[Feature][Observability] Scrape Autoscaler and Dashboard metrics (#1493…

…) (#1533)
ray-project · Oct 17, 2023 · 8e16bfe · 8e16bfe
1 parent 420cb9b
commit 8e16bfe
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 0 deletions.
diff --git a/config/prometheus/serviceMonitor.yaml b/config/prometheus/serviceMonitor.yaml
@@ -19,6 +19,8 @@ spec:
   # A list of endpoints allowed as part of this ServiceMonitor.
   endpoints:
     - port: metrics
+    - port: as-metrics # autoscaler metrics
+    - port: dash-metrics # dashboard metrics
   targetLabels:
   - ray.io/cluster
 
diff --git a/ray-operator/config/samples/ray-cluster.embed-grafana.yaml b/ray-operator/config/samples/ray-cluster.embed-grafana.yaml
@@ -26,6 +26,12 @@ spec:
             name: dashboard
           - containerPort: 10001
             name: client
+          # The name of a containerPort cannot be longer than 15 characters.
+          # Hence, we use the name "as-metrics" instead of "autoscaler-metrics".
+          - containerPort: 44217
+            name: as-metrics # autoscaler
+          - containerPort: 44227
+            name: dash-metrics # dashboard
           lifecycle:
             preStop:
               exec: