Add extra disks to talos-cp-2 via PostSync job, downsize memory-db to 2 instances

k8s/infra/databases/memory-db.yaml

@@ -9,7 +9,7 @@ metadata:
   annotations:
     argocd.argoproj.io/sync-options: SkipDryRunOnMissingResource=true
 spec:
-  instances: 3
+  instances: 2
   imageName: ghcr.io/cloudnative-pg/postgresql:16.2
   bootstrap:
     initdb:

k8s/infra/longhorn/kustomization.yaml

@@ -9,6 +9,7 @@ resources:
   - longhorn-nodes.yaml
   - expand-replicas-job.yaml
   - patch-csi-tolerations-job.yaml
+  - longhorn-add-disks-job.yaml  # Add extra disks to talos-cp-2
 # Longhorn deployed via bootstrap script or Helm.
 # These manifests configure it: unified StorageClass (default, 3 replicas),
 # Prometheus ServiceMonitor, taint toleration for control-plane nodes, explicit

k8s/infra/longhorn/longhorn-add-disks-job.yaml

@@ -0,0 +1,96 @@
+# PostSync hook Job that adds extra disks to Longhorn nodes.
+# talos-cp-2 has 4 extra disks mounted at /var/lib/longhorn-disk{1,2,3,4}
+# that are NOT auto-discovered by Longhorn.
+apiVersion: batch/v1
+kind: Job
+metadata:
+  name: longhorn-add-disks
+  namespace: longhorn-system
+  annotations:
+    argocd.argoproj.io/hook: PostSync
+    argocd.argoproj.io/hook-delete-policy: BeforeHookCreation
+spec:
+  backoffLimit: 3
+  template:
+    metadata:
+      name: longhorn-add-disks
+    spec:
+      restartPolicy: Never
+      serviceAccountName: longhorn-expand-replicas
+      containers:
+      - name: add-disks
+        image: bitnami/kubectl:latest
+        command:
+        - /bin/bash
+        - -c
+        - |
+          set -euo pipefail
+          
+          echo "Adding extra disks to Longhorn nodes..."
+          
+          # talos-cp-2 has 4 extra disks:
+          # - /var/lib/longhorn-disk1 (sdb1, 600GB)
+          # - /var/lib/longhorn-disk2 (sdc1, 500GB)
+          # - /var/lib/longhorn-disk3 (sdd1, 160GB)
+          # - /var/lib/longhorn-disk4 (sde1, 2TB)
+          
+          echo "Checking talos-cp-2..."
+          CURRENT_DISKS=$(kubectl -n longhorn-system get nodes.longhorn.io talos-cp-2 -o json | jq -r '.spec.disks | keys | length')
+          echo "  Current disk count: $CURRENT_DISKS"
+          
+          if [ "$CURRENT_DISKS" -lt 5 ]; then
+            echo "  Adding extra disks to talos-cp-2..."
+            kubectl -n longhorn-system patch nodes.longhorn.io talos-cp-2 --type merge -p '{
+              "spec": {
+                "disks": {
+                  "disk1": {
+                    "allowScheduling": true,
+                    "diskType": "filesystem",
+                    "evictionRequested": false,
+                    "path": "/var/lib/longhorn-disk1",
+                    "storageReserved": 10737418240,
+                    "tags": []
+                  },
+                  "disk2": {
+                    "allowScheduling": true,
+                    "diskType": "filesystem",
+                    "evictionRequested": false,
+                    "path": "/var/lib/longhorn-disk2",
+                    "storageReserved": 10737418240,
+                    "tags": []
+                  },
+                  "disk3": {
+                    "allowScheduling": true,
+                    "diskType": "filesystem",
+                    "evictionRequested": false,
+                    "path": "/var/lib/longhorn-disk3",
+                    "storageReserved": 5368709120,
+                    "tags": []
+                  },
+                  "disk4": {
+                    "allowScheduling": true,
+                    "diskType": "filesystem",
+                    "evictionRequested": false,
+                    "path": "/var/lib/longhorn-disk4",
+                    "storageReserved": 21474836480,
+                    "tags": []
+                  }
+                }
+              }
+            }'
+            echo "  ✓ Disks added to talos-cp-2"
+          else
+            echo "  ✓ talos-cp-2 already has $CURRENT_DISKS disks configured"
+          fi
+          
+          echo
+          echo "Waiting for disks to be ready..."
+          sleep 10
+          
+          echo
+          echo "Final storage summary:"
+          kubectl -n longhorn-system get nodes.longhorn.io -o json | \
+            jq -r '.items[] | "\(.metadata.name): \(.status.diskStatus | to_entries | map("\(.key): \(.value.storageAvailable/1073741824 | floor)GB avail") | join(", "))"'
+          
+          echo
+          echo "Done."