Pub/q2 dev

.github/workflows/ansible-lint.yml

@@ -8,6 +8,7 @@ on:
       - release_1.7.1
       - pub/build_stream
       - pub/q2_dev
+      - pub/telemetry
 
 jobs:
   build:

.github/workflows/pylint.yml

@@ -8,6 +8,7 @@ on:
       - release_1.7.1
       - pub/build_stream
       - pub/q2_dev
+      - pub/telemetry
 
 jobs:
   build:

common/library/module_utils/input_validation/common_utils/config.py

@@ -58,7 +58,8 @@
     "telemetry_config": "telemetry_config.yml",
     "high_availability_config": "high_availability_config.yml",
     "build_stream_config": "build_stream_config.yml",
-    "gitlab_config": "gitlab_config.yml"
+    "gitlab_config": "gitlab_config.yml",
+    "discovery_config": "discovery_config.yml"
     # "additional_software": "additional_software.json"
 }
 
@@ -103,6 +104,7 @@
     # "high_availability": [files["high_availability_config"]],
     # "additional_software": [files["additional_software"]],
     "build_stream": [files["build_stream_config"]],
+    "discovery": [files["discovery_config"]],
     "gitlab": [files["gitlab_config"], files["build_stream_config"]],
     "all": [
         files["local_repo_config"],

common/library/module_utils/input_validation/common_utils/en_us_validation_msg.py

@@ -70,7 +70,7 @@
                                  "and Ports fields.")
 SWITCH_DETAILS_NO_BMC_DETAILS_MSG = ("If switch details are provided then bmc_detail's "
                                     "static_range must also be provided.")
-INVALID_GROUP_NAME_MSG = "Groups must be defined in the form of grp<n> where n is 0-100, or SU<n> where n is 1-100."
+INVALID_GROUP_NAME_MSG = "Groups must be defined in the form of grp<n> where n is 0-99."
 INVALID_LOCATION_ID_MSG = ("location_id must follow the format SU-<n>.RACK-<n> where n is 0-99. "
                           "This input is case-sensitive. Please use uppercase letters only.")
 INVALID_ATTRIBUTES_ROLE_MSG = ("Please provide valid attributes for the role, "
@@ -264,6 +264,75 @@ def switch_snmp3_username_fail_msg(min_username_length, max_length):
                                              "service k8s/slurm roles in the mapping file or remove ldms from "
                                              "software_config.json and rerun the playbook.")
 
