Compare commits

...

33 Commits

Author SHA1 Message Date
Codex
266b9cb8be feat(github-runner): add top Linux repo runners 2026-05-17 13:55:55 -05:00
Codex
6f6ca50987 fix(github-runner): switch RUNNER_TOKEN -> ACCESS_TOKEN; set RUN_AS_ROOT=false
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 22:08:56 +00:00
Codex
c7be58c1f7 chore(github-runner): bump replicas 0 -> 1 (PAT provisioned)
Operator provisioned GitHub PAT (Runner Registration) 1P item. OnePasswordItem CRD already materialized the secret. Unblocks CI fleet-wide.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 22:04:03 +00:00
Codex
a1f5a393cd chore(github-runner): rename 1P item to GitHub PAT (Runner Registration)
Renames the OnePasswordItem.itemPath from "GitHub Runner Registration
Token" to "GitHub PAT (Runner Registration)" so the runner 1P entry
sits next to its siblings — GitHub PAT (Gitea Mirrors) and GitHub PAT
(NuGet Packages) — under a consistent "GitHub PAT (...)" naming pattern
and API_CREDENTIAL category.

Existing field "credential" remains the consumer (RUNNER_TOKEN env).
Comment block clarified to require Administration:read/write fine-grained
PAT scope on target repos.

Old 1P item renamed to "[DEPRECATED 2026-05-16] GitHub Runner
Registration" — kept as recovery backup; can be hard-deleted after the
first successful runner pod start against the new item path.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 22:01:41 +00:00
Codex
710340d8be chore(github-runner): rename 1P item to GitHub PAT (Runner Registration)
Renames the OnePasswordItem.itemPath from "GitHub Runner Registration
Token" to "GitHub PAT (Runner Registration)" so the runner 1P entry
sits next to its siblings — GitHub PAT (Gitea Mirrors) and GitHub PAT
(NuGet Packages) — under a consistent "GitHub PAT (...)" naming pattern
and API_CREDENTIAL category.

Existing field "credential" remains the consumer (RUNNER_TOKEN env).
Comment block clarified to require Administration:read/write fine-grained
PAT scope on target repos.

Old 1P item renamed to "[DEPRECATED 2026-05-16] GitHub Runner
Registration" — kept as recovery backup; can be hard-deleted after the
first successful runner pod start against the new item path.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 10:27:58 -05:00
Andrew Stoltz
7d2daaa4f8 chore(github-runner): replicas 1 → 0 until 1Password token provisioned
github-runner-token OnePasswordItem exists but the underlying 1Password
vault item hasn't been created yet, so the operator can't mint the K8s
Secret. Pod stuck in CreateContainerConfigError → DeploymentReplicasMismatch
alert fires.

Scaling to 0 keeps the manifest infrastructure intact but stops trying
to schedule until operator:
1. Creates "GitHub Runner Registration Token" item in IAmWorkin vault
2. Generates a token at github.com/astoltz/<repo>/settings/actions/runners/new
3. Updates the OnePasswordItem itemPath to point at it
4. Bumps replicas back to 1 via PR
2026-05-15 16:18:19 -05:00
Andrew Stoltz
e50e103ba0 fix(zabbix): bump web probe timeouts 5s→15s + add failureThreshold
zabbix-web nginx+PHP-FPM container serves / at ~3-5s baseline with
occasional 6-7s spikes (probe path renders full dashboard via PHP).
kube-probe was killing the container after 3 consecutive 5s-timeout
499s, producing CrashLoopBackOff alert noise even though the app
was serving real traffic fine.

15s timeout absorbs the natural variance; explicit failureThreshold=3
documents the policy (was implicit default).

Closes the firing PodCrashLoopBackOff (zabbix-web) + pending
HTTPServiceSlow/HTTPServiceDegraded alerts. zabbix.iamworkin.lan
remains slow at the application layer (separate work — PHP-FPM
warm-up + Zabbix server "host not found" agent lookup spam need
their own fixes) but the pod restart loop stops.
2026-05-15 15:59:04 -05:00
Codex
e8094eb0bd ci(github-runner): add Phase 2 ephemeral Linux runner K8s manifest
Namespace github-runner with myoung34/github-runner:latest Deployment,
5Gi Longhorn RWO NuGet cache PVC, zero-privilege ServiceAccount, and
OnePasswordItem CRD for the registration token. EPHEMERAL=true mode
re-registers after each job; Recreate strategy avoids RWO multi-attach.
Targets fc-build-linux label; single replica pinned to rke2-server node.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-14 12:46:25 -05:00
8d87d9172c Add Pi signage Phase 1 player artifacts
Squash merge Sprint 14 Pi signage player artifacts.
2026-05-14 01:46:09 +00:00
Codex
cfd9743afa Add Apple TV signage docs manifest 2026-05-13 20:32:48 -05:00
Andrew Stoltz
5029e209cd kubevirt-vms: boot ci1 from server template 2026-05-12 16:58:18 -05:00
Codex
f298339152 fix(guacamole): add --- separator between macmini-vnc-creds OnePasswordItem and guacamole-branding ConfigMap
Missing document separator caused YAML to merge the OnePasswordItem's
top-level `spec: itemPath:` block into the ConfigMap that follows.
Result: a ConfigMap with a `.spec` field whose K8s schema does not
declare one, triggering ArgoCD's structured-merge diff to fail since
2026-05-11T15:30:54Z:

  Failed to compare desired state to live state: failed to calculate
  diff: error calculating structured merge diff: error building typed
  value from config resource: .spec: field not declared in schema

App stayed Healthy (live K8s tolerated the extra field — ConfigMap
ignored it) but ArgoCD's diff calc was broken, leaving the app stuck at
sync=Unknown for all 21 resources. Adding the missing `---` separator
makes the OnePasswordItem and ConfigMap proper sibling YAML documents,
each with its own kind-correct schema.

Diagnosed during 2026-05-12 morning routine.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-12 09:26:03 -05:00
Codex
6e7d88db49 feat(fc-redis): add SignalR backplane for cross-product event bus (Q-SO-1 Phase A)
Per Q-SO-1 operator resolution 2026-05-11 PM, Redis SignalR backplane lands
in Phase A (was Phase C deferral). Treats Redis as a managed FC infrastructure
component, not a deferred scaling escalation.

Lands the minimal Phase A surface:
- Namespace fc-redis
- Single Redis 7-alpine pod with 1Gi Longhorn RWO PVC
- ConfigMap with AOF persistence (everysec), 256Mi maxmemory, allkeys-lru
- ClusterIP Service `redis.fc-redis.svc.cluster.local:6379` (in-cluster only)
- No AUTH Phase A (Phase B add via 1Password Connect rotation)
- No IngressRoute (backplane is server-to-server)

Consumers (Phase A IMPL across FC services) add:
  services.AddSignalR().AddStackExchangeRedis(
      "redis.fc-redis.svc.cluster.local:6379",
      opts => opts.Configuration.ChannelPrefix =
          StackExchange.Redis.RedisChannel.Literal("fc-opsconsole"));

Phase B/C follow-ons (not in this commit): Sentinel for HA, AUTH password
from 1Password, redis_exporter sidecar for Prometheus, network policies.

See FlowerCore.Notes/docs/signage/operations-console-phase-2-design.md
section 3.5 (rewritten) and decisions-waiting.html Q-SO-1 (RESOLVED).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-11 19:02:58 -05:00
Codex
5ae50bd491 fix(telephony): init container runs as root to chown hostPath /tmp/tts-audio
The fix-data-perms init container chowns /data (PVC) and /shared-tts
(hostPath /tmp/tts-audio on rke2-agent1) to uid 1654 so the non-root
telephony-web app can write Piper TTS .sln16 files.

Without an explicit container-level securityContext override, the init
container inherits pod-level runAsNonRoot:true / runAsUser:1654 and
fails with 'chown: /shared-tts: Operation not permitted' the first
time the hostPath comes up root-owned after a node reboot.

Outage 2026-05-11 23:00 UTC: telephony-web in Init:CrashLoopBackOff for
9 hours (100+ restarts) until init container was bumped to runAsUser:0.
Live cluster patched in the same operation; this commit makes the fix
durable in git so ArgoCD sync preserves it.

See Notes memory: feedback_hostpath_initcontainer_chown_perms

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-11 18:37:15 -05:00
Codex
653d4472f5 fix(monitoring): mirror Q-MR-3 MultusMemoryPressure + NamespacePendingPodBacklog alerts
Two new preventive alert rules added to the kubernetes-state group of the
K8s migration target ConfigMap. The live Podman Prometheus on noc1 has
already been updated via FlowerCore.Notes/scripts/monitoring/alerts.yml +
sudo cp + podman pod restart monitoring (this commit only locks it in
the bluejay-infra K8s mirror so a future migration carries it forward).

MultusMemoryPressure (critical, thermal_print): fires when kube-multus
working set exceeds 80% of its memory limit for 5m. Catches the next
multus OOM cascade BEFORE it kills the daemon cluster-wide. The 2026-05-10
21h outage hit because no alert fired on the rising multus working set;
only downstream blackbox / Traefik / service alerts triggered, after the
fact.

NamespacePendingPodBacklog (warning): fires when any single namespace has
>25 Pending pods sustained for 30m. Catches the operator-leak avalanche
pattern (orphan pods from a crashed reconciler emitting children without
ownerReferences) before it cascades into a CNI OOM.

See FlowerCore.Notes:
  - feedback_multus_50mi_limit_oom_orphan_pod_avalanche
  - feedback_monitoring_k8s_target_vs_live_podman (workflow)

Companion commits:
  - bluejay-infra@eb8693e (multus memory limit)
  - FlowerCore.RemoteDesktop@b02c59b (OwnerReferences fix)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-11 10:42:27 -05:00
Codex
eb8693e1ce fix(multus): bump kube-multus-ds memory 50Mi/50Mi -> 1Gi/512Mi (prevent OOM cascade)
Cluster outage 2026-05-10T17:43 through 2026-05-11 ~10:30 (~21h). Root cause:
FlowerCore.RemoteDesktop emitted 219 orphan rd-browser-only-* pods in fc-desktop
(missing OwnerReferences — see companion fix in FlowerCore.RemoteDesktop).
Kubelet's continuous CNI ADD retries for those pending pods drove a request
queue that exceeded the upstream default 50Mi limit on kube-multus-ds. Multus
OOMKilled (exit 137), restarted with an even bigger backlog, OOMKilled again,
positive feedback loop. Restart counts climbed to 276 / 412 / 261 across the
3 RKE2 nodes.

