if .component }} +target: {{ .component }} +release: {{ .ctx.Release.Name }} +{{- end }} +{{- else -}} +helm.sh/chart: {{ include "tempo.chart" .ctx }} +app.kubernetes.io/name: {{ include "tempo.name" .ctx }} +app.kubernetes.io/instance: {{ .ctx.Release.Name }} +app.kubernetes.io/version: {{ .ctx.Chart.AppVersion | quote }} +app.kubernetes.io/managed-by: {{ .ctx.Release.Service }} +{{- if .component }} +app.kubernetes.io/component: {{ .component }} +{{- end }} +{{- if .memberlist }} +app.kubernetes.io/part-of: memberlist +{{- end }} +{{- end }} +{{- with .ctx.Values.ingester.podLabels }} +{{ toYaml . }} +{{- end }} +{{- if .rolloutZoneName }} +{{- if not .component }} +{{- printf "Component name cannot be empty if rolloutZoneName (%s) is set" .rolloutZoneName | fail }} +{{- end }} +rollout-group: ingester +zone: {{ .rolloutZoneName }} +{{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/hpa.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/hpa.yaml new file mode 100644 index 0000000..66a3b23 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/hpa.yaml @@ -0,0 +1,45 @@ +{{- if .Values.ingester.autoscaling.enabled }} +{{- $apiVersion := include "tempo.hpa.apiVersion" . -}} +apiVersion: {{ $apiVersion }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "ingester") }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "ingester") | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: StatefulSet + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "ingester") }} + minReplicas: {{ .Values.ingester.autoscaling.minReplicas }} + maxReplicas: {{ .Values.ingester.autoscaling.maxReplicas }} + {{- with .Values.ingester.autoscaling.behavior }} + behavior: + {{- toYaml . | nindent 4 }} + {{- end }} + metrics: + {{- with .Values.ingester.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.ingester.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/pdb.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/pdb.yaml new file mode 100644 index 0000000..01c9db0 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/pdb.yaml @@ -0,0 +1,14 @@ +{{- if .Values.podDisruptionBudget -}} +apiVersion: {{ include "tempo.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "ingester") }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "ingester") | nindent 4 }} +spec: + selector: + matchLabels: + app: {{ include "tempo.resourceName" (dict "ctx" . "component" "ingester") }} +{{ toYaml .Values.podDisruptionBudget | indent 2 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/poddisruptionbudget-ingester.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/poddisruptionbudget-ingester.yaml new file mode 100644 index 0000000..413c477 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/poddisruptionbudget-ingester.yaml @@ -0,0 +1,14 @@ +{{- if gt (int .Values.ingester.replicas) 1 }} +{{ $dict := dict "ctx" . "component" "ingester" "memberlist" true }} +apiVersion: {{ include "tempo.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "tempo.resourceName" $dict }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + maxUnavailable: {{ sub (.Values.ingester.replicas) (add (div .Values.ingester.config.replication_factor 2) 1) }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/service-ingester-discovery.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/service-ingester-discovery.yaml new file mode 100644 index 0000000..6c26ccf --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/service-ingester-discovery.yaml @@ -0,0 +1,30 @@ +{{- $dict := dict "ctx" . "component" "ingester" true }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "tempo.resourceName" $dict }}-discovery + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + prometheus.io/service-monitor: "false" + {{- with .Values.ingester.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: http-metrics + port: 3100 + protocol: TCP + targetPort: 3100 + - name: grpc + port: 9095 + protocol: TCP + targetPort: 9095 + {{- if .Values.ingester.appProtocol.grpc }} + appProtocol: {{ .Values.ingester.appProtocol.grpc }} + {{- end }} + selector: + {{- include "tempo.selectorLabels" $dict | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/service-ingester.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/service-ingester.yaml new file mode 100644 index 0000000..61e2fa7 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/service-ingester.yaml @@ -0,0 +1,27 @@ +{{- $dict := dict "ctx" . "component" "ingester" true }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.ingester.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + ports: + - name: http-metrics + port: 3100 + protocol: TCP + targetPort: 3100 + - name: grpc + port: 9095 + protocol: TCP + targetPort: 9095 + {{- if .Values.ingester.appProtocol.grpc }} + appProtocol: {{ .Values.ingester.appProtocol.grpc }} + {{- end }} + selector: + {{- include "tempo.selectorLabels" $dict | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/servicemonitor-ingester.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/servicemonitor-ingester.yaml new file mode 100644 index 0000000..4804dc7 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/servicemonitor-ingester.yaml @@ -0,0 +1 @@ +{{- include "tempo.lib.serviceMonitor" (dict "ctx" $ "component" "ingester" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/statefulset-ingester.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/statefulset-ingester.yaml new file mode 100644 index 0000000..2a1e009 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/ingester/statefulset-ingester.yaml @@ -0,0 +1,195 @@ +{{- $dict := dict "ctx" . "component" "ingester" "memberlist" true -}} +{{- $zonesMap := include "ingester.zoneAwareReplicationMap" $dict | fromYaml -}} +{{- range $zoneName, $rolloutZone := $zonesMap -}} +{{- with $ -}} +{{- $_ := set $dict "rolloutZoneName" $zoneName -}} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ template "ingester.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "ingester.labels" $dict | indent 4 }} + {{- if .Values.ingester.zoneAwareReplication.enabled }} + annotations: + {{- include "ingester.Annotations" $dict | nindent 4}} + {{- else }} + {{- with .Values.ingester.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- end }} +spec: + {{- if not .Values.ingester.autoscaling.enabled }} + replicas: {{ $rolloutZone.replicas }} + {{- end }} + selector: + matchLabels: + {{- include "ingester.selectorLabels" $dict | nindent 6}} + serviceName: ingester + podManagementPolicy: Parallel + updateStrategy: + {{- if .Values.ingester.zoneAwareReplication.enabled }} + type: OnDelete + {{- else }} + rollingUpdate: + partition: 0 + {{- end }} + template: + metadata: + labels: + {{- include "ingester.podLabels" $dict | nindent 8 }} + {{- with .Values.tempo.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ingester.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap-tempo.yaml") . | sha256sum }} + {{- with .Values.tempo.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ingester.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if or (.Values.ingester.priorityClassName) (.Values.global.priorityClassName) }} + priorityClassName: {{ default .Values.ingester.priorityClassName .Values.global.priorityClassName }} + {{- end }} + serviceAccountName: {{ include "tempo.serviceAccountName" . }} + {{- with .Values.tempo.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + enableServiceLinks: false + {{- include "tempo.ingesterImagePullSecrets" . | nindent 6 -}} + {{- with .Values.ingester.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + initContainers: + {{- toYaml .Values.ingester.initContainers | nindent 8 }} + containers: + - args: + - -target=ingester + - -config.file=/conf/tempo.yaml + - -mem-ballast-size-mbs=1024 + {{- with .Values.ingester.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + image: {{ include "tempo.imageReference" $dict }} + imagePullPolicy: {{ .Values.tempo.image.pullPolicy }} + name: ingester + ports: + - name: grpc + containerPort: 9095 + - name: http-memberlist + containerPort: 7946 + - name: http-metrics + containerPort: 3100 + {{- with .Values.ingester.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.ingester.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + readinessProbe: + {{- toYaml .Values.tempo.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.ingester.resources | nindent 12 }} + {{- with .Values.tempo.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - mountPath: /conf + name: config + - mountPath: /runtime-config + name: runtime-config + - mountPath: /var/tempo + name: data + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + {{- with .Values.ingester.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.ingester.terminationGracePeriodSeconds }} + {{- if semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version }} + {{- with .Values.ingester.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- if eq $zoneName ""}} + {{- with $rolloutZone.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- if ne $zoneName "" }} + {{- with $rolloutZone.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + {{- with $rolloutZone.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.ingester.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- include "tempo.configVolume" . | nindent 10 }} + - name: runtime-config + {{- include "tempo.runtimeVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + {{- with .Values.ingester.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if not .Values.ingester.persistence.enabled }} + - name: data + emptyDir: {} + {{- else if .Values.ingester.persistence.inMemory }} + - name: data + {{- if .Values.ingester.persistence.inMemory }} + emptyDir: + medium: Memory + {{- end }} + {{- if .Values.ingester.persistence.size }} + sizeLimit: {{ .Values.ingester.persistence.size }} + {{- end }} + {{- else }} + volumeClaimTemplates: + - apiVersion: v1 + kind: PersistentVolumeClaim + metadata: + {{- with .Values.ingester.persistence.annotations }} + annotations: + {{- toYaml . | nindent 10 }} + {{- end }} + name: data + spec: + accessModes: + - ReadWriteOnce + {{- with .Values.ingester.persistence.storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: {{ .Values.ingester.persistence.size | quote }} + {{- end }} +--- +{{ end }} +{{ end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/lib/pdb.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/lib/pdb.tpl new file mode 100644 index 0000000..fa7c498 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/lib/pdb.tpl @@ -0,0 +1,25 @@ +{{/* +Tempo common PodDisruptionBudget definition +Params: + ctx = . context + component = name of the component +*/}} +{{- define "tempo.lib.podDisruptionBudget" -}} +{{- $componentSection := include "tempo.componentSectionFromName" . }} +{{ with (index $.ctx.Values $componentSection) }} +{{- if .podDisruptionBudget -}} +apiVersion: {{ include "tempo.podDisruptionBudget.apiVersion" $.ctx }} +kind: PodDisruptionBudget +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" $.ctx "component" $.component) }} + labels: + {{- include "tempo.labels" (dict "ctx" $.ctx "component" $.component) | nindent 4 }} + namespace: {{ $.ctx.Release.Namespace | quote }} +spec: + selector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" $.ctx "component" $.component) | nindent 6 }} +{{ toYaml .podDisruptionBudget | indent 2 }} +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/lib/service-monitor.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/lib/service-monitor.tpl new file mode 100644 index 0000000..896110f --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/lib/service-monitor.tpl @@ -0,0 +1,74 @@ +{{/* +Tempo common ServiceMonitor definition +Params: + ctx = . context + component = name of the component + memberlist = true/false, whether component is part of memberlist +*/}} +{{- define "tempo.lib.serviceMonitor" -}} +{{- with .ctx.Values.metaMonitoring.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "tempo.resourceName" $ }} + namespace: {{ .namespace | default $.ctx.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + namespaceSelector: + {{- if .namespaceSelector }} + {{- toYaml .namespaceSelector | nindent 4 }} + {{- else }} + matchNames: + - {{ $.ctx.Release.Namespace }} + {{- end }} + selector: + matchLabels: + {{- include "tempo.selectorLabels" $ | nindent 6 }} + matchExpressions: + - key: prometheus.io/service-monitor + operator: NotIn + values: + - "false" + endpoints: + - port: http-metrics + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + relabelings: + - action: replace + sourceLabels: [job] + replacement: "{{ $.ctx.Release.Namespace }}/{{ $.component }}" + targetLabel: job + {{- if kindIs "string" .clusterLabel }} + - replacement: "{{ .clusterLabel | default (include "tempo.clusterName" $.ctx) }}" + targetLabel: cluster + {{- end }} + {{- with .relabelings }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/license-secret.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/license-secret.yaml new file mode 100644 index 0000000..e45618a --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/license-secret.yaml @@ -0,0 +1,14 @@ +{{- if .Values.enterprise.enabled -}} +{{- if not .Values.license.external }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ tpl .Values.license.secretName . }} + labels: + {{- include "tempo.labels" (dict "ctx" .) | nindent 4 }} + namespace: {{ .Release.Namespace | quote }} +data: + license.jwt: {{ .Values.license.contents | b64enc }} +{{- end -}} +{{- end -}} + diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/_helpers-memcached.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/_helpers-memcached.tpl new file mode 100644 index 0000000..4780edb --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/_helpers-memcached.tpl @@ -0,0 +1,7 @@ +{{/* +memcachedExporter imagePullSecrets +*/}} +{{- define "tempo.memcachedExporterImagePullSecrets" -}} +{{- $dict := dict "component" .Values.memcachedExporter.image "global" .Values.global.image "tempo" (dict) -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/poddisruptionbudget-memcached.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/poddisruptionbudget-memcached.yaml new file mode 100644 index 0000000..1c5f6b1 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/poddisruptionbudget-memcached.yaml @@ -0,0 +1,14 @@ +{{- if gt (int .Values.memcached.replicas) 1 }} +{{ $dict := dict "ctx" . "component" "memcached" }} +apiVersion: {{ include "tempo.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "tempo.resourceName" $dict }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + maxUnavailable: 1 +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/service-memcached.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/service-memcached.yaml new file mode 100644 index 0000000..21e1455 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/service-memcached.yaml @@ -0,0 +1,23 @@ +{{- if .Values.memcached.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "memcached") }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "memcached") | nindent 4 }} + {{- with .Values.memcached.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + ports: + - name: memcached-client + port: 11211 + targetPort: 11211 + - name: http-metrics + port: 9150 + targetPort: http-metrics + selector: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "memcached") | nindent 4 }} +{{- end}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/servicemonitor-memcached.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/servicemonitor-memcached.yaml new file mode 100644 index 0000000..3c4fe92 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/servicemonitor-memcached.yaml @@ -0,0 +1 @@ +{{- include "tempo.lib.serviceMonitor" (dict "ctx" $ "component" "memcached") }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/statefulset-memcached.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/statefulset-memcached.yaml new file mode 100644 index 0000000..b1cc700 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/memcached/statefulset-memcached.yaml @@ -0,0 +1,116 @@ +{{- if .Values.memcached.enabled }} +{{ $dict := dict "ctx" . "component" "memcached" }} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.memcached.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + replicas: {{ .Values.memcached.replicas }} + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + serviceName: memcached + template: + metadata: + {{- if or .Values.tempo.podAnnotations .Values.memcached.podAnnotations }} + annotations: + {{- with .Values.tempo.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcached.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + labels: + {{- include "tempo.labels" $dict | nindent 8 }} + {{- with .Values.tempo.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcached.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if or (.Values.memcached.priorityClassName) (.Values.global.priorityClassName) }} + priorityClassName: {{ default .Values.memcached.priorityClassName .Values.global.priorityClassName }} + {{- end }} + serviceAccountName: {{ include "tempo.serviceAccountName" . }} + {{- with .Values.tempo.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + enableServiceLinks: false + {{- include "tempo.memcachedExporterImagePullSecrets" . | nindent 6 -}} + {{- with .Values.memcachedExporter.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - image: {{ include "tempo.imageReference" $dict }} + imagePullPolicy: {{ .Values.memcached.image.pullPolicy }} + name: memcached + {{- with .Values.memcached.extraArgs }} + args: + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - containerPort: 11211 + name: client + {{- with .Values.memcached.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.memcached.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.memcached.resources | nindent 12 }} + {{- with .Values.tempo.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.memcachedExporter.enabled }} + - args: + - --memcached.address=localhost:11211 + - --web.listen-address=0.0.0.0:9150 + image: {{ include "tempo.imageReference" (dict "ctx" . "component" "memcached-exporter") }} + imagePullPolicy: {{ .Values.memcachedExporter.image.pullPolicy }} + name: exporter + ports: + - containerPort: 9150 + name: http-metrics + resources: + {{- toYaml .Values.memcachedExporter.resources | nindent 12 }} + {{- with .Values.tempo.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- end }} + {{- if semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version }} + {{- with .Values.memcached.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.memcached.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.memcached.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.memcached.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + updateStrategy: + type: RollingUpdate +{{- end}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/_helpers.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/_helpers.tpl new file mode 100644 index 0000000..596d95d --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/_helpers.tpl @@ -0,0 +1,49 @@ +{{- define "tempo.metaMonitoring.metrics.remoteWrite" -}} +url: {{ .url }} +{{- if .auth }} +basicAuth: +{{- if .auth.username }} + username: + name: {{ include "tempo.resourceName" (dict "ctx" $.ctx "component" "metrics-instance-usernames") }} + key: {{ .usernameKey | quote }} +{{- end }} +{{- with .auth }} +{{- if and .passwordSecretKey .passwordSecretName }} + password: + name: {{ .passwordSecretName | quote }} + key: {{ .passwordSecretKey | quote }} +{{- else if or .passwordSecretKey .passwordSecretName }}{{ required "Set either both passwordSecretKey and passwordSecretName or neither" nil }} +{{- end }} +{{- end }} +{{- end }} +{{- with .headers }} +headers: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- end -}} + +{{- define "tempo.metaMonitoring.logs.client" -}} +url: {{ .url }} +{{- if .auth }} +{{- if .auth.tenantId }} +tenantId: {{ .auth.tenantId | quote }} +{{- end }} +basicAuth: +{{- if .auth.username }} + username: + name: {{ include "tempo.resourceName" (dict "ctx" $.ctx "component" "logs-instance-usernames") }} + key: {{ .usernameKey | quote }} +{{- end }} +{{- with .auth }} +{{- if and .passwordSecretKey .passwordSecretName }} + password: + name: {{ .passwordSecretName | quote }} + key: {{ .passwordSecretKey | quote }} +{{- else if or .passwordSecretKey .passwordSecretName }} +{{ required "Set either both passwordSecretKey and passwordSecretName or neither" nil }} +{{- end }} +{{- end }} +{{- end }} +externalLabels: + cluster: {{ include "tempo.clusterName" $.ctx | quote}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/grafana-agent-cluster-role-binding.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/grafana-agent-cluster-role-binding.yaml new file mode 100644 index 0000000..0fc2169 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/grafana-agent-cluster-role-binding.yaml @@ -0,0 +1,19 @@ +{{- with (.Values.metaMonitoring).grafanaAgent }} +{{- if .enabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "grafana-agent") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" (dict "ctx" $ "component" "meta-monitoring" ) | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "grafana-agent") }} +subjects: + - kind: ServiceAccount + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "grafana-agent") }} + namespace: {{ .namespace | default $.Release.Namespace }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/grafana-agent-cluster-role.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/grafana-agent-cluster-role.yaml new file mode 100644 index 0000000..c4cc2cd --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/grafana-agent-cluster-role.yaml @@ -0,0 +1,39 @@ +{{- with (.Values.metaMonitoring).grafanaAgent }} +{{- if .enabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "grafana-agent") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" (dict "ctx" $ "component" "meta-monitoring" ) | nindent 4 }} +rules: + - apiGroups: + - "" + resources: + - nodes + - nodes/proxy + - nodes/metrics + - services + - endpoints + - pods + - events + verbs: + - get + - list + - watch + - apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch + - nonResourceURLs: + - /metrics + - /metrics/cadvisor + verbs: + - get +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/grafana-agent-service-account.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/grafana-agent-service-account.yaml new file mode 100644 index 0000000..afda8bc --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/grafana-agent-service-account.yaml @@ -0,0 +1,11 @@ +{{- with (.Values.metaMonitoring).grafanaAgent }} +{{- if .enabled }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "grafana-agent") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" (dict "ctx" $ "component" "meta-monitoring" ) | nindent 4 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/grafana-agent.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/grafana-agent.yaml new file mode 100644 index 0000000..cfc2085 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/grafana-agent.yaml @@ -0,0 +1,31 @@ +{{- with (.Values.metaMonitoring).grafanaAgent }} +{{- if .enabled }} +apiVersion: monitoring.grafana.com/v1alpha1 +kind: GrafanaAgent +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "meta-monitoring") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" (dict "ctx" $ "component" "meta-monitoring" ) | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + serviceAccountName: {{ include "tempo.resourceName" (dict "ctx" $ "component" "grafana-agent") }} + logs: + instanceSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" $ "component" "meta-monitoring") | nindent 8 }} + # cluster label for logs is added in the LogsInstance + metrics: + instanceSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" $ "component" "meta-monitoring") | nindent 8 }} + externalLabels: + cluster: {{ include "tempo.clusterName" $ }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/kube-state-metrics-servmon.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/kube-state-metrics-servmon.yaml new file mode 100644 index 0000000..0c52f1d --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/kube-state-metrics-servmon.yaml @@ -0,0 +1,44 @@ +{{- if and ((.Values.metaMonitoring).grafanaAgent).enabled .Values.metaMonitoring.grafanaAgent.metrics.scrapeK8s.enabled }} +{{- with .Values.metaMonitoring.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "k8s-ksm") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" (dict "ctx" $ "component" "meta-monitoring") | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + endpoints: + - port: http-metrics + metricRelabelings: + - action: keep + regex: {{ include "tempo.resourceName" (dict "ctx" $) }}.* + sourceLabels: + - deployment + - statefulset + - pod + separator: '' + path: /metrics + honorLabels: true # retain namespace label from kube-state-metrics + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with ((((($.Values).metaMonitoring).grafanaAgent).metrics).scrapeK8s).kubeStateMetrics }} + namespaceSelector: + matchNames: + - {{ .namespace }} + selector: + matchLabels: + {{- toYaml .labelSelectors | nindent 6 }} + {{- end -}} +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/kubelet-cadvisor-servmon.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/kubelet-cadvisor-servmon.yaml new file mode 100644 index 0000000..8525b73 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/kubelet-cadvisor-servmon.yaml @@ -0,0 +1,83 @@ +{{- if and ((.Values.metaMonitoring).grafanaAgent).enabled .Values.metaMonitoring.grafanaAgent.metrics.scrapeK8s.enabled }} +{{- with .Values.metaMonitoring.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "k8s-kubelet-cadvisor") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" (dict "ctx" $ "component" "meta-monitoring") | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + port: https-metrics + honorLabels: true # retain namespace label from kubelet + relabelings: + - replacement: kubelet # add so that e.g. up{} metric doesn't get clashes with the other endpoint + targetLabel: source + {{- with .relabelings }} + {{- toYaml . | nindent 8 }} + {{- end }} + metricRelabelings: + - action: keep + regex: storage-{{ include "tempo.resourceName" (dict "ctx" $) }}.* + sourceLabels: + - persistentvolumeclaim # present on kubelet_volume_stats* metrics + - targetLabel: instance # replace so that the metrics work with the default metrics mixin + sourceLabels: + - node + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + path: /metrics/cadvisor + port: https-metrics + honorLabels: true # retain namespace label from cadvisor + relabelings: + - replacement: cadvisor # add so that e.g. up{} metric doesn't get clashes with the other endpoint + targetLabel: source + - targetLabel: instance # replace so that the metrics work with the default metrics mixin + sourceLabels: + - node + {{- with .relabelings }} + {{- toYaml . | nindent 8 }} + {{- end }} + metricRelabelings: + - action: keep + regex: {{ include "tempo.resourceName" (dict "ctx" $) }}.* + sourceLabels: + - pod + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + namespaceSelector: + matchNames: + # "default" is the default namespace in which the operator creates the kubelet service. + - default + selector: + matchLabels: + # This is a service added by the agent operator, so this labels is hardcoded to what the operator creates. + app.kubernetes.io/name: kubelet +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/logs-instance-usernames-secret.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/logs-instance-usernames-secret.yaml new file mode 100644 index 0000000..35ca464 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/logs-instance-usernames-secret.yaml @@ -0,0 +1,17 @@ +{{- if ((.Values.metaMonitoring).grafanaAgent).enabled }} +{{- with .Values.metaMonitoring.grafanaAgent.logs }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "logs-instance-usernames") }} + namespace: {{ (($.Values.metaMonitoring).grafanaAgent).namespace | default $.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" (dict "ctx" $ "component" "meta-monitoring") | nindent 4 }} +data: + {{- range $i, $cfg := prepend (.additionalClientConfigs | default list) .remote }} + {{- if (($cfg).auth).username }} + username-{{ $i }}: {{ (($cfg).auth).username | b64enc | quote }} + {{- end }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/logs-instance.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/logs-instance.yaml new file mode 100644 index 0000000..a8b3147 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/logs-instance.yaml @@ -0,0 +1,38 @@ +{{- with (.Values.metaMonitoring).grafanaAgent }} +{{- if .enabled }} +apiVersion: monitoring.grafana.com/v1alpha1 +kind: LogsInstance +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "meta-monitoring") }} + namespace: {{ (($.Values.metaMonitoring).grafanaAgent).namespace | default $.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" (dict "ctx" $ "component" "meta-monitoring" ) | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + clients: + {{- if or (.logs).additionalClientConfigs (.logs).remote }} + {{- range $i, $cfg := prepend ((.logs).additionalClientConfigs | default list) (.logs).remote }} + {{- with $cfg }} + {{- if $cfg.url }} + - {{- include "tempo.metaMonitoring.logs.client" (dict "ctx" $ "url" .url "auth" .auth "usernameKey" (printf "username-%d" $i)) | nindent 6 -}} + {{- end }} + {{- end }} + {{- end }} + {{- end }} + + # Supply an empty namespace selector to look in all namespaces. Remove + # this to only look in the same namespace as the LogsInstance CR + podLogsNamespaceSelector: {} + + podLogsSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" $) | nindent 6 }} + +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/metrics-instance-usernames-secret.