monitoring: add signage marquee Grafana alerts

apps/kubevirt-vms/ci1.yaml

@@ -396,16 +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 is SCSI (virtio-scsi controller). Bus
-            # choice is no longer load-bearing since the ISO is delivered via
-            # containerDisk (see volumes block below) — both SATA and SCSI
-            # work fine when the cdrom backing isn't a slow PVC. SCSI is kept
-            # because it's the modern bus and matches the standard FC
-            # KubeVirt VM template.
             - name: windows-iso
               bootOrder: 1
               cdrom:
-                bus: scsi
+                bus: sata
             - name: rootdisk
               bootOrder: 2
               disk:
@@ -436,40 +430,17 @@ spec:
           persistentVolumeClaim:
             claimName: ci1-rootdisk
         - name: windows-iso
-          # 2026-05-08 PM (Path C, CONTAINERDISK): the ISO is now packaged as
+          # Path B (2026-05-08): mount ISO from Synology NFS instead of
-          # a KubeVirt containerDisk OCI image baked from
+          # Longhorn Filesystem PVC. The Filesystem-PVC path was confirmed to
-          # `FROM scratch ; ADD --chown=107:107 disk.img /disk/disk.img`.
+          # contain a valid bootable ISO9660 image but caused OVMF's
-          # The qemu user (uid 107) reads the ISO directly from a tmpfs view
+          # SATA-CDROM read window to time out:
-          # of the OCI layer, bypassing both:
+          #   BdsDxe: failed to start Boot0001 ... Time out
-          #   - Synology NFS export ACL (Path B failed: uid 107 denied at
+          # Block-mode DataVolume was attempted as Path A but blocked by CDI
-          #     directory level even with mode 0777, see memory
+          # v1.65.0's upload pod capability drop. NFS-mounted ISO bypasses
-          #     feedback_synology_iso_export_root_only_uid_107_denied)
+          # both issues. See win2025-iso-nfs-pv.yaml header for full rationale
-          #   - OVMF cdrom read-window timeout (Path A and Path B's SCSI
+          # and Synology layout.
-          #     retry both hit `BdsDxe: failed to start Boot0001 ... Time out`
+          persistentVolumeClaim:
-          #     when the cdrom was backed by a PVC the storage controller
+            claimName: windows-server-2025-iso-nfs
-          #     couldn't satisfy reads from fast enough).
-          #
-          # Image build (one-time, per ISO version):
-          #   1. Copy ISO to disk.img, write Dockerfile
-          #   2. podman build --tag localhost/win-server-2025:1.0 .  (on noc1)
-          #   3. podman save -o win-server-2025-1.0.tar localhost/win-server-2025:1.0
-          #   4. SCP tar to all 3 RKE2 nodes (rke2-server, rke2-agent1, rke2-agent2)
-          #   5. sudo /var/lib/rancher/rke2/bin/ctr -a /run/k3s/containerd/containerd.sock \
-          #        -n k8s.io images import /tmp/win-server-2025-1.0.tar
-          # Standard FC pattern per `feedback_rke2_localhost_imagepullpolicy`.
-          #
-          # When a new Windows ISO version ships, bump the tag (1.1, 1.2, ...),
-          # rebuild + redistribute, and update the image: line below in a new
-          # commit. KubeVirt picks up the new image via a VM restart.
-          #
-          # The legacy NFS PVC + PV (apps/kubevirt-vms/win2025-iso-nfs-pv.yaml)
-          # and CDI Longhorn PVC (`windows-server-2025-iso`) are RETAINED for
-          # this commit so the prior states are recoverable. Once the
-          # containerDisk path proves on a successful Windows install, both
-          # legacy artifacts can be pruned in a follow-up commit.
-          containerDisk:
-            image: localhost/win-server-2025:1.0
-            imagePullPolicy: Never
         - 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