Initial commit

infrastructure/rook-ceph/cluster-values.yaml

@@ -0,0 +1,219 @@
+# Rook-Ceph Cluster Values
+# https://github.com/rook/rook/blob/master/deploy/charts/rook-ceph-cluster/values.yaml
+
+# Operator namespace (must match where operator is deployed)
+operatorNamespace: rook-ceph
+
+# Enable toolbox for debugging
+toolbox:
+  enabled: true
+  tolerations:
+    - key: "node-role.kubernetes.io/control-plane"
+      operator: "Exists"
+      effect: "NoSchedule"
+  resources:
+    limits:
+      memory: "256Mi"
+    requests:
+      cpu: "50m"
+      memory: "64Mi"
+
+# Enable Prometheus monitoring
+monitoring:
+  enabled: true
+  createPrometheusRules: true
+
+# Ceph Cluster specification
+cephClusterSpec:
+  # Ceph version - Squid (v19)
+  cephVersion:
+    image: quay.io/ceph/ceph:v19.2.0
+    allowUnsupported: false
+
+  # Data directory on host
+  dataDirHostPath: /var/lib/rook
+
+  # Skip upgrade checks (homelab - we control updates)
+  skipUpgradeChecks: false
+
+  # Continue if host not found
+  continueUpgradeAfterChecksEvenIfNotHealthy: false
+
+  # Wait for nodes before starting OSDs
+  waitTimeoutForHealthyOSDInMinutes: 10
+
+  # Mon configuration
+  mon:
+    count: 3
+    allowMultiplePerNode: false
+
+  # MGR configuration
+  mgr:
+    count: 2
+    allowMultiplePerNode: false
+    modules:
+      - name: pg_autoscaler
+        enabled: true
+      - name: rook
+        enabled: true
+      - name: dashboard
+        enabled: true
+
+  # Dashboard configuration
+  dashboard:
+    enabled: true
+    ssl: false  # TLS handled by ingress
+    port: 7000
+    # Authentication: OAuth2-Proxy via ingress annotations
+    # See: infrastructure/rook-ceph/ingress.yaml
+    # Blueprint: infrastructure/authentik/ceph-dashboard-blueprint.yaml
+    config:
+      mgr/dashboard/standby_behaviour: "error"
+      mgr/dashboard/remote_user_header: "X-Forwarded-User"
+      mgr/dashboard/remote_user_trust_proxy: "true"
+
+  # Network configuration
+  network:
+    connections:
+      encryption:
+        enabled: false
+      compression:
+        enabled: false
+
+  # Crash collector
+  crashCollector:
+    disable: false
+
+  # Log collector
+  logCollector:
+    enabled: true
+    periodicity: daily
+    maxLogSize: 500M
+
+  # Cleanup policy (for uninstall)
+  cleanupPolicy:
+    confirmation: ""
+    sanitizeDisks:
+      method: quick
+      dataSource: zero
+      iteration: 1
+    allowUninstallWithVolumes: false
+
+  # Resource limits
+  resources:
+    mgr:
+      limits:
+        memory: "1Gi"
+      requests:
+        cpu: "100m"
+        memory: "512Mi"
+    mon:
+      limits:
+        memory: "2Gi"
+      requests:
+        cpu: "100m"
+        memory: "512Mi"
+    osd:
+      limits:
+        memory: "16Gi"
+      requests:
+        cpu: "2"
+        memory: "16Gi"
+    prepareosd:
+      limits:
+        memory: "400Mi"
+      requests:
+        cpu: "100m"
+        memory: "50Mi"
+
+  # Storage configuration - explicit nodes with passthrough NVMe
+  # sdb = dedicated 60GB WAL/DB device per node
+  storage:
+    useAllNodes: false
+    useAllDevices: false
+    nodes:
+      - name: "talos-cp-01"
+        devices:
+          - name: "nvme0n1"
+        config:
+          metadataDevice: "sdb"
+      - name: "talos-cp-02"
+        devices:
+          - name: "nvme0n1"
+        config:
+          metadataDevice: "sdb"
+      - name: "talos-cp-03"
+        devices:
+          - name: "nvme0n1"
+        config:
+          metadataDevice: "sdb"
+      - name: "talos-cp-04"
+        devices:
+          - name: "nvme0n1"
+        config:
+          metadataDevice: "sdb"
+    config:
+      osdsPerDevice: "1"
+
+  # Placement - allow on control-plane
+  placement:
+    all:
+      tolerations:
+        - key: "node-role.kubernetes.io/control-plane"
+          operator: "Exists"
+          effect: "NoSchedule"
+
+  # Health check configuration
+  healthCheck:
+    daemonHealth:
+      mon:
+        disabled: false
+        interval: 45s
+      osd:
+        disabled: false
+        interval: 60s
+      status:
+        disabled: false
+        interval: 60s
+    livenessProbe:
+      mon:
+        disabled: false
+      mgr:
+        disabled: false
+      osd:
+        disabled: false
+
+# Block pools configuration - matches existing deployment
+cephBlockPools:
+  - name: replicapool
+    spec:
+      failureDomain: host
+      replicated:
+        size: 2  # 2 replicas
+    storageClass:
+      enabled: true
+      name: rook-ceph-block
+      isDefault: true
+      reclaimPolicy: Delete
+      allowVolumeExpansion: true
+      volumeBindingMode: Immediate
+      parameters:
+        imageFormat: "2"
+        imageFeatures: layering
+        csi.storage.k8s.io/provisioner-secret-name: rook-csi-rbd-provisioner
+        csi.storage.k8s.io/provisioner-secret-namespace: rook-ceph
+        csi.storage.k8s.io/controller-expand-secret-name: rook-csi-rbd-provisioner
+        csi.storage.k8s.io/controller-expand-secret-namespace: rook-ceph
+        csi.storage.k8s.io/node-stage-secret-name: rook-csi-rbd-node
+        csi.storage.k8s.io/node-stage-secret-namespace: rook-ceph
+        csi.storage.k8s.io/fstype: ext4
+
+# Disable CephFS (not needed)
+cephFileSystems: []
+
+# Object Store with OIDC support - simplified for now
+cephObjectStores: []
+
+# Ingress for dashboard (also applied via postsync hook)
+ingress:
+  dashboard: {}