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/metrics-instance-usernames-secret.yaml new file mode 100644 index 0000000..beda321 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/metrics-instance-usernames-secret.yaml @@ -0,0 +1,17 @@ +{{- if .Values.metaMonitoring.grafanaAgent.enabled }} +{{- with .Values.metaMonitoring.grafanaAgent.metrics }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "metrics-instance-usernames") }} + namespace: {{ $.Values.metaMonitoring.grafanaAgent.namespace | default $.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" (dict "ctx" $ "component" "meta-monitoring") | nindent 4 }} +data: + {{- range $i, $cfg := prepend (.additionalRemoteWriteConfigs | default list) .remote }} + {{- if (($cfg).auth).username }} + username-{{ $i }}: {{ $cfg.auth.username | b64enc | quote }} + {{- end }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/metrics-instance.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/metrics-instance.yaml new file mode 100644 index 0000000..14d9cb5 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/metrics-instance.yaml @@ -0,0 +1,38 @@ +{{- with .Values.metaMonitoring.grafanaAgent }} +{{- if .enabled }} +apiVersion: monitoring.grafana.com/v1alpha1 +kind: MetricsInstance +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "meta-monitoring") }} + namespace: {{ $.Values.metaMonitoring.grafanaAgent.namespace | default $.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" (dict "ctx" $ "component" "meta-monitoring" ) | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + remoteWrite: + {{- if or (.metrics).additionalRemoteWriteConfigs (.metrics).remote }} + {{- range $i, $cfg := prepend ((.metrics).additionalRemoteWriteConfigs | default list) (.metrics).remote }} + {{- with $cfg }} + {{- if $cfg.url }} + - {{- include "tempo.metaMonitoring.metrics.remoteWrite" (dict "ctx" $ "url" .url "auth" .auth "usernameKey" (printf "username-%d" $i) "headers" .headers ) | nindent 6 -}} + {{- end }} + {{- end }} + {{- end }} + {{- end }} + + # Supply an empty namespace selector to look in all namespaces. Remove + # this to only look in the same namespace as the MetricsInstance CR + serviceMonitorNamespaceSelector: {} + + serviceMonitorSelector: + # Scrape ServiceMonitors from all components + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" $) | nindent 6 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/pod-logs.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/pod-logs.yaml new file mode 100644 index 0000000..4f0e95a --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metamonitoring/pod-logs.yaml @@ -0,0 +1,45 @@ +{{- with (.Values.metaMonitoring).grafanaAgent }} +{{- if .enabled }} +apiVersion: monitoring.grafana.com/v1alpha1 +kind: PodLogs +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" $ "component" "meta-monitoring") }} + namespace: {{ .namespace | default $.Release.Namespace | quote }} + labels: + {{- include "tempo.labels" (dict "ctx" $ "component" "meta-monitoring") | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + pipelineStages: + - cri: { } + relabelings: + - action: replace # For consistency with metrics + replacement: $1 + separator: / + sourceLabels: + - __meta_kubernetes_namespace + - __meta_kubernetes_pod_container_name + targetLabel: job + - action: replace # Necessary for slow queries dashboard + sourceLabels: + - __meta_kubernetes_pod_container_name + targetLabel: name + - targetLabel: cluster + replacement: {{ include "tempo.clusterName" $ }} + + namespaceSelector: + matchNames: + - {{ $.Release.Namespace | quote }} + + selector: + matchLabels: + # Scrape logs from all components + {{- include "tempo.selectorLabels" (dict "ctx" $) | nindent 6 }} + +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/_helpers-metrics-generator.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/_helpers-metrics-generator.tpl new file mode 100644 index 0000000..09366e2 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/_helpers-metrics-generator.tpl @@ -0,0 +1,7 @@ +{{/* +metrics-generator imagePullSecrets +*/}} +{{- define "tempo.metricsGeneratorImagePullSecrets" -}} +{{- $dict := dict "tempo" .Values.tempo.image "component" .Values.metricsGenerator.image "global" .Values.global.image -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/deployment-metrics-generator.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/deployment-metrics-generator.yaml new file mode 100644 index 0000000..ed1cd3f --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/deployment-metrics-generator.yaml @@ -0,0 +1,134 @@ +{{- if and (.Values.metricsGenerator.enabled) (eq .Values.metricsGenerator.kind "Deployment") }} +{{ $dict := dict "ctx" . "component" "metrics-generator" "memberlist" true }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.metricsGenerator.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + minReadySeconds: 10 + replicas: {{ .Values.metricsGenerator.replicas }} + revisionHistoryLimit: 10 + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + template: + metadata: + labels: + {{- include "tempo.podLabels" $dict | nindent 8 }} + {{- with .Values.tempo.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.metricsGenerator.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap-tempo.yaml") . | sha256sum }} + {{- with .Values.tempo.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.metricsGenerator.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if or (.Values.metricsGenerator.priorityClassName) (.Values.global.priorityClassName) }} + priorityClassName: {{ default .Values.metricsGenerator.priorityClassName .Values.global.priorityClassName }} + {{- end }} + serviceAccountName: {{ include "tempo.serviceAccountName" . }} + {{- with .Values.tempo.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + enableServiceLinks: false + {{- include "tempo.metricsGeneratorImagePullSecrets" . | nindent 6 -}} + {{- with .Values.metricsGenerator.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - args: + - -target=metrics-generator + - -config.file=/conf/tempo.yaml + - -mem-ballast-size-mbs=1024 + {{- with .Values.metricsGenerator.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + image: {{ include "tempo.imageReference" $dict }} + imagePullPolicy: {{ .Values.tempo.image.pullPolicy }} + name: metrics-generator + ports: + {{- range .Values.metricsGenerator.ports }} + - name: {{ .name | quote }} + containerPort: {{ .port }} + {{- end }} + {{- with .Values.metricsGenerator.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.metricsGenerator.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + readinessProbe: + {{- toYaml .Values.tempo.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.metricsGenerator.resources | nindent 12 }} + {{- with .Values.tempo.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - mountPath: /conf + name: config + - mountPath: /runtime-config + name: runtime-config + - mountPath: /var/tempo + name: wal + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + {{- with .Values.metricsGenerator.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.metricsGenerator.terminationGracePeriodSeconds }} + {{- if semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version }} + {{- with .Values.metricsGenerator.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.metricsGenerator.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.metricsGenerator.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.metricsGenerator.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- include "tempo.configVolume" . | nindent 10 }} + - name: runtime-config + {{- include "tempo.runtimeVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + - name: wal + emptyDir: {{- toYaml .Values.metricsGenerator.walEmptyDir | nindent 12 }} + {{- with .Values.metricsGenerator.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/poddisruptionbudget-metrics-generator.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/poddisruptionbudget-metrics-generator.yaml new file mode 100644 index 0000000..34e0010 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/poddisruptionbudget-metrics-generator.yaml @@ -0,0 +1,16 @@ +{{- if .Values.metricsGenerator.enabled }} +{{- if gt (int .Values.metricsGenerator.replicas) 1 }} +{{ $dict := dict "ctx" . "component" "metrics-generator" "memberlist" true }} +apiVersion: {{ include "tempo.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "tempo.resourceName" $dict }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + maxUnavailable: 1 +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/service-metrics-generator-discovery.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/service-metrics-generator-discovery.yaml new file mode 100644 index 0000000..48eb846 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/service-metrics-generator-discovery.yaml @@ -0,0 +1,32 @@ +{{- if .Values.metricsGenerator.enabled }} +{{- $dict := dict "ctx" . "component" "metrics-generator" "memberlist" true }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "tempo.resourceName" $dict }}-discovery + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + prometheus.io/service-monitor: "false" + {{- with .Values.metricsGenerator.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + clusterIP: None + ports: + {{- range .Values.metricsGenerator.ports }} + {{- if .service }} + - name: {{ .name | quote }} + port: {{ .port }} + protocol: TCP + targetPort: {{ .port }} + {{- if and (hasPrefix .name "grpc") ($.Values.metricsGenerator.appProtocol.grpc) }} + appProtocol: {{ $.Values.metricsGenerator.appProtocol.grpc }} + {{- end }} + {{- end }} + {{- end }} + selector: + {{- include "tempo.selectorLabels" $dict | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/service-metrics-generator.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/service-metrics-generator.yaml new file mode 100644 index 0000000..c2550fd --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/service-metrics-generator.yaml @@ -0,0 +1,29 @@ +{{- if .Values.metricsGenerator.enabled }} +{{- $dict := dict "ctx" . "component" "metrics-generator" "memberlist" true }} +apiVersion: v1 +kind: Service +metadata: + name: {{ template "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.metricsGenerator.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + ports: + {{- range .Values.metricsGenerator.ports }} + {{- if .service }} + - name: {{ .name | quote }} + port: {{ .port }} + protocol: TCP + targetPort: {{ .port }} + {{- if and (hasPrefix .name "grpc") ($.Values.metricsGenerator.appProtocol.grpc) }} + appProtocol: {{ $.Values.metricsGenerator.appProtocol.grpc }} + {{- end }} + {{- end }} + {{- end }} + selector: + {{- include "tempo.selectorLabels" $dict | nindent 4 }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/servicemonitor-metrics-generator.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/servicemonitor-metrics-generator.yaml new file mode 100644 index 0000000..e9fab8d --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/servicemonitor-metrics-generator.yaml @@ -0,0 +1 @@ +{{- include "tempo.lib.serviceMonitor" (dict "ctx" $ "component" "metrics-generator" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/statefulset-metrics-generator.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/statefulset-metrics-generator.yaml new file mode 100644 index 0000000..5f1737d --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/metrics-generator/statefulset-metrics-generator.yaml @@ -0,0 +1,161 @@ +{{- if and (.Values.metricsGenerator.enabled) (eq .Values.metricsGenerator.kind "StatefulSet") }} +{{ $dict := dict "ctx" . "component" "metrics-generator" "memberlist" true }} +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.metricsGenerator.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + minReadySeconds: 10 + replicas: {{ .Values.metricsGenerator.replicas }} + revisionHistoryLimit: 10 + podManagementPolicy: Parallel + updateStrategy: + rollingUpdate: + partition: 0 + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + template: + metadata: + labels: + {{- include "tempo.podLabels" $dict | nindent 8 }} + {{- with .Values.tempo.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.metricsGenerator.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap-tempo.yaml") . | sha256sum }} + {{- with .Values.tempo.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.metricsGenerator.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if or (.Values.metricsGenerator.priorityClassName) (.Values.global.priorityClassName) }} + priorityClassName: {{ default .Values.metricsGenerator.priorityClassName .Values.global.priorityClassName }} + {{- end }} + serviceAccountName: {{ include "tempo.serviceAccountName" . }} + {{- with .Values.tempo.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + enableServiceLinks: false + {{- include "tempo.metricsGeneratorImagePullSecrets" . | nindent 6 -}} + {{- with .Values.metricsGenerator.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + initContainers: + {{- toYaml .Values.metricsGenerator.initContainers | nindent 8 }} + containers: + - args: + - -target=metrics-generator + - -config.file=/conf/tempo.yaml + - -mem-ballast-size-mbs=1024 + {{- with .Values.metricsGenerator.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + image: {{ include "tempo.imageReference" $dict }} + imagePullPolicy: {{ .Values.tempo.image.pullPolicy }} + name: metrics-generator + ports: + {{- range .Values.metricsGenerator.ports }} + - name: {{ .name | quote }} + containerPort: {{ .port }} + {{- end }} + {{- with .Values.metricsGenerator.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.metricsGenerator.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + readinessProbe: + {{- toYaml .Values.tempo.readinessProbe | nindent 12 }} + resources: + {{- toYaml .Values.metricsGenerator.resources | nindent 12 }} + {{- with .Values.tempo.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - mountPath: /conf + name: config + - mountPath: /runtime-config + name: runtime-config + - mountPath: /var/tempo + name: wal + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + {{- with .Values.metricsGenerator.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.metricsGenerator.terminationGracePeriodSeconds }} + {{- if semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version }} + {{- with .Values.metricsGenerator.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.metricsGenerator.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.metricsGenerator.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.metricsGenerator.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- include "tempo.configVolume" . | nindent 10 }} + - name: runtime-config + {{- include "tempo.runtimeVolume" . | nindent 10 }} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + {{- with .Values.metricsGenerator.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if not .Values.metricsGenerator.persistence.enabled }} + - name: wal + emptyDir: {{- toYaml .Values.metricsGenerator.walEmptyDir | nindent 12 }} + {{- else }} + volumeClaimTemplates: + - apiVersion: v1 + kind: PersistentVolumeClaim + metadata: + {{- with .Values.metricsGenerator.persistence.annotations }} + annotations: + {{- toYaml . | nindent 10 }} + {{- end }} + name: wal + spec: + accessModes: + - ReadWriteOnce + {{- with .Values.metricsGenerator.persistence.storageClass }} + storageClassName: {{ if (eq "-" .) }}""{{ else }}{{ . }}{{ end }} + {{- end }} + resources: + requests: + storage: {{ .Values.metricsGenerator.persistence.size | quote }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/podsecuritypolicy.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/podsecuritypolicy.yaml new file mode 100644 index 0000000..d796eb5 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/podsecuritypolicy.yaml @@ -0,0 +1,41 @@ +{{- if .Values.rbac.pspEnabled }} +{{- if .Capabilities.APIVersions.Has "policy/v1/PodSecurityPolicy" }} +apiVersion: policy/v1 +kind: PodSecurityPolicy +metadata: + name: {{ include "tempo.fullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" . | nindent 4 }} +spec: + privileged: false + allowPrivilegeEscalation: false + volumes: + - 'configMap' + - 'emptyDir' + - 'persistentVolumeClaim' + - 'secret' + - 'projected' + - 'downwardAPI' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + rule: 'MustRunAsNonRoot' + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'MustRunAs' + ranges: + - min: 1 + max: 65535 + fsGroup: + rule: 'MustRunAs' + ranges: + - min: 1 + max: 65535 + readOnlyRootFilesystem: true + requiredDropCapabilities: + - ALL +{{- end }} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/prometheusrule.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/prometheusrule.yaml new file mode 100644 index 0000000..10d540b --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/prometheusrule.yaml @@ -0,0 +1,23 @@ +{{- with .Values.prometheusRule }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ include "tempo.fullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "tempo.labels" (dict "ctx" $) | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + groups: + {{- toYaml .groups | nindent 4 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/_helpers-querier.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/_helpers-querier.tpl new file mode 100644 index 0000000..ca424e5 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/_helpers-querier.tpl @@ -0,0 +1,7 @@ +{{/* +querier imagePullSecrets +*/}} +{{- define "tempo.querierImagePullSecrets" -}} +{{- $dict := dict "tempo" .Values.tempo.image "component" .Values.querier.image "global" .Values.global.image -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/deployment-querier.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/deployment-querier.yaml new file mode 100644 index 0000000..480d14f --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/deployment-querier.yaml @@ -0,0 +1,141 @@ +{{ $dict := dict "ctx" . "component" "querier" "memberlist" true }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ template "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.querier.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + minReadySeconds: 10 +{{- if not .Values.querier.autoscaling.enabled }} + replicas: {{ .Values.querier.replicas }} +{{- end }} + revisionHistoryLimit: 10 + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + strategy: + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + template: + metadata: + labels: + {{- include "tempo.podLabels" $dict | nindent 8 }} + {{- with .Values.tempo.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap-tempo.yaml") . | sha256sum }} + {{- with .Values.tempo.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if or (.Values.querier.priorityClassName) (.Values.global.priorityClassName) }} + priorityClassName: {{ default .Values.querier.priorityClassName .Values.global.priorityClassName }} + {{- end }} + serviceAccountName: {{ include "tempo.serviceAccountName" . }} + {{- with .Values.tempo.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + enableServiceLinks: false + {{- include "tempo.querierImagePullSecrets" . | nindent 6 -}} + {{- with .Values.querier.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - args: + - -target=querier + - -config.file=/conf/tempo.yaml + - -mem-ballast-size-mbs=1024 + {{- with .Values.querier.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + image: {{ include "tempo.imageReference" $dict }} + imagePullPolicy: {{ .Values.tempo.image.pullPolicy }} + name: querier + ports: + - containerPort: 7946 + name: http-memberlist + protocol: TCP + - containerPort: 3100 + name: http-metrics + {{- with .Values.querier.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.querier.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.querier.resources | nindent 12 }} + {{- with .Values.tempo.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.tempo.readinessProbe }} + readinessProbe: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - mountPath: /conf + name: config + - mountPath: /runtime-config + name: runtime-config + - mountPath: /var/tempo + name: tempo-querier-store + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + {{- with .Values.querier.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + terminationGracePeriodSeconds: {{ .Values.querier.terminationGracePeriodSeconds }} + {{- if semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version }} + {{- with .Values.querier.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.querier.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.querier.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.querier.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- include "tempo.configVolume" . | nindent 10 }} + - name: runtime-config + {{- include "tempo.runtimeVolume" . | nindent 10 }} + - name: tempo-querier-store + emptyDir: {} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + {{- with .Values.querier.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/hpa.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/hpa.yaml new file mode 100644 index 0000000..1d497d6 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/hpa.yaml @@ -0,0 +1,45 @@ +{{- if .Values.querier.autoscaling.enabled }} +{{- $apiVersion := include "tempo.hpa.apiVersion" . -}} +apiVersion: {{ $apiVersion }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "querier") }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "querier") | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "querier") }} + minReplicas: {{ .Values.querier.autoscaling.minReplicas }} + maxReplicas: {{ .Values.querier.autoscaling.maxReplicas }} + {{- with .Values.querier.autoscaling.behavior }} + behavior: + {{- toYaml . | nindent 4 }} + {{- end }} + metrics: + {{- with .Values.querier.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.querier.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/poddisruptionbudget-querier.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/poddisruptionbudget-querier.yaml new file mode 100644 index 0000000..1f7abd2 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/poddisruptionbudget-querier.yaml @@ -0,0 +1,14 @@ +{{- if gt (int .Values.querier.replicas) 1 }} +{{ $dict := dict "ctx" . "component" "querier" "memberlist" true }} +apiVersion: {{ include "tempo.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "tempo.resourceName" $dict }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + maxUnavailable: 1 +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/service-querier.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/service-querier.yaml new file mode 100644 index 0000000..cea6816 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/service-querier.yaml @@ -0,0 +1,26 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ template "tempo.resourceName" (dict "ctx" . "component" "querier") }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "querier") | nindent 4 }} + {{- with .Values.querier.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + ports: + - name: http-metrics + port: 3100 + protocol: TCP + targetPort: 3100 + - name: grpc + port: 9095 + protocol: TCP + targetPort: 9095 + {{- if .Values.querier.appProtocol.grpc }} + appProtocol: {{ .Values.querier.appProtocol.grpc }} + {{- end }} + selector: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "querier" "memberlist" true) | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/servicemonitor-querier.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/servicemonitor-querier.yaml new file mode 100644 index 0000000..3294c84 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/querier/servicemonitor-querier.yaml @@ -0,0 +1 @@ +{{- include "tempo.lib.serviceMonitor" (dict "ctx" $ "component" "querier" "memberlist" true) }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/_helpers-query-frontend.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/_helpers-query-frontend.tpl new file mode 100644 index 0000000..eb7b6dc --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/_helpers-query-frontend.tpl @@ -0,0 +1,23 @@ +{{/* +query image +*/}} +{{- define "tempo.queryImage" -}} +{{- $dict := dict "tempo" .Values.tempo.image "component" .Values.queryFrontend.query.image "global" .Values.global.image "defaultVersion" .Chart.AppVersion -}} +{{- include "tempo.tempoImage" $dict -}} +{{- end }} + +{{/* +queryFrontend imagePullSecrets +*/}} +{{- define "tempo.queryFrontendImagePullSecrets" -}} +{{- $dict := dict "tempo" .Values.tempo.image "component" .Values.queryFrontend.image "global" .Values.global.image -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} + +{{/* +query imagePullSecrets +*/}} +{{- define "tempo.queryImagePullSecrets" -}} +{{- $dict := dict "tempo" .Values.tempo.image "component" .Values.queryFrontend.query.image "global" .Values.global.image -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/deployment-query-frontend.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/deployment-query-frontend.yaml new file mode 100644 index 0000000..26600a7 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/deployment-query-frontend.yaml @@ -0,0 +1,173 @@ +{{ $dict := dict "ctx" . "component" "query-frontend" }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "tempo.resourceName" $dict }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.queryFrontend.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + minReadySeconds: 10 +{{- if not .Values.queryFrontend.autoscaling.enabled }} + replicas: {{ .Values.queryFrontend.replicas }} +{{- end }} + revisionHistoryLimit: 10 + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + strategy: + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + template: + metadata: + labels: + {{- include "tempo.podLabels" $dict | nindent 8 }} + {{- with .Values.tempo.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.queryFrontend.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + annotations: + checksum/config: {{ include (print $.Template.BasePath "/configmap-tempo.yaml") . | sha256sum }} + {{- with .Values.tempo.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.queryFrontend.podAnnotations }} + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- if or (.Values.queryFrontend.priorityClassName) (.Values.global.priorityClassName) }} + priorityClassName: {{ default .Values.queryFrontend.priorityClassName .Values.global.priorityClassName }} + {{- end }} + serviceAccountName: {{ include "tempo.serviceAccountName" . }} + {{- with .Values.tempo.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + enableServiceLinks: false + {{- include "tempo.queryImagePullSecrets" . | nindent 6 -}} + {{- with .Values.queryFrontend.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - args: + - -target=query-frontend + - -config.file=/conf/tempo.yaml + - -mem-ballast-size-mbs=1024 + {{- with .Values.queryFrontend.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + image: {{ include "tempo.imageReference" $dict }} + imagePullPolicy: {{ .Values.tempo.image.pullPolicy }} + name: query-frontend + ports: + - containerPort: 3100 + name: http-metrics + - containerPort: 9095 + name: grpc + {{- with .Values.queryFrontend.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.queryFrontend.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.queryFrontend.resources | nindent 12 }} + {{- with .Values.tempo.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - mountPath: /conf + name: config + - mountPath: /runtime-config + name: runtime-config + - mountPath: /var/tempo + name: tempo-queryfrontend-store + {{- if .Values.enterprise.enabled }} + - name: license + mountPath: /license + {{- end }} + {{- with .Values.queryFrontend.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if .Values.queryFrontend.query.enabled }} + - args: + - --query.base-path=/ + - --grpc-storage-plugin.configuration-file=/conf/tempo-query.yaml + - --query.bearer-token-propagation=true + {{- with .Values.queryFrontend.query.extraArgs }} + {{- toYaml . | nindent 12 }} + {{- end }} + image: {{ include "tempo.queryImage" . }} + imagePullPolicy: {{ .Values.tempo.image.pullPolicy }} + name: tempo-query + ports: + - containerPort: {{ .Values.queryFrontend.service.port }} + name: jaeger-ui + - containerPort: 16687 + name: jaeger-metrics + {{- with .Values.queryFrontend.query.extraEnv }} + env: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.queryFrontend.query.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 12 }} + {{- end }} + resources: + {{- toYaml .Values.queryFrontend.query.resources | nindent 12 }} + {{- with .Values.tempo.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - mountPath: /conf + name: config + {{- with .Values.queryFrontend.query.extraVolumeMounts }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- end}} + terminationGracePeriodSeconds: {{ .Values.queryFrontend.terminationGracePeriodSeconds }} + {{- if semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version }} + {{- with .Values.queryFrontend.topologySpreadConstraints }} + topologySpreadConstraints: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- end }} + {{- with .Values.queryFrontend.affinity }} + affinity: + {{- tpl . $ | nindent 8 }} + {{- end }} + {{- with .Values.queryFrontend.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.queryFrontend.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} + volumes: + - name: config + {{- include "tempo.configVolume" . | nindent 10 }} + - name: runtime-config + {{- include "tempo.runtimeVolume" . | nindent 10 }} + - name: tempo-queryfrontend-store + emptyDir: {} + {{- if .Values.enterprise.enabled }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + {{- end }} + {{- with .Values.queryFrontend.extraVolumes }} + {{- toYaml . | nindent 8 }} + {{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/hpa.