+# PowerScale telemetry validation messages
+POWERSCALE_VICTORIA_REQUIRED_MSG = (
+    "PowerScale telemetry requires VictoriaMetrics to be deployed. "
+    "When powerscale_configurations.powerscale_telemetry_support is true, 'victoria' must be included in "
+    "telemetry_collection_type (e.g., 'victoria' or 'victoria,kafka')."
+)
+POWERSCALE_CSI_DRIVER_MISSING_MSG = (
+    "csi_driver_powerscale is not configured in software_config.json. "
+    "PowerScale telemetry requires the CSI driver for PowerScale to be configured."
+)
+POWERSCALE_SERVICE_CLUSTER_MISSING_MSG = (
+    "service cluster is not defined in functional_groups_config.yml. "
+    "PowerScale telemetry requires a service cluster."
+)
+POWERSCALE_CONFIGURATIONS_MISSING_MSG = (
+    "powerscale_configurations section is required and must contain powerscale_telemetry_support."
+)
+POWERSCALE_OTEL_STORAGE_SIZE_INVALID_MSG = (
+    "must be a non-empty string in format 'XGi' (e.g., '5Gi')"
+)
+POWERSCALE_CSM_VALUES_PATH_REQUIRED_MSG = (
+    "csm_observability_values_file_path is required when powerscale_configurations.powerscale_telemetry_support is true. "
+    "Please provide the path to the CSM Observability values.yaml file."
+)
+POWERSCALE_AUTH_PROXY_HOST_MISSING_MSG = (
+    "karaviMetricsPowerscale.authorization.proxyHost is required in the CSM Observability values file "
+    "when karaviMetricsPowerscale.authorization.enabled is true. "
+    "Please provide the hostname or IP of the CSM Authorization Proxy server."
+)
+def powerscale_csm_values_not_found_msg(path):
+    """Returns error message when CSM Observability values.yaml file is not found."""
+    return (
+        f"CSM Observability values.yaml file not found at '{path}'. "
+        "Please verify the file path is correct."
+    )
+POWERSCALE_CSM_VALUES_INVALID_YAML_MSG = (
+    "CSM Observability values.yaml must contain a valid YAML dictionary."
+)
+def powerscale_csm_values_parse_error_msg(error):
+    """Returns error message when CSM Observability values.yaml fails to parse."""
+    return f"Failed to parse CSM Observability values.yaml: {error}"
+POWERSCALE_CSM_VALUES_MISSING_KARAVI_SECTION_MSG = (
+    "CSM Observability values.yaml is missing 'karaviMetricsPowerscale' section."
+)
+POWERSCALE_CSM_METRICS_IMAGE_MISSING_MSG = (
+    "CSM Metrics PowerScale image is required in CSM Observability values.yaml."
+)
+POWERSCALE_OTEL_COLLECTOR_IMAGE_MISSING_MSG = (
+    "OTEL Collector image is required in CSM Observability values.yaml."
+)
+POWERSCALE_ADDITIONAL_ENDPOINTS_URL_EMPTY_MSG = (
+    "Each additional_remote_write_endpoint must have a non-empty 'url' field."
+)
+POWERSCALE_ADDITIONAL_ENDPOINTS_URL_INVALID_MSG = (
+    "URL must start with 'http://' or 'https://'."
+)
+def powerscale_image_version_mismatch_msg(image_name, values_image, service_k8s_image):
+    """Returns error message when CSM values.yaml image version doesn't match service_k8s.json."""
+    return (
+        f"Image version mismatch for '{image_name}': "
+        f"CSM Observability values.yaml has '{values_image}' but "
+        f"service_k8s.json has '{service_k8s_image}'. "
+        f"Please update service_k8s.json to match the values.yaml version "
+        f"and re-run local_repo.yml to mirror the correct image to Pulp."
+    )
+POWERSCALE_SERVICE_K8S_JSON_NOT_FOUND_MSG = (
+    "service_k8s.json not found. Cannot validate PowerScale telemetry image versions. "
+    "Please ensure local_repo.yml has been executed."
+)
 def boolean_fail_msg(value):
     """Returns a formatted message indicating boolean_fail_msg."""
     return f"{value} must be set to either true or false."

common/library/module_utils/input_validation/schema/discovery_config.json

@@ -0,0 +1,38 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "Discovery Configuration",
+  "type": "object",
+  "properties": {
+    "enable_bmc_discovery": {
+      "type": "boolean",
+      "description": "Enable BMC discovery via OME. When true, ome_ip must be a valid IP address."
+    },
+    "ome_ip": {
+      "type": "string",
+      "description": "IP address of the Dell OpenManage Enterprise (OME) instance."
+    }
+  },
+  "required": [
+    "enable_bmc_discovery",
+    "ome_ip"
+  ],
+  "allOf": [
+    {
+      "if": {
+        "properties": {
+          "enable_bmc_discovery": { "const": true }
+        }
+      },
+      "then": {
+        "properties": {
+          "ome_ip": {
+            "type": "string",
+            "minLength": 7,
+            "pattern": "^(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)$",
+            "errorMessage": "ome_ip must be a valid IPv4 address when enable_bmc_discovery is true. Example: 192.168.1.100"
+          }
+        }
+      }
+    }
+  ]
+}