Downstream blast radius: both Traefik pods stuck ContainerCreating (101m +
4h35m), all Longhorn CSI attacher/provisioner/instance-manager stuck, every
Prometheus blackbox probe for *.iamworkin.lan failing, UpdateCenterPublicEdgeDown
critical on update.flowercore.io, every ArgoCD app showing sync=Unknown
because repo-server lost git connectivity. 45 firing Prometheus alerts.

Recovery sequence (Q-MR-1 from FlowerCore.Notes morning routine):
1. kubectl patch kube-multus-ds memory live (this commit locks it in git so
   ArgoCD doesn't revert on next sync)
2. Force-delete the 219 orphan pods (kubectl --grace-period=0 --force) to
   break the avalanche
3. Rollout restart kube-multus-ds — STABLE after restart with new limit
4. Restart Traefik + Longhorn CSI to clear stuck ContainerCreating
5. Verify update.flowercore.io returns 200 + ArgoCD apps reconcile

Tested incrementally: 256Mi limit was insufficient (still OOMed on catchup
burst), 512Mi was insufficient on rke2-agent1 (most pods concentrated there),
1Gi/512Mi handled the full 200+ pending pod CNI catchup cleanly with 0 multus
restarts after rollout. Nodes are 64GB with <25% used in steady-state, so the
~256Mi typical working-set is well within the new limit.

Companion change: FlowerCore.RemoteDesktop must set OwnerReferences on every
worker pod so future operator crashes don't leak orphans (Q-MR-2). Preventive
alerts (Q-MR-3) MultusMemoryPressure + NamespacePendingPodBacklog are coming
in a follow-up commit to apps/monitoring/.

Memory: feedback_multus_50mi_limit_oom_orphan_pod_avalanche
Decisions card: docs/dashboards/decisions-waiting.html Q-MR-1..3

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-11 10:30:05 -05:00
Codex
667777a653 revert(ci1): back to cdrom:scsi (virtio-blk disk hit QEMU flock)
The virtio-blk disk swap (commit 84c9feb) didn't help: qemu fails to
acquire the write lock on the rootdisk PVC because the previous
launcher's qemu process didn't release it cleanly. Same family of
bug as the "stale QEMU flock" already documented in
feedback_kubevirt_iso_first_install_bootorder_and_runstrategy, but
now triggered on rke2-agent1 instead of agent2.

OVMF cdrom timeout is the real blocker and remains open:
  -  Distribution pipeline (build → save → scp → ctr import on all
    3 RKE2 nodes) is proven. localhost/win-server-2025:1.0 lives in
    each node's containerd k8s.io namespace.
  -  containerDisk + cdrom:scsi gets qemu domain Running (no NFS
    Permission denied, no rootdisk flock).
  -  OVMF BdsDxe times out reading the SCSI cdrom regardless of
    SecureBoot setting and bus type.

Reverting the disk type to cdrom:scsi so the VM lands back on the
"qemu Running, OVMF stuck at Boot Manager" state — known-stable and
easier to attack than the QEMU-flock state we hit by trying
virtio-blk disk.

Operator decision for next architectural step (one of):
  - Custom OVMF firmware build with longer Boot0001 timeout
  - KubeVirt version bump (v1.5+ has OVMF fixes)
  - Hyper-V/VirtualBox install + export VHD to ci1
  - BIOS legacy boot (Win Server 2025 needs UEFI but install media
    has a BIOS path)
  - DataVolume HTTP datasource (CDI internalizes ISO bytes via
    different code path)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 21:35:00 -05:00
Codex
84c9feb893 fix(ci1): present ISO as virtio-blk disk instead of cdrom
OVMF BdsDxe "starting Boot0001 ... Time out" persists across:
  - SATA cdrom + Longhorn Filesystem PVC (Path A)
  - SATA cdrom + Synology NFS (Path B failed: storage perms)
  - SCSI cdrom + Longhorn (Path B variant)
  - SCSI cdrom + containerDisk tmpfs (Path C)
  - + SecureBoot=false

That rules out: storage IO speed, cdrom bus type, signature
verification. Remaining cause is deeper in qemu's cdrom device
emulation under KubeVirt v1.4.0's OVMF firmware — the cdrom read
window for OVMF's first-sector probe is too short to satisfy from
the cdrom controller path regardless of bus type.

Workaround: present the ISO bytes as a regular virtio-blk DISK
(not a cdrom). UEFI/OVMF still recognizes ISO9660 + El Torito
boot records on any block device, so it can find and boot the
EFI bootloader the same way it would from a USB stick. virtio-blk
has a different read path that doesn't hit the cdrom-specific
timeout.

This also better aligns with the FlowerCore.Distribution USB-key
pattern: ISO bytes on a block device, UEFI boots from the El
Torito boot record, Windows installer takes over. The autounattend
ConfigMap (ci1-autounattend) drives unattended Windows setup once
the installer kicks off.

The containerDisk OCI image (localhost/win-server-2025:1.0)
remains unchanged — only the disk type in the VM spec changes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 21:29:59 -05:00
Codex
427dbfcef2 [uc] Phase 1 auth gate deploy v20260509-4162dca-authgate 2026-05-08 21:16:54 -05:00
Codex
b651a4e2d0 fix(ci1): disable SecureBoot to allow OVMF to boot Windows ISO
containerDisk delivery (commit b998f50) successfully gave qemu fast
in-memory access to the ISO bytes (no NFS denial, no Longhorn read
latency), but OVMF's BdsDxe still timed out:

  BdsDxe: loading Boot0001 "UEFI QEMU QEMU CD-ROM " from
    PciRoot(0x0)/Pci(0x2,0x4)/Pci(0x0,0x0)/Scsi(0x0,0x0)
  BdsDxe: starting Boot0001 ... Time out

That rules out storage IO speed and bus type as causes (already
tested both sata and scsi against both Longhorn-PVC and tmpfs-backed
containerDisk). Remaining likely cause: SecureBoot signature
verification on the ISO's EFI bootloader. KubeVirt's stock
`/usr/share/OVMF/OVMF_VARS.secboot.fd` doesn't appear to ship with
the Microsoft KEK/DB enrolled by default, so signed Windows EFI
bootloaders fail the trust-chain check and OVMF reports a generic
"Time out" rather than a verification failure.

Disabling SecureBoot lets OVMF skip the chain check entirely and
boot the El Torito EFI image. SMM stays enabled (KubeVirt only
requires it WITH SecureBoot, not the inverse). TPM 2.0 emulation
also stays on (`tpm: {}`), so BitLocker, Hyper-V, and WSL2 still
work in the guest.

This is acceptable for a CI runner. Long-term path back to
SecureBoot:
  1. Custom-build OVMF_VARS.fd with Microsoft KEK/DB pre-enrolled
  2. Mount via firmware.bootloader.efi.persistent
  3. secureBoot: true

Tracked as a Phase 2 hardening task once the runner is doing real
work and we want signed-boot guarantees.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 21:06:18 -05:00
Codex
b998f50f48 fix(ci1): switch ISO delivery to containerDisk OCI image (Path C)
OCI image: localhost/win-server-2025:1.0 (8.27 GB)
Built FROM scratch + ADD disk.img → /disk/disk.img on noc1, podman
saved as tar (8.27 GB), SCP'd in parallel to all 3 RKE2 nodes,
imported via ctr in k8s.io namespace. Verified present on all 3
schedulable nodes (rke2-server, rke2-agent1, rke2-agent2).

Why containerDisk over the prior PVC paths:
  - Path A (Longhorn Filesystem PVC, sata): OVMF BdsDxe SATA-CDROM
    read timeout. Cdrom-backed PVC is too slow for OVMF's first-sector
    read window.
  - Path B (Synology NFS): uid 107 (qemu) denied at directory level by
    Synology export ACL despite file mode 0777. Memory:
    feedback_synology_iso_export_root_only_uid_107_denied.
  - Path B+SCSI: same OVMF timeout, just on SCSI controller. Bus
    choice was not load-bearing — the issue was always the slow PVC
    backing.
  - Path C (this commit): containerDisk delivers the ISO bytes from
    a tmpfs view of the OCI layer, no PVC controller in the read path.
    qemu reads at native FS speed; OVMF first-sector read completes
    well within timeout. This is also the KubeVirt-recommended pattern
    for installer ISOs.

Connects to FlowerCore.Distribution / Provisioning USB story: same
"OCI image of the OS installer + autounattend on a sysprep CDROM"
pattern that the USB provisioning agent will use. The Windows
install proceeds hands-off via the existing autounattend.xml in
ci1-autounattend ConfigMap (RDP enabled, WinRM, UAC disabled,
Administrator password from 1Password vault item
h3ix4mgfk65gmkcmvh6ly3d3hu).

Image lifecycle: bump tag (1.1, 1.2, ...) when ISO version changes,
rebuild on noc1, redistribute to RKE2 nodes, update image: line.

Legacy NFS PVC + PV manifest and CDI Longhorn PVC RETAINED for this
commit so prior states are recoverable. Will prune in follow-up
once containerDisk boot proves.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 20:45:38 -05:00
Codex
8fd9ae1cd3 fix(ci1): revert NFS Path B + flip ISO cdrom bus sata→scsi
NFS Path B (commit fc2aca0) failed at storage layer: Synology export
`/volume1/ISOs` denies non-root client UIDs at the directory level.
qemu uid 107 cannot `ls /iso/` even though disk.img is mode 0777.