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/hpa.yaml new file mode 100644 index 0000000..abaa744 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/hpa.yaml @@ -0,0 +1,45 @@ +{{- if .Values.queryFrontend.autoscaling.enabled }} +{{- $apiVersion := include "tempo.hpa.apiVersion" . -}} +apiVersion: {{ $apiVersion }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "query-frontend") }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "query-frontend") | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "query-frontend") }} + minReplicas: {{ .Values.queryFrontend.autoscaling.minReplicas }} + maxReplicas: {{ .Values.queryFrontend.autoscaling.maxReplicas }} + {{- with .Values.queryFrontend.autoscaling.behavior }} + behavior: + {{- toYaml . | nindent 4 }} + {{- end }} + metrics: + {{- with .Values.queryFrontend.autoscaling.targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.queryFrontend.autoscaling.targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + {{- if (eq $apiVersion "autoscaling/v2") }} + target: + type: Utilization + averageUtilization: {{ . }} + {{- else }} + targetAverageUtilization: {{ . }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/ingress-query-frontend.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/ingress-query-frontend.yaml new file mode 100644 index 0000000..39d5682 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/ingress-query-frontend.yaml @@ -0,0 +1,54 @@ +{{- if and .Values.queryFrontend.query.enabled .Values.queryFrontend.ingress.enabled -}} +{{ $dict := dict "ctx" . "component" "query-frontend" }} +{{- $ingressApiIsStable := eq (include "tempo.ingress.isStable" .) "true" -}} +{{- $ingressSupportsIngressClassName := eq (include "tempo.ingress.supportsIngressClassName" .) "true" -}} +{{- $ingressSupportsPathType := eq (include "tempo.ingress.supportsPathType" .) "true" -}} +apiVersion: {{ include "tempo.ingress.apiVersion" . }} +kind: Ingress +metadata: + name: {{ include "tempo.resourceName" $dict }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + {{- with .Values.queryFrontend.ingress.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if and $ingressSupportsIngressClassName .Values.queryFrontend.ingress.ingressClassName }} + ingressClassName: {{ .Values.queryFrontend.ingress.ingressClassName }} + {{- end -}} + {{- if .Values.queryFrontend.ingress.tls }} + tls: + {{- range .Values.queryFrontend.ingress.tls }} + - hosts: + {{- range .hosts }} + - {{ . | quote }} + {{- end }} + {{- with .secretName }} + secretName: {{ . }} + {{- end }} + {{- end }} + {{- end }} + rules: + {{- range .Values.queryFrontend.ingress.hosts }} + - host: {{ .host | quote }} + http: + paths: + {{- range .paths }} + - path: {{ .path }} + {{- if $ingressSupportsPathType }} + pathType: {{ .pathType }} + {{- end }} + backend: + {{- if $ingressApiIsStable }} + service: + name: {{ include "tempo.resourceName" $dict }} + port: + number: {{ $.Values.queryFrontend.service.port }} + {{- else }} + serviceName: {{ include "tempo.resourceName" $dict }} + servicePort: {{ $.Values.queryFrontend.service.port }} + {{- end }} + {{- end }} + {{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/poddisruptionbudget-query-frontend.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/poddisruptionbudget-query-frontend.yaml new file mode 100644 index 0000000..d3f0c23 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/poddisruptionbudget-query-frontend.yaml @@ -0,0 +1,14 @@ +{{- if gt (int .Values.queryFrontend.replicas) 1 }} +{{ $dict := dict "ctx" . "component" "query-frontend" }} +apiVersion: {{ include "tempo.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "tempo.resourceName" $dict }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "tempo.selectorLabels" $dict | nindent 6 }} + maxUnavailable: 1 +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/service-query-frontend-discovery.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/service-query-frontend-discovery.yaml new file mode 100644 index 0000000..ba91e8f --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/service-query-frontend-discovery.yaml @@ -0,0 +1,46 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "query-frontend-discovery") }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "query-frontend") | nindent 4 }} + {{- with .Values.queryFrontend.serviceDiscovery.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.queryFrontend.serviceDiscovery.annotations }} + annotations: + {{ toYaml . | nindent 4 }} + {{- end }} +spec: + type: ClusterIP + clusterIP: None + ports: + - name: http + port: 3100 + targetPort: 3100 + - name: grpc + port: 9095 + protocol: TCP + targetPort: 9095 + {{- if .Values.queryFrontend.appProtocol.grpc }} + appProtocol: {{ .Values.queryFrontend.appProtocol.grpc }} + {{- end }} + - name: grpclb + port: 9096 + protocol: TCP + targetPort: grpc + {{- if .Values.queryFrontend.appProtocol.grpc }} + appProtocol: {{ .Values.queryFrontend.appProtocol.grpc }} + {{- end }} + {{- if .Values.queryFrontend.query.enabled }} + - name: tempo-query-jaeger-ui + port: {{ .Values.queryFrontend.service.port }} + targetPort: {{ .Values.queryFrontend.service.port }} + - name: tempo-query-metrics + port: 16687 + targetPort: jaeger-metrics + {{- end }} + publishNotReadyAddresses: true + selector: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "query-frontend") | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/service-query-frontend.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/service-query-frontend.yaml new file mode 100644 index 0000000..153ca95 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/service-query-frontend.yaml @@ -0,0 +1,44 @@ +apiVersion: v1 +kind: Service +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" . "component" "query-frontend") }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" . "component" "query-frontend") | nindent 4 }} + {{- with .Values.queryFrontend.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.queryFrontend.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + type: {{ .Values.queryFrontend.service.type }} + ports: + - name: http-metrics + port: 3100 + targetPort: 3100 + - name: grpc + port: 9095 + protocol: TCP + targetPort: 9095 + {{- if .Values.queryFrontend.appProtocol.grpc }} + appProtocol: {{ .Values.queryFrontend.appProtocol.grpc }} + {{- end }} + {{- if .Values.queryFrontend.query.enabled }} + - name: tempo-query-jaeger-ui + port: {{ .Values.queryFrontend.service.port }} + targetPort: {{ .Values.queryFrontend.service.port }} + - name: tempo-query-metrics + port: 16687 + targetPort: jaeger-metrics + {{- end }} + {{- if .Values.queryFrontend.service.loadBalancerIP }} + loadBalancerIP: {{ .Values.queryFrontend.service.loadBalancerIP }} + {{- end }} + {{- with .Values.queryFrontend.service.loadBalancerSourceRanges}} + loadBalancerSourceRanges: + {{ toYaml . | nindent 4 }} + {{- end }} + selector: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "query-frontend") | nindent 4 }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/servicemonitor-jaeger-query.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/servicemonitor-jaeger-query.yaml new file mode 100644 index 0000000..5d8fa1a --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/servicemonitor-jaeger-query.yaml @@ -0,0 +1 @@ +{{- include "tempo.lib.serviceMonitor" (dict "ctx" $ "component" "tempo-query") }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/servicemonitor-query-frontend.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/servicemonitor-query-frontend.yaml new file mode 100644 index 0000000..e2a4ac1 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/query-frontend/servicemonitor-query-frontend.yaml @@ -0,0 +1 @@ +{{- include "tempo.lib.serviceMonitor" (dict "ctx" $ "component" "query-frontend") }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/role.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/role.yaml new file mode 100644 index 0000000..561ac4a --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/role.yaml @@ -0,0 +1,16 @@ +{{- if .Values.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ include "tempo.resourceName" (dict "ctx" .) }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" .) | nindent 4 }} +{{- if .Values.rbac.pspEnabled }} +rules: +- apiGroups: ['extensions'] + resources: ['podsecuritypolicies'] + verbs: ['use'] + resourceNames: [{{ include "tempo.resourceName" (dict "ctx" .) }}] +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/rolebinding.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/rolebinding.yaml new file mode 100644 index 0000000..944ddf6 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/rolebinding.yaml @@ -0,0 +1,16 @@ +{{- if .Values.rbac.create }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "tempo.fullname" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" .) | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "tempo.fullname" . }} +subjects: +- kind: ServiceAccount + name: {{ include "tempo.serviceAccountName" . }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/serviceaccount.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/serviceaccount.yaml new file mode 100644 index 0000000..a158d42 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/serviceaccount.yaml @@ -0,0 +1,18 @@ +{{ if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "tempo.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} + labels: + {{- include "tempo.labels" (dict "ctx" .) | nindent 4 }} + {{- with .Values.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }} +{{- with .Values.serviceAccount.imagePullSecrets }} +imagePullSecrets: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/tokengen/__helpers.tpl b/observability/lgtm-distributed/charts/tempo-distributed/templates/tokengen/__helpers.tpl new file mode 100644 index 0000000..f23d971 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/tokengen/__helpers.tpl @@ -0,0 +1,7 @@ +{{/* +tokengen-job imagePullSecrets +*/}} +{{- define "tempo.tokengenJobImagePullSecrets" -}} +{{- $dict := dict "tempo" .Values.tempo.image "component" .Values.tokengenJob.image "global" .Values.global.image -}} +{{- include "tempo.imagePullSecrets" $dict -}} +{{- end }} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/templates/tokengen/tokengen-job.yaml b/observability/lgtm-distributed/charts/tempo-distributed/templates/tokengen/tokengen-job.yaml new file mode 100644 index 0000000..0af6800 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/templates/tokengen/tokengen-job.yaml @@ -0,0 +1,94 @@ +{{- if .Values.enterprise.enabled -}} +{{ if .Values.tokengenJob.enable }} +{{ $dict := dict "ctx" . "component" "tokengen-job" }} +apiVersion: batch/v1 +kind: Job +metadata: + name: {{ include "tempo.resourceName" $dict }} + labels: + {{- include "tempo.labels" $dict | nindent 4 }} + annotations: + {{- if .Values.tokengenJob.annotations }} + {{- toYaml .Values.tokengenJob.annotations | nindent 4 }} + {{- end }} + "helm.sh/hook": post-install + namespace: {{ .Release.Namespace | quote }} +spec: + backoffLimit: 6 + completions: 1 + parallelism: 1 + template: + metadata: + labels: + {{- include "tempo.podLabels" $dict | nindent 8 }} + {{- with .Values.tokengenJob.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + namespace: {{ .Release.Namespace | quote }} + spec: + serviceAccountName: {{ template "tempo.serviceAccountName" . }} + {{- if .Values.tokengenJob.priorityClassName }} + priorityClassName: {{ .Values.tokengenJob.priorityClassName }} + {{- end }} + securityContext: + {{- toYaml .Values.tokengenJob.securityContext | nindent 8 }} + {{- include "tempo.tokengenJobImagePullSecrets" . | nindent 6 -}} + {{- with .Values.tokengenJob.hostAliases }} + hostAliases: + {{- toYaml . | nindent 8 }} + {{- end }} + initContainers: + {{- toYaml .Values.tokengenJob.initContainers | nindent 8 }} + containers: + - name: tokengen + image: "{{ include "tempo.imageReference" $dict }}" + imagePullPolicy: {{ .Values.tempo.image.pullPolicy }} + args: + - "-target=tokengen" + - "-config.expand-env=true" + - "-config.file=/conf/tempo.yaml" + {{- range $key, $value := .Values.tokengenJob.extraArgs }} + - "-{{ $key }}={{ $value }}" + {{- end }} + volumeMounts: + - mountPath: /conf + name: config + - mountPath: /runtime-config + name: runtime-config + - name: license + mountPath: /license + {{- if .Values.tokengenJob.extraVolumeMounts }} + {{ toYaml .Values.tokengenJob.extraVolumeMounts | nindent 12 }} + {{- end }} + env: + {{- with .Values.global.extraEnv }} + {{ toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.tokengenJob.env }} + {{ toYaml . | nindent 12 }} + {{- end }} + envFrom: + {{- with .Values.global.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + {{- with .Values.tokengenJob.extraEnvFrom }} + {{- toYaml . | nindent 12 }} + {{- end }} + securityContext: + {{- toYaml .Values.tokengenJob.containerSecurityContext | nindent 12 }} + restartPolicy: OnFailure + volumes: + - name: config + {{- include "tempo.configVolume" . | nindent 10 }} + - name: runtime-config + {{- include "tempo.runtimeVolume" . | nindent 10 }} + {{- if .Values.tokengenJob.extraVolumes }} + {{ toYaml .Values.tokengenJob.extraVolumes | nindent 8 }} + {{- end }} + - name: license + secret: + secretName: {{ tpl .Values.license.secretName . }} + - name: storage + emptyDir: {} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/charts/tempo-distributed/values.yaml b/observability/lgtm-distributed/charts/tempo-distributed/values.yaml new file mode 100644 index 0000000..3f4aea9 --- /dev/null +++ b/observability/lgtm-distributed/charts/tempo-distributed/values.yaml @@ -0,0 +1,2235 @@ +global: + image: + # -- Overrides the Docker registry globally for all images, excluding enterprise. + registry: docker.io + # -- Optional list of imagePullSecrets for all images, excluding enterprise. + # Names of existing secrets with private container registry credentials. + # Ref: https://kubernetes.io/docs/concepts/containers/images/#specifying-imagepullsecrets-on-a-pod + # Example: + # pullSecrets: [ my-dockerconfigjson-secret ] + pullSecrets: [] + # -- Overrides the priorityClassName for all pods + priorityClassName: null + # -- configures cluster domain ("cluster.local" by default) + clusterDomain: 'cluster.local' + # -- configures DNS service name + dnsService: 'kube-dns' + # -- configures DNS service namespace + dnsNamespace: 'kube-system' +fullnameOverride: '' +# fullnameOverride: tempo + +# -- Configuration is loaded from the secret called 'externalConfigSecretName'. +# If 'useExternalConfig' is true, then the configuration is not generated, just +# consumed. Top level keys for `tempo.yaml` and `overrides.yaml` are to be +# provided by the user. +useExternalConfig: false + +# -- Defines what kind of object stores the configuration, a ConfigMap or a Secret. +# In order to move sensitive information (such as credentials) from the ConfigMap/Secret to a more secure location (e.g. vault), it is possible to use [environment variables in the configuration](https://grafana.com/docs/mimir/latest/operators-guide/configuring/reference-configuration-parameters/#use-environment-variables-in-the-configuration). +# Such environment variables can be then stored in a separate Secret and injected via the global.extraEnvFrom value. For details about environment injection from a Secret please see [Secrets](https://kubernetes.io/docs/concepts/configuration/secret/#use-case-as-container-environment-variables). +configStorageType: ConfigMap + +# -- Name of the Secret or ConfigMap that contains the configuration (used for naming even if config is internal). +externalConfigSecretName: '{{ include "tempo.resourceName" (dict "ctx" . "component" "config") }}' + +# -- Name of the Secret or ConfigMap that contains the runtime configuration (used for naming even if config is internal). +externalRuntimeConfigName: '{{ include "tempo.resourceName" (dict "ctx" . "component" "runtime") }}' + +# -- When 'useExternalConfig' is true, then changing 'externalConfigVersion' triggers restart of services - otherwise changes to the configuration cause a restart. +externalConfigVersion: '0' + +# -- If true, Tempo will report anonymous usage data about the shape of a deployment to Grafana Labs +reportingEnabled: true + +tempo: + image: + # -- The Docker registry + registry: docker.io + # -- Optional list of imagePullSecrets. Overrides `global.image.pullSecrets` + pullSecrets: [] + # -- Docker image repository + repository: grafana/tempo + # -- Overrides the image tag whose default is the chart's appVersion + tag: null + pullPolicy: IfNotPresent + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 30 + timeoutSeconds: 1 + # -- Global labels for all tempo pods + podLabels: {} + # -- Common annotations for all pods + podAnnotations: {} + # -- SecurityContext holds container-level security attributes and common container settings + securityContext: + runAsNonRoot: true + runAsUser: 1000 + runAsGroup: 1000 + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + # -- podSecurityContext holds pod-level security attributes and common container settings + podSecurityContext: + fsGroup: 1000 + # -- Structured tempo configuration + structuredConfig: {} + # -- Memberlist service configuration. + memberlist: + # -- Adds the appProtocol field to the memberlist service. This allows memberlist to work with istio protocol selection. Set the optional service protocol. Ex: "tcp", "http" or "https". + appProtocol: null + +serviceAccount: + # -- Specifies whether a ServiceAccount should be created + create: true + # -- The name of the ServiceAccount to use. + # If not set and create is true, a name is generated using the fullname template + name: null + # -- Image pull secrets for the service account + imagePullSecrets: [] + # -- Annotations for the service account + annotations: {} + automountServiceAccountToken: false + +rbac: + # -- Specifies whether RBAC manifests should be created + create: false + # -- Specifies whether a PodSecurityPolicy should be created + pspEnabled: false + +# Configuration for the ingester +ingester: + # -- Annotations for the ingester StatefulSet + annotations: {} + # -- Number of replicas for the ingester + replicas: 3 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + initContainers: [] + autoscaling: + # -- Enable autoscaling for the ingester. WARNING: Autoscaling ingesters can result in lost data. Only do this if you know what you're doing. + enabled: false + # -- Minimum autoscaling replicas for the ingester + minReplicas: 2 + # -- Maximum autoscaling replicas for the ingester + maxReplicas: 3 + # -- Autoscaling behavior configuration for the ingester + behavior: {} + # -- Target CPU utilisation percentage for the ingester + targetCPUUtilizationPercentage: 60 + # -- Target memory utilisation percentage for the ingester + targetMemoryUtilizationPercentage: + image: + # -- The Docker registry for the ingester image. Overrides `tempo.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` + pullSecrets: [] + # -- Docker image repository for the ingester image. Overrides `tempo.image.repository` + repository: null + # -- Docker image tag for the ingester image. Overrides `tempo.image.tag` + tag: null + # -- The name of the PriorityClass for ingester pods + priorityClassName: null + # -- Labels for ingester pods + podLabels: {} + # -- Annotations for ingester pods + podAnnotations: {} + # -- Additional CLI args for the ingester + extraArgs: [] + # -- Environment variables to add to the ingester pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the ingester pods + extraEnvFrom: [] + # -- Resource requests and limits for the ingester + resources: {} + # -- Grace period to allow the ingester to shutdown before it is killed. Especially for the ingestor, + # this must be increased. It must be long enough so ingesters can be gracefully shutdown flushing/transferring + # all data and to successfully leave the member ring on shutdown. + terminationGracePeriodSeconds: 300 + # -- topologySpread for ingester pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Defaults to allow skew no more then 1 node per AZ + topologySpreadConstraints: | + - maxSkew: 1 + topologyKey: topology.kubernetes.io/zone + whenUnsatisfiable: ScheduleAnyway + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "ingester") | nindent 6 }} + # -- Affinity for ingester pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Soft node and soft zone anti-affinity + affinity: | + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "ingester") | nindent 12 }} + topologyKey: kubernetes.io/hostname + - weight: 75 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "ingester") | nindent 12 }} + topologyKey: topology.kubernetes.io/zone + # -- Node selector for ingester pods + nodeSelector: {} + # -- Tolerations for ingester pods + tolerations: [] + # -- Extra volumes for ingester pods + extraVolumeMounts: [] + # -- Extra volumes for ingester deployment + extraVolumes: [] + persistence: + # -- Enable creating PVCs which is required when using boltdb-shipper + enabled: false + # -- use emptyDir with ramdisk instead of PVC. **Please note that all data in ingester will be lost on pod restart** + inMemory: false + # -- Size of persistent or memory disk + size: 10Gi + # -- Storage class to be used. + # If defined, storageClassName: . + # If set to "-", storageClassName: "", which disables dynamic provisioning. + # If empty or set to null, no storageClassName spec is + # set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). + storageClass: null + # -- Annotations for ingester's persist volume claim + annotations: {} + config: + # -- Number of copies of spans to store in the ingester ring + replication_factor: 3 + # -- Amount of time a trace must be idle before flushing it to the wal. + trace_idle_period: null + # -- How often to sweep all tenants and move traces from live -> wal -> completed blocks. + flush_check_period: null + # -- Maximum size of a block before cutting it + max_block_bytes: null + # -- Maximum length of time before cutting a block + max_block_duration: null + # -- Duration to keep blocks in the ingester after they have been flushed + complete_block_timeout: null + # -- Flush all traces to backend when ingester is stopped + flush_all_on_shutdown: false + service: + # -- Annotations for ingester service + annotations: {} + # -- Adds the appProtocol field to the ingester service. This allows ingester to work with istio protocol selection. + appProtocol: + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + grpc: null + # -- EXPERIMENTAL Feature, disabled by default + zoneAwareReplication: + # -- Enable zone-aware replication for ingester + enabled: false + # -- Maximum number of ingesters that can be unavailable per zone during rollout + maxUnavailable: 50 + # -- topologyKey to use in pod anti-affinity. If unset, no anti-affinity rules are generated. If set, the generated anti-affinity rule makes sure that pods from different zones do not mix. + # E.g.: topologyKey: 'kubernetes.io/hostname' + topologyKey: null + # -- Zone definitions for ingester zones. Note: you have to redefine the whole list to change parts as YAML does not allow to modify parts of a list. + zones: + # -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + - name: zone-a + # -- nodeselector to restrict where pods of this zone can be placed. E.g.: + # nodeSelector: + # topology.kubernetes.io/zone: zone-a + nodeSelector: null + # -- extraAffinity adds user defined custom affinity rules (merged with generated rules) + extraAffinity: {} + # -- Ingester data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning + # If undefined or set to null (the default), then fall back to the value of `ingester.persistentVolume.storageClass`. + storageClass: null + # -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + - name: zone-b + # -- nodeselector to restrict where pods of this zone can be placed. E.g.: + # nodeSelector: + # topology.kubernetes.io/zone: zone-b + nodeSelector: null + # -- extraAffinity adds user defined custom affinity rules (merged with generated rules) + extraAffinity: {} + # -- Ingester data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning + # If undefined or set to null (the default), then fall back to the value of `ingester.persistentVolume.storageClass`. + storageClass: null + # -- Name of the zone, used in labels and selectors. Must follow Kubernetes naming restrictions: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ + - name: zone-c + # -- nodeselector to restrict where pods of this zone can be placed. E.g.: + # nodeSelector: + # topology.kubernetes.io/zone: zone-c + nodeSelector: null + # -- extraAffinity adds user defined custom affinity rules (merged with generated rules) + extraAffinity: {} + # -- Ingester data Persistent Volume Storage Class + # If defined, storageClassName: + # If set to "-", then use `storageClassName: ""`, which disables dynamic provisioning + # If undefined or set to null (the default), then fall back to the value of `ingester.persistentVolume.storageClass`. + storageClass: null + +# Configuration for the metrics-generator +metricsGenerator: + # -- Specifies whether a metrics-generator should be deployed + enabled: false + # -- Kind of deployment [StatefulSet/Deployment] + kind: Deployment + # -- Annotations for the metrics-generator StatefulSet + annotations: {} + # -- Number of replicas for the metrics-generator + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + initContainers: [] + image: + # -- The Docker registry for the metrics-generator image. Overrides `tempo.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` + pullSecrets: [] + # -- Docker image repository for the metrics-generator image. Overrides `tempo.image.repository` + repository: null + # -- Docker image tag for the metrics-generator image. Overrides `tempo.image.tag` + tag: null + # -- The name of the PriorityClass for metrics-generator pods + priorityClassName: null + # -- Labels for metrics-generator pods + podLabels: {} + # -- Annotations for metrics-generator pods + podAnnotations: {} + # -- Additional CLI args for the metrics-generator + extraArgs: [] + # -- Environment variables to add to the metrics-generator pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the metrics-generator pods + extraEnvFrom: [] + # -- Resource requests and limits for the metrics-generator + resources: {} + # -- Grace period to allow the metrics-generator to shutdown before it is killed. Especially for the ingestor, + # this must be increased. It must be long enough so metrics-generators can be gracefully shutdown flushing/transferring + # all data and to successfully leave the member ring on shutdown. + terminationGracePeriodSeconds: 300 + # -- topologySpread for metrics-generator pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Defaults to allow skew no more then 1 node per AZ + topologySpreadConstraints: | + - maxSkew: 1 + topologyKey: topology.kubernetes.io/zone + whenUnsatisfiable: ScheduleAnyway + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "metrics-generator") | nindent 6 }} + # -- Affinity for metrics-generator pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "metrics-generator") | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "metrics-generator") | nindent 12 }} + topologyKey: topology.kubernetes.io/zone + # -- Node selector for metrics-generator pods + nodeSelector: {} + # -- Tolerations for metrics-generator pods + tolerations: [] + # -- Persistence configuration for metrics-generator + persistence: + # -- Enable creating PVCs if you have kind set to StatefulSet. This disables using local disk or memory configured in walEmptyDir + enabled: false + size: 10Gi + # -- Storage class to be used. + # If defined, storageClassName: . + # If set to "-", storageClassName: "", which disables dynamic provisioning. + # If empty or set to null, no storageClassName spec is + # set, choosing the default provisioner (gp2 on AWS, standard on GKE, AWS, and OpenStack). + storageClass: null + # -- Annotations for metrics generator PVCs + annotations: {} + # -- The EmptyDir location where the /var/tempo will be mounted on. Defaults to local disk, can be set to memory. + walEmptyDir: {} + ## Here shows how to configure 1Gi memory as emptyDir. + ## Ref: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.19/#emptydirvolumesource-v1-core + # medium: "Memory" + # sizeLimit: 1Gi + # -- Extra volumes for metrics-generator pods + extraVolumeMounts: [] + # -- Extra volumes for metrics-generator deployment + extraVolumes: [] + # -- Default ports + ports: + - name: grpc + port: 9095 + service: true + - name: http-memberlist + port: 7946 + service: false + - name: http-metrics + port: 3100 + service: true + # -- More information on configuration: https://grafana.com/docs/tempo/latest/configuration/#metrics-generator + config: + registry: + collection_interval: 15s + external_labels: {} + stale_duration: 15m + processor: + # -- For processors to be enabled and generate metrics, pass the names of the processors to overrides.metrics_generator_processors value like [service-graphs, span-metrics] + service_graphs: + # -- Additional dimensions to add to the metrics. Dimensions are searched for in the + # -- resource and span attributes and are added to the metrics if present. + dimensions: [] + histogram_buckets: [0.1, 0.2, 0.4, 0.8, 1.6, 3.2, 6.4, 12.8] + max_items: 10000 + wait: 10s + workers: 10 + span_metrics: + # -- Additional dimensions to add to the metrics along with the default dimensions. + # -- Dimensions are searched for in the resource and span attributes and are added to the metrics if present. + dimensions: [] + histogram_buckets: [0.002, 0.004, 0.008, 0.016, 0.032, 0.064, 0.128, 0.256, 0.512, 1.02, 2.05, 4.10] + storage: + path: /var/tempo/wal + wal: + remote_write_flush_deadline: 1m + # Whether to add X-Scope-OrgID header in remote write requests + remote_write_add_org_id_header: true + # -- A list of remote write endpoints. + # -- https://prometheus.io/docs/prometheus/latest/configuration/configuration/#remote_write + remote_write: [] + # -- Used by the local blocks processor to store a wal for traces. + traces_storage: + path: /var/tempo/traces + metrics_ingestion_time_range_slack: 30s + service: + # -- Annotations for Metrics Generator service + annotations: {} + # -- Adds the appProtocol field to the metricsGenerator service. This allows metricsGenerator to work with istio protocol selection. + appProtocol: + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + grpc: null + +# Configuration for the distributor +distributor: + # -- Number of replicas for the distributor + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + autoscaling: + # -- Enable autoscaling for the distributor + enabled: false + # -- Minimum autoscaling replicas for the distributor + minReplicas: 1 + # -- Maximum autoscaling replicas for the distributor + maxReplicas: 3 + # -- Autoscaling behavior configuration for the distributor + behavior: {} + # -- Target CPU utilisation percentage for the distributor + targetCPUUtilizationPercentage: 60 + # -- Target memory utilisation percentage for the distributor + targetMemoryUtilizationPercentage: + image: + # -- The Docker registry for the ingester image. Overrides `tempo.