monitoring: add signage marquee Grafana alerts

apps/kubevirt-vms/ci1.yaml

@@ -396,15 +396,10 @@ spec:
             # Confirmed via debug pod: PVC content IS a real bootable ISO9660
             # (file: "ISO 9660 CD-ROM filesystem data ... (bootable)"), so the
             # only bug was boot priority.
-            # 2026-05-08 PM: cdrom bus flipped sata→scsi for windows-iso to address
-            # the OVMF SATA-CDROM read timeout (`BdsDxe: failed to start Boot0001 ...
-            # Time out`). The SCSI CDROM uses virtio-scsi controller which has a
-            # longer read window and works cleanly on Filesystem-backed PVCs.
-            # See diagnostic chain in HANDOFF.md / CODEX-STATUS.md "OPEN — ci1".
             - name: windows-iso
               bootOrder: 1
               cdrom:
-                bus: scsi
+                bus: sata
             - name: rootdisk
               bootOrder: 2
               disk:
@@ -435,25 +430,17 @@ spec:
           persistentVolumeClaim:
             claimName: ci1-rootdisk
         - name: windows-iso
-          # 2026-05-08 PM: REVERTED from NFS Path B back to the original CDI
-          # Longhorn Filesystem PVC. NFS Path B (commit fc2aca0) failed at the
-          # storage layer because the Synology export `/volume1/ISOs` denies
-          # non-root client UIDs at the directory level (qemu uid 107 cannot
-          # `ls /iso/` even with file mode 0777). Confirmed via uid-107 +
-          # uid-0 busybox probe pods on rke2-agent2 — same export-only-root
-          # pattern as `/volume1/kubernetes` documented in
-          # `feedback_synology_nfs_kubernetes_export_root_only`. Memory:
-          # `feedback_synology_iso_export_root_only_uid_107_denied.md`.
-          #
-          # The Longhorn PVC `windows-server-2025-iso` (CDI Filesystem mode,
-          # 10Gi) was confirmed to contain valid ISO bytes that uid 107 CAN
-          # read (mode 0660 root:107). The OVMF SATA-CDROM read timeout from
-          # the original Path A is now addressed by the `bus: scsi` swap on
-          # the disks block above. The NFS PVC + PV are RETAINED on disk so
-          # the Path B state is recoverable; they can be pruned in a
-          # follow-up commit once SCSI boot is proven.
+          # Path B (2026-05-08): mount ISO from Synology NFS instead of
+          # Longhorn Filesystem PVC. The Filesystem-PVC path was confirmed to
+          # contain a valid bootable ISO9660 image but caused OVMF's
+          # SATA-CDROM read window to time out:
+          #   BdsDxe: failed to start Boot0001 ... Time out
+          # Block-mode DataVolume was attempted as Path A but blocked by CDI
+          # v1.65.0's upload pod capability drop. NFS-mounted ISO bypasses
+          # both issues. See win2025-iso-nfs-pv.yaml header for full rationale
+          # and Synology layout.
           persistentVolumeClaim:
-            claimName: windows-server-2025-iso
+            claimName: windows-server-2025-iso-nfs
         - name: virtio-drivers
           containerDisk:
             # Pinned to v1.8.2 (latest stable as of 2026-05-08).