Diagnosed via uid-107 + uid-0 busybox probe pods on rke2-agent2:
- libvirt error: "Cannot access storage file ... Permission denied"
  (virStorageSourceReportBrokenChain:1281, virError Code=38 Domain=18)
- uid 107 pod: "ls: can't open '/iso/': Permission denied"
- uid 0 pod (same mount): "drwxrwxrwx 1 root root 16 ... disk.img"
- SELinux Enforcing + virt_use_nfs=on, no AVC denials → not SELinux
- File mode 0777 with owner 107:107 → not POSIX

Same export-only-root pattern as `/volume1/kubernetes`. Memory:
feedback_synology_iso_export_root_only_uid_107_denied.md

Existing CDI-uploaded Longhorn PVC `windows-server-2025-iso` (10Gi
Filesystem mode) verified to contain valid ISO bytes readable by
uid 107 (mode 0660 root:107, 9.85 GB sparse, 8.27 GB blocks ≈
original 7.7 GB ISO). Reverting to it.

The original OVMF SATA-CDROM read timeout that drove yesterday's
NFS pivot is now addressed by `cdrom: bus: scsi` (virtio-scsi has
a longer read window than the IDE/SATA emulator). Per user-prompt
diagnostic chain Step 5.

NFS PVC + PV (apps/kubevirt-vms/win2025-iso-nfs-pv.yaml) RETAINED
so Path B state is recoverable; can be pruned in follow-up once
SCSI boot is proven.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 18:54:36 -05:00
Codex
fc2aca0e9e fix(ci1): mount Windows ISO via Synology NFS (Path B for SATA-CDROM timeout)
Previous fix attempts confirmed the Longhorn-backed Filesystem PVC contains
a perfectly valid bootable ISO9660 image. The bug is that SATA-CDROM
emulation reading from a Longhorn Filesystem PVC is too slow for OVMF's
boot read window — DVD-ROM enumeration times out before the bootloader
loads. Symptom on the serial console:
  BdsDxe: failed to start Boot0001 "UEFI QEMU DVD-ROM QM00001 " ... Time out
  BdsDxe: No bootable option or device was found

Block-mode PVC (Path A) was attempted and would likely fix the timing,
but CDI v1.65.0's upload-target pod cannot open the underlying block
device (runAsUser:107 + capabilities.drop:[ALL]):
  blockdev: cannot open /dev/cdi-block-volume: Permission denied

Path B (this change): mount the ISO directly from Synology NAS over
NFSv4.1. Bypasses both the Longhorn slowness and the CDI permission
issue. QEMU's SATA emulator reads at native LAN speed.

Layout:
  /volume1/ISOs/ — existing Synology export, RKE2 ACL already granted
  /volume1/ISOs/win2025-iso-disk/disk.img — new subdir, hardlink to the
    ISO file, named so KubeVirt's launcher finds it at the PV root

A hardlink (not symlink) is required because symlinks with relative
targets pointing to the parent directory are broken when the NFS PV
sub-mounts the subdir as its root.

Validated 2026-05-08 from rke2-server, rke2-agent1, rke2-agent2:
  mount -t nfs -o nfsvers=4.1,ro 10.0.58.3:/volume1/ISOs/win2025-iso-disk
  file disk.img -> ISO 9660 CD-ROM filesystem data ... (bootable)

The original Longhorn Filesystem ISO PVC is RETAINED unused (so ArgoCD
doesn't prune the populated PVC and so we have a fallback). Can be
removed in a follow-up commit after the NFS path is proven on a
successful Windows install.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 17:03:42 -05:00
Codex
ba18c52130 docs(ci1): record open rootdisk-flock and SATA-CDROM-timeout issues
Documenting the remaining 2 unresolved issues for the next operator
session, with the recovery paths from this session captured inline so
the next agent doesn't repeat the same blind alleys:

1. **rootdisk QEMU flock** — every new launcher pod fails QEMU start with
   `Failed to get "write" lock` on the rootdisk Filesystem-mode disk.img.
   Stale flock from a previous force-deleted virt-launcher pod. Longhorn
   engine on rke2-agent2 needs to release the lock; `kubectl patch
   volume.longhorn.io/<pvc-name> spec.nodeID=""` is reverted by the
   Longhorn controller. Operator-level recovery only.

2. **SATA CDROM read timeout** — even with bootOrder=1 (windows-iso first),
   OVMF UEFI fails Boot0001 with "Time out" reading the SATA CDROM backed
   by the Filesystem-mode PVC. Block-mode DataVolume migration was
   attempted but blocked by CDI v1.65.0's upload pod running with
   `capabilities.drop: [ALL]` and `runAsUser: 107`, preventing direct
   block-device writes (`blockdev: cannot open /dev/cdi-block-volume:
   Permission denied`). See ISO PVC header docstring for 3 forward paths.

Net commits during this session:
- 1c4145a: bootOrder swap (windows-iso=1, rootdisk=2)
- 87a7d7c: deprecated `running:` -> `runStrategy: Always`
- 0bf47df: ISO migration to Block-mode DataVolume (REVERTED)
- 9f6dc1a: revert to Filesystem PVC (CDI block-upload blocked)
- 1c4145a + 87a7d7c + 9f6dc1a are the live, correct configuration.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 15:18:38 -05:00
Codex
9f6dc1a9d5 fix(ci1): revert ISO to Filesystem PVC; CDI v1.65.0 block-upload pod blocked by capability drop
The Block-mode DataVolume migration (commit 0bf47df) hit a CDI v1.65.0 limitation:
the upload-target pod runs as uid 107 with `capabilities.drop: [ALL]`, so it
cannot open the underlying block device:

  blockdev: cannot open /dev/cdi-block-volume: Permission denied
  Saving stream failed: Unable to transfer source data to target file:
  error determining if block device exists: exit status 1

Reverting to a Filesystem-mode PVC + virtctl image-upload pvc, which DID work
(uploaded the 7.7 GiB ISO with valid ISO9660 magic intact). Boot timeout is
unresolved (header docstring captures the open issue + 3 paths to revisit).

The bootOrder swap (1c4145a) and runStrategy migration (87a7d7c) stay landed —
those are correct improvements regardless of the volume-mode question.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 14:32:52 -05:00
Codex
0bf47dfa33 fix(ci1): switch ISO from filesystem PVC to Block-mode DataVolume
The bootOrder swap alone didn't fix the install — even with `windows-iso` at
bootOrder:1, OVMF UEFI still timed out reading the SATA CDROM:

  BdsDxe: starting Boot0001 "UEFI QEMU DVD-ROM QM00001 " from ... Sata(...)
  BdsDxe: failed to start Boot0001 ... : Time out
  BdsDxe: No bootable option or device was found.

Diagnosis (debug pod mounting the live PVC):
- /pvc/disk.img IS a valid bootable ISO9660 image — `file` reports
  "ISO 9660 CD-ROM filesystem data 'SSS_X64FRE_EN-US_DV9' (bootable)".
- bytes 0..15: zeros (NOT QCOW2 magic 51 46 49 fb).
- bytes 32769..32773: "CD001" — ISO9660 primary volume descriptor at the
  correct offset.

So content was fine. The bug is in how KubeVirt + QEMU + Longhorn expose a
Filesystem-mode PVC's `/disk.img` as a SATA CDROM. With Block-mode the
underlying volume IS the raw ISO9660 sectors, OVMF reads them directly,
no QEMU file-emulation layer. This is the recommended pattern for ISO
install media on KubeVirt + Longhorn.

Migration:
- Replace `kind: PersistentVolumeClaim` with `kind: DataVolume` (CDI manages
  the underlying PVC + upload-target pod).
- Set `pvc.volumeMode: Block`.
- Annotate `cdi.kubevirt.io/storage.contentType: kubevirt` so CDI keeps raw
  bytes (no QCOW2 wrap).
- VM volume reference changes from `persistentVolumeClaim.claimName` to
  `dataVolume.name`. KubeVirt's VMI controller blocks VM start until DV
  phase is Succeeded (upload completed).

Operator step after this lands:
1. Wait for DV `phase: UploadReady`
   kubectl get dv -n kubevirt-vms windows-server-2025-iso -w
2. virtctl image-upload dv windows-server-2025-iso -n kubevirt-vms \
     --image-path "...\en-us_windows_server_2025...iso" \
     --uploadproxy-url https://localhost:8443 --insecure --no-create
3. Re-flip runStrategy to Always (was set to Halted live-side during
   migration; this commit keeps the manifest at Always).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 14:23:31 -05:00
Codex
87a7d7c70a fix(ci1): switch deprecated running: true -> runStrategy: Always
Required to clear OutOfSync state after the bootOrder fix. Live VM had
runStrategy: Halted (set during diagnosis to release the PVC for inspection).
Manifest had running: true. KubeVirt's validating webhook rejects sync:
  admission webhook "virtualmachine-validator.kubevirt.io" denied the request:
  Running and RunStrategy are mutually exclusive.

Switching to runStrategy: Always preserves the original "auto-start +
auto-restart" semantics with the non-deprecated field, and gives ArgoCD a
clean diff target to flip Halted -> Always.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 14:12:07 -05:00
Codex
1c4145a581 fix(ci1): swap bootOrder so Windows install ISO boots first
Original order: rootdisk=1 (empty 200Gi virtio), windows-iso=2 (SATA CDROM).
UEFI tried the empty virtio disk first, got nothing, fell back to Boot0001
(the SATA CDROM) with a short timeout, and aborted with:
  BdsDxe: failed to start Boot0001 ... Time out
  BdsDxe: No bootable option or device was found.

VM had been running 38+ min with rootdisk actualSize stuck at 4.13 GiB and
no AgentConnected condition — install never started.

Diagnosis via debug pod mounting the windows-server-2025-iso PVC:
  /pvc/disk.img: ISO 9660 CD-ROM filesystem data 'SSS_X64FRE_EN-US_DV9' (bootable)
  bytes 0..15: zeros (NOT QCOW2 magic 51 46 49 fb)
  bytes 32769..32773: "CD001" (ISO9660 primary volume descriptor)

So the PVC content is a real bootable ISO — the only fix needed is to make
the ISO bootOrder=1 for first install. After Windows installs, it writes its
own UEFI Boot#### entries pointing at the rootdisk EFI partition; UEFI then
boots from rootdisk going forward and the ISO at bootOrder:2 is a fallback
for re-install scenarios.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 14:10:17 -05:00
Codex
c50a403f74 fix(infra): pin virtio-container-disk to v1.8.2 (containerd 2.1 manifest fix)
KubeVirt v1.4.0 + RKE2 containerd 2.1.5 cannot pull
quay.io/kubevirt/virtio-container-disk:latest:
  rpc error: code = Unimplemented
  desc = failed to pull and unpack image: not implemented:
  media type "application/vnd.docker.distribution.manifest.v1+prettyjws"
  is no longer supported since containerd v2.1, please rebuild the image as
  "application/vnd.docker.distribution.manifest.v2+json" or
  "application/vnd.oci.image.manifest.v1+json"

The :latest tag was last rebuilt with the v1 manifest schema. Tagged versions
v1.6.5+, v1.7.3, v1.8.2 are rebuilt with v2/OCI manifests.