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` + pullSecrets: [] + # -- Docker image repository for the ingester image. Overrides `tempo.image.repository` + repository: null + # -- Docker image tag for the ingester image. Overrides `tempo.image.tag` + tag: null + service: + # -- Annotations for distributor service + annotations: {} + # -- Labels for distributor service + labels: {} + # -- Type of service for the distributor + type: ClusterIP + # -- If type is LoadBalancer you can assign the IP to the LoadBalancer + loadBalancerIP: '' + # -- If type is LoadBalancer limit incoming traffic from IPs. + loadBalancerSourceRanges: [] + serviceDiscovery: + # -- Annotations for distributorDiscovery service + annotations: {} + # -- Labels for distributorDiscovery service + labels: {} + # -- The name of the PriorityClass for distributor pods + priorityClassName: null + # -- Labels for distributor pods + podLabels: {} + # -- Annotations for distributor pods + podAnnotations: {} + # -- Additional CLI args for the distributor + extraArgs: [] + # -- Environment variables to add to the distributor pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the distributor pods + extraEnvFrom: [] + # -- Resource requests and limits for the distributor + resources: {} + # -- Grace period to allow the distributor to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- topologySpread for distributor pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Defaults to allow skew no more then 1 node per AZ + topologySpreadConstraints: | + - maxSkew: 1 + topologyKey: topology.kubernetes.io/zone + whenUnsatisfiable: ScheduleAnyway + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "distributor") | nindent 6 }} + # -- Affinity for distributor pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "distributor") | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "distributor") | nindent 12 }} + topologyKey: topology.kubernetes.io/zone + # -- Node selector for distributor pods + nodeSelector: {} + # -- Tolerations for distributor pods + tolerations: [] + # -- Extra volumes for distributor pods + extraVolumeMounts: [] + # -- Extra volumes for distributor deployment + extraVolumes: [] + config: + # -- Enable to log every received trace id to help debug ingestion + # -- WARNING: Deprecated. Use log_received_spans instead. + log_received_traces: null + # -- Enable to log every received span to help debug ingestion or calculate span error distributions using the logs + log_received_spans: + enabled: false + include_all_attributes: false + filter_by_status_error: false + # -- Disables write extension with inactive ingesters + extend_writes: null + # -- Adds the appProtocol field to the distributor service. This allows distributor to work with istio protocol selection. + appProtocol: + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + grpc: null + +# Configuration for the compactor +compactor: + # -- Number of replicas for the compactor + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + image: + # -- The Docker registry for the compactor image. Overrides `tempo.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` + pullSecrets: [] + # -- Docker image repository for the compactor image. Overrides `tempo.image.repository` + repository: null + # -- Docker image tag for the compactor image. Overrides `tempo.image.tag` + tag: null + # -- The name of the PriorityClass for compactor pods + priorityClassName: null + # -- Labels for compactor pods + podLabels: {} + # -- Annotations for compactor pods + podAnnotations: {} + # -- Additional CLI args for the compactor + extraArgs: [] + # -- Environment variables to add to the compactor pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the compactor pods + extraEnvFrom: [] + # -- Resource requests and limits for the compactor + resources: {} + # -- Grace period to allow the compactor to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- Node selector for compactor pods + nodeSelector: {} + # -- Tolerations for compactor pods + tolerations: [] + # -- Extra volumes for compactor pods + extraVolumeMounts: [] + # -- Extra volumes for compactor deployment + extraVolumes: [] + config: + compaction: + # -- Duration to keep blocks + block_retention: 48h + # Duration to keep blocks that have been compacted elsewhere + compacted_block_retention: 1h + # -- Blocks in this time window will be compacted together + compaction_window: 1h + # -- Amount of data to buffer from input blocks + v2_in_buffer_bytes: 5242880 + # -- Flush data to backend when buffer is this large + v2_out_buffer_bytes: 20971520 + # -- Maximum number of traces in a compacted block. WARNING: Deprecated. Use max_block_bytes instead. + max_compaction_objects: 6000000 + # -- Maximum size of a compacted block in bytes + max_block_bytes: 107374182400 + # -- Number of tenants to process in parallel during retention + retention_concurrency: 10 + # -- Number of traces to buffer in memory during compaction + v2_prefetch_traces_count: 1000 + # -- The maximum amount of time to spend compacting a single tenant before moving to the next + max_time_per_tenant: 5m + # -- The time between compaction cycles + compaction_cycle: 30s + service: + # -- Annotations for compactor service + annotations: {} + dnsConfigOverides: + enabled: false + dnsConfig: + options: + - name: ndots + value: "3" # This is required for Azure Kubernetes Service (AKS) https://github.com/grafana/tempo/issues/1462 + +# Configuration for the querier +querier: + # -- Number of replicas for the querier + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + autoscaling: + # -- Enable autoscaling for the querier + enabled: false + # -- Minimum autoscaling replicas for the querier + minReplicas: 1 + # -- Maximum autoscaling replicas for the querier + maxReplicas: 3 + # -- Autoscaling behavior configuration for the querier + behavior: {} + # -- Target CPU utilisation percentage for the querier + targetCPUUtilizationPercentage: 60 + # -- Target memory utilisation percentage for the querier + targetMemoryUtilizationPercentage: + image: + # -- The Docker registry for the querier image. Overrides `tempo.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` + pullSecrets: [] + # -- Docker image repository for the querier image. Overrides `tempo.image.repository` + repository: null + # -- Docker image tag for the querier image. Overrides `tempo.image.tag` + tag: null + # -- The name of the PriorityClass for querier pods + priorityClassName: null + # -- Labels for querier pods + podLabels: {} + # -- Annotations for querier pods + podAnnotations: {} + # -- Additional CLI args for the querier + extraArgs: [] + # -- Environment variables to add to the querier pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the querier pods + extraEnvFrom: [] + # -- Resource requests and limits for the querier + resources: {} + # -- Grace period to allow the querier to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- topologySpread for querier pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Defaults to allow skew no more then 1 node per AZ + topologySpreadConstraints: | + - maxSkew: 1 + topologyKey: topology.kubernetes.io/zone + whenUnsatisfiable: ScheduleAnyway + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "querier") | nindent 6 }} + # -- Affinity for querier pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "querier" "memberlist" true) | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "querier" "memberlist" true) | nindent 12 }} + topologyKey: topology.kubernetes.io/zone + # -- Node selector for querier pods + nodeSelector: {} + # -- Tolerations for querier pods + tolerations: [] + # -- Extra volumes for querier pods + extraVolumeMounts: [] + # -- Extra volumes for querier deployment + extraVolumes: [] + config: + frontend_worker: + # -- grpc client configuration + grpc_client_config: {} + trace_by_id: + # -- Timeout for trace lookup requests + query_timeout: 10s + search: + # -- Timeout for search requests + query_timeout: 30s + # -- If search_external_endpoints is set then the querier will primarily act as a proxy for whatever serverless backend you have configured. This setting allows the operator to have the querier prefer itself for a configurable number of subqueries. + prefer_self: 10 + # -- If set to a non-zero value a second request will be issued at the provided duration. Recommended to be set to p99 of external search requests to reduce long tail latency. + external_hedge_requests_at: 8s + # -- The maximum number of requests to execute when hedging. Requires hedge_requests_at to be set. + external_hedge_requests_up_to: 2 + # -- A list of external endpoints that the querier will use to offload backend search requests + external_endpoints: [] + # -- The serverless backend to use. The default value of "" omits + # -- credentials when querying the external backend. + external_backend: "" + # -- Google Cloud Run configuration. Will be used only if the value of + # -- external_backend is "google_cloud_run". + google_cloud_run: {} + # -- This value controls the overall number of simultaneous subqueries that the querier will service at once. It does not distinguish between the types of queries. + max_concurrent_queries: 20 + + service: + # -- Annotations for querier service + annotations: {} + # -- Adds the appProtocol field to the querier service. This allows querier to work with istio protocol selection. + appProtocol: + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + grpc: null + +# Configuration for the query-frontend +queryFrontend: + query: + # -- Required for grafana version <7.5 for compatibility with jaeger-ui. Doesn't work on ARM arch + enabled: false + image: + # -- The Docker registry for the query-frontend image. Overrides `tempo.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` + pullSecrets: [] + # -- Docker image repository for the query-frontend image. Overrides `tempo.image.repository` + repository: grafana/tempo-query + # -- Docker image tag for the query-frontend image. Overrides `tempo.image.tag` + tag: null + # -- Resource requests and limits for the query + resources: {} + # -- Additional CLI args for tempo-query pods + extraArgs: [] + # -- Environment variables to add to the tempo-query pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the tempo-query pods + extraEnvFrom: [] + # -- Extra volumes for tempo-query pods + extraVolumeMounts: [] + # -- Extra volumes for tempo-query deployment + extraVolumes: [] + config: | + backend: 127.0.0.1:3100 + # -- Number of replicas for the query-frontend + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + config: + # -- Maximum number of outstanding requests per tenant per frontend; requests beyond this error with HTTP 429. + max_outstanding_per_tenant: 2000 + # -- Number of times to retry a request sent to a querier + max_retries: 2 + search: + # -- The number of concurrent jobs to execute when searching the backend + concurrent_jobs: 1000 + # -- The target number of bytes for each job to handle when performing a backend search + target_bytes_per_job: 104857600 + # -- Trace by ID lookup configuration + trace_by_id: + # -- The number of shards to split a trace by id query into. + query_shards: 50 + autoscaling: + # -- Enable autoscaling for the query-frontend + enabled: false + # -- Minimum autoscaling replicas for the query-frontend + minReplicas: 1 + # -- Maximum autoscaling replicas for the query-frontend + maxReplicas: 3 + # -- Autoscaling behavior configuration for the query-frontend + behavior: {} + # -- Target CPU utilisation percentage for the query-frontend + targetCPUUtilizationPercentage: 60 + # -- Target memory utilisation percentage for the query-frontend + targetMemoryUtilizationPercentage: + image: + # -- The Docker registry for the query-frontend image. Overrides `tempo.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` + pullSecrets: [] + # -- Docker image repository for the query-frontend image. Overrides `tempo.image.repository` + repository: null + # -- Docker image tag for the query-frontend image. Overrides `tempo.image.tag` + tag: null + service: + # -- Port of the query-frontend service + port: 16686 + # -- Annotations for queryFrontend service + annotations: {} + # -- Labels for queryFrontend service + labels: {} + # -- Type of service for the queryFrontend + type: ClusterIP + # -- If type is LoadBalancer you can assign the IP to the LoadBalancer + loadBalancerIP: "" + # -- If type is LoadBalancer limit incoming traffic from IPs. + loadBalancerSourceRanges: [] + serviceDiscovery: + # -- Annotations for queryFrontendDiscovery service + annotations: {} + # -- Labels for queryFrontendDiscovery service + labels: {} + ingress: + # -- Specifies whether an ingress for the Jaeger should be created + enabled: false + # -- Ingress Class Name. MAY be required for Kubernetes versions >= 1.18 + # ingressClassName: nginx + # -- Annotations for the Jaeger ingress + annotations: {} + # -- Hosts configuration for the Jaeger ingress + hosts: + - host: query.tempo.example.com + paths: + - path: / + # -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers + # pathType: Prefix + # -- TLS configuration for the Jaeger ingress + tls: + - secretName: tempo-query-tls + hosts: + - query.tempo.example.com + # -- The name of the PriorityClass for query-frontend pods + priorityClassName: null + # -- Labels for queryFrontend pods + podLabels: {} + # -- Annotations for query-frontend pods + podAnnotations: {} + # -- Additional CLI args for the query-frontend + extraArgs: [] + # -- Environment variables to add to the query-frontend pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the query-frontend pods + extraEnvFrom: [] + # -- Resource requests and limits for the query-frontend + resources: {} + # -- Grace period to allow the query-frontend to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- topologySpread for query-frontend pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Defaults to allow skew no more then 1 node per AZ + topologySpreadConstraints: | + - maxSkew: 1 + topologyKey: topology.kubernetes.io/zone + whenUnsatisfiable: ScheduleAnyway + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "query-frontend") | nindent 6 }} + # -- Affinity for query-frontend pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "query-frontend") | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "query-frontend") | nindent 12 }} + topologyKey: topology.kubernetes.io/zone + # -- Node selector for query-frontend pods + nodeSelector: {} + # -- Tolerations for query-frontend pods + tolerations: [] + # -- Extra volumes for query-frontend pods + extraVolumeMounts: [] + # -- Extra volumes for query-frontend deployment + extraVolumes: [] + # -- Adds the appProtocol field to the queryFrontend service. This allows queryFrontend to work with istio protocol selection. + appProtocol: + # -- Set the optional grpc service protocol. Ex: "grpc", "http2" or "https" + grpc: null + +# Configuration for the federation-frontend +# Can only be enabled if enterprise.enabled is true - requires license. +enterpriseFederationFrontend: + # -- Specifies whether a federation-frontend should be deployed + enabled: false + # -- Number of replicas for the federation-frontend + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + # proxy_targets: + # - name: own-data-center + # url: http://get/tempo + # - name: grafana-cloud + # url: https://tempo-us-central1.grafana.net/tempo + # basic_auth: + # username: + # password: + proxy_targets: [] + autoscaling: + # -- Enable autoscaling for the federation-frontend + enabled: false + # -- Minimum autoscaling replicas for the federation-frontend + minReplicas: 1 + # -- Maximum autoscaling replicas for the federation-frontend + maxReplicas: 3 + # -- Target CPU utilisation percentage for the federation-frontend + targetCPUUtilizationPercentage: 60 + # -- Target memory utilisation percentage for the federation-frontend + targetMemoryUtilizationPercentage: + image: + # -- The Docker registry for the federation-frontend image. Overrides `tempo.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` + pullSecrets: [] + # -- Docker image repository for the federation-frontend image. Overrides `tempo.image.repository` + repository: null + # -- Docker image tag for the federation-frontend image. Overrides `tempo.image.tag` + tag: null + service: + # -- Port of the federation-frontend service + port: 3100 + # -- Annotations for enterpriseFederationFrontend service + annotations: {} + # -- Type of service for the enterpriseFederationFrontend + type: ClusterIP + # -- If type is LoadBalancer you can assign the IP to the LoadBalancer + loadBalancerIP: "" + # -- If type is LoadBalancer limit incoming traffic from IPs. + loadBalancerSourceRanges: [] + # -- The name of the PriorityClass for federation-frontend pods + priorityClassName: null + # -- Labels for enterpriseFederationFrontend pods + podLabels: {} + # -- Annotations for federation-frontend pods + podAnnotations: {} + # -- Additional CLI args for the federation-frontend + extraArgs: [] + # -- Environment variables to add to the federation-frontend pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the federation-frontend pods + extraEnvFrom: [] + # -- Resource requests and limits for the federation-frontend + resources: {} + # -- Grace period to allow the federation-frontend to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- topologySpread for federation-frontend pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Defaults to allow skew no more then 1 node per AZ + topologySpreadConstraints: | + - maxSkew: 1 + topologyKey: failure-domain.beta.kubernetes.io/zone + whenUnsatisfiable: ScheduleAnyway + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "federation-frontend") | nindent 6 }} + # -- Affinity for federation-frontend pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "federation-frontend") | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "federation-frontend") | nindent 12 }} + topologyKey: failure-domain.beta.kubernetes.io/zone + # -- Node selector for federation-frontend pods + nodeSelector: {} + # -- Tolerations for federation-frontend pods + tolerations: [] + # -- Extra volumes for federation-frontend pods + extraVolumeMounts: [] + # -- Extra volumes for federation-frontend deployment + extraVolumes: [] + +multitenancyEnabled: false + +rollout_operator: +# -- Enable rollout-operator. It must be enabled when using Zone Aware Replication. + enabled: false + + podSecurityContext: + fsGroup: 10001 + runAsGroup: 10001 + runAsNonRoot: true + runAsUser: 10001 + seccompProfile: + type: RuntimeDefault + + # Set the container security context + securityContext: + readOnlyRootFilesystem: true + capabilities: + drop: [ALL] + allowPrivilegeEscalation: false + +traces: + jaeger: + grpc: + # -- Enable Tempo to ingest Jaeger GRPC traces + enabled: false + # -- Jaeger GRPC receiver config + receiverConfig: {} + thriftBinary: + # -- Enable Tempo to ingest Jaeger Thrift Binary traces + enabled: false + # -- Jaeger Thrift Binary receiver config + receiverConfig: {} + thriftCompact: + # -- Enable Tempo to ingest Jaeger Thrift Compact traces + enabled: false + # -- Jaeger Thrift Compact receiver config + receiverConfig: {} + thriftHttp: + # -- Enable Tempo to ingest Jaeger Thrift HTTP traces + enabled: false + # -- Jaeger Thrift HTTP receiver config + receiverConfig: {} + zipkin: + # -- Enable Tempo to ingest Zipkin traces + enabled: false + # -- Zipkin receiver config + receiverConfig: {} + otlp: + http: + # -- Enable Tempo to ingest Open Telemetry HTTP traces + enabled: false + # -- HTTP receiver advanced config + receiverConfig: {} + grpc: + # -- Enable Tempo to ingest Open Telemetry GRPC traces + enabled: false + # -- GRPC receiver advanced config + receiverConfig: {} + opencensus: + # -- Enable Tempo to ingest Open Census traces + enabled: false + # -- Open Census receiver config + receiverConfig: {} + # -- Enable Tempo to ingest traces from Kafka. Reference: https://github.com/open-telemetry/opentelemetry-collector-contrib/tree/main/receiver/kafkareceiver + kafka: {} + +# -- Memberlist configuration. Please refer to https://grafana.com/docs/tempo/latest/configuration/#memberlist +memberlist: + node_name: "" + randomize_node_name: true + stream_timeout: "10s" + retransmit_factor: 2 + pull_push_interval: "30s" + gossip_interval: "1s" + gossip_nodes: 2 + gossip_to_dead_nodes_time: "30s" + min_join_backoff: "1s" + max_join_backoff: "1m" + max_join_retries: 10 + abort_if_cluster_join_fails: false + rejoin_interval: "0s" + left_ingesters_timeout: "5m" + leave_timeout: "5s" + bind_addr: [] + bind_port: 7946 + packet_dial_timeout: "5s" + packet_write_timeout: "5s" + +# -- Config file contents for Tempo distributed. Passed through the `tpl` function to allow templating + +# @default -- See values.yaml +config: | + multitenancy_enabled: {{ .Values.multitenancyEnabled }} + + usage_report: + reporting_enabled: {{ .Values.reportingEnabled }} + + {{- if .Values.enterprise.enabled }} + license: + path: "/license/license.jwt" + + admin_api: + leader_election: + enabled: true + ring: + kvstore: + store: "memberlist" + + auth: + type: enterprise + + http_api_prefix: {{get .Values.tempo.structuredConfig "http_api_prefix"}} + + admin_client: + storage: + backend: {{.Values.storage.admin.backend}} + {{- if eq .Values.storage.admin.backend "s3"}} + s3: + {{- toYaml .Values.storage.admin.s3 | nindent 6}} + {{- end}} + {{- if eq .Values.storage.admin.backend "gcs"}} + gcs: + {{- toYaml .Values.storage.admin.gcs | nindent 6}} + {{- end}} + {{- if eq .Values.storage.admin.backend "azure"}} + azure: + {{- toYaml .Values.storage.admin.azure | nindent 6}} + {{- end}} + {{- if eq .Values.storage.admin.backend "swift"}} + swift: + {{- toYaml .Values.storage.admin.swift | nindent 6}} + {{- end}} + {{- if eq .Values.storage.admin.backend "filesystem"}} + filesystem: + {{- toYaml .Values.storage.admin.filesystem | nindent 6}} + {{- end}} + {{- end }} + + {{- if and .Values.enterprise.enabled .Values.enterpriseGateway.useDefaultProxyURLs }} + gateway: + proxy: + admin_api: + url: http://{{ template "tempo.fullname" . }}-admin-api.{{ .Release.Namespace }}.svc:{{ include "tempo.serverHttpListenPort" . }} + compactor: + url: http://{{ template "tempo.fullname" . }}-compactor.{{ .Release.Namespace }}.svc:{{ include "tempo.serverHttpListenPort" . }} + default: + url: http://{{ template "tempo.fullname" . }}-admin-api.{{ .Release.Namespace }}.svc:{{ include "tempo.serverHttpListenPort" . }} + distributor: + url: http://{{ template "tempo.fullname" . }}-distributor.{{ .Release.Namespace }}.svc:{{ include "tempo.serverHttpListenPort" . }} + otlp/grpc: + url: h2c://{{ template "tempo.fullname" . }}-distributor.{{ .Release.Namespace }}.svc:4317 + otlp/http: + url: http://{{ template "tempo.fullname" . }}-distributor.{{ .Release.Namespace }}.svc:4318 + ingester: + url: http://{{ template "tempo.fullname" . }}-ingester.{{ .Release.Namespace }}.svc:{{ include "tempo.serverHttpListenPort" . }} + querier: + url: http://{{ template "tempo.fullname" . }}-querier.{{ .Release.Namespace }}.svc:{{ include "tempo.serverHttpListenPort" . }} + query_frontend: + url: http://{{ template "tempo.fullname" . }}-query-frontend.{{ .Release.Namespace }}.svc:{{ include "tempo.serverHttpListenPort" . }}{{get .Values.tempo.structuredConfig "http_api_prefix"}} + {{else}} + {{- if and .Values.enterprise.enabled .Values.enterpriseGateway.proxy }} + gateway: + proxy: {{- toYaml .Values.enterpriseGateway.proxy | nindent 6 }} + {{- end }} + {{- end }} + + compactor: + compaction: + block_retention: {{ .Values.compactor.config.compaction.block_retention }} + compacted_block_retention: {{ .Values.compactor.config.compaction.compacted_block_retention }} + compaction_window: {{ .Values.compactor.config.compaction.compaction_window }} + v2_in_buffer_bytes: {{ .Values.compactor.config.compaction.v2_in_buffer_bytes }} + v2_out_buffer_bytes: {{ .Values.compactor.config.compaction.v2_out_buffer_bytes }} + max_compaction_objects: {{ .Values.compactor.config.compaction.max_compaction_objects }} + max_block_bytes: {{ .Values.compactor.config.compaction.max_block_bytes }} + retention_concurrency: {{ .Values.compactor.config.compaction.retention_concurrency }} + v2_prefetch_traces_count: {{ .Values.compactor.config.compaction.v2_prefetch_traces_count }} + max_time_per_tenant: {{ .Values.compactor.config.compaction.max_time_per_tenant }} + compaction_cycle: {{ .Values.compactor.config.compaction.compaction_cycle }} + ring: + kvstore: + store: memberlist + {{- if and .Values.enterprise.enabled .Values.enterpriseFederationFrontend.enabled }} + federation: + proxy_targets: + {{- toYaml .Values.enterpriseFederationFrontend.proxy_targets | nindent 6 }} + {{- end }} + {{- if .Values.metricsGenerator.enabled }} + metrics_generator: + ring: + kvstore: + store: memberlist + processor: + {{- toYaml .Values.metricsGenerator.config.processor | nindent 6 }} + storage: + {{- toYaml .Values.metricsGenerator.config.storage | nindent 6 }} + traces_storage: + {{- toYaml .Values.metricsGenerator.config.traces_storage | nindent 6 }} + registry: + {{- toYaml .Values.metricsGenerator.config.registry | nindent 6 }} + metrics_ingestion_time_range_slack: {{ .Values.metricsGenerator.config.metrics_ingestion_time_range_slack }} + {{- end }} + distributor: + ring: + kvstore: + store: memberlist + receivers: + {{- if or (.Values.traces.jaeger.thriftCompact.enabled) (.Values.traces.jaeger.thriftBinary.enabled) (.Values.traces.jaeger.thriftHttp.enabled) (.Values.traces.jaeger.grpc.enabled) }} + jaeger: + protocols: + {{- if .Values.traces.jaeger.thriftCompact.enabled }} + thrift_compact: + {{- $mergedJaegerThriftCompactConfig := mustMergeOverwrite (dict "endpoint" "0.0.0.0:6831") .Values.traces.jaeger.thriftCompact.receiverConfig }} + {{- toYaml $mergedJaegerThriftCompactConfig | nindent 10 }} + {{- end }} + {{- if .Values.traces.jaeger.thriftBinary.enabled }} + thrift_binary: + {{- $mergedJaegerThriftBinaryConfig := mustMergeOverwrite (dict "endpoint" "0.0.0.0:6832") .Values.traces.jaeger.thriftBinary.receiverConfig }} + {{- toYaml $mergedJaegerThriftBinaryConfig | nindent 10 }} + {{- end }} + {{- if .Values.traces.jaeger.thriftHttp.enabled }} + thrift_http: + {{- $mergedJaegerThriftHttpConfig := mustMergeOverwrite (dict "endpoint" "0.0.0.0:14268") .Values.traces.jaeger.thriftHttp.receiverConfig }} + {{- toYaml $mergedJaegerThriftHttpConfig | nindent 10 }} + {{- end }} + {{- if .Values.traces.jaeger.grpc.enabled }} + grpc: + {{- $mergedJaegerGrpcConfig := mustMergeOverwrite (dict "endpoint" "0.0.0.0:14250") .Values.traces.jaeger.grpc.receiverConfig }} + {{- toYaml $mergedJaegerGrpcConfig | nindent 10 }} + {{- end }} + {{- end }} + {{- if .Values.traces.zipkin.enabled }} + zipkin: + {{- $mergedZipkinReceiverConfig := mustMergeOverwrite (dict "endpoint" "0.0.0.0:9411") .Values.traces.zipkin.receiverConfig }} + {{- toYaml $mergedZipkinReceiverConfig | nindent 6 }} + {{- end }} + {{- if or (.Values.traces.otlp.http.enabled) (.Values.traces.otlp.grpc.enabled) }} + otlp: + protocols: + {{- if .Values.traces.otlp.http.enabled }} + http: + {{- $mergedOtlpHttpReceiverConfig := mustMergeOverwrite (dict "endpoint" "0.0.0.0:4318") .Values.traces.otlp.http.receiverConfig }} + {{- toYaml $mergedOtlpHttpReceiverConfig | nindent 10 }} + {{- end }} + {{- if .Values.traces.otlp.grpc.enabled }} + grpc: + {{- $mergedOtlpGrpcReceiverConfig := mustMergeOverwrite (dict "endpoint" "0.0.0.0:4317") .Values.traces.otlp.grpc.receiverConfig }} + {{- toYaml $mergedOtlpGrpcReceiverConfig | nindent 10 }} + {{- end }} + {{- end }} + {{- if .Values.traces.opencensus.enabled }} + opencensus: + {{- $mergedOpencensusReceiverConfig := mustMergeOverwrite (dict "endpoint" "0.0.0.0:55678") .Values.traces.opencensus.receiverConfig }} + {{- toYaml $mergedOpencensusReceiverConfig | nindent 6 }} + {{- end }} + {{- if .Values.traces.kafka }} + kafka: + {{- toYaml .Values.traces.kafka | nindent 6 }} + {{- end }} + {{- if or .Values.distributor.config.log_received_traces .Values.distributor.config.log_received_spans.enabled }} + log_received_spans: + enabled: {{ or .Values.distributor.config.log_received_traces .Values.distributor.config.log_received_spans.enabled }} + include_all_attributes: {{ .Values.distributor.config.log_received_spans.include_all_attributes }} + filter_by_status_error: {{ .Values.distributor.config.log_received_spans.filter_by_status_error }} + {{- end }} + {{- if .Values.distributor.config.extend_writes }} + extend_writes: {{ .Values.distributor.config.extend_writes }} + {{- end }} + querier: + frontend_worker: + frontend_address: {{ include "tempo.resourceName" (dict "ctx" . "component" "query-frontend-discovery") }}:9095 + {{- if .Values.querier.config.frontend_worker.grpc_client_config }} + grpc_client_config: + {{- toYaml .Values.querier.config.frontend_worker.grpc_client_config | nindent 6 }} + {{- end }} + trace_by_id: + query_timeout: {{ .Values.querier.config.trace_by_id.query_timeout }} + search: + external_endpoints: {{- toYaml .Values.querier.config.search.external_endpoints | nindent 6 }} + query_timeout: {{ .Values.querier.config.search.query_timeout }} + prefer_self: {{ .Values.querier.config.search.prefer_self }} + external_hedge_requests_at: {{ .Values.querier.config.search.external_hedge_requests_at }} + external_hedge_requests_up_to: {{ .Values.querier.config.search.external_hedge_requests_up_to }} + external_backend: {{ .Values.querier.config.search.external_backend }} + {{- if .Values.querier.config.search.google_cloud_run }} + google_cloud_run: + {{- toYaml .Values.querier.config.search.google_cloud_run | nindent 6 }} + {{- end }} + max_concurrent_queries: {{ .Values.querier.config.max_concurrent_queries }} + query_frontend: + max_outstanding_per_tenant: {{ .Values.queryFrontend.config.max_outstanding_per_tenant }} + max_retries: {{ .Values.queryFrontend.config.max_retries }} + search: + target_bytes_per_job: {{ .Values.queryFrontend.config.search.target_bytes_per_job }} + concurrent_jobs: {{ .Values.queryFrontend.config.search.concurrent_jobs }} + trace_by_id: + query_shards: {{ .Values.queryFrontend.config.trace_by_id.query_shards }} + + ingester: + lifecycler: + ring: + replication_factor: {{ .Values.ingester.config.replication_factor }} + {{- if .Values.ingester.zoneAwareReplication.enabled }} + zone_awareness_enabled: true + {{- end }} + kvstore: + store: memberlist + tokens_file_path: /var/tempo/tokens.json + {{- if .Values.ingester.config.trace_idle_period }} + trace_idle_period: {{ .Values.ingester.config.trace_idle_period }} + {{- end }} + {{- if .Values.ingester.config.flush_check_period }} + flush_check_period: {{ .Values.ingester.config.flush_check_period }} + {{- end }} + {{- if .Values.ingester.config.max_block_bytes }} + max_block_bytes: {{ .Values.ingester.config.max_block_bytes }} + {{- end }} + {{- if .Values.ingester.config.max_block_duration }} + max_block_duration: {{ .Values.ingester.config.max_block_duration }} + {{- end }} + {{- if .Values.ingester.config.complete_block_timeout }} + complete_block_timeout: {{ .Values.ingester.config.complete_block_timeout }} + {{- end }} + {{- if .Values.ingester.config.flush_all_on_shutdown }} + flush_all_on_shutdown: {{ .Values.ingester.config.flush_all_on_shutdown }} + {{- end }} + memberlist: + {{- with .Values.memberlist }} + {{- toYaml . | nindent 2 }} + {{- end }} + join_members: + - dns+{{ include "tempo.fullname" . }}-gossip-ring:{{ .Values.memberlist.bind_port }} + overrides: + {{- toYaml .Values.global_overrides | nindent 2 }} + server: + http_listen_port: {{ .Values.server.httpListenPort }} + log_level: {{ .Values.server.logLevel }} + log_format: {{ .Values.server.logFormat }} + grpc_server_max_recv_msg_size: {{ .Values.server.grpc_server_max_recv_msg_size }} + grpc_server_max_send_msg_size: {{ .Values.server.grpc_server_max_send_msg_size }} + http_server_read_timeout: {{ .Values.server.http_server_read_timeout }} + http_server_write_timeout: {{ .Values.server.http_server_write_timeout }} + cache: + {{- toYaml .Values.cache | nindent 2}} + storage: + trace: + {{- if .Values.storage.trace.block.version }} + block: + version: {{.Values.storage.trace.block.version}} + {{- if .Values.storage.trace.block.dedicated_columns}} + parquet_dedicated_columns: + {{ .Values.storage.trace.block.dedicated_columns | toYaml | nindent 8}} + {{- end }} + {{- end }} + pool: + max_workers: {{ .Values.storage.trace.pool.max_workers }} + queue_depth: {{ .Values.storage.trace.pool.queue_depth }} + backend: {{.Values.storage.trace.backend}} + {{- if eq .Values.storage.trace.backend "s3"}} + s3: + {{- toYaml .Values.storage.trace.s3 | nindent 6}} + {{- end }} + {{- if eq .Values.storage.trace.backend "gcs"}} + gcs: + {{- toYaml .Values.storage.trace.gcs | nindent 6}} + {{- end }} + {{- if eq .Values.storage.trace.backend "azure"}} + azure: + {{- toYaml .Values.storage.trace.azure | nindent 6}} + {{- end }} + blocklist_poll: 5m + local: + path: /var/tempo/traces + wal: + path: /var/tempo/wal + +# Set Tempo server configuration +# Refers to https://grafana.com/docs/tempo/latest/configuration/#server +server: + # -- HTTP server listen host + httpListenPort: 3100 + # -- Log level. Can be set to trace, debug, info (default), warn, error, fatal, panic + logLevel: info + # -- Log format. Can be set to logfmt (default) or json. + logFormat: logfmt + # -- Max gRPC message size that can be received + grpc_server_max_recv_msg_size: 4194304 + # -- Max gRPC message size that can be sent + grpc_server_max_send_msg_size: 4194304 + # -- Read timeout for HTTP server + http_server_read_timeout: 30s + # -- Write timeout for HTTP server + http_server_write_timeout: 30s + +# Use this block to configure caches available throughout the application. +# Multiple caches can be created and assigned roles which determine how they are used by Tempo. +# https://grafana.com/docs/tempo/latest/configuration/#cache +cache: + caches: + - memcached: + host: '{{ include "tempo.fullname" . }}-memcached' + service: memcached-client + consistent_hash: true + timeout: 500ms + roles: + - parquet-footer + - bloom + - frontend-search + +# To configure a different storage backend instead of local storage: +# storage: +# trace: +# backend: azure +# azure: +# container_name: +# storage_account_name: +# storage_account_key: +storage: + trace: + # Settings for the block storage backend and buckets. + block: + # -- The supported block versions are specified here https://grafana.com/docs/tempo/latest/configuration/parquet/ + version: null + # -- Lis with dedicated attribute columns (only for vParquet3 or later) + dedicated_columns: [] + # -- The supported storage backends are gcs, s3 and azure, as specified in https://grafana.com/docs/tempo/latest/configuration/#storage + backend: local + # The worker pool is used primarily when finding traces by id, but is also used by other. + pool: + # -- Total number of workers pulling jobs from the queue + max_workers: 400 + # -- Length of job queue. imporatant for querier as it queues a job for every block it has to search + queue_depth: 20000 + # Settings for the Admin client storage backend and buckets. Only valid is enterprise.enabled is true. + admin: + # -- The supported storage backends are gcs, s3 and azure, as specified in https://grafana.com/docs/enterprise-traces/latest/config/reference/#admin_client_config + backend: filesystem + +# Global overrides +global_overrides: + per_tenant_override_config: /runtime-config/overrides.yaml + +# Per tenants overrides +overrides: | + overrides: {} + +# memcached is for all of the Tempo pieces to coordinate with each other. +# you can use your self memcacherd by set enable: false and host + service +memcached: + # -- Specified whether the memcached cachce should be enabled + enabled: true + image: + # -- The Docker registry for the Memcached image. Overrides `global.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `global.image.pullSecrets` + pullSecrets: [] + # -- Memcached Docker image repository + repository: memcached + # -- Memcached Docker image tag + tag: 1.6.23-alpine + # -- Memcached Docker image pull policy + pullPolicy: IfNotPresent + host: memcached + # Number of replicas for memchached + replicas: 1 + # -- Additional CLI args for memcached + extraArgs: [] + # -- Environment variables to add to memcached pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to memcached pods + extraEnvFrom: [] + # -- Labels for memcached pods + podLabels: {} + # -- Annotations for memcached pods + podAnnotations: {} + # -- Resource requests and limits for memcached + resources: {} + # -- topologySpread for memcached pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Defaults to allow skew no more then 1 node per AZ + topologySpreadConstraints: | + - maxSkew: 1 + topologyKey: topology.kubernetes.io/zone + whenUnsatisfiable: ScheduleAnyway + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "memcached") | nindent 6 }} + # -- Affinity for memcached pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "memcached") | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "memcached") | nindent 12 }} + topologyKey: topology.kubernetes.io/zone + service: + # -- Annotations for memcached service + annotations: {} + +memcachedExporter: + # -- Specifies whether the Memcached Exporter should be enabled + enabled: false + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + image: + # -- The Docker registry for the Memcached Exporter image. Overrides `global.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `global.image.pullSecrets` + pullSecrets: [] + # -- Memcached Exporter Docker image repository + repository: prom/memcached-exporter + # -- Memcached Exporter Docker image tag + tag: v0.8.0 + # -- Memcached Exporter Docker image pull policy + pullPolicy: IfNotPresent + # -- Memcached Exporter resource requests and limits + resources: {} + +metaMonitoring: + # ServiceMonitor configuration + serviceMonitor: + # -- If enabled, ServiceMonitor resources for Prometheus Operator are created + enabled: false + # -- Alternative namespace for ServiceMonitor resources + namespace: null + # -- Namespace selector for ServiceMonitor resources + namespaceSelector: {} + # -- ServiceMonitor annotations + annotations: {} + # -- Additional ServiceMonitor labels + labels: {} + # -- ServiceMonitor scrape interval + interval: null + # -- ServiceMonitor scrape timeout in Go duration format (e.g. 15s) + scrapeTimeout: null + # -- ServiceMonitor relabel configs to apply to samples before scraping + # https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig + relabelings: [] + # -- ServiceMonitor metric relabel configs to apply to samples before ingestion + # https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#endpoint + metricRelabelings: [] + # -- ServiceMonitor will use http by default, but you can pick https as well + scheme: http + # -- ServiceMonitor will use these tlsConfig settings to make the health check requests + tlsConfig: null + + # metaMonitoringAgent configures the built in Grafana Agent that can scrape metrics and logs and send them to a local or remote destination + grafanaAgent: + # -- Controls whether to create PodLogs, MetricsInstance, LogsInstance, and GrafanaAgent CRs to scrape the + # ServiceMonitors of the chart and ship metrics and logs to the remote endpoints below. + # Note that you need to configure serviceMonitor in order to have some metrics available. + enabled: false + + # -- Controls whether to install the Grafana Agent Operator and its CRDs. + # Note that helm will not install CRDs if this flag is enabled during an upgrade. + # In that case install the CRDs manually from https://github.com/grafana/agent/tree/main/production/operator/crds + installOperator: false + + logs: + # -- Default destination for logs. The config here is translated to Promtail client + # configuration to write logs to this Loki-compatible remote. Optional. + remote: + # -- Full URL for Loki push endpoint. Usually ends in /loki/api/v1/push + url: '' + + auth: + # -- Used to set X-Scope-OrgID header on requests. Usually not used in combination with username and password. + tenantId: '' + + # -- Basic authentication username. Optional. + username: '' + + # -- The value under key passwordSecretKey in this secret will be used as the basic authentication password. Required only if passwordSecretKey is set. + passwordSecretName: '' + # -- The value under this key in passwordSecretName will be used as the basic authentication password. Required only if passwordSecretName is set. + passwordSecretKey: '' + + # -- Client configurations for the LogsInstance that will scrape Mimir pods. Follows the format of .remote. + additionalClientConfigs: [] + + metrics: + # -- Default destination for metrics. The config here is translated to remote_write + # configuration to push metrics to this Prometheus-compatible remote. Optional. + # Note that you need to configure serviceMonitor in order to have some metrics available. + remote: + # -- Full URL for Prometheus remote-write. Usually ends in /push + url: '' + + # -- Used to add HTTP headers to remote-write requests. + headers: {} + auth: + # -- Basic authentication username. Optional. + username: '' + + # -- The value under key passwordSecretKey in this secret will be used as the basic authentication password. Required only if passwordSecretKey is set. + passwordSecretName: '' + # -- The value under this key in passwordSecretName will be used as the basic authentication password. Required only if passwordSecretName is set. + passwordSecretKey: '' + + # -- Additional remote-write for the MetricsInstance that will scrape Mimir pods. Follows the format of .remote. + additionalRemoteWriteConfigs: [] + + scrapeK8s: + # -- When grafanaAgent.enabled and serviceMonitor.enabled, controls whether to create ServiceMonitors CRs + # for cadvisor, kubelet, and kube-state-metrics. The scraped metrics are reduced to those pertaining to + # Mimir pods only. + enabled: true + + # -- Controls service discovery of kube-state-metrics. + kubeStateMetrics: + namespace: kube-system + labelSelectors: + app.kubernetes.io/name: kube-state-metrics + + # -- Sets the namespace of the resources. Leave empty or unset to use the same namespace as the Helm release. + namespace: '' + + # -- Labels to add to all monitoring.grafana.com custom resources. + # Does not affect the ServiceMonitors for kubernetes metrics; use serviceMonitor.labels for that. + labels: {} + + # -- Annotations to add to all monitoring.grafana.com custom resources. + # Does not affect the ServiceMonitors for kubernetes metrics; use serviceMonitor.annotations for that. + annotations: {} + +# Rules for the Prometheus Operator +prometheusRule: + # -- If enabled, a PrometheusRule resource for Prometheus Operator is created + enabled: false + # -- Alternative namespace for the PrometheusRule resource + namespace: null + # -- PrometheusRule annotations + annotations: {} + # -- Additional PrometheusRule labels + labels: {} + # -- Contents of Prometheus rules file + groups: [] + # - name: loki-rules + # rules: + # - record: job:loki_request_duration_seconds_bucket:sum_rate + # expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job) + # - record: job_route:loki_request_duration_seconds_bucket:sum_rate + # expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route) + # - record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate + # expr: sum(rate(container_cpu_usage_seconds_total[1m])) by (node, namespace, pod, container) + +minio: + enabled: false + mode: standalone + rootUser: grafana-tempo + rootPassword: supersecret + buckets: + # Default Tempo storage bucket. + - name: tempo-traces + policy: none + purge: false + # Bucket for traces storage if enterprise.enabled is true - requires license. + - name: enterprise-traces + policy: none + purge: false + # Admin client bucket if enterprise.enabled is true - requires license. + - name: enterprise-traces-admin + policy: none + purge: false + persistence: + size: 5Gi + resources: + requests: + cpu: 100m + memory: 128Mi + # Changed the mc config path to '/tmp' from '/etc' as '/etc' is only writable by root and OpenShift will not permit this. + configPathmc: '/tmp/minio/mc/' + +# Configuration for the gateway +gateway: + # -- Specifies whether the gateway should be enabled + enabled: false + # -- Number of replicas for the gateway + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + autoscaling: + # -- Enable autoscaling for the gateway + enabled: false + # -- Minimum autoscaling replicas for the gateway + minReplicas: 1 + # -- Maximum autoscaling replicas for the gateway + maxReplicas: 3 + # -- Autoscaling behavior configuration for the gateway + behavior: {} + # -- Target CPU utilisation percentage for the gateway + targetCPUUtilizationPercentage: 60 + # -- Target memory utilisation percentage for the gateway + targetMemoryUtilizationPercentage: + # -- Enable logging of 2xx and 3xx HTTP requests + verboseLogging: true + image: + # -- The Docker registry for the gateway image. Overrides `global.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `global.image.pullSecrets` + pullSecrets: [] + # -- The gateway image repository + repository: nginxinc/nginx-unprivileged + # -- The gateway image tag + tag: 1.19-alpine + # -- The gateway image pull policy + pullPolicy: IfNotPresent + # -- The name of the PriorityClass for gateway pods + priorityClassName: null + # -- Labels for gateway pods + podLabels: {} + # -- Annotations for gateway pods + podAnnotations: {} + # -- Additional CLI args for the gateway + extraArgs: [] + # -- Environment variables to add to the gateway pods + extraEnv: [] + # -- Environment variables from secrets or configmaps to add to the gateway pods + extraEnvFrom: [] + # -- Volumes to add to the gateway pods + extraVolumes: [] + # -- Volume mounts to add to the gateway pods + extraVolumeMounts: [] + # -- Resource requests and limits for the gateway + resources: {} + # -- Grace period to allow the gateway to shutdown before it is killed + terminationGracePeriodSeconds: 30 + # -- topologySpread for gateway pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Defaults to allow skew no more then 1 node per AZ + topologySpreadConstraints: | + - maxSkew: 1 + topologyKey: topology.kubernetes.io/zone + whenUnsatisfiable: ScheduleAnyway + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "gateway") | nindent 6 }} + # -- Affinity for gateway pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Hard node and soft zone anti-affinity + affinity: | + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "gateway") | nindent 10 }} + topologyKey: kubernetes.io/hostname + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "gateway") | nindent 12 }} + topologyKey: topology.kubernetes.io/zone + # -- Node selector for gateway pods + nodeSelector: {} + # -- Tolerations for gateway pods + tolerations: [] + # Gateway service configuration + service: + # -- Port of the gateway service + port: 80 + # -- Type of the gateway service + type: ClusterIP + # -- ClusterIP of the gateway service + clusterIP: null + # -- Node port if service type is NodePort + nodePort: null + # -- Load balancer IPO address if service type is LoadBalancer + loadBalancerIP: null + # -- Annotations for the gateway service + annotations: {} + # -- Labels for gateway service + labels: {} + # -- Additional ports to be opneed on gateway service (e.g. for RPC connections) + additionalPorts: [] + # Gateway ingress configuration + ingress: + # -- Specifies whether an ingress for the gateway should be created + enabled: false + # -- Labels for the gateway ingress + labels: {} + # -- Ingress Class Name. MAY be required for Kubernetes versions >= 1.18 + # ingressClassName: nginx + # -- Annotations for the gateway ingress + annotations: {} + # -- Hosts configuration for the gateway ingress + hosts: + - host: gateway.tempo.example.com + paths: + - path: / + # -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers + # pathType: Prefix + # -- TLS configuration for the gateway ingress + tls: + - secretName: tempo-gateway-tls + hosts: + - gateway.tempo.example.com + # Basic auth configuration + basicAuth: + # -- Enables basic authentication for the gateway + enabled: false + # -- The basic auth username for the gateway + username: null + # -- The basic auth password for the gateway + password: null + # -- Uses the specified username and password to compute a htpasswd using Sprig's `htpasswd` function. + # The value is templated using `tpl`. Override this to use a custom htpasswd, e.g. in case the default causes + # high CPU load. + htpasswd: >- + {{ htpasswd (required "'gateway.basicAuth.username' is required" .Values.gateway.basicAuth.username) (required "'gateway.basicAuth.password' is required" .Values.gateway.basicAuth.password) }} + # -- Existing basic auth secret to use. Must contain '.htpasswd' + existingSecret: null + # Configures the readiness probe for the gateway + readinessProbe: + httpGet: + path: / + port: http-metrics + initialDelaySeconds: 15 + timeoutSeconds: 1 + nginxConfig: + # -- NGINX log format + logFormat: |- + main '$remote_addr - $remote_user [$time_local] $status ' + '"$request" $body_bytes_sent "$http_referer" ' + '"$http_user_agent" "$http_x_forwarded_for"'; + # -- Allows appending custom configuration to the server block + serverSnippet: '' + # -- Allows appending custom configuration to the http block + httpSnippet: '' + # -- Allows overriding the DNS resolver address nginx will use + resolver: '' + # -- Config file contents for Nginx. Passed through the `tpl` function to allow templating + # @default -- See values.yaml + file: | + worker_processes 5; ## Default: 1 + error_log /dev/stderr; + pid /tmp/nginx.pid; + worker_rlimit_nofile 8192; + + events { + worker_connections 4096; ## Default: 1024 + } + + http { + client_body_temp_path /tmp/client_temp; + proxy_temp_path /tmp/proxy_temp_path; + fastcgi_temp_path /tmp/fastcgi_temp; + uwsgi_temp_path /tmp/uwsgi_temp; + scgi_temp_path /tmp/scgi_temp; + + proxy_http_version 1.1; + + default_type application/octet-stream; + log_format {{ .Values.gateway.nginxConfig.logFormat }} + + {{- if .Values.gateway.verboseLogging }} + access_log /dev/stderr main; + {{- else }} + + map $status $loggable { + ~^[23] 0; + default 1; + } + access_log /dev/stderr main if=$loggable; + {{- end }} + + sendfile on; + tcp_nopush on; + {{- if .Values.gateway.nginxConfig.resolver }} + resolver {{ .Values.gateway.nginxConfig.resolver }}; + {{- else }} + resolver {{ .Values.global.dnsService }}.{{ .Values.global.dnsNamespace }}.svc.{{ .Values.global.clusterDomain }}; + {{- end }} + + {{- with .Values.gateway.nginxConfig.httpSnippet }} + {{ . | nindent 2 }} + {{- end }} + + server { + listen 8080; + + {{- if .Values.gateway.basicAuth.enabled }} + auth_basic "Tempo"; + auth_basic_user_file /etc/nginx/secrets/.htpasswd; + {{- end }} + + location = / { + return 200 'OK'; + auth_basic off; + } + + location = /jaeger/api/traces { + proxy_pass http://{{ include "tempo.resourceName" (dict "ctx" . "component" "distributor") }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:14268/api/traces; + } + + location = /zipkin/spans { + proxy_pass http://{{ include "tempo.resourceName" (dict "ctx" . "component" "distributor") }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:9411/spans; + } + + location = /v1/traces { + proxy_pass http://{{ include "tempo.resourceName" (dict "ctx" . "component" "distributor") }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:4318/v1/traces; + } + + location = /otlp/v1/traces { + proxy_pass http://{{ include "tempo.resourceName" (dict "ctx" . "component" "distributor") }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:4318/v1/traces; + } + + location ^~ /api { + proxy_pass http://{{ include "tempo.resourceName" (dict "ctx" . "component" "query-frontend") }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:3100$request_uri; + } + + location = /flush { + proxy_pass http://{{ include "tempo.resourceName" (dict "ctx" . "component" "ingester") }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:3100$request_uri; + } + + location = /shutdown { + proxy_pass http://{{ include "tempo.resourceName" (dict "ctx" . "component" "ingester") }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:3100$request_uri; + } + + location = /distributor/ring { + proxy_pass http://{{ include "tempo.resourceName" (dict "ctx" . "component" "distributor") }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:3100$request_uri; + } + + location = /ingester/ring { + proxy_pass http://{{ include "tempo.resourceName" (dict "ctx" . "component" "distributor") }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:3100$request_uri; + } + + location = /compactor/ring { + proxy_pass http://{{ include "tempo.resourceName" (dict "ctx" . "component" "compactor") }}.{{ .Release.Namespace }}.svc.{{ .Values.global.clusterDomain }}:3100$request_uri; + } + + {{- with .Values.gateway.nginxConfig.serverSnippet }} + {{ . | nindent 4 }} + {{- end }} + } + } + +############################################################################## +# The values in and after the `enterprise:` key configure the enterprise features +enterprise: + # Enable enterprise features. License must be provided, nginx gateway is not installed, instead + # the enterprise gateway is used. + enabled: false + + image: + # -- Grafana Enterprise Metrics container image repository. Note: for Grafana Tempo use the value 'image.repository' + repository: grafana/enterprise-traces + # -- Grafana Enterprise Metrics container image tag. Note: for Grafana Tempo use the value 'image.tag' + tag: v2.4.0 + # Note: pullPolicy and optional pullSecrets are set in toplevel 'image' section, not here + +# In order to use Grafana Enterprise Traces features, you will need to provide the contents of your Grafana Enterprise Traces +# license, either by providing the contents of the license.jwt, or the name Kubernetes Secret that contains your license.jwt. +# To set the license contents, use the flag `--set-file 'license.contents=./license.jwt'` +# To use your own Kubernetes Secret, `--set license.external=true`. +license: + contents: 'NOTAVALIDLICENSE' + external: false + secretName: '{{ include "tempo.resourceName" (dict "ctx" . "component" "license") }}' + +# Settings for the initial admin(istrator) token generator job. Can only be enabled if +# enterprise.enabled is true - requires license. +tokengenJob: + enable: true + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + extraArgs: {} + env: [] + extraEnvFrom: [] + annotations: {} + image: + # -- The Docker registry for the tokengenJob image. Overrides `tempo.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` + pullSecrets: [] + # -- Docker image repository for the tokengenJob image. Overrides `tempo.image.repository` + repository: null + # -- Docker image tag for the tokengenJob image. Overrides `tempo.image.tag` + tag: null + initContainers: [] + # -- The SecurityContext for tokenjobgen containers + containerSecurityContext: + readOnlyRootFilesystem: true + +# Settings for the admin_api service providing authentication and authorization service. +# Can only be enabled if enterprise.enabled is true - requires license. +adminApi: + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + + annotations: {} + service: + annotations: {} + labels: {} + + image: + # -- The Docker registry for the adminApi image. Overrides `tempo.