Added prom-stack

2026-10-07 18:35:17 +01:00
1 parent 089bc9bfb5
commit 52bfa88a33
@@ -0,0 +1,144 @@
+# Prepare the node-local directories before the local PersistentVolumes are
+# made available. The hook is idempotent and runs before every Argo CD sync.
+apiVersion: batch/v1
+kind: Job
+metadata:
+  name: monitoring-storage-prepare
+  namespace: prometheus
+  annotations:
+    argocd.argoproj.io/hook: PreSync
+    argocd.argoproj.io/hook-delete-policy: BeforeHookCreation,HookSucceeded
+    argocd.argoproj.io/sync-wave: "-2"
+spec:
+  backoffLimit: 3
+  template:
+    spec:
+      restartPolicy: OnFailure
+      nodeSelector:
+        kubernetes.io/hostname: music
+      containers:
+        - name: prepare
+          image: docker.io/busybox:1.37.0
+          command:
+            - sh
+            - -ec
+            - |
+              mkdir -p /storage/prometheus /storage/alertmanager /storage/loki
+              chown 1000:2000 /storage/prometheus /storage/alertmanager
+              chown 10001:10001 /storage/loki
+              chmod 0770 /storage/prometheus /storage/alertmanager /storage/loki
+          securityContext:
+            runAsNonRoot: false
+            runAsUser: 0
+            allowPrivilegeEscalation: false
+            seccompProfile:
+              type: RuntimeDefault
+          volumeMounts:
+            - name: storage
+              mountPath: /storage
+      volumes:
+        - name: storage
+          hostPath:
+            path: /data/k8s/monitoring
+            type: DirectoryOrCreate
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: monitoring-local
+  annotations:
+    argocd.argoproj.io/sync-wave: "-1"
+    argocd.argoproj.io/sync-options: Prune=false
+provisioner: kubernetes.io/no-provisioner
+volumeBindingMode: WaitForFirstConsumer
+reclaimPolicy: Retain
+---
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: monitoring-prometheus-music
+  labels:
+    monitoring.hexor.cy/volume: prometheus
+  annotations:
+    argocd.argoproj.io/sync-wave: "-1"
+    argocd.argoproj.io/sync-options: Prune=false
+spec:
+  capacity:
+    storage: 500Gi
+  volumeMode: Filesystem
+  accessModes: [ReadWriteOnce]
+  persistentVolumeReclaimPolicy: Retain
+  storageClassName: monitoring-local
+  local:
+    path: /data/k8s/monitoring/prometheus
+  nodeAffinity:
+    required:
+      nodeSelectorTerms:
+        - matchExpressions:
+            - key: kubernetes.io/hostname
+              operator: In
+              values: [music]
+---
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: monitoring-alertmanager-music
+  labels:
+    monitoring.hexor.cy/volume: alertmanager
+  annotations:
+    argocd.argoproj.io/sync-wave: "-1"
+    argocd.argoproj.io/sync-options: Prune=false
+spec:
+  capacity:
+    storage: 5Gi
+  volumeMode: Filesystem
+  accessModes: [ReadWriteOnce]
+  persistentVolumeReclaimPolicy: Retain
+  storageClassName: monitoring-local
+  local:
+    path: /data/k8s/monitoring/alertmanager
+  nodeAffinity:
+    required:
+      nodeSelectorTerms:
+        - matchExpressions:
+            - key: kubernetes.io/hostname
+              operator: In
+              values: [music]
+---
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: monitoring-loki-music
+  labels:
+    monitoring.hexor.cy/volume: loki
+  annotations:
+    argocd.argoproj.io/sync-wave: "-1"
+    argocd.argoproj.io/sync-options: Prune=false
+spec:
+  capacity:
+    storage: 200Gi
+  volumeMode: Filesystem
+  accessModes: [ReadWriteOnce]
+  persistentVolumeReclaimPolicy: Retain
+  storageClassName: monitoring-local
+  local:
+    path: /data/k8s/monitoring/loki
+  nodeAffinity:
+    required:
+      nodeSelectorTerms:
+        - matchExpressions:
+            - key: kubernetes.io/hostname
+              operator: In
+              values: [music]
+---
+# Keep monitoring schedulable under application-node pressure without competing
+# with Kubernetes' system-cluster-critical classes.
+apiVersion: scheduling.k8s.io/v1
+kind: PriorityClass
+metadata:
+  name: monitoring-critical
+  annotations:
+    argocd.argoproj.io/sync-wave: "-1"
+value: 1000000
+globalDefault: false
+description: Monitoring control plane and storage workloads