Pinning to v1.8.2 (newest available, contains current Windows VirtIO drivers).
The image only contains the Windows VirtIO driver ISO mounted as a CDROM —
not the KubeVirt runtime — so it is decoupled from the cluster KubeVirt
version.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 13:28:22 -05:00
Codex
fb7bd10528 feat(infra): activate ci1 VM — running:true + 10Gi ISO PVC + 1P password
Phase 1 prereqs all satisfied:
- Multus CNI v4.2.2 thick-plugin DS Running on rke2-server/agent1/agent2
- CDI v1.65.0 operator + CR Deployed (cdi-apiserver/deployment/uploadproxy
  all Running 1/1)
- Windows Server 2025 ISO (7.7GiB, March 2026 update) uploaded via CDI
  virtctl image-upload to PVC windows-server-2025-iso. Verified via PVC
  annotations: cdi.kubevirt.io/storage.condition.running.message="Upload
  Complete", storage.pod.phase="Succeeded"
- Local Administrator password generated (26 char, FANTASTIC strength).
  Stored in 1Password vault IAmWorkin (qaphopopkryhbg353ukzhhuqoq) item
  h3ix4mgfk65gmkcmvh6ly3d3hu. UTF-16-LE base64 in autounattend.xml Value
  field matches the 1P "autounattend AdministratorPassword Value" field.

Changes:
- ISO PVC bumped 6Gi → 10Gi (ISO is 7.7GiB, need headroom)
- Added labels app=ci-runner, flowercore.io/managed-by=bluejay-infra
- autounattend.xml AdministratorPassword Value: real base64-encoded password
- spec.running: false → true (VM starts on next ArgoCD sync)
- Header comment refreshed to LIVE state with prereq references

Network: still pod-network masquerade. Multus NAD prod-vlan57 is registered
but the VM doesn't use it yet (Phase 1.5 host bridge needed first).

Verify after sync:
  kubectl --kubeconfig $env:USERPROFILE\.kube\rke2.yaml -n kubevirt-vms get vm,vmi
  virtctl --kubeconfig $env:USERPROFILE\.kube\rke2.yaml vnc ci1 -n kubevirt-vms

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 13:24:46 -05:00
Codex
6c21d14a98 deploy(fc-updater): bump image to v20260508-pub3-deepening-2bdf108
Promotes the fleet to FlowerCore.Updater main @ 2bdf108 which combines:
- PR #6 publish pre-signed releases (1a188f4)
- PR #7 deeper public-host privacy enforcement (8cd8544)
- PublishPreSignedAsync(stream, sig) Integration coverage (2bdf108)

Live image already imported to rke2-server and rolled via deploy-web.ps1.
This commit aligns the bluejay-infra source of truth so ArgoCD doesn't
snap the spec back to the previous tag (per
feedback_argocd_managed_image_overrides_do_not_stick).
2026-05-08 13:07:24 -05:00
Codex
b3529f8e96 feat(infra): add Multus CNI + CDI + PROD VLAN 57 NAD as GitOps prereqs for ci1
Adds three new bluejay-infra apps that auto-pickup via ApplicationSet (apps/*
directory generator on main):

* apps/multus/multus.yaml — Multus CNI v4.2.2 thick-plugin daemonset (verbatim
  upstream, project-annotated). Enables KubeVirt VMs to attach additional
  network interfaces. Required by ci1 to bridge onto PROD VLAN 57.

* apps/cdi/{cdi-operator.yaml,cdi-cr.yaml,README.md} — Containerized Data
  Importer v1.65.0 (verbatim upstream). Operator + CR pattern. Enables
  populating PVCs from HTTP/registry/upload sources, used to load the Windows
  Server 2025 ISO into the windows-server-2025-iso PVC.

* apps/kubevirt-vms/prod-vlan57-nad.yaml — NetworkAttachmentDefinition for
  PROD VLAN 57 bridge. **Deploy gated on Phase 1.5 host work**: requires
  br-prod bridge enslaving enp86s0.57 on each RKE2 node (Puppet config-as-code).
  ci1.yaml continues to use pod-network masquerade until that lands; switching
  to multus.networkName: kubevirt-vms/prod-vlan57 is a one-line YAML edit
  followed by a GitOps push.

Cluster verification (2026-05-08):
- KubeVirt LIVE (3 nodes, virt-api/controller/handler/operator all Running)
- Calico CNI on /etc/cni/net.d + /opt/cni/bin (Multus default paths)
- ApplicationSet `bluejay-infra` already watches `apps/*` on main

Reproducibility: upstream YAMLs vendored verbatim with project header diffs
only. Bumping versions = re-curl + git push. No deploy-time internet fetch.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 13:05:58 -05:00
Codex
00c11b4eaa feat(infra): stage ci1 Windows Server 2025 KubeVirt VM (Phase 1, NOT YET APPLIED)
Stages a draft VirtualMachine + Namespace + ISO PVC + rootdisk PVC + sysprep
ConfigMap for the dedicated GitHub Actions self-hosted runner that replaces
the never-registered bluejay-ws-sandbox-1 placeholder.

Status: STAGED ONLY. spec.running = false. ISO PVC empty. Two operator
decisions still pending before this can boot:
  1. Network choice — pod-network fallback (in this draft) vs Multus +
     PROD VLAN NAD (preferred, requires Multus install).
  2. ISO path — manual upload via helper pod (Path A) vs CDI HTTP import
     (Path B, requires CDI install).

Cluster baseline 2026-05-08:
  - KubeVirt operator: installed, healthy, 14d
  - CDI: NOT installed
  - Multus: NOT installed
  - Calico-only CNI

See docs/infrastructure/windows-server-build-runner-plan.md "Phase 1 readiness
gate" for the full operator pickup checklist.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-08 12:32:47 -05:00
37 changed files with 8674 additions and 9 deletions

69
apps/cdi/README.md Normal file
View File

@@ -0,0 +1,69 @@
# CDI — Containerized Data Importer
KubeVirt's `containerized-data-importer` for populating PVCs from external
sources (HTTP, HTTPS, container registry, S3, virtctl upload). Required to
import the Windows Server 2025 ISO into the `windows-server-2025-iso` PVC
that `apps/kubevirt-vms/ci1.yaml` mounts as a CDROM.
## Files
| File | Source | Purpose |
| ----------------- | ----------------------------------------------------------------------------------------------------------------- | -------------------------------------------------- |
| `cdi-operator.yaml` | [`v1.65.0`](https://github.com/kubevirt/containerized-data-importer/releases/tag/v1.65.0) — verbatim copy | Installs operator + CRDs (5779 lines, large) |
| `cdi-cr.yaml` | [`v1.65.0`](https://github.com/kubevirt/containerized-data-importer/releases/tag/v1.65.0) — annotated + commented | Tells operator to deploy CDI components |
`cdi-operator.yaml` is **vendored verbatim** from the upstream release for
air-gap reproducibility (no internet fetch at deploy time, ArgoCD prune
contracts hold). To bump versions:
```bash
CDI_VER=v1.66.0 # for example
curl -sL "https://github.com/kubevirt/containerized-data-importer/releases/download/${CDI_VER}/cdi-operator.yaml" \
-o apps/cdi/cdi-operator.yaml
curl -sL "https://github.com/kubevirt/containerized-data-importer/releases/download/${CDI_VER}/cdi-cr.yaml" \
-o /tmp/cdi-cr-new.yaml # then re-apply project header diff
git diff apps/cdi/ # review
git commit + push
```
## Verify after deploy
```bash
kubectl -n cdi get pods # operator + apiserver + deployment + uploadproxy
kubectl get cdis cdi -o jsonpath='{.status.phase}' # "Deployed"
kubectl get crd | grep cdi.kubevirt.io
# Expected CRDs: datavolumes.cdi.kubevirt.io, cdiconfigs.cdi.kubevirt.io,
# storageprofiles.cdi.kubevirt.io, dataimportcrons.cdi.kubevirt.io,
# datasources.cdi.kubevirt.io, objecttransfers.cdi.kubevirt.io
```
## Use after install
```yaml
# Example DataVolume that imports from HTTP
apiVersion: cdi.kubevirt.io/v1beta1
kind: DataVolume
metadata:
name: my-iso
spec:
source:
http:
url: "https://server/path/to.iso"
pvc:
accessModes: [ReadWriteOnce]
resources:
requests:
storage: 10Gi
storageClassName: longhorn
```
```bash
# Or upload from local disk via virtctl
virtctl image-upload pvc my-iso \
--image-path ./my.iso \
--size 10Gi \
--storage-class longhorn \
--access-mode ReadWriteOnce \
--uploadproxy-url https://cdi-uploadproxy.cdi.svc:443 \
--insecure
```