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` + pullSecrets: [] + # -- Docker image repository for the adminApi image. Overrides `tempo.image.repository` + repository: null + # -- Docker image tag for the adminApi image. Overrides `tempo.image.tag` + tag: null + + initContainers: [] + + strategy: + type: RollingUpdate + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + + podLabels: {} + podAnnotations: {} + + nodeSelector: {} + # -- topologySpread for admin-api pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Defaults to allow skew no more then 1 node per AZ + topologySpreadConstraints: | + - maxSkew: 1 + topologyKey: topology.kubernetes.io/zone + whenUnsatisfiable: ScheduleAnyway + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "admin-api") | nindent 6 }} + # -- Affinity for admin-api pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Soft node and soft zone anti-affinity + affinity: | + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "admin-api") | nindent 12 }} + topologyKey: kubernetes.io/hostname + - weight: 75 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "admin-api") | nindent 12 }} + topologyKey: topology.kubernetes.io/zone + + # Pod Disruption Budget + podDisruptionBudget: {} + + securityContext: {} + + # -- The SecurityContext for admin_api containers + containerSecurityContext: + readOnlyRootFilesystem: true + + extraArgs: {} + + persistence: + subPath: + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + + resources: + requests: + cpu: 10m + memory: 32Mi + + terminationGracePeriodSeconds: 60 + + tolerations: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + env: [] + extraEnvFrom: [] + +# Settings for the gateway service providing authentication and authorization via the admin_api. +# Can only be enabled if enterprise.enabled is true - requires license. +enterpriseGateway: + # -- If you want to use your own proxy URLs, set this to false. + useDefaultProxyURLs: true + # -- Proxy URLs defined in this object will be used if useDefaultProxyURLs is set to false. + proxy: {} + replicas: 1 + # -- hostAliases to add + hostAliases: [] + # - ip: 1.2.3.4 + # hostnames: + # - domain.tld + + image: + # -- The Docker registry for the enterpriseGateway image. Overrides `tempo.image.registry` + registry: null + # -- Optional list of imagePullSecrets. Overrides `tempo.image.pullSecrets` + pullSecrets: [] + # -- Docker image repository for the enterpriseGateway image. Overrides `tempo.image.repository` + repository: null + # -- Docker image tag for the enterpriseGateway image. Overrides `tempo.image.tag` + tag: null + + annotations: {} + service: + # -- Port of the enterprise gateway service; if left undefined, the service will listen on the same port as the pod + port: null + # -- Type of the enterprise gateway service + type: ClusterIP + # -- ClusterIP of the enterprise gateway service + clusterIP: null + # -- Load balancer IPO address if service type is LoadBalancer for enterprise gateway service + loadBalancerIP: null + # -- Annotations for the enterprise gateway service + annotations: {} + # -- Labels for enterprise gateway service + labels: {} + + strategy: + type: RollingUpdate + rollingUpdate: + maxSurge: 0 + maxUnavailable: 1 + + podLabels: {} + podAnnotations: {} + + # Pod Disruption Budget + podDisruptionBudget: {} + + nodeSelector: {} + # -- topologySpread for enterprise-gateway pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Defaults to allow skew no more then 1 node per AZ + topologySpreadConstraints: | + - maxSkew: 1 + topologyKey: topology.kubernetes.io/zone + whenUnsatisfiable: ScheduleAnyway + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "enterprise-gateway") | nindent 6 }} + # -- Affinity for enterprise-gateway pods. Passed through `tpl` and, thus, to be configured as string + # @default -- Soft node and soft zone anti-affinity + affinity: | + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - weight: 100 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "enterprise-gateway") | nindent 12 }} + topologyKey: kubernetes.io/hostname + - weight: 75 + podAffinityTerm: + labelSelector: + matchLabels: + {{- include "tempo.selectorLabels" (dict "ctx" . "component" "enterprise-gateway") | nindent 12 }} + topologyKey: topology.kubernetes.io/zone + + securityContext: + {} + + # -- The SecurityContext for gateway containers + containerSecurityContext: + readOnlyRootFilesystem: true + + initContainers: [] + + extraArgs: {} + + persistence: + subPath: + + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 45 + + resources: + requests: + cpu: 10m + memory: 32Mi + + terminationGracePeriodSeconds: 60 + + tolerations: [] + extraContainers: [] + extraVolumes: [] + extraVolumeMounts: [] + env: [] + extraEnvFrom: [] + + # Ingress configuration + ingress: + # -- Specifies whether an ingress for the gateway should be created + enabled: false + # -- Ingress Class Name. MAY be required for Kubernetes versions >= 1.18 + # ingressClassName: gateway + # -- Annotations for the gateway ingress + annotations: {} + # -- Hosts configuration for the gateway ingress + hosts: + - host: gateway.gem.example.com + paths: + - path: / + # -- pathType (e.g. ImplementationSpecific, Prefix, .. etc.) might also be required by some Ingress Controllers + # pathType: Prefix + # -- TLS configuration for the gateway ingress + tls: + - secretName: gem-gateway-tls + hosts: + - gateway.gem.example.com + +# -- Create extra manifests via values. +extraObjects: [] + # - apiVersion: "kubernetes-client.io/v1" + # kind: ExternalSecret + # metadata: + # name: tempo-secrets + # spec: + # backendType: aws + # data: + # - key: secret-access-key + # name: awssm-secret diff --git a/observability/lgtm-distributed/templates/NOTES.txt b/observability/lgtm-distributed/templates/NOTES.txt new file mode 100644 index 0000000..482f35c --- /dev/null +++ b/observability/lgtm-distributed/templates/NOTES.txt @@ -0,0 +1 @@ +Release name should be limited to 25 characters to not exceed the resource name limits of 63 characters. diff --git a/observability/lgtm-distributed/templates/_helpers.tpl b/observability/lgtm-distributed/templates/_helpers.tpl new file mode 100644 index 0000000..4c1d430 --- /dev/null +++ b/observability/lgtm-distributed/templates/_helpers.tpl @@ -0,0 +1,18 @@ + {{/* +Create a default fully qualified app name without trimming it at all. +If release name contains chart name it will be used as a full name. +This value is essentially the same as "mimir.fullname" in the upstream chart. +*/}} +{{- define "mimir.fullname" -}} +{{- if .Values.mimir.fullnameOverride -}} +{{- .Values.mimir.fullnameOverride | trunc 25 | trimSuffix "-" -}} +{{- else -}} +{{- $name := .Values.mimir.nameOverride | default ( include "mimir.infixName" . ) | trunc 25 | trimSuffix "-" -}} +{{- $releasename := .Release.Name | trunc 25 | trimSuffix "-" -}} +{{- if contains $name .Release.Name -}} +{{- $releasename -}} +{{- else -}} +{{- printf "%s-%s" $releasename $name -}} +{{- end -}} +{{- end -}} +{{- end -}} diff --git a/observability/lgtm-distributed/values.yaml b/observability/lgtm-distributed/values.yaml new file mode 100644 index 0000000..1bc71d4 --- /dev/null +++ b/observability/lgtm-distributed/values.yaml @@ -0,0 +1,112 @@ +--- +grafana: + # -- Deploy Grafana if enabled. See [upstream readme](https://github.com/grafana/helm-charts/tree/main/charts/grafana#configuration) for full values reference. + enabled: true + + # -- Grafana data sources config. Connects to all three by default + datasources: + datasources.yaml: + apiVersion: 1 + # -- Datasources linked to the Grafana instance. Override if you disable any components. + datasources: + # https://grafana.com/docs/grafana/latest/datasources/loki/#provision-the-loki-data-source + - name: Loki + uid: loki + type: loki + url: http://{{ .Release.Name }}-loki-gateway + isDefault: false + # https://grafana.com/docs/grafana/latest/datasources/prometheus/#provision-the-data-source + - name: Mimir + uid: prom + type: prometheus + url: http://{{ .Release.Name }}-mimir-nginx/prometheus + isDefault: true + # https://grafana.com/docs/grafana/latest/datasources/tempo/configure-tempo-data-source/#provision-the-data-source + - name: Tempo + uid: tempo + type: tempo + url: http://{{ .Release.Name }}-tempo-query-frontend:3100 + isDefault: false + jsonData: + tracesToLogsV2: + datasourceUid: loki + lokiSearch: + datasourceUid: loki + tracesToMetrics: + datasourceUid: prom + serviceMap: + datasourceUid: prom + +loki: + # -- Deploy Loki if enabled. See [upstream readme](https://github.com/grafana/helm-charts/tree/main/charts/loki-distributed#values) for full values reference. + enabled: true + +# -- Mimir chart values. Resources are set to a minimum by default. +mimir: + # -- Deploy Mimir if enabled. See [upstream values.yaml](https://github.com/grafana/mimir/blob/main/operations/helm/charts/mimir-distributed/values.yaml) for full values reference. + enabled: true + alertmanager: + resources: + requests: + cpu: 20m + compactor: + resources: + requests: + cpu: 20m + distributor: + resources: + requests: + cpu: 20m + ingester: + replicas: 2 + zoneAwareReplication: + enabled: false + resources: + requests: + cpu: 20m + overrides_exporter: + resources: + requests: + cpu: 20m + querier: + replicas: 1 + resources: + requests: + cpu: 20m + query_frontend: + resources: + requests: + cpu: 20m + query_scheduler: + replicas: 1 + resources: + requests: + cpu: 20m + ruler: + resources: + requests: + cpu: 20m + store_gateway: + zoneAwareReplication: + enabled: false + resources: + requests: + cpu: 20m + minio: + resources: + requests: + cpu: 20m + rollout_operator: + resources: + requests: + cpu: 20m + +tempo: + # -- Deploy Tempo if enabled. See [upstream readme](https://github.com/grafana/helm-charts/blob/main/charts/tempo-distributed/README.md#values) for full values reference. + enabled: true + ingester: + replicas: 1 + +grafana-oncall: + # -- Deploy Grafana OnCall if enabled. See [upstream values.yaml](https://github.com/grafana/oncall/blob/dev/helm/oncall/values.yaml) for full values reference. + enabled: false diff --git a/observability/persistent-volumes.yaml b/observability/persistent-volumes.yaml new file mode 100644 index 0000000..691595c --- /dev/null +++ b/observability/persistent-volumes.yaml @@ -0,0 +1,82 @@ +apiVersion: v1 +kind: PersistentVolume +metadata: + name: lgtm-minio-pv +spec: + capacity: + storage: 5Gi + accessModes: + - ReadWriteOnce + persistentVolumeReclaimPolicy: Retain + hostPath: + path: "/mnt/data/lgtm-minio" + +--- +apiVersion: v1 +kind: PersistentVolume +metadata: + name: storage-lgtm-mimir-alertmanager-0-pv +spec: + capacity: + storage: 1Gi + accessModes: + - ReadWriteOnce + persistentVolumeReclaimPolicy: Retain + hostPath: + path: "/mnt/data/storage-lgtm-mimir-alertmanager-0" + +--- +apiVersion: v1 +kind: PersistentVolume +metadata: + name: storage-lgtm-mimir-compactor-0-pv +spec: + capacity: + storage: 2Gi + accessModes: + - ReadWriteOnce + persistentVolumeReclaimPolicy: Retain + hostPath: + path: "/mnt/data/storage-lgtm-mimir-compactor-0" + +--- +apiVersion: v1 +kind: PersistentVolume +metadata: + name: storage-lgtm-mimir-ingester-0-pv +spec: + capacity: + storage: 2Gi + accessModes: + - ReadWriteOnce + persistentVolumeReclaimPolicy: Retain + hostPath: + path: "/mnt/data/storage-lgtm-mimir-ingester-0" + +--- +apiVersion: v1 +kind: PersistentVolume +metadata: + name: storage-lgtm-mimir-ingester-1-pv +spec: + capacity: + storage: 2Gi + accessModes: + - ReadWriteOnce + persistentVolumeReclaimPolicy: Retain + hostPath: + path: "/mnt/data/storage-lgtm-mimir-ingester-1" + +--- +apiVersion: v1 +kind: PersistentVolume +metadata: + name: storage-lgtm-mimir-store-gateway-0-pv +spec: + capacity: + storage: 2Gi + accessModes: + - ReadWriteOnce + persistentVolumeReclaimPolicy: Retain + hostPath: + path: "/mnt/data/storage-lgtm-mimir-store-gateway-0" diff --git a/observability/promtail/.helmignore b/observability/promtail/.helmignore new file mode 100644 index 0000000..50af031 --- /dev/null +++ b/observability/promtail/.helmignore @@ -0,0 +1,22 @@ +# Patterns to ignore when building packages. +# This supports shell glob matching, relative path matching, and +# negation (prefixed with !). Only one pattern per line. +.DS_Store +# Common VCS dirs +.git/ +.gitignore +.bzr/ +.bzrignore +.hg/ +.hgignore +.svn/ +# Common backup files +*.swp +*.bak +*.tmp +*~ +# Various IDEs +.project +.idea/ +*.tmproj +.vscode/ diff --git a/observability/promtail/Chart.yaml b/observability/promtail/Chart.yaml new file mode 100644 index 0000000..fce1f93 --- /dev/null +++ b/observability/promtail/Chart.yaml @@ -0,0 +1,17 @@ +apiVersion: v2 +appVersion: 3.0.0 +description: Promtail is an agent which ships the contents of local logs to a Loki + instance +home: https://grafana.com/loki +icon: https://raw.githubusercontent.com/grafana/loki/master/docs/sources/logo.png +maintainers: +- email: lokiproject@googlegroups.com + name: Loki Maintainers +- name: unguiculus +name: promtail +sources: +- https://github.com/grafana/loki +- https://grafana.com/oss/loki/ +- https://grafana.com/docs/loki/latest/ +type: application +version: 6.16.6 diff --git a/observability/promtail/README.md b/observability/promtail/README.md new file mode 100644 index 0000000..ed9aa7a --- /dev/null +++ b/observability/promtail/README.md @@ -0,0 +1,347 @@ +# promtail + +![Version: 6.16.6](https://img.shields.io/badge/Version-6.16.6-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 3.0.0](https://img.shields.io/badge/AppVersion-3.0.0-informational?style=flat-square) + +Promtail is an agent which ships the contents of local logs to a Loki instance + +## Source Code + +* +* +* + +## Chart Repo + +Add the following repo to use the chart: + +```console +helm repo add grafana https://grafana.github.io/helm-charts +``` + +## Upgrading + +A major chart version change indicates that there is an incompatible breaking change needing manual actions. + +### From Chart Versions >= 3.0.0 + +* Customizeable initContainer added. + +### From Chart Versions < 3.0.0 + +#### Notable Changes + +* Helm 3 is required +* Labels have been updated to follow the official Kubernetes [label recommendations](https://kubernetes.io/docs/concepts/overview/working-with-objects/common-labels/) +* The default scrape configs have been updated to take new and old labels into consideration +* The config file must be specified as string which can be templated. + See below for details +* The config file is now stored in a Secret and no longer in a ConfigMap because it may contain sensitive data, such as basic auth credentials + +Due to the label changes, an existing installation cannot be upgraded without manual interaction. +There are basically two options: + +##### Option 1 + +Uninstall the old release and re-install the new one. +There will be no data loss. +Promtail will cleanly shut down and write the `positions.yaml`. +The new release which will pick up again from the existing `positions.yaml`. + +##### Option 2 + +* Add new selector labels to the existing pods: + + ``` + kubectl label pods -n -l app=promtail,release= app.kubernetes.io/name=promtail app.kubernetes.io/instance= + ``` + +* Perform a non-cascading deletion of the DaemonSet which will keep the pods running: + + ``` + kubectl delete daemonset -n -l app=promtail,release= --cascade=false + ``` + +* Perform a regular Helm upgrade on the existing release. + The new DaemonSet will pick up the existing pods and perform a rolling upgrade. + +## Values + +| Key | Type | Default | Description | +|-----|------|---------|-------------| +| affinity | object | `{}` | Affinity configuration for pods | +| annotations | object | `{}` | Annotations for the DaemonSet | +| automountServiceAccountToken | bool | `true` | Automatically mount API credentials for a particular Pod | +| config | object | See `values.yaml` | Section for crafting Promtails config file. The only directly relevant value is `config.file` which is a templated string that references the other values and snippets below this key. | +| config.clients | list | See `values.yaml` | The config of clients of the Promtail server Must be reference in `config.file` to configure `clients` | +| config.enableTracing | bool | `false` | The config to enable tracing | +| config.enabled | bool | `true` | Enable Promtail config from Helm chart Set `configmap.enabled: true` and this to `false` to manage your own Promtail config See default config in `values.yaml` | +| config.file | string | See `values.yaml` | Config file contents for Promtail. Must be configured as string. It is templated so it can be assembled from reusable snippets in order to avoid redundancy. | +| config.logFormat | string | `"logfmt"` | The log format of the Promtail server Must be reference in `config.file` to configure `server.log_format` Valid formats: `logfmt, json` See default config in `values.yaml` | +| config.logLevel | string | `"info"` | The log level of the Promtail server Must be reference in `config.file` to configure `server.log_level` See default config in `values.yaml` | +| config.positions | object | `{"filename":"/run/promtail/positions.yaml"}` | Configures where Promtail will save it's positions file, to resume reading after restarts. Must be referenced in `config.file` to configure `positions` | +| config.serverPort | int | `3101` | The port of the Promtail server Must be reference in `config.file` to configure `server.http_listen_port` See default config in `values.yaml` | +| config.snippets | object | See `values.yaml` | A section of reusable snippets that can be reference in `config.file`. Custom snippets may be added in order to reduce redundancy. This is especially helpful when multiple `kubernetes_sd_configs` are use which usually have large parts in common. | +| config.snippets.extraLimitsConfig | string | empty | You can put here any keys that will be directly added to the config file's 'limits_config' block. | +| config.snippets.extraRelabelConfigs | list | `[]` | You can put here any additional relabel_configs to "kubernetes-pods" job | +| config.snippets.extraScrapeConfigs | string | empty | You can put here any additional scrape configs you want to add to the config file. | +| config.snippets.extraServerConfigs | string | empty | You can put here any keys that will be directly added to the config file's 'server' block. | +| configmap.enabled | bool | `false` | If enabled, promtail config will be created as a ConfigMap instead of a secret | +| containerSecurityContext | object | `{"allowPrivilegeEscalation":false,"capabilities":{"drop":["ALL"]},"readOnlyRootFilesystem":true}` | The security context for containers | +| daemonset.autoscaling.controlledResources | list | `[]` | List of resources that the vertical pod autoscaler can control. Defaults to cpu and memory | +| daemonset.autoscaling.enabled | bool | `false` | Creates a VerticalPodAutoscaler for the daemonset | +| daemonset.autoscaling.maxAllowed | object | `{}` | Defines the max allowed resources for the pod | +| daemonset.autoscaling.minAllowed | object | `{}` | Defines the min allowed resources for the pod | +| daemonset.enabled | bool | `true` | Deploys Promtail as a DaemonSet | +| defaultVolumeMounts | list | See `values.yaml` | Default volume mounts. Corresponds to `volumes`. | +| defaultVolumes | list | See `values.yaml` | Default volumes that are mounted into pods. In most cases, these should not be changed. Use `extraVolumes`/`extraVolumeMounts` for additional custom volumes. | +| deployment.autoscaling.enabled | bool | `false` | Creates a HorizontalPodAutoscaler for the deployment | +| deployment.autoscaling.maxReplicas | int | `10` | | +| deployment.autoscaling.minReplicas | int | `1` | | +| deployment.autoscaling.targetCPUUtilizationPercentage | int | `80` | | +| deployment.autoscaling.targetMemoryUtilizationPercentage | string | `nil` | | +| deployment.enabled | bool | `false` | Deploys Promtail as a Deployment | +| deployment.replicaCount | int | `1` | | +| deployment.strategy | object | `{"type":"RollingUpdate"}` | Set deployment object update strategy | +| enableServiceLinks | bool | `true` | Configure enableServiceLinks in pod | +| extraArgs | list | `[]` | | +| extraContainers | object | `{}` | | +| extraEnv | list | `[]` | Extra environment variables. Set up tracing enviroment variables here if .Values.config.enableTracing is true. Tracing currently only support configure via environment variables. See: https://grafana.com/docs/loki/latest/clients/promtail/configuration/#tracing_config https://www.jaegertracing.io/docs/1.16/client-features/ | +| extraEnvFrom | list | `[]` | Extra environment variables from secrets or configmaps | +| extraObjects | list | `[]` | Extra K8s manifests to deploy | +| extraPorts | object | `{}` | Configure additional ports and services. For each configured port, a corresponding service is created. See values.yaml for details | +| extraVolumeMounts | list | `[]` | | +| extraVolumes | list | `[]` | | +| fullnameOverride | string | `nil` | Overrides the chart's computed fullname | +| global.imagePullSecrets | list | `[]` | Allow parent charts to override registry credentials | +| global.imageRegistry | string | `""` | Allow parent charts to override registry hostname | +| hostAliases | list | `[]` | hostAliases to add | +| hostNetwork | string | `nil` | Controls whether the pod has the `hostNetwork` flag set. | +| httpPathPrefix | string | `""` | Base path to server all API routes fro | +| image.pullPolicy | string | `"IfNotPresent"` | Docker image pull policy | +| image.registry | string | `"docker.io"` | The Docker registry | +| image.repository | string | `"grafana/promtail"` | Docker image repository | +| image.tag | string | `""` | Overrides the image tag whose default is the chart's appVersion | +| imagePullSecrets | list | `[]` | Image pull secrets for Docker images | +| initContainer | list | `[]` | | +| livenessProbe | object | `{}` | Liveness probe | +| nameOverride | string | `nil` | Overrides the chart's name | +| namespace | string | `nil` | The name of the Namespace to deploy If not set, `.Release.Namespace` is used | +| networkPolicy.enabled | bool | `false` | Specifies whether Network Policies should be created | +| networkPolicy.k8sApi.cidrs | list | `[]` | Specifies specific network CIDRs you want to limit access to | +| networkPolicy.k8sApi.port | int | `8443` | Specify the k8s API endpoint port | +| networkPolicy.metrics.cidrs | list | `[]` | Specifies specific network CIDRs which are allowed to access the metrics port. In case you use namespaceSelector, you also have to specify your kubelet networks here. The metrics ports are also used for probes. | +| networkPolicy.metrics.namespaceSelector | object | `{}` | Specifies the namespaces which are allowed to access the metrics port | +| networkPolicy.metrics.podSelector | object | `{}` | Specifies the Pods which are allowed to access the metrics port. As this is cross-namespace communication, you also neeed the namespaceSelector. | +| nodeSelector | object | `{}` | Node selector for pods | +| podAnnotations | object | `{}` | Pod annotations | +| podLabels | object | `{}` | Pod labels | +| podSecurityContext | object | `{"runAsGroup":0,"runAsUser":0}` | The security context for pods | +| podSecurityPolicy | object | See `values.yaml` | PodSecurityPolicy configuration. | +| priorityClassName | string | `nil` | The name of the PriorityClass | +| rbac.create | bool | `true` | Specifies whether RBAC resources are to be created | +| rbac.pspEnabled | bool | `false` | Specifies whether a PodSecurityPolicy is to be created | +| readinessProbe | object | See `values.yaml` | Readiness probe | +| resources | object | `{}` | Resource requests and limits | +| secret.annotations | object | `{}` | Annotations for the Secret | +| secret.labels | object | `{}` | Labels for the Secret | +| service.annotations | object | `{}` | Annotations for the service | +| service.enabled | bool | `false` | | +| service.labels | object | `{}` | Labels for the service | +| serviceAccount.annotations | object | `{}` | Annotations for the service account | +| serviceAccount.automountServiceAccountToken | bool | `true` | Automatically mount a ServiceAccount's API credentials | +| serviceAccount.create | bool | `true` | Specifies whether a ServiceAccount should be created | +| serviceAccount.imagePullSecrets | list | `[]` | Image pull secrets for the service account | +| serviceAccount.name | string | `nil` | The name of the ServiceAccount to use. If not set and `create` is true, a name is generated using the fullname template | +| serviceMonitor.annotations | object | `{}` | ServiceMonitor annotations | +| serviceMonitor.enabled | bool | `false` | If enabled, ServiceMonitor resources for Prometheus Operator are created | +| serviceMonitor.interval | string | `nil` | ServiceMonitor scrape interval | +| serviceMonitor.labels | object | `{}` | Additional ServiceMonitor labels | +| serviceMonitor.metricRelabelings | list | `[]` | ServiceMonitor relabel configs to apply to samples as the last step before ingestion https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig (defines `metric_relabel_configs`) | +| serviceMonitor.namespace | string | `nil` | Alternative namespace for ServiceMonitor resources | +| serviceMonitor.namespaceSelector | object | `{}` | Namespace selector for ServiceMonitor resources | +| serviceMonitor.prometheusRule | object | `{"additionalLabels":{},"enabled":false,"rules":[]}` | Prometheus rules will be deployed for alerting purposes | +| serviceMonitor.relabelings | list | `[]` | ServiceMonitor relabel configs to apply to samples before scraping https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig (defines `relabel_configs`) | +| serviceMonitor.scheme | string | `"http"` | ServiceMonitor will use http by default, but you can pick https as well | +| serviceMonitor.scrapeTimeout | string | `nil` | ServiceMonitor scrape timeout in Go duration format (e.g. 15s) | +| serviceMonitor.targetLabels | list | `[]` | ServiceMonitor will add labels from the service to the Prometheus metric https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#servicemonitorspec | +| serviceMonitor.tlsConfig | string | `nil` | ServiceMonitor will use these tlsConfig settings to make the health check requests | +| sidecar.configReloader.config.serverPort | int | `9533` | The port of the config-reloader server | +| sidecar.configReloader.containerSecurityContext | object | `{"allowPrivilegeEscalation":false,"capabilities":{"drop":["ALL"]},"readOnlyRootFilesystem":true}` | The security context for containers for sidecar config-reloader | +| sidecar.configReloader.enabled | bool | `false` | | +| sidecar.configReloader.extraArgs | list | `[]` | | +| sidecar.configReloader.extraEnv | list | `[]` | Extra environment variables for sidecar config-reloader | +| sidecar.configReloader.extraEnvFrom | list | `[]` | Extra environment variables from secrets or configmaps for sidecar config-reloader | +| sidecar.configReloader.image.pullPolicy | string | `"IfNotPresent"` | Docker image pull policy for sidecar config-reloader | +| sidecar.configReloader.image.registry | string | `"ghcr.io"` | The Docker registry for sidecar config-reloader | +| sidecar.configReloader.image.repository | string | `"jimmidyson/configmap-reload"` | Docker image repository for sidecar config-reloader | +| sidecar.configReloader.image.tag | string | `"v0.12.0"` | Docker image tag for sidecar config-reloader | +| sidecar.configReloader.livenessProbe | object | `{}` | Liveness probe for sidecar config-reloader | +| sidecar.configReloader.readinessProbe | object | `{}` | Readiness probe for sidecar config-reloader | +| sidecar.configReloader.resources | object | `{}` | Resource requests and limits for sidecar config-reloader | +| sidecar.configReloader.serviceMonitor.enabled | bool | `true` | | +| tolerations | list | `[{"effect":"NoSchedule","key":"node-role.kubernetes.io/master","operator":"Exists"},{"effect":"NoSchedule","key":"node-role.kubernetes.io/control-plane","operator":"Exists"}]` | Tolerations for pods. By default, pods will be scheduled on master/control-plane nodes. | +| updateStrategy | object | `{}` | The update strategy for the DaemonSet | + +## Configuration + +The config file for Promtail must be configured as string. +This is necessary because the contents are passed through the `tpl` function. +With this, the file can be templated and assembled from reusable YAML snippets. +It is common to have multiple `kubernetes_sd_configs` that, in turn, usually need the same `pipeline_stages`. +Thus, extracting reusable snippets helps reduce redundancy and avoid copy/paste errors. +See `values.yaml´ for details. +Also, the following examples make use of this feature. + +For additional reference, please refer to Promtail's docs: + +https://grafana.com/docs/loki/latest/clients/promtail/configuration/ + +### Syslog Support + +```yaml +extraPorts: + syslog: + name: tcp-syslog + containerPort: 1514 + service: + port: 80 + type: LoadBalancer + externalTrafficPolicy: Local + loadBalancerIP: 123.234.123.234 + +config: + snippets: + extraScrapeConfigs: | + # Add an additional scrape config for syslog + - job_name: syslog + syslog: + listen_address: 0.0.0.0:{{ .Values.extraPorts.syslog.containerPort }} + labels: + job: syslog + relabel_configs: + - source_labels: + - __syslog_message_hostname + target_label: hostname + + # example label values: kernel, CRON, kubelet + - source_labels: + - __syslog_message_app_name + target_label: app + + # example label values: debug, notice, informational, warning, error + - source_labels: + - __syslog_message_severity + target_label: level +``` + +Find additional source labels in the Promtail's docs: + +https://grafana.com/docs/loki/latest/clients/promtail/configuration/#syslog + +### Journald Support + +```yaml +config: + snippets: + extraScrapeConfigs: | + # Add an additional scrape config for syslog + - job_name: journal + journal: + path: /var/log/journal + max_age: 12h + labels: + job: systemd-journal + relabel_configs: + - source_labels: + - __journal__hostname + target_label: hostname + + # example label values: kubelet.service, containerd.service + - source_labels: + - __journal__systemd_unit + target_label: unit + + # example label values: debug, notice, info, warning, error + - source_labels: + - __journal_priority_keyword + target_label: level + +# Mount journal directory and machine-id file into promtail pods +extraVolumes: + - name: journal + hostPath: + path: /var/log/journal + - name: machine-id + hostPath: + path: /etc/machine-id + +extraVolumeMounts: + - name: journal + mountPath: /var/log/journal + readOnly: true + - name: machine-id + mountPath: /etc/machine-id + readOnly: true +``` + +Find additional configuration options in Promtail's docs: + +https://grafana.com/docs/loki/latest/clients/promtail/configuration/#journal + +More journal source labels can be found here https://www.freedesktop.org/software/systemd/man/systemd.journal-fields.html. +> Note that each message from the journal may have a different set of fields and software may write an arbitrary set of custom fields for their logged messages. [(related issue)](https://github.com/grafana/loki/issues/2048#issuecomment-626234611) + +The machine-id needs to be available in the container as it is required for scraping. +This is described in Promtail's scraping docs: + +https://grafana.com/docs/loki/latest/clients/promtail/scraping/#journal-scraping-linux-only + +### Push API Support + +```yaml +extraPorts: + httpPush: + name: http-push + containerPort: 3500 + grpcPush: + name: grpc-push + containerPort: 3600 + +config: + file: | + server: + log_level: {{ .Values.config.logLevel }} + http_listen_port: {{ .Values.config.serverPort }} + + clients: + - url: {{ .Values.config.lokiAddress }} + + positions: + filename: /run/promtail/positions.yaml + + scrape_configs: + {{- tpl .Values.config.snippets.scrapeConfigs . | nindent 2 }} + + - job_name: push1 + loki_push_api: + server: + http_listen_port: {{ .Values.extraPorts.httpPush.containerPort }} + grpc_listen_port: {{ .Values.extraPorts.grpcPush.containerPort }} + labels: + pushserver: push1 +``` + +### Customize client config options + +By default, promtail send logs scraped to `loki` server at `http://loki-gateway/loki/api/v1/push`. +If you want to customize clients or add additional options to `loki`, please use the `clients` section. For example, to enable HTTP basic auth and include OrgID header, you can use: + +```yaml +config: + clients: + - url: http://loki.server/loki/api/v1/push + tenant_id: 1 + basic_auth: + username: loki + password: secret +``` diff --git a/observability/promtail/README.md.gotmpl b/observability/promtail/README.md.gotmpl new file mode 100644 index 0000000..01387a5 --- /dev/null +++ b/observability/promtail/README.md.gotmpl @@ -0,0 +1,229 @@ +{{ template "chart.header" . }} + +{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }} + +{{ template "chart.description" . }} + +{{ template "chart.sourcesSection" . }} + +{{ template "chart.requirementsSection" . }} + +## Chart Repo + +Add the following repo to use the chart: + +```console +helm repo add grafana https://grafana.github.io/helm-charts +``` + +## Upgrading + +A major chart version change indicates that there is an incompatible breaking change needing manual actions. + +### From Chart Versions >= 3.0.0 + +* Customizeable initContainer added. + +### From Chart Versions < 3.0.0 + +#### Notable Changes + +* Helm 3 is required +* Labels have been updated to follow the official Kubernetes [label recommendations](https://kubernetes.io/docs/concepts/overview/working-with-objects/common-labels/) +* The default scrape configs have been updated to take new and old labels into consideration +* The config file must be specified as string which can be templated. + See below for details +* The config file is now stored in a Secret and no longer in a ConfigMap because it may contain sensitive data, such as basic auth credentials + +Due to the label changes, an existing installation cannot be upgraded without manual interaction. +There are basically two options: + +##### Option 1 + +Uninstall the old release and re-install the new one. +There will be no data loss. +Promtail will cleanly shut down and write the `positions.yaml`. +The new release which will pick up again from the existing `positions.yaml`. + +##### Option 2 + +* Add new selector labels to the existing pods: + + ``` + kubectl label pods -n -l app=promtail,release= app.kubernetes.io/name=promtail app.kubernetes.io/instance= + ``` + +* Perform a non-cascading deletion of the DaemonSet which will keep the pods running: + + ``` + kubectl delete daemonset -n -l app=promtail,release= --cascade=false + ``` + +* Perform a regular Helm upgrade on the existing release. + The new DaemonSet will pick up the existing pods and perform a rolling upgrade. + +{{ template "chart.valuesSection" . }} + +## Configuration + +The config file for Promtail must be configured as string. +This is necessary because the contents are passed through the `tpl` function. +With this, the file can be templated and assembled from reusable YAML snippets. +It is common to have multiple `kubernetes_sd_configs` that, in turn, usually need the same `pipeline_stages`. +Thus, extracting reusable snippets helps reduce redundancy and avoid copy/paste errors. +See `values.yaml´ for details. +Also, the following examples make use of this feature. + +For additional reference, please refer to Promtail's docs: + +https://grafana.com/docs/loki/latest/clients/promtail/configuration/ + +### Syslog Support + +```yaml +extraPorts: + syslog: + name: tcp-syslog + containerPort: 1514 + service: + port: 80 + type: LoadBalancer + externalTrafficPolicy: Local + loadBalancerIP: 123.234.123.234 + +config: + snippets: + extraScrapeConfigs: | + # Add an additional scrape config for syslog + - job_name: syslog + syslog: + listen_address: 0.0.0.0:{{"{{"}} .Values.extraPorts.syslog.containerPort {{"}}"}} + labels: + job: syslog + relabel_configs: + - source_labels: + - __syslog_message_hostname + target_label: hostname + + # example label values: kernel, CRON, kubelet + - source_labels: + - __syslog_message_app_name + target_label: app + + # example label values: debug, notice, informational, warning, error + - source_labels: + - __syslog_message_severity + target_label: level +``` + +Find additional source labels in the Promtail's docs: + +https://grafana.com/docs/loki/latest/clients/promtail/configuration/#syslog + +### Journald Support + +```yaml +config: + snippets: + extraScrapeConfigs: | + # Add an additional scrape config for syslog + - job_name: journal + journal: + path: /var/log/journal + max_age: 12h + labels: + job: systemd-journal + relabel_configs: + - source_labels: + - __journal__hostname + target_label: hostname + + # example label values: kubelet.service, containerd.service + - source_labels: + - __journal__systemd_unit + target_label: unit + + # example label values: debug, notice, info, warning, error + - source_labels: + - __journal_priority_keyword + target_label: level + +# Mount journal directory and machine-id file into promtail pods +extraVolumes: + - name: journal + hostPath: + path: /var/log/journal + - name: machine-id + hostPath: + path: /etc/machine-id + +extraVolumeMounts: + - name: journal + mountPath: /var/log/journal + readOnly: true + - name: machine-id + mountPath: /etc/machine-id + readOnly: true +``` + +Find additional configuration options in Promtail's docs: + +https://grafana.com/docs/loki/latest/clients/promtail/configuration/#journal + +More journal source labels can be found here https://www.freedesktop.org/software/systemd/man/systemd.journal-fields.html. +> Note that each message from the journal may have a different set of fields and software may write an arbitrary set of custom fields for their logged messages. [(related issue)](https://github.com/grafana/loki/issues/2048#issuecomment-626234611) + +The machine-id needs to be available in the container as it is required for scraping. +This is described in Promtail's scraping docs: + +https://grafana.com/docs/loki/latest/clients/promtail/scraping/#journal-scraping-linux-only + +### Push API Support + +```yaml +extraPorts: + httpPush: + name: http-push + containerPort: 3500 + grpcPush: + name: grpc-push + containerPort: 3600 + +config: + file: | + server: + log_level: {{"{{"}} .Values.config.logLevel {{"}}"}} + http_listen_port: {{"{{"}} .Values.config.serverPort {{"}}"}} + + clients: + - url: {{"{{"}} .Values.config.lokiAddress {{"}}"}} + + positions: + filename: /run/promtail/positions.yaml + + scrape_configs: + {{"{{"}}- tpl .Values.config.snippets.scrapeConfigs . | nindent 2 {{"}}"}} + + - job_name: push1 + loki_push_api: + server: + http_listen_port: {{"{{"}} .Values.extraPorts.httpPush.containerPort {{"}}"}} + grpc_listen_port: {{"{{"}} .Values.extraPorts.grpcPush.containerPort {{"}}"}} + labels: + pushserver: push1 +``` + +### Customize client config options + +By default, promtail send logs scraped to `loki` server at `http://loki-gateway/loki/api/v1/push`. +If you want to customize clients or add additional options to `loki`, please use the `clients` section. For example, to enable HTTP basic auth and include OrgID header, you can use: + +```yaml +config: + clients: + - url: http://loki.server/loki/api/v1/push + tenant_id: 1 + basic_auth: + username: loki + password: secret +``` diff --git a/observability/promtail/ci/autoscaled-deployment-values.yaml b/observability/promtail/ci/autoscaled-deployment-values.yaml new file mode 100644 index 0000000..1dfdf81 --- /dev/null +++ b/observability/promtail/ci/autoscaled-deployment-values.yaml @@ -0,0 +1,6 @@ +daemonset: + enabled: false +deployment: + enabled: true + autoscaling: + enabled: true diff --git a/observability/promtail/ci/default-values.yaml b/observability/promtail/ci/default-values.yaml new file mode 100644 index 0000000..e69de29 diff --git a/observability/promtail/ci/deployment-values.yaml b/observability/promtail/ci/deployment-values.yaml new file mode 100644 index 0000000..4acd40e --- /dev/null +++ b/observability/promtail/ci/deployment-values.yaml @@ -0,0 +1,4 @@ +daemonset: + enabled: false +deployment: + enabled: true diff --git a/observability/promtail/ci/netpol-values.yaml b/observability/promtail/ci/netpol-values.yaml new file mode 100644 index 0000000..70d31af --- /dev/null +++ b/observability/promtail/ci/netpol-values.yaml @@ -0,0 +1,53 @@ +extraPorts: + syslog: + name: tcp-syslog + containerPort: 1514 + service: + port: 1234 + type: NodePort + httpPush: + name: http-push + containerPort: 3500 + grpcPush: + name: grpc-push + containerPort: 3600 + +config: + snippets: + extraScrapeConfigs: | + - job_name: syslog + syslog: + listen_address: 0.0.0.0:{{ .Values.extraPorts.syslog.containerPort }} + labels: + job: syslog + relabel_configs: + - source_labels: + - __syslog_message_hostname + target_label: host + + - job_name: push1 + loki_push_api: + server: + http_listen_port: {{ .Values.extraPorts.httpPush.containerPort }} + grpc_listen_port: {{ .Values.extraPorts.grpcPush.containerPort }} + labels: + pushserver: push1 + +networkPolicy: + # -- Specifies whether Network Policies should be created + enabled: true + metrics: + # -- Specifies the Pods which are allowed to access the metrics port. + # As this is cross-namespace communication, you also neeed the namespaceSelector. + podSelector: {} + # -- Specifies the namespaces which are allowed to access the metrics port + namespaceSelector: {} + # -- Specifies specific network CIDRs which are allowed to access the metrics port. + # In case you use namespaceSelector, you also have to specify your kubelet networks here. + # The metrics ports are also used for probes. + cidrs: [] + k8sApi: + # -- Specify the k8s API endpoint port + port: 8443 + # -- Specifies specific network CIDRs you want to limit access to + cidrs: [] diff --git a/observability/promtail/ci/service-values.yaml b/observability/promtail/ci/service-values.yaml new file mode 100644 index 0000000..52226e9 --- /dev/null +++ b/observability/promtail/ci/service-values.yaml @@ -0,0 +1,37 @@ +extraPorts: + syslog: + name: tcp-syslog + containerPort: 1514 + service: + port: 1234 + type: NodePort + httpPush: + name: http-push + containerPort: 3500 + ingress: + hosts: + - chart-example.local + grpcPush: + name: grpc-push + containerPort: 3600 + +config: + snippets: + extraScrapeConfigs: | + - job_name: syslog + syslog: + listen_address: 0.0.0.0:{{ .Values.extraPorts.syslog.containerPort }} + labels: + job: syslog + relabel_configs: + - source_labels: + - __syslog_message_hostname + target_label: host + + - job_name: push1 + loki_push_api: + server: + http_listen_port: {{ .Values.extraPorts.httpPush.containerPort }} + grpc_listen_port: {{ .Values.extraPorts.grpcPush.containerPort }} + labels: + pushserver: push1 diff --git a/observability/promtail/templates/NOTES.txt b/observability/promtail/templates/NOTES.txt new file mode 100644 index 0000000..01bf66b --- /dev/null +++ b/observability/promtail/templates/NOTES.txt @@ -0,0 +1,15 @@ +*********************************************************************** + Welcome to Grafana Promtail + Chart version: {{ .Chart.Version }} + Promtail version: {{ .Values.image.tag | default .Chart.AppVersion }} +*********************************************************************** + +Verify the application is working by running these commands: + +{{- if .Values.daemonset.enabled }} +* kubectl --namespace {{ .Release.Namespace }} port-forward daemonset/{{ include "promtail.fullname" . }} {{ .Values.config.serverPort }} +{{- end }} +{{- if .Values.deployment.enabled }} +* kubectl --namespace {{ .Release.Namespace }} port-forward deployment/{{ include "promtail.fullname" . }} {{ .Values.config.serverPort }} +{{- end }} +* curl http://127.0.0.1:{{ .Values.config.serverPort }}/metrics diff --git a/observability/promtail/templates/_helpers.tpl b/observability/promtail/templates/_helpers.tpl new file mode 100644 index 0000000..8892e51 --- /dev/null +++ b/observability/promtail/templates/_helpers.tpl @@ -0,0 +1,116 @@ +{{/* +Expand the name of the chart. +*/}} +{{- define "promtail.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "promtail.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default .Chart.Name .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "promtail.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }} +{{- end }} + +{{/* +Common labels +*/}} +{{- define "promtail.labels" -}} +helm.sh/chart: {{ include "promtail.chart" . }} +{{ include "promtail.selectorLabels" . }} +{{- if or .Chart.AppVersion .Values.image.tag }} +app.kubernetes.io/version: {{ mustRegexReplaceAllLiteral "@sha.*" .Values.image.tag "" | default .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- end }} + +{{/* +Selector labels +*/}} +{{- define "promtail.selectorLabels" -}} +app.kubernetes.io/name: {{ include "promtail.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end }} + +{{/* +Create the name of the namespace +*/}} +{{- define "promtail.namespaceName" -}} +{{- default .Release.Namespace .Values.namespace }} +{{- end }} + +{{/* +Create the name of the service account +*/}} +{{- define "promtail.serviceAccountName" -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "promtail.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} + +{{/* +Configure enableServiceLinks in pod +*/}} +{{- define "promtail.enableServiceLinks" -}} +{{- if semverCompare ">=1.13-0" .Capabilities.KubeVersion.GitVersion }} +{{- if or (.Values.enableServiceLinks) (eq (.Values.enableServiceLinks | toString) "") }} +{{- printf "enableServiceLinks: true" }} +{{- else }} +{{- printf "enableServiceLinks: false" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Return the appropriate apiVersion for ingress. +*/}} +{{- define "promtail.ingress.apiVersion" -}} +{{- if and ($.Capabilities.APIVersions.Has "networking.k8s.io/v1") (semverCompare ">= 1.19-0" .Capabilities.KubeVersion.Version) }} +{{- print "networking.k8s.io/v1" }} +{{- else if $.Capabilities.APIVersions.Has "networking.k8s.io/v1beta1" }} +{{- print "networking.k8s.io/v1beta1" }} +{{- else }} +{{- print "extensions/v1beta1" }} +{{- end }} +{{- end }} + +{{/* +Return if ingress is stable. +*/}} +{{- define "promtail.ingress.isStable" -}} +{{- eq (include "promtail.ingress.apiVersion" .) "networking.k8s.io/v1" }} +{{- end }} + +{{/* +Return if ingress supports ingressClassName. +*/}} +{{- define "promtail.ingress.supportsIngressClassName" -}} +{{- or (eq (include "promtail.ingress.isStable" .) "true") (and (eq (include "promtail.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) }} +{{- end }} + +{{/* +Return if ingress supports pathType. +*/}} +{{- define "promtail.ingress.supportsPathType" -}} +{{- or (eq (include "promtail.ingress.isStable" .) "true") (and (eq (include "promtail.ingress.apiVersion" .) "networking.k8s.io/v1beta1") (semverCompare ">= 1.18-0" .Capabilities.KubeVersion.Version)) }} +{{- end }} diff --git a/observability/promtail/templates/_pod.tpl b/observability/promtail/templates/_pod.tpl new file mode 100644 index 0000000..6c75908 --- /dev/null +++ b/observability/promtail/templates/_pod.tpl @@ -0,0 +1,172 @@ +{{/* +Pod template used in Daemonset and Deployment +*/}} +{{- define "promtail.podTemplate" -}} +metadata: + labels: + {{- include "promtail.selectorLabels" . | nindent 4 }} + {{- with .Values.podLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} + annotations: + {{- if not .Values.sidecar.configReloader.enabled }} + checksum/config: {{ tpl .Values.config.file . | sha256sum }} + {{- end }} + {{- with .Values.podAnnotations }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + serviceAccountName: {{ include "promtail.serviceAccountName" . }} + automountServiceAccountToken: {{ .Values.automountServiceAccountToken }} + {{- include "promtail.enableServiceLinks" . | nindent 2 }} + {{- with .Values.hostNetwork }} + hostNetwork: {{ . }} + {{- end }} + {{- with .Values.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.initContainer }} + initContainers: + {{- tpl (toYaml .) $ | nindent 4 }} + {{- end }} + {{- with .Values.global.imagePullSecrets | default .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.hostAliases }} + hostAliases: + {{- toYaml . | nindent 4 }} + {{- end }} + securityContext: + {{- toYaml .Values.podSecurityContext | nindent 4 }} + containers: + - name: promtail + image: "{{ .Values.global.imageRegistry | default .Values.image.registry }}/{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "-config.file=/etc/promtail/promtail.yaml" + {{- if .Values.sidecar.configReloader.enabled }} + - "-server.enable-runtime-reload" + {{- end }} + {{- with .Values.extraArgs }} + {{- toYaml . | nindent 8 }} + {{- end }} + volumeMounts: + - name: config + mountPath: /etc/promtail + {{- with .Values.defaultVolumeMounts }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.extraVolumeMounts }} + {{- toYaml . | nindent 8 }} + {{- end }} + env: + - name: HOSTNAME + valueFrom: + fieldRef: + fieldPath: spec.nodeName + {{- with .Values.extraEnv }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 8 }} + {{- end }} + ports: + - name: http-metrics + containerPort: {{ .Values.config.serverPort }} + protocol: TCP + {{- range $key, $values := .Values.extraPorts }} + - name: {{ .name | default $key }} + containerPort: {{ $values.containerPort }} + protocol: {{ $values.protocol | default "TCP" }} + {{- end }} + securityContext: + {{- toYaml .Values.containerSecurityContext | nindent 8 }} + {{- with .Values.livenessProbe }} + livenessProbe: + {{- tpl (toYaml .) $ | nindent 8 }} + {{- end }} + {{- with .Values.readinessProbe }} + readinessProbe: + {{- tpl (toYaml .) $ | nindent 8 }} + {{- end }} + {{- with .Values.resources }} + resources: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.sidecar.configReloader.enabled }} + - name: config-reloader + image: "{{ .Values.sidecar.configReloader.image.registry }}/{{ .Values.sidecar.configReloader.image.repository }}:{{ .Values.sidecar.configReloader.image.tag }}" + imagePullPolicy: {{ .Values.sidecar.configReloader.image.pullPolicy }} + args: + - '-web.listen-address=:{{ .Values.sidecar.configReloader.config.serverPort }}' + - '-volume-dir=/etc/promtail/' + - '-webhook-method=GET' + - '-webhook-url=http://127.0.0.1:{{ .Values.config.serverPort }}/reload' + {{- range .Values.sidecar.configReloader.extraArgs }} + - {{ . }} + {{- end }} + ports: + - name: reloader + containerPort: {{ .Values.sidecar.configReloader.config.serverPort }} + protocol: TCP + {{- with .Values.sidecar.configReloader.extraEnv }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.sidecar.configReloader.extraEnvFrom }} + envFrom: + {{- toYaml . | nindent 8 }} + {{- end }} + securityContext: + {{- toYaml .Values.sidecar.configReloader.containerSecurityContext | nindent 8 }} + {{- with .Values.sidecar.configReloader.livenessProbe }} + livenessProbe: + {{- tpl (toYaml .) $ | nindent 8 }} + {{- end }} + {{- with .Values.sidecar.configReloader.readinessProbe }} + readinessProbe: + {{- tpl (toYaml .) $ | nindent 8 }} + {{- end }} + {{- with .Values.sidecar.configReloader.resources }} + resources: + {{- toYaml . | nindent 8 }} + {{- end }} + volumeMounts: + - name: config + mountPath: /etc/promtail + {{- end }} + {{- if .Values.extraContainers }} + {{- range $name, $values := .Values.extraContainers }} + - name: {{ $name }} + {{ toYaml $values | nindent 6 }} + {{- end }} + {{- end }} + {{- with .Values.affinity }} + affinity: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.nodeSelector }} + nodeSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: + {{- toYaml . | nindent 4 }} + {{- end }} + volumes: + - name: config + {{- if .Values.configmap.enabled }} + configMap: + name: {{ include "promtail.fullname" . }} + {{- else }} + secret: + secretName: {{ include "promtail.fullname" . }} + {{- end }} + {{- with .Values.defaultVolumes }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.extraVolumes }} + {{- tpl (toYaml .) $ | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/promtail/templates/clusterrole.yaml b/observability/promtail/templates/clusterrole.yaml new file mode 100644 index 0000000..4702e60 --- /dev/null +++ b/observability/promtail/templates/clusterrole.yaml @@ -0,0 +1,21 @@ +{{- if .Values.rbac.create }} +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ include "promtail.fullname" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +rules: + - apiGroups: + - "" + resources: + - nodes + - nodes/proxy + - services + - endpoints + - pods + verbs: + - get + - watch + - list +{{- end }} diff --git a/observability/promtail/templates/clusterrolebinding.yaml b/observability/promtail/templates/clusterrolebinding.yaml new file mode 100644 index 0000000..e92bf9a --- /dev/null +++ b/observability/promtail/templates/clusterrolebinding.yaml @@ -0,0 +1,16 @@ +{{- if .Values.rbac.create }} +kind: ClusterRoleBinding +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: {{ include "promtail.fullname" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +subjects: + - kind: ServiceAccount + name: {{ include "promtail.serviceAccountName" . }} + namespace: {{ include "promtail.namespaceName" . }} +roleRef: + kind: ClusterRole + name: {{ include "promtail.fullname" . }} + apiGroup: rbac.authorization.k8s.io +{{- end }} diff --git a/observability/promtail/templates/configmap.yaml b/observability/promtail/templates/configmap.yaml new file mode 100644 index 0000000..3b7e247 --- /dev/null +++ b/observability/promtail/templates/configmap.yaml @@ -0,0 +1,12 @@ +{{- if and .Values.config.enabled .Values.configmap.enabled }} +apiVersion: v1 +kind: ConfigMap +metadata: + name: {{ include "promtail.fullname" . }} + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +data: + promtail.yaml: | + {{- tpl .Values.config.file . | nindent 4 }} +{{- end }} diff --git a/observability/promtail/templates/daemonset.yaml b/observability/promtail/templates/daemonset.yaml new file mode 100644 index 0000000..18fd42c --- /dev/null +++ b/observability/promtail/templates/daemonset.yaml @@ -0,0 +1,24 @@ +{{- if .Values.daemonset.enabled }} +apiVersion: apps/v1 +kind: DaemonSet +metadata: + name: {{ include "promtail.fullname" . }} + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if .Values.revisionHistoryLimit }} + revisionHistoryLimit: {{ .Values.revisionHistoryLimit }} + {{- end }} + selector: + matchLabels: + {{- include "promtail.selectorLabels" . | nindent 6 }} + updateStrategy: + {{- toYaml .Values.updateStrategy | nindent 4 }} + template: + {{- include "promtail.podTemplate" . | nindent 4 }} +{{- end }} diff --git a/observability/promtail/templates/deployment.yaml b/observability/promtail/templates/deployment.yaml new file mode 100644 index 0000000..3409f63 --- /dev/null +++ b/observability/promtail/templates/deployment.yaml @@ -0,0 +1,29 @@ +{{- if .Values.deployment.enabled }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "promtail.fullname" . }} + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} + {{- with .Values.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if not .Values.deployment.autoscaling.enabled }} + replicas: {{ .Values.deployment.replicaCount }} + {{- end }} + {{- if .Values.revisionHistoryLimit }} + revisionHistoryLimit: {{ .Values.revisionHistoryLimit }} + {{- end }} + {{- with .Values.deployment.strategy }} + strategy: + {{- toYaml . | trim | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "promtail.selectorLabels" . | nindent 6 }} + template: + {{- include "promtail.podTemplate" . | nindent 4 }} +{{- end }} diff --git a/observability/promtail/templates/extra-manifests.yaml b/observability/promtail/templates/extra-manifests.yaml new file mode 100644 index 0000000..a9bb3b6 --- /dev/null +++ b/observability/promtail/templates/extra-manifests.yaml @@ -0,0 +1,4 @@ +{{ range .Values.extraObjects }} +--- +{{ tpl (toYaml .) $ }} +{{ end }} diff --git a/observability/promtail/templates/hpa.yaml b/observability/promtail/templates/hpa.yaml new file mode 100644 index 0000000..a53bbc7 --- /dev/null +++ b/observability/promtail/templates/hpa.yaml @@ -0,0 +1,43 @@ +{{- if and .Values.deployment.enabled .Values.deployment.autoscaling.enabled }} +apiVersion: {{ if or (.Capabilities.APIVersions.Has "autoscaling/v2/HorizontalPodAutoscaler") (semverCompare ">=1.23" .Capabilities.KubeVersion.Version) -}} +autoscaling/v2 +{{- else -}} +autoscaling/v2beta2 +{{- end }} +kind: HorizontalPodAutoscaler +metadata: + name: {{ include "promtail.fullname" . }} + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +spec: + scaleTargetRef: + apiVersion: apps/v1 + kind: Deployment + name: {{ include "promtail.fullname" . }} + {{- with .Values.deployment.autoscaling }} + minReplicas: {{ .minReplicas }} + maxReplicas: {{ .maxReplicas }} + metrics: + {{- with .targetCPUUtilizationPercentage }} + - type: Resource + resource: + name: cpu + target: + type: Utilization + averageUtilization: {{ . }} + {{- end }} + {{- with .targetMemoryUtilizationPercentage }} + - type: Resource + resource: + name: memory + target: + type: Utilization + averageUtilization: {{ . }} + {{- end }} + {{- end }} + {{- with .Values.deployment.autoscaling.behavior }} + behavior: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/promtail/templates/ingress.yaml b/observability/promtail/templates/ingress.yaml new file mode 100644 index 0000000..e8a8892 --- /dev/null +++ b/observability/promtail/templates/ingress.yaml @@ -0,0 +1,62 @@ +{{ range $key, $values := .Values.extraPorts }} +{{ if .ingress }} +{{ $ingressApiIsStable := eq (include "promtail.ingress.isStable" $ ) "true" }} +{{ $ingressSupportsIngressClassName := eq (include "promtail.ingress.supportsIngressClassName" $ ) "true" }} +{{ $ingressSupportsPathType := eq (include "promtail.ingress.supportsPathType" $ ) "true" }} +--- +apiVersion: {{ include "promtail.ingress.apiVersion" $ }} +kind: Ingress +metadata: + name: {{ include "promtail.fullname" $ }}-{{ $key | lower }} + labels: + {{- include "promtail.labels" $ | nindent 4 }} + {{- with .ingress.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- if and $ingressSupportsIngressClassName .ingress.ingressClassName }} + ingressClassName: {{ .ingress.ingressClassName }} + {{- end -}} + {{- if .ingress.tls }} + tls: + {{- range .ingress.tls }} + - hosts: + {{- range .hosts }} + - {{ . | quote }} + {{- end }} + {{- with .secretName }} + secretName: {{ . }} + {{- end }} + {{- end }} + {{- end }} + rules: + {{- range .ingress.hosts }} + - host: {{ . | quote }} + http: + paths: + - path: {{ $values.ingress.path | default "/" }} + {{- if $ingressSupportsPathType }} + pathType: Prefix + {{- end }} + backend: + {{- if $ingressApiIsStable }} + service: + name: {{ include "promtail.fullname" $ }}-{{ $key | lower }} + port: + {{- if $values.service }} + number: {{ $values.service.port }} + {{ else }} + number: {{ $values.containerPort }} + {{ end }} + {{- else }} + serviceName: {{ include "promtail.fullname" $ }}-{{ $key | lower }} + {{- if $values.service }} + servicePort: {{ $values.service.port }} + {{ else }} + number: {{ $values.containerPort }} + {{ end }} + {{- end }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/promtail/templates/networkpolicy.yaml b/observability/promtail/templates/networkpolicy.yaml new file mode 100644 index 0000000..9467df5 --- /dev/null +++ b/observability/promtail/templates/networkpolicy.yaml @@ -0,0 +1,123 @@ +{{- if .Values.networkPolicy.enabled }} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ template "promtail.name" . }}-namespace-only + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +spec: + podSelector: {} + policyTypes: + - Ingress + - Egress + egress: + - to: + - podSelector: {} + ingress: + - from: + - podSelector: {} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ template "promtail.name" . }}-egress-dns + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +spec: + podSelector: + matchLabels: + {{- include "promtail.selectorLabels" . | nindent 6 }} + policyTypes: + - Egress + egress: + - ports: + - port: 53 + protocol: UDP + to: + - namespaceSelector: {} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ template "promtail.name" . }}-egress-k8s-api + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +spec: + podSelector: + matchLabels: + {{- include "promtail.selectorLabels" . | nindent 6 }} + policyTypes: + - Egress + egress: + - ports: + - port: {{ .Values.networkPolicy.k8sApi.port }} + protocol: TCP + {{- if len .Values.networkPolicy.k8sApi.cidrs }} + to: + {{- range $cidr := .Values.networkPolicy.k8sApi.cidrs }} + - ipBlock: + cidr: {{ $cidr }} + {{- end }} + {{- end }} + +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ template "promtail.name" . }}-ingress-metrics + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +spec: + podSelector: + matchLabels: + {{- include "promtail.selectorLabels" . | nindent 6 }} + policyTypes: + - Ingress + ingress: + - ports: + - port: http-metrics + protocol: TCP + {{- if len .Values.networkPolicy.metrics.cidrs }} + from: + {{- range $cidr := .Values.networkPolicy.metrics.cidrs }} + - ipBlock: + cidr: {{ $cidr }} + {{- end }} + {{- if .Values.networkPolicy.metrics.namespaceSelector }} + - namespaceSelector: + {{- toYaml .Values.networkPolicy.metrics.namespaceSelector | nindent 12 }} + {{- if .Values.networkPolicy.metrics.podSelector }} + podSelector: + {{- toYaml .Values.networkPolicy.metrics.podSelector | nindent 12 }} + {{- end }} + {{- end }} + {{- end }} + +{{- if .Values.extraPorts }} +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + name: {{ template "promtail.name" . }}-egress-extra-ports + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +spec: + podSelector: + matchLabels: + {{- include "promtail.selectorLabels" . | nindent 6 }} + policyTypes: + - Egress + egress: + - ports: + {{- range $extraPortConfig := .Values.extraPorts }} + - port: {{ $extraPortConfig.containerPort }} + protocol: {{ $extraPortConfig.protocol }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/promtail/templates/podsecuritypolicy.yaml b/observability/promtail/templates/podsecuritypolicy.yaml new file mode 100644 index 0000000..a229388 --- /dev/null +++ b/observability/promtail/templates/podsecuritypolicy.yaml @@ -0,0 +1,10 @@ +{{- if and (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") .Values.rbac.create .Values.rbac.pspEnabled }} +apiVersion: policy/v1beta1 +kind: PodSecurityPolicy +metadata: + name: {{ include "promtail.fullname" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +spec: + {{- toYaml .Values.podSecurityPolicy | nindent 2 }} +{{- end }} diff --git a/observability/promtail/templates/prometheus-rules.yaml b/observability/promtail/templates/prometheus-rules.yaml new file mode 100644 index 0000000..6ec3f26 --- /dev/null +++ b/observability/promtail/templates/prometheus-rules.yaml @@ -0,0 +1,21 @@ +{{- if and .Values.serviceMonitor.enabled .Values.serviceMonitor.prometheusRule.enabled -}} +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: {{ include "promtail.fullname" . }} + {{- with .Values.serviceMonitor.prometheusRule.namespace }} + namespace: {{ . | quote }} + {{- end }} + labels: + {{- include "promtail.labels" . | nindent 4 }} + {{- with .Values.serviceMonitor.prometheusRule.additionalLabels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: +{{- if .Values.serviceMonitor.prometheusRule.rules }} + groups: + - name: {{ template "promtail.fullname" . }} + rules: + {{- toYaml .Values.serviceMonitor.prometheusRule.rules | nindent 4 }} +{{- end }} +{{- end }} diff --git a/observability/promtail/templates/role.yaml b/observability/promtail/templates/role.yaml new file mode 100644 index 0000000..a193b3f --- /dev/null +++ b/observability/promtail/templates/role.yaml @@ -0,0 +1,18 @@ +{{- if and (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") .Values.rbac.create .Values.rbac.pspEnabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: {{ include "promtail.fullname" . }}-psp + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +rules: + - apiGroups: + - policy + resources: + - podsecuritypolicies + verbs: + - use + resourceNames: + - {{ include "promtail.fullname" . }} +{{- end }} diff --git a/observability/promtail/templates/rolebinding.yaml b/observability/promtail/templates/rolebinding.yaml new file mode 100644 index 0000000..0527fdc --- /dev/null +++ b/observability/promtail/templates/rolebinding.yaml @@ -0,0 +1,16 @@ +{{- if and (.Capabilities.APIVersions.Has "policy/v1beta1/PodSecurityPolicy") .Values.rbac.create .Values.rbac.pspEnabled }} +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: {{ include "promtail.fullname" . }}-psp + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: {{ include "promtail.fullname" . }}-psp +subjects: + - kind: ServiceAccount + name: {{ include "promtail.serviceAccountName" . }} +{{- end }} diff --git a/observability/promtail/templates/secret.yaml b/observability/promtail/templates/secret.yaml new file mode 100644 index 0000000..f5d61ac --- /dev/null +++ b/observability/promtail/templates/secret.yaml @@ -0,0 +1,19 @@ +{{- if not .Values.configmap.enabled }} +apiVersion: v1 +kind: Secret +metadata: + name: {{ include "promtail.fullname" . }} + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} + {{- with .Values.secret.