补齐集群状态、主机与通知链路基础监控 (#149)

Co-authored-by: panxiao81 <[email protected]>
2026-09-25 17:45:56 +00:00
parent a43b7d3c26
commit 39aeac25ee
9 changed files with 474 additions and 0 deletions
@@ -0,0 +1,60 @@
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring
+spec:
+  interval: 30m
+  timeout: 5m
+  dependsOn:
+  - name: vm-operator
+  - name: prometheus-operator-crds
+  chart:
+    spec:
+      chart: kube-state-metrics
+      version: 8.5.0
+      sourceRef:
+        kind: HelmRepository
+        name: prometheus-community
+        namespace: monitoring
+      interval: 1h
+  driftDetection:
+    mode: enabled
+  install:
+    remediation:
+      retries: 3
+  upgrade:
+    remediation:
+      retries: 3
+  values:
+    fullnameOverride: kube-state-metrics
+    collectors:
+    - cronjobs
+    - daemonsets
+    - deployments
+    - jobs
+    - namespaces
+    - nodes
+    - persistentvolumeclaims
+    - persistentvolumes
+    - pods
+    - statefulsets
+    resources:
+      requests:
+        cpu: 100m
+        memory: 128Mi
+      limits:
+        cpu: 500m
+        memory: 384Mi
+    prometheus:
+      monitor:
+        enabled: true
+        jobLabel: app.kubernetes.io/name
+        http:
+          interval: 30s
+          honorLabels: true
+        metrics:
+          interval: 30s
+          honorLabels: true
+    selfMonitor:
+      enabled: true