36
apps/cdi/cdi-cr.yaml Normal file
View File

@@ -0,0 +1,36 @@
# =============================================================================
# CDI CR — Tells the CDI operator to install CDI components into the cluster.
# =============================================================================
# After cdi-operator.yaml is applied, the operator watches for THIS resource
# (CDI named "cdi"). When found, it deploys cdi-apiserver, cdi-deployment,
# cdi-uploadproxy, cdi-cronjob, and the importer/uploadserver/cloner pods.
#
# Configuration:
# - HonorWaitForFirstConsumer: PVCs created by DataVolumes wait for first
# pod to schedule before binding (lets storage class pick best node).
# - WebhookPvcRendering: validates PVC creation against CDI policies.
# - imagePullPolicy IfNotPresent: re-pull only on tag rotation.
# - nodeSelector linux: pin to Linux nodes (no Windows worker support).
#
# Andrew may want to add a `uploadProxyURLOverride` later to expose the
# uploadproxy via Traefik IngressRoute for `virtctl image-upload` from
# BLUEJAY-WS without `kubectl port-forward`. Phase 2 enhancement.
# =============================================================================
apiVersion: cdi.kubevirt.io/v1beta1
kind: CDI
metadata:
name: cdi
annotations:
bluejay.iamworkin.lan/source: "kubevirt/containerized-data-importer v1.65.0"
spec:
config:
featureGates:
- HonorWaitForFirstConsumer
- WebhookPvcRendering
imagePullPolicy: IfNotPresent
infra:
nodeSelector:
kubernetes.io/os: linux
workload:
nodeSelector:
kubernetes.io/os: linux

5779
apps/cdi/cdi-operator.yaml Normal file

File diff suppressed because it is too large Load Diff

171
apps/fc-redis/fc-redis.yaml Normal file
View File

@@ -0,0 +1,171 @@
# fc-redis — SignalR backplane for cross-product event bus
#
# Lands per Q-SO-1 resolution (2026-05-11 PM): SignalR backplane in Phase A,
# not Phase C as originally drafted. Operator directive: "Redis can be
# deployed just fine as it's another FlowerCore technology we'll want to
# manage."
#
# Phase A scope (this file):
# - Single Redis 7.x Alpine pod
# - 1Gi Longhorn RWO PVC for AOF persistence
# - ClusterIP Service at `redis.fc-redis.svc.cluster.local:6379`
# - No AUTH (in-cluster only; not exposed externally)
# - No IngressRoute (backplane is server-to-server only)
#
# Consumers (Phase A IMPL across FC services):
# - FlowerCore.Signage.Web (OpsConsoleHub)
# - FlowerCore.Scoreboard.Web (ScoreboardHub)
# - FlowerCore.SignalControl.Web
# - FlowerCore.DMS.Web
# - Any other product joining the cross-product event bus
#
# Each consumer adds:
# services.AddSignalR()
# .AddStackExchangeRedis(
# "redis.fc-redis.svc.cluster.local:6379",
# opts => opts.Configuration.ChannelPrefix =
# StackExchange.Redis.RedisChannel.Literal("fc-opsconsole"));
#
# Phase B / C follow-ons (out of scope here):
# - Redis Sentinel for HA (3-node)
# - AUTH password from 1Password Connect (rotate via /rotate-password)
# - redis_exporter sidecar for Prometheus scrape
# - Network policies restricting which namespaces can dial 6379
#
# Design: docs/signage/operations-console-phase-2-design.md §3.5
# Decision: Q-SO-1 (RESOLVED 2026-05-11 PM)
# Memory: feedback_blooming_ui_pattern_no_iframes
---
apiVersion: v1
kind: Namespace
metadata:
name: fc-redis
labels:
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: fc-redis-data
namespace: fc-redis
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 1Gi
---
apiVersion: v1
kind: ConfigMap
metadata:
name: fc-redis-config
namespace: fc-redis
data:
redis.conf: |
# Phase A — minimal config; no AUTH, no replication.
bind 0.0.0.0
protected-mode no
port 6379
tcp-backlog 511
timeout 0
tcp-keepalive 300
# Persistence: AOF (fsync every second is the standard SignalR-backplane
# durability sweet spot — the backplane only needs to survive Redis
# restarts, not absolute zero loss).
appendonly yes
appendfsync everysec
auto-aof-rewrite-percentage 100
auto-aof-rewrite-min-size 64mb
# Reasonable defaults — let Redis pick most things.
maxmemory-policy allkeys-lru
maxmemory 256mb
# Logging
loglevel notice
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: fc-redis
namespace: fc-redis
labels:
app: fc-redis
spec:
replicas: 1
strategy:
type: Recreate # RWO PVC; do not do rolling update
selector:
matchLabels:
app: fc-redis
template:
metadata:
labels:
app: fc-redis
spec:
securityContext:
runAsNonRoot: true
runAsUser: 999 # redis:7-alpine default uid
runAsGroup: 999
fsGroup: 999
containers:
- name: redis
image: redis:7-alpine
imagePullPolicy: IfNotPresent
command: ["redis-server", "/etc/redis/redis.conf"]
ports:
- name: redis
containerPort: 6379
resources:
requests:
cpu: "50m"
memory: "128Mi"
limits:
cpu: "500m"
memory: "384Mi"
volumeMounts:
- name: data
mountPath: /data
- name: config
mountPath: /etc/redis
readOnly: true
livenessProbe:
tcpSocket:
port: 6379
initialDelaySeconds: 5
periodSeconds: 10
readinessProbe:
exec:
command: ["redis-cli", "ping"]
initialDelaySeconds: 2
periodSeconds: 5
securityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop: [ALL]
volumes:
- name: data
persistentVolumeClaim:
claimName: fc-redis-data
- name: config
configMap:
name: fc-redis-config
---
apiVersion: v1
kind: Service
metadata:
name: redis
namespace: fc-redis
spec:
type: ClusterIP
selector:
app: fc-redis
ports:
- name: redis
port: 6379
targetPort: 6379
protocol: TCP

View File

@@ -0,0 +1,14 @@
# fc-signage-appletv
Apple TV signage is a sealed appliance running the `FlowerCore.Signage.Agent.AppleTv` tvOS app per ADR-134.
This ApplicationSet entry is documentation and inventory metadata only. It intentionally creates no `Deployment`, `Service`, or `Pod`.
The Apple TV app connects outbound to existing FC.Signage.Web surfaces:
- `https://signage.iamworkin.lan/hub/signage` for SignalR live status.
- `GET /api/v1/nodes/{nodeId}/state` for the 30 second polling fallback.
- `POST /api/v1/nodes/register` and `POST /api/v1/nodes/{nodeId}/enroll` for pairing and mTLS enrollment.
- `POST /api/v1/nodes/{nodeId}/heartbeat` for metrics, current content identity, and local audit excerpts.
Distribution is via Apple Developer Enterprise Program or TestFlight plus FC.Distribution / UpdateCenter publishing once Apple credentials are available.

View File

@@ -0,0 +1,5 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
resources:
- manifest.yaml

View File

@@ -0,0 +1,26 @@
# Apple TV signage is a sealed tvOS appliance. This ArgoCD app intentionally
# carries documentation metadata only; no Deployment, Service, or Pod resources
# are created for the player.
---
apiVersion: v1
kind: ConfigMap
metadata:
name: fc-signage-appletv-docs
namespace: fc-signage
labels:
app.kubernetes.io/name: fc-signage-appletv
app.kubernetes.io/part-of: flowercore-signage
flowercore.io/manifest-kind: docs-only
data:
README: |
FlowerCore.Signage.Agent.AppleTv is distributed through Apple Developer
Enterprise Program or TestFlight, not Kubernetes.
The app connects outbound to FC.Signage.Web:
- SignalR: https://signage.iamworkin.lan/hub/signage
- Polling fallback: GET /api/v1/nodes/{nodeId}/state
- Enrollment: POST /api/v1/nodes/{nodeId}/enroll
- Heartbeat: POST /api/v1/nodes/{nodeId}/heartbeat
This placeholder gives ArgoCD and inventory dashboards a first-class
Apple TV signage app entry without creating runtime pods.

View File

@@ -0,0 +1,17 @@
# FlowerCore Signage Pi Player
Phase 1 Raspberry Pi signage player packaging for Chromium kiosk deployments.
This bundle is intentionally air-gap friendly: systemd units, shell scripts,
udev rules, and Chromium managed policy are all checked into the repo and are
installed by `FlowerCore.Puppet`.
## Scope
- Bootstrap a stable node identity and mTLS client certificate.
- Launch Chromium in kiosk mode against `FC.Signage.Web` player routes.
- Restart the kiosk on HDMI hotplug.
- Renew mTLS certificates daily when fewer than 30 days remain.
- Detect display capabilities at boot, daily, and on HDMI hotplug.
Phase 2 native Avalonia rendering is documented separately in Notes and remains
deferred.

View File

@@ -0,0 +1,15 @@
{
"AutofillAddressEnabled": false,
"AutofillCreditCardEnabled": false,
"PasswordManagerEnabled": false,
"BrowserSignin": 0,
"MetricsReportingEnabled": false,
"SafeBrowsingProtectionLevel": 0,
"DefaultNotificationsSetting": 2,
"DefaultPopupsSetting": 2,
"BackgroundModeEnabled": false,
"DefaultBrowserSettingEnabled": false,
"PromotionalTabsEnabled": false,
"CommandLineFlagSecurityWarningsEnabled": false,
"ExtensionInstallBlocklist": ["*"]
}

