monitoring: alert on remotedesktop longhorn pvc growth

apps/fc-devicemgmt/argocd-application.yaml

@@ -0,0 +1,33 @@
+# Explicit ArgoCD Application shape for bootstrap/review.
+#
+# The live bluejay-infra ApplicationSet already discovers apps/* directories
+# and creates this same Application name (`infra-fc-devicemgmt`) automatically.
+# Keep repoURL on the internal Gitea ClusterIP URL; ArgoCD does not trust the
+# external step-ca HTTPS endpoint.
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: infra-fc-devicemgmt
+  namespace: argocd
+  labels:
+    app.kubernetes.io/name: fc-devicemgmt
+    app.kubernetes.io/part-of: flowercore
+    app.kubernetes.io/managed-by: argocd
+    flowercore.io/tenant-id: system
+    flowercore.io/created-by: bluejay-infra
+spec:
+  project: default
+  source:
+    repoURL: http://gitea-clusterip.gitea.svc.cluster.local:3000/bluejay/bluejay-infra.git
+    targetRevision: main
+    path: apps/fc-devicemgmt
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: fc-devicemgmt
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+      - CreateNamespace=true
+      - ServerSideApply=true

apps/monitoring/noc-monitoring.yaml

@@ -824,6 +824,53 @@ data:
               summary: "desktop.iamworkin.lan TLS cert expires within 2 days"
               description: "The desktop.iamworkin.lan cert is inside the 2-day renewal window and cert-manager has not renewed. Check cert-manager logs, step-ca reachability, and pfSense DNS overrides per the ACME DNS-01 gate."
 
+          - alert: LonghornPVCGrowthRapid
+            expr: |
+              (
+                (
+                  (
+                    longhorn_volume_actual_size_bytes
+                    - (longhorn_volume_actual_size_bytes offset 1h)
+                  )
+                  / clamp_min(longhorn_volume_actual_size_bytes offset 1h, 1)
+                )
+                * on(volume) group_left(namespace, persistentvolumeclaim) (
+                  (
+                    label_replace(kube_persistentvolumeclaim_info{storageclass="longhorn"}, "volume", "$1", "volumename", "(.+)")
+                    * on(namespace, persistentvolumeclaim) group_left()
+                      kube_persistentvolumeclaim_labels{label_flowercore_io_managed_by="remotedesktop"}
+                  )
+                  or
+                  label_replace(kube_persistentvolumeclaim_info{namespace="fc-desktop", storageclass="longhorn", persistentvolumeclaim=~"fc-profile-.*|remotedesktop-data"}, "volume", "$1", "volumename", "(.+)")
+                )
+              ) > 0.20
+              or
+              (
+                (
+                  longhorn_volume_actual_size_bytes
+                  / on(volume) clamp_min(longhorn_volume_capacity_bytes, 1)
+                )
+                * on(volume) group_left(namespace, persistentvolumeclaim) (
+                  (
+                    label_replace(kube_persistentvolumeclaim_info{storageclass="longhorn"}, "volume", "$1", "volumename", "(.+)")
+                    * on(namespace, persistentvolumeclaim) group_left()
+                      kube_persistentvolumeclaim_labels{label_flowercore_io_managed_by="remotedesktop"}
+                  )
+                  or
+                  label_replace(kube_persistentvolumeclaim_info{namespace="fc-desktop", storageclass="longhorn", persistentvolumeclaim=~"fc-profile-.*|remotedesktop-data"}, "volume", "$1", "volumename", "(.+)")
+                )
+              ) > 0.80
+            for: 5m
+            labels:
+              severity: warning
+              alert_channel: thermal_print
+              service: remotedesktop
+            annotations:
+              summary: "RemoteDesktop Longhorn PVC {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} growing rapidly"
+              description: "Longhorn volume {{ $labels.volume }} backing RemoteDesktop PVC {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} grew more than 20% in 1h or is over 80% capacity. Check for runaway SQLite/user-profile growth; this alert was added after the 2026-05-16 RemoteDesktop web SQLite Error 13 incident."
+              runbook: "1. kubectl -n {{ $labels.namespace }} describe pvc {{ $labels.persistentvolumeclaim }} 2. Open Longhorn UI volume {{ $labels.volume }} 3. Check RemoteDesktop web/user-volume SQLite files for permission or runaway growth 4. Expand PVC only after confirming the writer is healthy"
+              todo: "2026-05-19 metric gate: live noc1 Prometheus currently exposes kube_persistentvolumeclaim_info and kube_persistentvolumeclaim_resource_requests_storage_bytes, but not longhorn_volume_actual_size_bytes, longhorn_volume_capacity_bytes, kube_persistentvolumeclaim_labels, or kubelet_volume_stats_used_bytes. Keep the fc-desktop PVC fallback until kube-state-metrics label allowlist exposes flowercore.io/managed-by=remotedesktop."
+
       - name: pi-fleet
         rules:
           - alert: PiManagerDown