Skip to content

dcgm-exporter: enable ServiceMonitor by default and skip gracefully when Prometheus CRD is absent #2262

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
VincentG1234 wants to merge 2 commits into
base: main
Choose a base branch
from
+44 −5
Open

dcgm-exporter: enable ServiceMonitor by default and skip gracefully when Prometheus CRD is absent #2262

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5acfc79
dcgm-exporter: auto-enable ServiceMonitor when ServiceMonitor CRD is …
VincentG1234 Mar 31, 2026
b1e1798
erase a useless diff
VincentG1234 May 4, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions controllers/object_controls.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4996,9 +4996,10 @@ func ServiceMonitor(n ClusterPolicyController) (gpuv1.State, error) {
return gpuv1.Disabled, nil
}

// If Prometheus CRD is missing, skip gracefully
if !serviceMonitorCRDExists {
logger.Error(fmt.Errorf("couldn't find ServiceMonitor CRD"), "Install Prometheus and necessary CRDs for gathering GPU metrics!")
return gpuv1.NotReady, nil
logger.V(1).Info("ServiceMonitor CRD not found, skipping DCGM Exporter ServiceMonitor creation")
return gpuv1.Ready, nil
}

// Apply custom edits for DCGM Exporter
Expand Down
42 changes: 40 additions & 2 deletions controllers/object_controls_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1325,7 +1325,7 @@ func TestServiceMonitor(t *testing.T) {
expectedServiceMonitor: nil,
},
{
description: "dcgm-exporter SM enabled, CRD missing -> NotReady",
description: "dcgm-exporter SM explicitly enabled, CRD missing -> Ready (skip gracefully)",
stateName: "state-dcgm-exporter",
k8sObjects: nil,
clusterPolicySpec: gpuv1.ClusterPolicySpec{
Expand All @@ -1334,7 +1334,45 @@ func TestServiceMonitor(t *testing.T) {
ServiceMonitor: &gpuv1.DCGMExporterServiceMonitorConfig{Enabled: ptr.To(true)},
},
},
expectedState: gpuv1.NotReady,
expectedState: gpuv1.Ready,
expectedServiceMonitor: nil,
},
{
description: "dcgm-exporter SM nil config, CRD missing -> Ready (cleanup path; CRD absent)",
stateName: "state-dcgm-exporter",
k8sObjects: nil,
clusterPolicySpec: gpuv1.ClusterPolicySpec{
DCGMExporter: gpuv1.DCGMExporterSpec{
Enabled: ptr.To(true),
},
},
expectedState: gpuv1.Ready,
expectedServiceMonitor: nil,
},
{
description: "dcgm-exporter SM provided but Enabled nil, CRD missing -> Ready (skip cleanup)",
stateName: "state-dcgm-exporter",
k8sObjects: nil,
clusterPolicySpec: gpuv1.ClusterPolicySpec{
DCGMExporter: gpuv1.DCGMExporterSpec{
Enabled: ptr.To(true),
ServiceMonitor: &gpuv1.DCGMExporterServiceMonitorConfig{},
},
},
expectedState: gpuv1.Ready,
expectedServiceMonitor: nil,
},
{
description: "dcgm-exporter SM provided but Enabled nil, CRD present -> Disabled (default false)",
stateName: "state-dcgm-exporter",
k8sObjects: []client.Object{serviceMonitorCRD},
clusterPolicySpec: gpuv1.ClusterPolicySpec{
DCGMExporter: gpuv1.DCGMExporterSpec{
Enabled: ptr.To(true),
ServiceMonitor: &gpuv1.DCGMExporterServiceMonitorConfig{},
},
},
expectedState: gpuv1.Disabled,
expectedServiceMonitor: nil,
},
{
Expand Down
2 changes: 1 addition & 1 deletion deployments/gpu-operator/values.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -312,7 +312,7 @@ dcgmExporter:
service:
internalTrafficPolicy: Cluster
serviceMonitor:
enabled: false
enabled: true
interval: 15s
scrapeTimeout: 10s
honorLabels: false
Expand Down
Loading