common/library/module_utils/input_validation/schema/telemetry_config.json

@@ -10,7 +10,7 @@
       "type": "boolean",
       "description": "Enable or disable NVIDIA DCGM (Data Center GPU Manager) on GPU compute nodes. When true, nvidia-dcgm.service is started during cloud-init provisioning. Default: true"
     },
-    "idrac_telemetry_collection_type": {
+    "telemetry_collection_type": {
       "anyOf": [
         {
           "type": "string",
@@ -43,6 +43,53 @@
       "default": 10001,
       "description": "LDMS sampler port on compute nodes. Valid range: 10001-10100. Default: 10001"
     },
+    "powerscale_configurations": {
+      "type": "object",
+      "properties": {
+        "powerscale_telemetry_support": {
+          "type": "boolean",
+          "default": true,
+          "description": "Enable or disable PowerScale telemetry support. Requires csi_driver_powerscale in software_config.json."
+        },
+        "powerscale_log_enabled": {
+          "type": "boolean",
+          "default": false,
+          "description": "Enable or disable PowerScale log collection (syslog to VictoriaLogs). Requires powerscale_telemetry_support: true."
+        },
+        "otel_collector_storage_size": {
+          "type": "string",
+          "pattern": "^[0-9]+(Ki|Mi|Gi|Ti|Pi|Ei)$",
+          "default": "5Gi",
+          "description": "PVC size for OTEL Collector metric batching and buffering."
+        },
+        "csm_observability_values_file_path": {
+          "type": "string",
+          "description": "Path to the user-provided Helm values file for karavi-observability chart. Required when powerscale_telemetry_support is true."
+        },
+        "additional_remote_write_endpoints": {
+          "type": "array",
+          "default": [],
+          "items": {
+            "type": "object",
+            "properties": {
+              "url": {
+                "type": "string",
+                "pattern": "^https?://",
+                "description": "VictoriaMetrics remote_write endpoint URL."
+              },
+              "tls_insecure_skip_verify": {
+                "type": "boolean",
+                "default": false,
+                "description": "Skip TLS certificate verification for this endpoint."
+              }
+            },
+            "required": ["url"]
+          },
+          "description": "Additional VictoriaMetrics remote_write endpoints. vmagent writes to all configured endpoints."
+        }
+      },
+      "required": ["powerscale_telemetry_support", "otel_collector_storage_size", "csm_observability_values_file_path"]
+    },
     "ldms_sampler_configurations": {
       "anyOf": [
         {
@@ -126,7 +173,7 @@
       ]
     }
   },
-  "required": ["idrac_telemetry_support", "dcgm_support", "idrac_telemetry_collection_type", "ldms_sampler_configurations", "ldms_agg_port", "ldms_store_port", "ldms_sampler_port" ],
+  "required": ["idrac_telemetry_support", "dcgm_support", "telemetry_collection_type", "ldms_sampler_configurations", "ldms_agg_port", "ldms_store_port", "ldms_sampler_port", "powerscale_configurations" ],
   "$defs": {
     "kafka_configurations": {
       "type": "object",
@@ -177,7 +224,7 @@
             }
           },
           "uniqueItems": true,
-          "description": "IMPORTANT: At least one Kafka topic must be defined. Topic names 'idrac' and 'ldms' are CONSTANTS. 'idrac' is required if idrac_telemetry_support is true and kafka is in idrac_telemetry_collection_type. 'ldms' is required if LDMS software is configured in software_config.json (automatic detection). Only partition counts can be changed.",
+          "description": "IMPORTANT: At least one Kafka topic must be defined. Topic names 'idrac' and 'ldms' are CONSTANTS. 'idrac' is required if idrac_telemetry_support is true and kafka is in telemetry_collection_type. 'ldms' is required if LDMS software is configured in software_config.json (automatic detection). Only partition counts can be changed.",