View File

@@ -0,0 +1,132 @@
#!/usr/bin/env bash
set -euo pipefail
NODE_JSON="/etc/flowercore/signage-node.json"
CERT_DIR="/etc/fc-signage-player"
SIGNAGE_URL="${FC_SIGNAGE_URL:-https://signage.iamworkin.lan}"
NODE_ID=$(jq -r '.nodeId' "$NODE_JSON")
CONNECTORS=()
for dir in /sys/class/drm/card*-HDMI-A-*; do
[[ -e "$dir/status" ]] || continue
if [[ "$(cat "$dir/status")" == "connected" ]]; then
CONNECTORS+=("$(basename "$dir")")
fi
done
if [[ ${#CONNECTORS[@]} -eq 0 ]]; then
CAPABILITIES_JSON=$(jq -n --arg id "$NODE_ID" '{
nodeId: $id,
platform: "linux-arm64-pi",
displayConnected: false,
detectedAt: (now | todate),
note: "No HDMI display detected"
}')
else
PRIMARY="${CONNECTORS[0]}"
EDID_PATH="/sys/class/drm/${PRIMARY}/edid"
WIDTH=0
HEIGHT=0
REFRESH=60
HDR=false
AUDIO_HDMI=false
MFG=""
MODEL=""
PHYSICAL_SIZE=null
if [[ -s "$EDID_PATH" ]] && command -v edid-decode >/dev/null 2>&1; then
EDID_INFO=$(edid-decode < "$EDID_PATH" 2>/dev/null || true)
MFG=$(echo "$EDID_INFO" | grep -m1 -oP 'Manufacturer:\s*\K\S+' || true)
MODEL=$(echo "$EDID_INFO" | grep -m1 -oP 'Model:\s*\K\S+' || true)
PREF=$(echo "$EDID_INFO" | grep -m1 -oP '\d+x\d+\s*@\s*\d+(?:\.\d+)?\s*Hz' || true)
if [[ -n "$PREF" ]]; then
WIDTH=$(echo "$PREF" | grep -oP '^\d+')
HEIGHT=$(echo "$PREF" | grep -oP 'x\K\d+')
REFRESH=$(echo "$PREF" | grep -oP '@\s*\K[\d.]+' | cut -d. -f1)
fi
if echo "$EDID_INFO" | grep -qiE 'HDR (Static|Dynamic) Metadata Block'; then HDR=true; fi
if echo "$EDID_INFO" | grep -qiE 'CEA Audio Block|Audio Format Descriptor'; then AUDIO_HDMI=true; fi
PH_W=$(echo "$EDID_INFO" | grep -m1 -oP 'Maximum image size:\s*\K\d+\s*cm\s*x\s*\d+' || true)
if [[ -n "$PH_W" ]]; then
PH_CM_W=$(echo "$PH_W" | grep -oP '^\d+')
PH_CM_H=$(echo "$PH_W" | grep -oP 'x\s*\K\d+')
if (( PH_CM_W > 0 && PH_CM_H > 0 )); then
PHYSICAL_SIZE=$(awk -v w="$PH_CM_W" -v h="$PH_CM_H" 'BEGIN { printf "%.1f", sqrt(w*w + h*h)/2.54 }')
fi
fi
fi
if [[ "$WIDTH" == "0" ]] && command -v kmsprint >/dev/null 2>&1; then
KMS=$(kmsprint 2>/dev/null | grep -A2 "$PRIMARY" | grep -oP '\d+x\d+' | head -1 || true)
if [[ -n "$KMS" ]]; then
WIDTH=$(echo "$KMS" | grep -oP '^\d+')
HEIGHT=$(echo "$KMS" | grep -oP 'x\K\d+')
fi
fi
AUDIO_ALSA=false
if aplay -l 2>/dev/null | grep -qi 'card.*HDMI'; then AUDIO_ALSA=true; fi
HAS_AUDIO=false
if [[ "$AUDIO_HDMI" == "true" && "$AUDIO_ALSA" == "true" ]]; then HAS_AUDIO=true; fi
CAPABILITIES_JSON=$(jq -n \
--arg id "$NODE_ID" \
--argjson w "$WIDTH" \
--argjson h "$HEIGHT" \
--argjson r "$REFRESH" \
--argjson hdr "$HDR" \
--argjson audio "$HAS_AUDIO" \
--arg connector "$PRIMARY" \
--arg mfg "$MFG" \
--arg model "$MODEL" \
--argjson size "$PHYSICAL_SIZE" \
'{
nodeId: $id,
platform: "linux-arm64-pi",
displayConnected: true,
detectedAt: (now | todate),
hardware: {
maxResolution: { width: $w, height: $h },
nativeResolution: { width: $w, height: $h },
refreshRateHz: $r,
colorDepth: ($hdr | if . then "Color30Hdr" else "Color24" end),
hasAudioOutput: $audio,
audioChannelCount: ($audio | if . then 2 else 0 end),
physicalSizeInches: $size,
connector: $connector,
manufacturer: $mfg,
modelName: $model
},
render: { codecs: ["h264", "vp9", "mp4"] }
}')
fi
ENDPOINT_CANDIDATES=(
"${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/capabilities"
"${SIGNAGE_URL}/api/v1/displays/${NODE_ID}/capability-profile"
)
SUCCESS=false
for url in "${ENDPOINT_CANDIDATES[@]}"; do
HTTP_STATUS=$(curl -sk -o /tmp/cap-response.json -w "%{http_code}" \
--max-time 10 \
--cert "$CERT_DIR/client.crt" --key "$CERT_DIR/client.key" \
-X POST "$url" \
-H "Content-Type: application/json" \
-d "$CAPABILITIES_JSON" || echo "000")
if [[ "$HTTP_STATUS" == "200" || "$HTTP_STATUS" == "201" || "$HTTP_STATUS" == "204" ]]; then
SUCCESS=true
break
fi
done
mkdir -p /var/log/fc-signage-player
if [[ "$SUCCESS" != "true" ]]; then
echo "[$(date -Is)] capability declare: no endpoint accepted the profile; logging locally" \
| tee -a /var/log/fc-signage-player/capabilities.log
echo "$CAPABILITIES_JSON" | tee -a /var/log/fc-signage-player/capabilities.log
else
echo "[$(date -Is)] capability declare: ok ($url)" | tee -a /var/log/fc-signage-player/capabilities.log
fi
echo "$CAPABILITIES_JSON"

View File

@@ -0,0 +1,144 @@
#!/usr/bin/env bash
set -euo pipefail
NODE_JSON="/etc/flowercore/signage-node.json"
CERT_DIR="/etc/fc-signage-player"
SIGNAGE_URL="${FC_SIGNAGE_URL:-https://signage.iamworkin.lan}"
SETUP_CODE_FILE="/etc/flowercore/signage-setup-code"
mkdir -p /etc/flowercore "$CERT_DIR" /var/log/fc-signage-player
chown fc-signage:fc-signage /etc/flowercore "$CERT_DIR" /var/log/fc-signage-player
chmod 0750 "$CERT_DIR"
if [[ -s "$NODE_JSON" && -s "$CERT_DIR/client.p12" ]]; then
ENROLLED=$(jq -r '.enrolledAt // empty' "$NODE_JSON")
if [[ -n "$ENROLLED" ]]; then
echo "[$(date -Is)] bootstrap: already enrolled at $ENROLLED; skipping"
exit 0
fi
fi
if [[ -s "$NODE_JSON" ]]; then
NODE_UUID=$(jq -r '.nodeUuid // empty' "$NODE_JSON")
MACHINE_ID=$(jq -r '.machineId // empty' "$NODE_JSON")
else
NODE_UUID=$(uuidgen)
MACHINE_ID=$(echo "$NODE_UUID" | tr -d '-' | cut -c1-16)
jq -n --arg uuid "$NODE_UUID" --arg machine "$MACHINE_ID" --arg host "$(hostname -f)" --arg ts "$(date -Is)" \
'{nodeUuid: $uuid, machineId: $machine, hostname: $host, platform: "linux-arm64-pi", createdAt: $ts}' \
> "$NODE_JSON"
chmod 0640 "$NODE_JSON"
chown fc-signage:fc-signage "$NODE_JSON"
fi
SETUP_CODE=""
if [[ -s "$SETUP_CODE_FILE" ]]; then
SETUP_CODE=$(tr -d '\r\n\t ' < "$SETUP_CODE_FILE")
fi
MODEL=$(tr -d '\0' < /sys/firmware/devicetree/base/model 2>/dev/null || echo Unknown)
REG_PAYLOAD=$(jq -n \
--arg machine "$MACHINE_ID" \
--arg name "$(hostname -f)" \
--arg setup "$SETUP_CODE" \
--arg resolution "1920x1080" \
--arg model "$MODEL" \
'{
machineId: $machine,
name: $name,
setupCode: ($setup | if . == "" then null else . end),
resolution: $resolution,
hardwareModel: $model,
platform: "linux-arm64-pi"
}')
for attempt in 1 2; do
HTTP_STATUS=$(curl -sk -o /tmp/register-response.json -w "%{http_code}" \
--max-time 15 \
-X POST "${SIGNAGE_URL}/api/v1/nodes/register" \
-H "Content-Type: application/json" \
-d "$REG_PAYLOAD" || echo "000")
if [[ "$HTTP_STATUS" == "200" || "$HTTP_STATUS" == "201" ]]; then
break
fi
echo "[$(date -Is)] bootstrap: register attempt $attempt returned $HTTP_STATUS" >&2
sleep 5
done
if [[ "$HTTP_STATUS" != "200" && "$HTTP_STATUS" != "201" ]]; then
echo "[$(date -Is)] bootstrap: register failed after 2 attempts" >&2
exit 2
fi
NODE_ID=$(jq -r '.nodeId // empty' /tmp/register-response.json)
if [[ -z "$NODE_ID" ]]; then
echo "[$(date -Is)] bootstrap: register response did not include nodeId" >&2
exit 2
fi
jq --arg id "$NODE_ID" '.nodeId = $id' "$NODE_JSON" > "${NODE_JSON}.tmp" && mv "${NODE_JSON}.tmp" "$NODE_JSON"
if [[ -s "$SETUP_CODE_FILE" ]]; then
curl -sk -X POST "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/approve-via-setup-code" \
-H "Content-Type: application/json" \
-d "{\"setupCode\":\"${SETUP_CODE}\"}" \
-o /dev/null || true
fi
STATUS=""
DEADLINE=$(( $(date +%s) + 1800 ))
while (( $(date +%s) < DEADLINE )); do
STATUS=$(curl -sk --max-time 5 "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/status" | jq -r '.status // empty')
if [[ "$STATUS" == "Approved" || "$STATUS" == "Enrolled" || "$STATUS" == "Online" ]]; then
break
fi
sleep 15
done
if [[ "$STATUS" != "Approved" && "$STATUS" != "Enrolled" && "$STATUS" != "Online" ]]; then
echo "[$(date -Is)] bootstrap: approval not granted within 30min budget" >&2
exit 3
fi
KEY_PATH="${CERT_DIR}/client.key"
CSR_PATH="${CERT_DIR}/client.csr"
openssl ecparam -genkey -name prime256v1 -out "$KEY_PATH"
openssl req -new -key "$KEY_PATH" -out "$CSR_PATH" \
-subj "/CN=${NODE_ID}/O=FlowerCore/OU=SignagePlayer-Pi"
ENROLL_PAYLOAD=$(jq -n --arg csr "$(cat "$CSR_PATH")" '{certificateSigningRequest: $csr}')
HTTP_STATUS=$(curl -sk -o /tmp/enroll-response.json -w "%{http_code}" \
--max-time 15 \
-X POST "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/enroll" \
-H "Content-Type: application/json" \
-d "$ENROLL_PAYLOAD")
if [[ "$HTTP_STATUS" != "200" && "$HTTP_STATUS" != "201" ]]; then
echo "[$(date -Is)] bootstrap: enroll failed with HTTP $HTTP_STATUS" >&2
exit 4
fi
jq -r '.clientCertificatePem // .signedCertificatePem' /tmp/enroll-response.json > "${CERT_DIR}/client.crt"
jq -r '.caCertificatePem' /tmp/enroll-response.json > "${CERT_DIR}/ca-chain.pem"
P12_PASS=$(openssl rand -hex 24)
echo -n "$P12_PASS" > "${CERT_DIR}/client.p12.pass"
chmod 0600 "${CERT_DIR}/client.p12.pass"
openssl pkcs12 -export \
-inkey "$KEY_PATH" \
-in "${CERT_DIR}/client.crt" \
-certfile "${CERT_DIR}/ca-chain.pem" \
-out "${CERT_DIR}/client.p12" \
-password "pass:${P12_PASS}"
chown fc-signage:fc-signage "${CERT_DIR}"/* "$NODE_JSON"
chmod 0640 "${CERT_DIR}/client.p12" "${CERT_DIR}/client.crt" "${CERT_DIR}/ca-chain.pem" "$KEY_PATH"
chmod 0600 "${CERT_DIR}/client.p12.pass"
EXPIRY=$(openssl x509 -in "${CERT_DIR}/client.crt" -enddate -noout | sed 's/notAfter=//')
jq --arg ts "$(date -Is)" --arg exp "$EXPIRY" \
'.enrolledAt = $ts | .certExpiry = $exp' "$NODE_JSON" > "${NODE_JSON}.tmp" \
&& mv "${NODE_JSON}.tmp" "$NODE_JSON"
systemctl start flowercore-signage-detect-display.service || true
systemctl start flowercore-signage-player-pi.service || true
echo "[$(date -Is)] bootstrap: enrolled and kiosk started (NodeId=${NODE_ID})"

