[Grafana] Use PodMonitor instead of ServiceMonitor for the Head Node …

…to avoid metric duplication

Signed-off-by: win5923 <[email protected]>

config/prometheus/podMonitor.yaml

@@ -22,3 +22,42 @@ spec:
     relabelings:
     - sourceLabels: [__meta_kubernetes_pod_label_ray_io_cluster]
       targetLabel: ray_io_cluster
+---
+apiVersion: monitoring.coreos.com/v1
+kind: PodMonitor
+metadata:
+  labels:
+    # `release: $HELM_RELEASE`: Prometheus can only detect PodMonitor with this label.
+    release: prometheus
+  name: ray-head-monitor
+  namespace: prometheus-system
+spec:
+  jobLabel: ray-head
+  # Only select Kubernetes Pods in the "default" namespace.
+  namespaceSelector:
+    matchNames:
+      - default
+  # Only select Kubernetes Pods with "matchLabels".
+  selector:
+    matchLabels:
+      ray.io/node-type: head
+  # A list of endpoints allowed as part of this PodMonitor.
+  podMetricsEndpoints:
+    - port: metrics
+      relabelings:
+        - action: replace
+          sourceLabels:
+            - __meta_kubernetes_pod_label_ray_io_cluster
+          targetLabel: ray_io_cluster
+    - port: as-metrics # autoscaler metrics
+      relabelings:
+        - action: replace
+          sourceLabels:
+            - __meta_kubernetes_pod_label_ray_io_cluster
+          targetLabel: ray_io_cluster
+    - port: dash-metrics # dashboard metrics
+      relabelings:
+        - action: replace
+          sourceLabels:
+            - __meta_kubernetes_pod_label_ray_io_cluster
+          targetLabel: ray_io_cluster