           "errorMessage": {
             "minItems": "At least 1 Kafka topic must be defined. Configure based on enabled features.",
             "maxItems": "Maximum 2 topics allowed: 'idrac' and 'ldms'",
@@ -194,18 +241,9 @@
       ],
       "additionalProperties": false
     },
-    "victoria_configurations": {
+    "victoria_metrics_configurations": {
       "type": "object",
       "properties": {
-        "deployment_mode": {
-          "type": "string",
-          "enum": ["single-node", "cluster"],
-          "default": "cluster",
-          "description": "VictoriaMetrics deployment mode. 'single-node' for simple deployment (1 pod), 'cluster' for high-availability deployment (7 pods). Default: 'cluster'",
-          "errorMessage": {
-            "enum": "deployment_mode must be either 'single-node' or 'cluster'"
-          }
-        },
         "persistence_size": {
           "type": "string",
           "pattern": "^[0-9]+(Ki|Mi|Gi|Ti|Pi|Ei)$"
@@ -216,19 +254,37 @@
         }
       },
       "required": [
-        "deployment_mode",
         "persistence_size",
         "retention_period"
       ],
       "additionalProperties": false
+    },
+    "victoria_logs_configurations": {
+      "type": "object",
+      "description": "VictoriaLogs cluster mode configuration. Deployed alongside VictoriaMetrics when 'victoria' is in collection type.",
+      "properties": {
+        "storage_size": {
+          "type": "string",
+          "pattern": "^[0-9]+(Ki|Mi|Gi|Ti|Pi|Ei)$",
+          "default": "8Gi",
+          "description": "Storage size per vlstorage replica PVC. Total = storage_size x 3 replicas.",
+          "errorMessage": "storage_size must be a valid Kubernetes PVC size (e.g., '8Gi', '50Gi', '1Ti')"
+        },
+        "retention_period": {
+          "type": "integer",
+          "minimum": 24
+        }
+      },
+      "required": ["storage_size", "retention_period"],
+      "additionalProperties": false
     }
   },
   "allOf": [
     {
       "if": {
         "properties": {
             "idrac_telemetry_support": { "const": true },
-            "idrac_telemetry_collection_type": { "pattern": "(?i)^kafka$" }
+            "telemetry_collection_type": { "pattern": "(?i)^kafka$" }
         }
       },
       "then": {
@@ -242,30 +298,32 @@
       "if": {
         "properties": {
           "idrac_telemetry_support": { "const": true },
-          "idrac_telemetry_collection_type": { "pattern": "(?i)^victoria$" }
+          "telemetry_collection_type": { "pattern": "(?i)^victoria$" }
         }
       },
       "then": {
-        "required": ["victoria_configurations"],
+        "required": ["victoria_metrics_configurations", "victoria_logs_configurations"],
         "properties": {
-          "victoria_configurations": { "$ref": "#/$defs/victoria_configurations" }
+          "victoria_metrics_configurations": { "$ref": "#/$defs/victoria_metrics_configurations" },
+          "victoria_logs_configurations": { "$ref": "#/$defs/victoria_logs_configurations" }
         }
       }
     },
     {
       "if": {
         "properties": {
           "idrac_telemetry_support": { "const": true },
-          "idrac_telemetry_collection_type": {
+          "telemetry_collection_type": {
             "pattern": "(?i)^(victoria,kafka|kafka,victoria)$"
           }
         }
       },
       "then": {
-        "required": ["kafka_configurations", "victoria_configurations"],
+        "required": ["kafka_configurations", "victoria_metrics_configurations", "victoria_logs_configurations"],
         "properties": {
           "kafka_configurations": { "$ref": "#/$defs/kafka_configurations" },
-          "victoria_configurations": { "$ref": "#/$defs/victoria_configurations" }
+          "victoria_metrics_configurations": { "$ref": "#/$defs/victoria_metrics_configurations" },
+          "victoria_logs_configurations": { "$ref": "#/$defs/victoria_logs_configurations" }
         }
       }
     }