View File

@@ -0,0 +1,6 @@
#!/usr/bin/env bash
set -euo pipefail
sleep 2
systemctl start flowercore-signage-detect-display.service || true
systemctl restart flowercore-signage-player-pi.service

View File

@@ -0,0 +1,44 @@
#!/usr/bin/env bash
set -euo pipefail
NODE_JSON="/etc/flowercore/signage-node.json"
NODE_ID=$(jq -r '.nodeId' "$NODE_JSON")
SIGNAGE_URL="${FC_SIGNAGE_URL:-https://signage.iamworkin.lan}"
CERT_DIR="/etc/fc-signage-player"
CERT_THUMB=$(openssl pkcs12 -in "$CERT_DIR/client.p12" -passin file:"$CERT_DIR/client.p12.pass" -nodes -nokeys 2>/dev/null \
| openssl x509 -fingerprint -sha256 -noout \
| sed 's/.*=//' \
| tr -d ':')
PLAYER_URL="${SIGNAGE_URL}/player/${NODE_ID}/embed?token=${CERT_THUMB}"
HTTP_STATUS=$(curl -sk -o /dev/null -w "%{http_code}" --max-time 5 \
--cert-type P12 --cert "$CERT_DIR/client.p12:$(cat "$CERT_DIR/client.p12.pass")" \
"$PLAYER_URL" || echo "000")
mkdir -p /var/log/fc-signage-player
if [[ "$HTTP_STATUS" != "200" && "$HTTP_STATUS" != "301" && "$HTTP_STATUS" != "302" ]]; then
echo "[$(date -Is)] /embed returned $HTTP_STATUS; falling back to /player/${NODE_ID}" \
>> /var/log/fc-signage-player/url-divergence.log
PLAYER_URL="${SIGNAGE_URL}/player/${NODE_ID}?token=${CERT_THUMB}"
fi
exec chromium-browser \
--kiosk \
--noerrdialogs \
--disable-infobars \
--disable-translate \
--disable-features=TranslateUI,InfiniteSessionRestore \
--autoplay-policy=no-user-gesture-required \
--password-store=basic \
--user-data-dir=/var/lib/fc-signage-player/profile \
--disk-cache-dir=/var/lib/fc-signage-player/cache \
--disk-cache-size=104857600 \
--no-first-run \
--no-default-browser-check \
--check-for-update-interval=2592000 \
--enable-features=OverlayScrollbar \
--start-fullscreen \
--window-position=0,0 \
--window-size=1920,1080 \
"$PLAYER_URL"

View File

@@ -0,0 +1,20 @@
#!/usr/bin/env bash
set -euo pipefail
mkdir -p /var/log/fc-signage-player
for f in /etc/flowercore/signage-node.json /etc/fc-signage-player/client.p12 /etc/fc-signage-player/client.p12.pass; do
if [[ ! -r "$f" ]]; then
echo "[$(date -Is)] prelaunch: missing or unreadable $f" >&2
exit 1
fi
done
if openssl pkcs12 -in /etc/fc-signage-player/client.p12 -passin file:/etc/fc-signage-player/client.p12.pass -nokeys -clcerts 2>/dev/null \
| openssl x509 -checkend $((7*24*3600)) -noout; then
:
else
echo "[$(date -Is)] prelaunch: client cert expires within 7 days" >&2
fi
echo "[$(date -Is)] prelaunch: ok" | tee -a /var/log/fc-signage-player/prelaunch.log

View File

@@ -0,0 +1,46 @@
#!/usr/bin/env bash
set -euo pipefail
CERT_DIR="/etc/fc-signage-player"
NODE_JSON="/etc/flowercore/signage-node.json"
SIGNAGE_URL="${FC_SIGNAGE_URL:-https://signage.iamworkin.lan}"
[[ -s "$CERT_DIR/client.crt" ]] || { echo "no cert to renew"; exit 0; }
if openssl x509 -in "$CERT_DIR/client.crt" -checkend $((30*24*3600)) -noout; then
exit 0
fi
NODE_ID=$(jq -r '.nodeId' "$NODE_JSON")
NEW_KEY="$CERT_DIR/client.key.new"
NEW_CSR="$CERT_DIR/client.csr.new"
openssl ecparam -genkey -name prime256v1 -out "$NEW_KEY"
openssl req -new -key "$NEW_KEY" -out "$NEW_CSR" \
-subj "/CN=${NODE_ID}/O=FlowerCore/OU=SignagePlayer-Pi"
HTTP_STATUS=$(curl -sk -o /tmp/renew-response.json -w "%{http_code}" \
--cert "$CERT_DIR/client.crt" --key "$CERT_DIR/client.key" \
-X POST "${SIGNAGE_URL}/api/v1/nodes/${NODE_ID}/renew" \
-H "Content-Type: application/json" \
-d "$(jq -n --arg csr "$(cat "$NEW_CSR")" '{certificateSigningRequest: $csr}')")
if [[ "$HTTP_STATUS" != "200" && "$HTTP_STATUS" != "201" ]]; then
echo "[$(date -Is)] renew: failed HTTP $HTTP_STATUS; leaving old cert in place" >&2
exit 5
fi
jq -r '.clientCertificatePem // .signedCertificatePem' /tmp/renew-response.json > "$CERT_DIR/client.crt.new"
jq -r '.caCertificatePem' /tmp/renew-response.json > "$CERT_DIR/ca-chain.pem.new"
P12_PASS=$(cat "$CERT_DIR/client.p12.pass")
openssl pkcs12 -export -inkey "$NEW_KEY" -in "$CERT_DIR/client.crt.new" \
-certfile "$CERT_DIR/ca-chain.pem.new" \
-out "$CERT_DIR/client.p12.new" -password "pass:${P12_PASS}"
mv "$CERT_DIR/client.key.new" "$CERT_DIR/client.key"
mv "$CERT_DIR/client.crt.new" "$CERT_DIR/client.crt"
mv "$CERT_DIR/ca-chain.pem.new" "$CERT_DIR/ca-chain.pem"
mv "$CERT_DIR/client.p12.new" "$CERT_DIR/client.p12"
chown fc-signage:fc-signage "$CERT_DIR"/client.*
systemctl restart flowercore-signage-player-pi.service

View File

@@ -0,0 +1,3 @@
# Restart kiosk and redeclare capabilities when HDMI connect/disconnect changes DRM state.
SUBSYSTEM=="drm", KERNEL=="card?-HDMI-A-?", ACTION=="change", RUN+="/usr/bin/systemctl restart flowercore-signage-player-pi.service"
SUBSYSTEM=="drm", KERNEL=="card?-HDMI-A-?", ACTION=="change", RUN+="/usr/bin/systemctl start flowercore-signage-detect-display.service"

View File

@@ -0,0 +1,16 @@
[Unit]
Description=FlowerCore Signage Pi: first-boot identity + mTLS enrollment
Wants=network-online.target
After=network-online.target
Before=flowercore-signage-player-pi.service
[Service]
Type=oneshot
ExecStart=/usr/local/bin/flowercore-signage-bootstrap.sh
RemainAfterExit=yes
StandardOutput=journal
StandardError=journal
TimeoutStartSec=2100
[Install]
WantedBy=multi-user.target

View File

@@ -0,0 +1,8 @@
[Unit]
Description=FlowerCore Signage Pi: detect connected display + declare capabilities
After=flowercore-signage-bootstrap.service
[Service]
Type=oneshot
User=fc-signage
ExecStart=/usr/local/bin/fc-signage-detect-display

View File

@@ -0,0 +1,11 @@
[Unit]
Description=Daily FlowerCore Signage Pi display capability redeclaration
[Timer]
OnCalendar=daily
RandomizedDelaySec=1h
Persistent=true
OnBootSec=30s
[Install]
WantedBy=timers.target

View File

@@ -0,0 +1,7 @@
[Unit]
Description=FlowerCore Signage Pi Player HDMI hotplug responder
DefaultDependencies=no
[Service]
Type=oneshot
ExecStart=/usr/local/bin/flowercore-signage-hdmi-respond.sh

