fix(monitoring): let intel_gpu_top pick the GPU instead of hard-coding card0

The -device flag named /dev/dri/card0. That is the right node today on
every host, but nothing guarantees the number: a second GPU or a
different probe order and the exporter would silently watch the wrong
device or none. The plugin's monitoring resource injects every GPU on
the node and intel_gpu_top selects it on its own — verified with a probe
pod on k8s-2, which produced the same gpumon_* series without the flag.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

kubernetes/apps/monitoring-rules/intel-gpu-exporter-servicemonitor.yaml

@@ -0,0 +1,20 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: intel-gpu-exporter
+  namespace: monitoring
+  labels:
+    app.kubernetes.io/name: intel-gpu-exporter
+    release: kube-prometheus-stack
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: intel-gpu-exporter
+  endpoints:
+    - port: http-metrics
+      path: /metrics
+      interval: 30s
+      relabelings:
+        # The series would otherwise carry only the exporter pod's IP.
+        - sourceLabels: [__meta_kubernetes_pod_node_name]
+          targetLabel: node

kubernetes/apps/monitoring-rules/kustomization.yaml

@@ -39,4 +39,5 @@ resources:
   - immich-servicemonitor.yaml
   - loki-servicemonitor.yaml
   - smartctl-exporter-servicemonitor.yaml
+  - intel-gpu-exporter-servicemonitor.yaml
   - probes-blackbox.yaml

kubernetes/apps/monitoring/intel-gpu-exporter.yaml

@@ -0,0 +1,81 @@
+# Intel iGPU utilisation, frequency and power for every node (#752).
+#
+# Not privileged: /dev/dri comes from the device plugin's monitoring resource
+# (every GPU on the node, no hostPath), and the i915 PMU that intel_gpu_top
+# reads needs CAP_PERFMON — the one capability granted. No hostPID, no
+# hostNetwork.
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: intel-gpu-exporter
+  namespace: monitoring
+  labels:
+    app.kubernetes.io/name: intel-gpu-exporter
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: intel-gpu-exporter
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: intel-gpu-exporter
+    spec:
+      # Every node is a control plane; without this the exporter covers nothing.
+      tolerations:
+        - key: node-role.kubernetes.io/control-plane
+          operator: Exists
+          effect: NoSchedule
+      securityContext:
+        seccompProfile:
+          type: RuntimeDefault
+      containers:
+        - name: intel-gpu-exporter
+          image: ghcr.io/clambin/intel-gpu-exporter:0.7.4@sha256:d78761fef018834c759db154fe9dcf3dd9db5974703fa50ca21f6abc35221be1
+          args:
+            # No -device: intel_gpu_top picks the only GPU the plugin injects.
+            - -interval=5s
+          ports:
+            - name: http-metrics
+              containerPort: 9100
+              protocol: TCP
+          securityContext:
+            # Root so the PERFMON capability is effective without file
+            # capabilities on the binary.
+            runAsUser: 0
+            runAsNonRoot: false
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            capabilities:
+              drop: ["ALL"]
+              add: ["PERFMON"]
+          resources:
+            requests:
+              cpu: 10m
+              memory: 32Mi
+              gpu.intel.com/monitoring: 1
+            limits:
+              memory: 128Mi
+              gpu.intel.com/monitoring: 1
+          livenessProbe:
+            httpGet:
+              path: /metrics
+              port: http-metrics
+            initialDelaySeconds: 15
+            periodSeconds: 30
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: intel-gpu-exporter
+  namespace: monitoring
+  labels:
+    app.kubernetes.io/name: intel-gpu-exporter
+spec:
+  clusterIP: None
+  selector:
+    app.kubernetes.io/name: intel-gpu-exporter
+  ports:
+    - name: http-metrics
+      port: 9100
+      targetPort: http-metrics
+      protocol: TCP

kubernetes/apps/monitoring/kustomization.yaml

@@ -16,6 +16,7 @@ resources:
   - prometheus-gate-ingress.yaml
   - ci-diagnostics-rbac.yaml
   - smartctl-exporter.yaml
+  - intel-gpu-exporter.yaml
   - dashboards/
 # prometheusrule-garage.yaml lives in ./monitoring-rules/ and is applied by a
 # separate Flux Kustomization that dependsOn `monitoring` — otherwise the

kubernetes/infrastructure/intel-gpu-plugin/daemonset.yaml

@@ -72,6 +72,9 @@ spec:
             # they contend for it. Sized for an inference server plus room for
             # a transcoder and a benchmark pod alongside it.
             - -shared-dev-num=4
+            # Advertises gpu.intel.com/monitoring: one resource that grants a
+            # pod every GPU on the node instead of a slot. The exporter needs it.
+            - -enable-monitoring
           securityContext:
             seLinuxOptions:
               type: "container_device_plugin_t"