apps/monitoring/noc-monitoring.yaml

@@ -3362,6 +3362,92 @@ data:
                 relativeTimeRange: {from: 120, to: 0}
                 datasourceUid: __expr__
                 model: {type: threshold, expression: B, conditions: [{evaluator: {params: [600], type: gt}}], refId: C}
+      - orgId: 1
+        name: Signage Marquee
+        folder: AI Stack Alerts
+        interval: 1m
+        rules:
+          - uid: marquee-dropped-frames-high
+            title: MarqueeDroppedFramesHigh
+            condition: C
+            for: 5m
+            noDataState: OK
+            execErrState: OK
+            annotations:
+              summary: Marquee dropped-frame rate above 5%
+              description: "Dropped frames exceeded the IR-21 budget for a renderer/phase/node tuple. Grafana owns alert delivery to IRC #alerts; Prometheus rules remain only the visibility source."
+              runbook: "1. Open /d/fc-marquee-perf/marquee-animation-performance 2. Filter renderer/node/phase 3. Compare latest AAT baseline diff 4. Restart only the affected player if the issue is node-local"
+            labels:
+              severity: warning
+              service: signage
+              alert_channel: irc
+            data:
+              - refId: A
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: prometheus
+                model: {expr: '(sum by (renderer, node_id, phase) (rate(marquee_dropped_frames_total[5m])) / sum by (renderer, node_id, phase) (rate(marquee_render_latency_ms_count[5m]))) * 100', instant: true, refId: A}
+              - refId: B
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: __expr__
+                model: {type: reduce, expression: A, reducer: last, refId: B}
+              - refId: C
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: __expr__
+                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [5], type: gt}}], refId: C}
+          - uid: marquee-render-latency-p99-high
+            title: MarqueeRenderLatencyP99High
+            condition: C
+            for: 5m
+            noDataState: OK
+            execErrState: OK
+            annotations:
+              summary: Marquee render latency p99 above 16ms
+              description: "Renderer p99 latency exceeded the Pi-class 16ms budget. Grafana delivers this alert to IRC #alerts."
+              runbook: "1. Open /d/fc-marquee-perf/marquee-animation-performance 2. Check render latency p99 by renderer/node/phase 3. Compare with dropped frames and node CPU 4. If isolated to WPF, capture current Player.Wpf frame set before restart"
+            labels:
+              severity: warning
+              service: signage
+              alert_channel: irc
+            data:
+              - refId: A
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: prometheus
+                model: {expr: 'histogram_quantile(0.99, sum by (renderer, node_id, phase, le) (rate(marquee_render_latency_ms_bucket[5m])))', instant: true, refId: A}
+              - refId: B
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: __expr__
+                model: {type: reduce, expression: A, reducer: last, refId: B}
+              - refId: C
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: __expr__
+                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [16], type: gt}}], refId: C}
+          - uid: marquee-animation-duration-drift
+            title: MarqueeAnimationDurationDrift
+            condition: C
+            for: 10m
+            noDataState: OK
+            execErrState: OK
+            annotations:
+              summary: Marquee animation duration drift above 10%
+              description: "Observed cycle duration has drifted more than 10% from target for a renderer/phase pair. Grafana delivers this alert to IRC #alerts."
+              runbook: "1. Open /d/fc-marquee-perf/marquee-animation-performance 2. Compare observed vs target duration 3. Check recent theme/preset changes 4. Re-run MarqueeHolidayBrandTrajectoryTests before promoting a baseline"
+            labels:
+              severity: warning
+              service: signage
+              alert_channel: irc
+            data:
+              - refId: A
+                relativeTimeRange: {from: 900, to: 0}
+                datasourceUid: prometheus
+                model: {expr: 'abs((histogram_quantile(0.5, sum by (renderer, phase, le) (rate(marquee_animation_duration_ms_bucket[15m]))) - avg by (renderer, phase) (marquee_animation_duration_target_ms)) / avg by (renderer, phase) (marquee_animation_duration_target_ms))', instant: true, refId: A}
+              - refId: B
+                relativeTimeRange: {from: 900, to: 0}
+                datasourceUid: __expr__
+                model: {type: reduce, expression: A, reducer: last, refId: B}
+              - refId: C
+                relativeTimeRange: {from: 900, to: 0}
+                datasourceUid: __expr__
+                model: {type: threshold, expression: B, conditions: [{evaluator: {params: [0.1], type: gt}}], refId: C}
       - orgId: 1
         name: Infrastructure
         folder: AI Stack Alerts