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.secret.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +stringData: + promtail.yaml: | + {{- tpl .Values.config.file . | nindent 4 }} +{{- end }} diff --git a/observability/promtail/templates/service-extra.yaml b/observability/promtail/templates/service-extra.yaml new file mode 100644 index 0000000..c3ec3fc --- /dev/null +++ b/observability/promtail/templates/service-extra.yaml @@ -0,0 +1,52 @@ +{{- range $key, $values := .Values.extraPorts }} +--- +apiVersion: v1 +kind: Service +metadata: + name: {{ include "promtail.fullname" $ }}-{{ $key | lower }} + namespace: {{ include "promtail.namespaceName" $ }} + labels: + {{- include "promtail.labels" $ | nindent 4 }} + {{- with $values.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with $values.service }} + type: {{ .type | default "ClusterIP" }} + {{- with .clusterIP }} + clusterIP: {{ . }} + {{- end }} + {{- with .loadBalancerIP }} + loadBalancerIP: {{ . }} + {{- end }} + {{- with .loadBalancerSourceRanges }} + loadBalancerSourceRanges: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .externalIPs }} + externalIPs: + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .externalTrafficPolicy }} + externalTrafficPolicy: {{ . }} + {{- end }} + {{- end }} + ports: + - name: {{ .name | default $key }} + targetPort: {{ .name | default $key }} + protocol: {{ $values.protocol | default "TCP" }} + {{- if $values.service }} + port: {{ $values.service.port | default $values.containerPort }} + {{- if $values.service.nodePort }} + nodePort: {{ $values.service.nodePort }} + {{- end }} + {{- else }} + port: {{ $values.containerPort }} + {{- end }} + selector: + {{- include "promtail.selectorLabels" $ | nindent 4 }} +{{- end }} diff --git a/observability/promtail/templates/service-metrics.yaml b/observability/promtail/templates/service-metrics.yaml new file mode 100644 index 0000000..631d906 --- /dev/null +++ b/observability/promtail/templates/service-metrics.yaml @@ -0,0 +1,25 @@ +{{- if or .Values.serviceMonitor.enabled .Values.service.enabled }} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "promtail.fullname" . }}-metrics + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} + {{- with .Values.service.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} + {{- with .Values.service.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + clusterIP: None + ports: + - name: http-metrics + port: {{ .Values.config.serverPort }} + targetPort: http-metrics + protocol: TCP + selector: + {{- include "promtail.selectorLabels" . | nindent 4 }} +{{- end }} diff --git a/observability/promtail/templates/serviceaccount.yaml b/observability/promtail/templates/serviceaccount.yaml new file mode 100644 index 0000000..8d799ff --- /dev/null +++ b/observability/promtail/templates/serviceaccount.yaml @@ -0,0 +1,18 @@ +{{- if .Values.serviceAccount.create }} +apiVersion: v1 +kind: ServiceAccount +metadata: + name: {{ include "promtail.serviceAccountName" . }} + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} + {{- with .Values.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} +automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }} +{{- with .Values.serviceAccount.imagePullSecrets }} +imagePullSecrets: + {{- toYaml . | nindent 2 }} +{{- end }} +{{- end }} diff --git a/observability/promtail/templates/servicemonitor.yaml b/observability/promtail/templates/servicemonitor.yaml new file mode 100644 index 0000000..f73ff64 --- /dev/null +++ b/observability/promtail/templates/servicemonitor.yaml @@ -0,0 +1,83 @@ +{{- with .Values.serviceMonitor }} +{{- if .enabled }} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "promtail.fullname" $ }} + {{- with .namespace }} + namespace: {{ . }} + {{- end }} + {{- with .annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} + labels: + {{- include "promtail.labels" $ | nindent 4 }} + {{- with .labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + {{- with .namespaceSelector }} + namespaceSelector: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "promtail.selectorLabels" $ | nindent 6 }} + endpoints: + - port: http-metrics + {{- with $.Values.httpPathPrefix }} + path: {{ printf "%s/metrics" . }} + {{- end }} + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if and $.Values.sidecar.configReloader.enabled $.Values.sidecar.configReloader.serviceMonitor.enabled }} + - port: reloader + path: "/metrics" + {{- with .interval }} + interval: {{ . }} + {{- end }} + {{- with .scrapeTimeout }} + scrapeTimeout: {{ . }} + {{- end }} + {{- with .relabelings }} + relabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .metricRelabelings }} + metricRelabelings: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .scheme }} + scheme: {{ . }} + {{- end }} + {{- with .tlsConfig }} + tlsConfig: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- end }} + {{- with .targetLabels }} + targetLabels: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} +{{- end }} diff --git a/observability/promtail/templates/verticalpodautoscaler.yaml b/observability/promtail/templates/verticalpodautoscaler.yaml new file mode 100644 index 0000000..b68c5bd --- /dev/null +++ b/observability/promtail/templates/verticalpodautoscaler.yaml @@ -0,0 +1,40 @@ +{{- if and (.Capabilities.APIVersions.Has "autoscaling.k8s.io/v1") .Values.daemonset.enabled .Values.daemonset.autoscaling.enabled }} +apiVersion: autoscaling.k8s.io/v1 +kind: VerticalPodAutoscaler +metadata: + name: {{ include "promtail.fullname" . }} + namespace: {{ include "promtail.namespaceName" . }} + labels: + {{- include "promtail.labels" . | nindent 4 }} +spec: + {{- with .Values.daemonset.autoscaling.recommenders }} + recommenders: + {{- toYaml . | nindent 4 }} + {{- end }} + resourcePolicy: + containerPolicies: + - containerName: promtail + {{- with .Values.daemonset.autoscaling.controlledResources }} + controlledResources: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if .Values.daemonset.autoscaling.controlledValues }} + controlledValues: {{ .Values.daemonset.autoscaling.controlledValues }} + {{- end }} + {{- if .Values.daemonset.autoscaling.maxAllowed }} + maxAllowed: + {{ toYaml .Values.daemonset.autoscaling.maxAllowed | nindent 8 }} + {{- end }} + {{- if .Values.daemonset.autoscaling.minAllowed }} + minAllowed: + {{ toYaml .Values.daemonset.autoscaling.minAllowed | nindent 8 }} + {{- end }} + targetRef: + apiVersion: apps/v1 + kind: DaemonSet + name: {{ include "promtail.fullname" . }} + {{- with .Values.daemonset.autoscaling.updatePolicy }} + updatePolicy: + {{- toYaml . | nindent 4 }} + {{- end }} +{{- end }} diff --git a/observability/promtail/values.yaml b/observability/promtail/values.yaml new file mode 100644 index 0000000..3048cde --- /dev/null +++ b/observability/promtail/values.yaml @@ -0,0 +1,647 @@ +# -- Overrides the chart's name +nameOverride: null + +# -- Overrides the chart's computed fullname +fullnameOverride: null + +global: + # -- Allow parent charts to override registry hostname + imageRegistry: "" + # -- Allow parent charts to override registry credentials + imagePullSecrets: [] + +daemonset: + # -- Deploys Promtail as a DaemonSet + enabled: true + autoscaling: + # -- Creates a VerticalPodAutoscaler for the daemonset + enabled: false + + # Recommender responsible for generating recommendation for the object. + # List should be empty (then the default recommender will generate the recommendation) + # or contain exactly one recommender. + # recommenders: + # - name: custom-recommender-performance + + # -- List of resources that the vertical pod autoscaler can control. Defaults to cpu and memory + controlledResources: [] + + # Specifies which resource values should be controlled: RequestsOnly or RequestsAndLimits. + # controlledValues: RequestsAndLimits + + # -- Defines the max allowed resources for the pod + maxAllowed: {} + # cpu: 200m + # memory: 100Mi + # -- Defines the min allowed resources for the pod + minAllowed: {} + # cpu: 200m + # memory: 100Mi + + # updatePolicy: + # Specifies minimal number of replicas which need to be alive for VPA Updater to attempt pod eviction + # minReplicas: 1 + # Specifies whether recommended updates are applied when a Pod is started and whether recommended updates + # are applied during the life of a Pod. Possible values are "Off", "Initial", "Recreate", and "Auto". + # updateMode: Auto + +deployment: + # -- Deploys Promtail as a Deployment + enabled: false + replicaCount: 1 + autoscaling: + # -- Creates a HorizontalPodAutoscaler for the deployment + enabled: false + minReplicas: 1 + maxReplicas: 10 + targetCPUUtilizationPercentage: 80 + targetMemoryUtilizationPercentage: + # behavior: {} + + # -- Set deployment object update strategy + strategy: + type: RollingUpdate + +service: + enabled: false + # -- Labels for the service + labels: {} + # -- Annotations for the service + annotations: {} + +secret: + # -- Labels for the Secret + labels: {} + # -- Annotations for the Secret + annotations: {} + +configmap: + # -- If enabled, promtail config will be created as a ConfigMap instead of a secret + enabled: false + +initContainer: + # -- Specifies whether the init container for setting inotify max user instances is to be enabled + - name: init + # -- Docker registry, image and tag for the init container image + image: docker.io/busybox:1.33 + # -- Docker image pull policy for the init container image + imagePullPolicy: IfNotPresent + # -- The inotify max user instances to configure + command: + - sh + - -c + - sysctl -w fs.inotify.max_user_instances=65000 + securityContext: + privileged: true + +image: + # -- The Docker registry + registry: docker.io + # -- Docker image repository + repository: grafana/promtail + # -- Overrides the image tag whose default is the chart's appVersion + tag: "" + # -- Docker image pull policy + pullPolicy: IfNotPresent + +# -- Image pull secrets for Docker images +imagePullSecrets: [] + +# -- hostAliases to add +hostAliases: [] +# - ip: 1.2.3.4 +# hostnames: +# - domain.tld + +# -- Controls whether the pod has the `hostNetwork` flag set. +hostNetwork: null + +# -- Annotations for the DaemonSet +annotations: {} + +# -- Number of old history to retain to allow rollback (If not set, default Kubernetes value is set to 10) +# revisionHistoryLimit: 1 + +# -- The update strategy for the DaemonSet +updateStrategy: {} + +# -- Pod labels +podLabels: {} + +# -- Pod annotations +podAnnotations: {} +# prometheus.io/scrape: "true" +# prometheus.io/port: "http-metrics" + +# -- The name of the PriorityClass +priorityClassName: null + +# -- Liveness probe +livenessProbe: {} + +# -- Readiness probe +# @default -- See `values.yaml` +readinessProbe: + failureThreshold: 5 + httpGet: + path: "{{ printf `%s/ready` .Values.httpPathPrefix }}" + port: http-metrics + initialDelaySeconds: 10 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + +# -- Resource requests and limits +resources: {} +# limits: +# cpu: 200m +# memory: 128Mi +# requests: +# cpu: 100m +# memory: 128Mi + +# -- The security context for pods +podSecurityContext: + runAsUser: 0 + runAsGroup: 0 + +# -- The security context for containers +containerSecurityContext: + readOnlyRootFilesystem: true + capabilities: + drop: + - ALL + allowPrivilegeEscalation: false + +rbac: + # -- Specifies whether RBAC resources are to be created + create: true + # -- Specifies whether a PodSecurityPolicy is to be created + pspEnabled: false + +# -- The name of the Namespace to deploy +# If not set, `.Release.Namespace` is used +namespace: null + +serviceAccount: + # -- Specifies whether a ServiceAccount should be created + create: true + # -- The name of the ServiceAccount to use. + # If not set and `create` is true, a name is generated using the fullname template + name: null + # -- Image pull secrets for the service account + imagePullSecrets: [] + # -- Annotations for the service account + annotations: {} + # -- Automatically mount a ServiceAccount's API credentials + automountServiceAccountToken: true + +# -- Automatically mount API credentials for a particular Pod +automountServiceAccountToken: true + +# -- Node selector for pods +nodeSelector: {} + +# -- Affinity configuration for pods +affinity: {} + +# -- Tolerations for pods. By default, pods will be scheduled on master/control-plane nodes. +tolerations: + - key: node-role.kubernetes.io/master + operator: Exists + effect: NoSchedule + - key: node-role.kubernetes.io/control-plane + operator: Exists + effect: NoSchedule + +# -- Default volumes that are mounted into pods. In most cases, these should not be changed. +# Use `extraVolumes`/`extraVolumeMounts` for additional custom volumes. +# @default -- See `values.yaml` +defaultVolumes: + - name: run + hostPath: + path: /run/promtail + - name: containers + hostPath: + path: /var/lib/docker/containers + - name: pods + hostPath: + path: /var/log/pods + +# -- Default volume mounts. Corresponds to `volumes`. +# @default -- See `values.yaml` +defaultVolumeMounts: + - name: run + mountPath: /run/promtail + - name: containers + mountPath: /var/lib/docker/containers + readOnly: true + - name: pods + mountPath: /var/log/pods + readOnly: true + +# Extra volumes to be added in addition to those specified under `defaultVolumes`. +extraVolumes: [] + +# Extra volume mounts together. Corresponds to `extraVolumes`. +extraVolumeMounts: [] + +# Extra args for the Promtail container. +extraArgs: [] +# -- Example: +# -- extraArgs: +# -- - -client.external-labels=hostname=$(HOSTNAME) + +# -- Extra environment variables. Set up tracing enviroment variables here if .Values.config.enableTracing is true. +# Tracing currently only support configure via environment variables. See: +# https://grafana.com/docs/loki/latest/clients/promtail/configuration/#tracing_config +# https://www.jaegertracing.io/docs/1.16/client-features/ +extraEnv: [] + +# -- Extra environment variables from secrets or configmaps +extraEnvFrom: [] + +# -- Configure enableServiceLinks in pod +enableServiceLinks: true + +# ServiceMonitor configuration +serviceMonitor: + # -- If enabled, ServiceMonitor resources for Prometheus Operator are created + enabled: false + # -- Alternative namespace for ServiceMonitor resources + namespace: null + # -- Namespace selector for ServiceMonitor resources + namespaceSelector: {} + # -- ServiceMonitor annotations + annotations: {} + # -- Additional ServiceMonitor labels + labels: {} + # -- ServiceMonitor scrape interval + interval: null + # -- ServiceMonitor scrape timeout in Go duration format (e.g. 15s) + scrapeTimeout: null + # -- ServiceMonitor relabel configs to apply to samples before scraping + # https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig + # (defines `relabel_configs`) + relabelings: [] + # -- ServiceMonitor relabel configs to apply to samples as the last + # step before ingestion + # https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig + # (defines `metric_relabel_configs`) + metricRelabelings: [] + # -- ServiceMonitor will add labels from the service to the Prometheus metric + # https://github.com/prometheus-operator/prometheus-operator/blob/main/Documentation/api.md#servicemonitorspec + targetLabels: [] + # -- ServiceMonitor will use http by default, but you can pick https as well + scheme: http + # -- ServiceMonitor will use these tlsConfig settings to make the health check requests + tlsConfig: null + # -- Prometheus rules will be deployed for alerting purposes + prometheusRule: + enabled: false + additionalLabels: {} + # namespace: + rules: [] + # - alert: PromtailRequestErrors + # expr: 100 * sum(rate(promtail_request_duration_seconds_count{status_code=~"5..|failed"}[1m])) by (namespace, job, route, instance) / sum(rate(promtail_request_duration_seconds_count[1m])) by (namespace, job, route, instance) > 10 + # for: 5m + # labels: + # severity: critical + # annotations: + # description: | + # The {{ $labels.job }} {{ $labels.route }} is experiencing + # {{ printf \"%.2f\" $value }} errors. + # VALUE = {{ $value }} + # LABELS = {{ $labels }} + # summary: Promtail request errors (instance {{ $labels.instance }}) + # - alert: PromtailRequestLatency + # expr: histogram_quantile(0.99, sum(rate(promtail_request_duration_seconds_bucket[5m])) by (le)) > 1 + # for: 5m + # labels: + # severity: critical + # annotations: + # summary: Promtail request latency (instance {{ $labels.instance }}) + # description: | + # The {{ $labels.job }} {{ $labels.route }} is experiencing + # {{ printf \"%.2f\" $value }}s 99th percentile latency. + # VALUE = {{ $value }} + # LABELS = {{ $labels }} + +# Extra containers created as part of a Promtail Deployment resource +# - spec for Container: +# https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core +# +# Note that the key is used as the `name` field, i.e. below will create a +# container named `promtail-proxy`. +extraContainers: {} + # promtail-proxy: + # image: nginx + # ... + +# -- Configure additional ports and services. For each configured port, a corresponding service is created. +# See values.yaml for details +extraPorts: {} +# syslog: +# name: tcp-syslog +# annotations: {} +# labels: {} +# containerPort: 1514 +# protocol: TCP +# service: +# type: ClusterIP +# clusterIP: null +# port: 1514 +# externalIPs: [] +# nodePort: null +# loadBalancerIP: null +# loadBalancerSourceRanges: [] +# externalTrafficPolicy: null +# ingress: +# # For Kubernetes >= 1.18 you should specify the ingress-controller via the field ingressClassName +# # See https://kubernetes.io/blog/2020/04/02/improvements-to-the-ingress-api-in-kubernetes-1.18/#specifying-the-class-of-an-ingress +# # ingressClassName: nginx +# # Values can be templated +# annotations: {} +# # kubernetes.io/ingress.class: nginx +# # kubernetes.io/tls-acme: "true" +# paths: "/" +# hosts: +# - chart-example.local +# +# tls: [] +# # - secretName: chart-example-tls +# # hosts: +# # - chart-example.local + + +# -- PodSecurityPolicy configuration. +# @default -- See `values.yaml` +podSecurityPolicy: + privileged: true + allowPrivilegeEscalation: true + volumes: + - 'secret' + - 'hostPath' + - 'downwardAPI' + hostNetwork: false + hostIPC: false + hostPID: false + runAsUser: + rule: 'RunAsAny' + seLinux: + rule: 'RunAsAny' + supplementalGroups: + rule: 'RunAsAny' + fsGroup: + rule: 'RunAsAny' + readOnlyRootFilesystem: true + requiredDropCapabilities: + - ALL + +# -- Section for crafting Promtails config file. The only directly relevant value is `config.file` +# which is a templated string that references the other values and snippets below this key. +# @default -- See `values.yaml` +config: + # -- Enable Promtail config from Helm chart + # Set `configmap.enabled: true` and this to `false` to manage your own Promtail config + # See default config in `values.yaml` + enabled: true + # -- The log level of the Promtail server + # Must be reference in `config.file` to configure `server.log_level` + # See default config in `values.yaml` + logLevel: info + # -- The log format of the Promtail server + # Must be reference in `config.file` to configure `server.log_format` + # Valid formats: `logfmt, json` + # See default config in `values.yaml` + logFormat: logfmt + # -- The port of the Promtail server + # Must be reference in `config.file` to configure `server.http_listen_port` + # See default config in `values.yaml` + serverPort: 3101 + # -- The config of clients of the Promtail server + # Must be reference in `config.file` to configure `clients` + # @default -- See `values.yaml` + clients: + - url: http://lgtm-loki-gateway.observability.svc.cluster.local:80/loki/api/v1/push + # -- Configures where Promtail will save it's positions file, to resume reading after restarts. + # Must be referenced in `config.file` to configure `positions` + positions: + filename: /run/promtail/positions.yaml + # -- The config to enable tracing + enableTracing: false + # -- A section of reusable snippets that can be reference in `config.file`. + # Custom snippets may be added in order to reduce redundancy. + # This is especially helpful when multiple `kubernetes_sd_configs` are use which usually have large parts in common. + # @default -- See `values.yaml` + snippets: + pipelineStages: + - cri: {} + common: + - action: replace + source_labels: + - __meta_kubernetes_pod_node_name + target_label: node_name + - action: replace + source_labels: + - __meta_kubernetes_namespace + target_label: namespace + - action: replace + replacement: $1 + separator: / + source_labels: + - namespace + - app + target_label: job + - action: replace + source_labels: + - __meta_kubernetes_pod_name + target_label: pod + - action: replace + source_labels: + - __meta_kubernetes_pod_container_name + target_label: container + - action: replace + replacement: /var/log/pods/*$1/*.log + separator: / + source_labels: + - __meta_kubernetes_pod_uid + - __meta_kubernetes_pod_container_name + target_label: __path__ + - action: replace + replacement: /var/log/pods/*$1/*.log + regex: true/(.*) + separator: / + source_labels: + - __meta_kubernetes_pod_annotationpresent_kubernetes_io_config_hash + - __meta_kubernetes_pod_annotation_kubernetes_io_config_hash + - __meta_kubernetes_pod_container_name + target_label: __path__ + + # If set to true, adds an additional label for the scrape job. + # This helps debug the Promtail config. + addScrapeJobLabel: false + + # -- You can put here any keys that will be directly added to the config file's 'limits_config' block. + # @default -- empty + extraLimitsConfig: "" + + # -- You can put here any keys that will be directly added to the config file's 'server' block. + # @default -- empty + extraServerConfigs: "" + + # -- You can put here any additional scrape configs you want to add to the config file. + # @default -- empty + extraScrapeConfigs: "" + + # -- You can put here any additional relabel_configs to "kubernetes-pods" job + extraRelabelConfigs: [] + + scrapeConfigs: | + # See also https://github.com/grafana/loki/blob/master/production/ksonnet/promtail/scrape_config.libsonnet for reference + - job_name: kubernetes-pods + pipeline_stages: + {{- toYaml .Values.config.snippets.pipelineStages | nindent 4 }} + kubernetes_sd_configs: + - role: pod + relabel_configs: + - source_labels: + - __meta_kubernetes_pod_controller_name + regex: ([0-9a-z-.]+?)(-[0-9a-f]{8,10})? + action: replace + target_label: __tmp_controller_name + - source_labels: + - __meta_kubernetes_pod_label_app_kubernetes_io_name + - __meta_kubernetes_pod_label_app + - __tmp_controller_name + - __meta_kubernetes_pod_name + regex: ^;*([^;]+)(;.*)?$ + action: replace + target_label: app + - source_labels: + - __meta_kubernetes_pod_label_app_kubernetes_io_instance + - __meta_kubernetes_pod_label_instance + regex: ^;*([^;]+)(;.*)?$ + action: replace + target_label: instance + - source_labels: + - __meta_kubernetes_pod_label_app_kubernetes_io_component + - __meta_kubernetes_pod_label_component + regex: ^;*([^;]+)(;.*)?$ + action: replace + target_label: component + {{- if .Values.config.snippets.addScrapeJobLabel }} + - replacement: kubernetes-pods + target_label: scrape_job + {{- end }} + {{- toYaml .Values.config.snippets.common | nindent 4 }} + {{- with .Values.config.snippets.extraRelabelConfigs }} + {{- toYaml . | nindent 4 }} + {{- end }} + + # -- Config file contents for Promtail. + # Must be configured as string. + # It is templated so it can be assembled from reusable snippets in order to avoid redundancy. + # @default -- See `values.yaml` + file: | + server: + log_level: {{ .Values.config.logLevel }} + log_format: {{ .Values.config.logFormat }} + http_listen_port: {{ .Values.config.serverPort }} + {{- with .Values.httpPathPrefix }} + http_path_prefix: {{ . }} + {{- end }} + {{- tpl .Values.config.snippets.extraServerConfigs . | nindent 2 }} + + clients: + {{- tpl (toYaml .Values.config.clients) . | nindent 2 }} + + positions: + {{- tpl (toYaml .Values.config.positions) . | nindent 2 }} + + scrape_configs: + {{- tpl .Values.config.snippets.scrapeConfigs . | nindent 2 }} + {{- tpl .Values.config.snippets.extraScrapeConfigs . | nindent 2 }} + + limits_config: + {{- tpl .Values.config.snippets.extraLimitsConfig . | nindent 2 }} + + tracing: + enabled: {{ .Values.config.enableTracing }} + +networkPolicy: + # -- Specifies whether Network Policies should be created + enabled: false + metrics: + # -- Specifies the Pods which are allowed to access the metrics port. + # As this is cross-namespace communication, you also neeed the namespaceSelector. + podSelector: {} + # -- Specifies the namespaces which are allowed to access the metrics port + namespaceSelector: {} + # -- Specifies specific network CIDRs which are allowed to access the metrics port. + # In case you use namespaceSelector, you also have to specify your kubelet networks here. + # The metrics ports are also used for probes. + cidrs: [] + k8sApi: + # -- Specify the k8s API endpoint port + port: 8443 + # -- Specifies specific network CIDRs you want to limit access to + cidrs: [] + +# -- Base path to server all API routes fro +httpPathPrefix: "" + +sidecar: + configReloader: + enabled: false + image: + # -- The Docker registry for sidecar config-reloader + registry: ghcr.io + # -- Docker image repository for sidecar config-reloader + repository: jimmidyson/configmap-reload + # -- Docker image tag for sidecar config-reloader + tag: v0.12.0 + # -- Docker image pull policy for sidecar config-reloader + pullPolicy: IfNotPresent + # Extra args for the config-reloader container. + extraArgs: [] + # -- Extra environment variables for sidecar config-reloader + extraEnv: [] + # -- Extra environment variables from secrets or configmaps for sidecar config-reloader + extraEnvFrom: [] + # -- The security context for containers for sidecar config-reloader + containerSecurityContext: + readOnlyRootFilesystem: true + capabilities: + drop: + - ALL + allowPrivilegeEscalation: false + # -- Readiness probe for sidecar config-reloader + readinessProbe: {} + # -- Liveness probe for sidecar config-reloader + livenessProbe: {} + # -- Resource requests and limits for sidecar config-reloader + resources: {} + # limits: + # cpu: 200m + # memory: 128Mi + # requests: + # cpu: 100m + # memory: 128Mi + config: + # -- The port of the config-reloader server + serverPort: 9533 + serviceMonitor: + enabled: true + +# -- Extra K8s manifests to deploy +extraObjects: [] + # - apiVersion: "kubernetes-client.io/v1" + # kind: ExternalSecret + # metadata: + # name: promtail-secrets + # spec: + # backendType: gcpSecretsManager + # data: + # - key: promtail-oauth2-creds + # name: client_secret