View File

@@ -0,0 +1,30 @@
[Unit]
Description=FlowerCore Digital Signage Pi Player (Chromium kiosk)
Documentation=https://github.com/astoltz/FlowerCore.Notes/blob/master/docs/standards/appletv-pi-signage-agents-design.md
Wants=network-online.target
After=network-online.target graphical.target
ConditionPathExists=/etc/flowercore/signage-node.json
ConditionPathExists=/etc/fc-signage-player/client.p12
[Service]
Type=simple
User=fc-signage
Group=fc-signage
WorkingDirectory=/var/lib/fc-signage-player
EnvironmentFile=-/etc/flowercore/signage-player.env
ExecStartPre=/usr/local/bin/flowercore-signage-prelaunch.sh
ExecStart=/usr/local/bin/flowercore-signage-launch.sh
Restart=always
RestartSec=10s
StartLimitBurst=5
StartLimitIntervalSec=300s
MemoryMax=2G
MemoryHigh=1500M
ProtectSystem=strict
ProtectHome=true
ReadWritePaths=/var/lib/fc-signage-player /var/log/fc-signage-player
PrivateTmp=true
NoNewPrivileges=true
[Install]
WantedBy=graphical.target

View File

@@ -0,0 +1,6 @@
[Unit]
Description=FlowerCore Signage Pi: cert renewal worker
[Service]
Type=oneshot
ExecStart=/usr/local/bin/flowercore-signage-renew-cert.sh

View File

@@ -0,0 +1,10 @@
[Unit]
Description=Daily check for FlowerCore Signage Pi cert renewal
[Timer]
OnCalendar=daily
RandomizedDelaySec=2h
Persistent=true
[Install]
WantedBy=timers.target

View File

@@ -58,7 +58,7 @@ spec:
nodeName: rke2-server nodeName: rke2-server
containers: containers:
- name: web - name: web
image: localhost/fc-updater-web:v20260507-public-privacy image: localhost/fc-updater-web:v20260509-4162dca-authgate
imagePullPolicy: Never imagePullPolicy: Never
ports: ports:
- containerPort: 8080 - containerPort: 8080

View File

@@ -0,0 +1,38 @@
# github-runner
ArgoCD-managed repo-scoped Linux GitHub Actions runners for FlowerCore.
`astoltz` is a GitHub user account, not an organization, so each repository
needs its own runner registration. The existing Common runner remains
`Deployment/github-runner`; Sprint 29 adds one single-replica Deployment for
each top Linux-cost repo:
- `FlowerCore.Puppet`
- `FlowerCore.Signage`
- `FlowerCore.DMS`
- `FlowerCore.Telephony`
- `FlowerCore.Print.Web`
- `FlowerCore.Chat`
- `FlowerCore.MySQL`
- `FlowerCore.Kiosk.Linux`
Each runner uses `myoung34/github-runner:latest`, `EPHEMERAL=true`, and labels
`self-hosted,linux,fc-build-linux`. The shared `github-runner-token` Secret is
synced from the existing 1Password item `GitHub PAT (Runner Registration)` and
is consumed as `ACCESS_TOKEN`.
Do not `kubectl apply` this app over ArgoCD. Merge to `main`, let
`infra-github-runner` sync, then verify from `noc1`:
```bash
kubectl -n github-runner get deploy,pods,pvc
for repo in FlowerCore.Puppet FlowerCore.Signage FlowerCore.DMS FlowerCore.Telephony FlowerCore.Print.Web FlowerCore.Chat FlowerCore.MySQL FlowerCore.Kiosk.Linux; do
gh api "/repos/astoltz/$repo/actions/runners" \
--jq '.runners[] | select((.labels[].name == "fc-build-linux") and (.status == "online")) | {name,status,busy,labels:[.labels[].name]}'
done
```
`LinuxRunnerOffline` is declared in `apps/monitoring/noc-monitoring.yaml` and
fires when any Common or top-8 Linux runner deployment has no available replica
for 10 minutes.

View File

@@ -0,0 +1,999 @@
# GitHub Actions self-hosted Linux runner fleet
#
# ArgoCD owns this namespace. Do not kubectl-apply ad hoc runner changes over
# it; update this manifest and let the bluejay-infra ApplicationSet reconcile.
#
# astoltz is a GitHub user account, not an org, so runners must be repo-scoped.
# Each Deployment below registers exactly one ephemeral myoung34/github-runner
# instance against one private FlowerCore repo using the shared PAT from the
# github-runner-token Secret.
#
# Current shape:
# - Common runner preserved from the phase-2 pilot.
# - Sprint 29 top-8 Linux-cost repos added first:
# Puppet, Signage, DMS, Telephony, Print.Web, Chat, MySQL, Kiosk.Linux.
#
# Security:
# - No ClusterRole / ClusterRoleBinding.
# - ServiceAccount has no K8s API privileges.
# - Self-hosted runners are for private repos and trusted branches only.
# - Fork pull-request approval must remain required in GitHub repo settings.
---
apiVersion: v1
kind: Namespace
metadata:
name: github-runner
labels:
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
---
# 1Password secret sync — creates github-runner-token K8s Secret.
# Fields expected in the 1Password item:
# credential — GitHub fine-grained PAT with Administration:read/write on
# each target repo. myoung34/github-runner uses ACCESS_TOKEN to
# mint fresh short-lived registration tokens at pod startup.
# Item path: IAmWorkin vault > "GitHub PAT (Runner Registration)"
apiVersion: onepassword.com/v1
kind: OnePasswordItem
metadata:
name: github-runner-token
namespace: github-runner
labels:
app.kubernetes.io/component: credentials
app.kubernetes.io/part-of: flowercore
spec:
itemPath: vaults/IAmWorkin/items/GitHub PAT (Runner Registration)
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: github-runner
namespace: github-runner
labels:
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: github-runner-nuget-cache
namespace: github-runner
labels:
app.kubernetes.io/component: cache
app.kubernetes.io/part-of: flowercore
flowercore.io/github-repo: FlowerCore.Common
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 5Gi
volumeMode: Filesystem
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: github-runner-puppet-nuget-cache
namespace: github-runner
labels:
app.kubernetes.io/component: cache
app.kubernetes.io/part-of: flowercore
flowercore.io/github-repo: FlowerCore.Puppet
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 5Gi
volumeMode: Filesystem
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: github-runner-signage-nuget-cache
namespace: github-runner
labels:
app.kubernetes.io/component: cache
app.kubernetes.io/part-of: flowercore
flowercore.io/github-repo: FlowerCore.Signage
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 5Gi
volumeMode: Filesystem
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: github-runner-dms-nuget-cache
namespace: github-runner
labels:
app.kubernetes.io/component: cache
app.kubernetes.io/part-of: flowercore
flowercore.io/github-repo: FlowerCore.DMS
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 5Gi
volumeMode: Filesystem
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: github-runner-telephony-nuget-cache
namespace: github-runner
labels:
app.kubernetes.io/component: cache
app.kubernetes.io/part-of: flowercore
flowercore.io/github-repo: FlowerCore.Telephony
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 5Gi
volumeMode: Filesystem
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: github-runner-print-web-nuget-cache
namespace: github-runner
labels:
app.kubernetes.io/component: cache
app.kubernetes.io/part-of: flowercore
flowercore.io/github-repo: FlowerCore.Print.Web
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 5Gi
volumeMode: Filesystem
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: github-runner-chat-nuget-cache
namespace: github-runner
labels:
app.kubernetes.io/component: cache
app.kubernetes.io/part-of: flowercore
flowercore.io/github-repo: FlowerCore.Chat
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 5Gi
volumeMode: Filesystem
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: github-runner-mysql-nuget-cache
namespace: github-runner
labels:
app.kubernetes.io/component: cache
app.kubernetes.io/part-of: flowercore
flowercore.io/github-repo: FlowerCore.MySQL
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 5Gi
volumeMode: Filesystem
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: github-runner-kiosk-linux-nuget-cache
namespace: github-runner
labels:
app.kubernetes.io/component: cache
app.kubernetes.io/part-of: flowercore
flowercore.io/github-repo: FlowerCore.Kiosk.Linux
spec:
accessModes:
- ReadWriteOnce
storageClassName: longhorn
resources:
requests:
storage: 5Gi
volumeMode: Filesystem
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: github-runner
namespace: github-runner
labels:
app.kubernetes.io/name: github-runner
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Common
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: github-runner
strategy:
type: Recreate
template:
metadata:
labels:
app.kubernetes.io/name: github-runner
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Common
spec:
serviceAccountName: github-runner
nodeSelector:
kubernetes.io/hostname: rke2-server
securityContext:
runAsNonRoot: true
runAsUser: 1001
runAsGroup: 1001
fsGroup: 1001
containers:
- name: runner
image: myoung34/github-runner:latest
imagePullPolicy: Always
env:
- name: REPO_URL
value: "https://github.com/astoltz/FlowerCore.Common"
- name: RUNNER_NAME_PREFIX
value: "rke2-linux"
- name: RUNNER_WORKDIR
value: "/tmp/runner/work"
- name: EPHEMERAL
value: "true"
- name: LABELS
value: "self-hosted,linux,fc-build-linux"
- name: ACCESS_TOKEN
valueFrom:
secretKeyRef:
name: github-runner-token
key: credential
- name: RUN_AS_ROOT
value: "false"
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "2000m"
memory: "4Gi"
volumeMounts:
- name: nuget-cache
mountPath: /home/runner/.nuget/packages
- name: tmp
mountPath: /tmp
livenessProbe:
exec:
command:
- /bin/sh
- -c
- "pgrep -f Runner.Listener > /dev/null"
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
volumes:
- name: nuget-cache
persistentVolumeClaim:
claimName: github-runner-nuget-cache
- name: tmp
emptyDir: {}
restartPolicy: Always
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: github-runner-puppet
namespace: github-runner
labels:
app.kubernetes.io/name: github-runner-puppet
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Puppet
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: github-runner-puppet
strategy:
type: Recreate
template:
metadata:
labels:
app.kubernetes.io/name: github-runner-puppet
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Puppet
spec:
serviceAccountName: github-runner
nodeSelector:
kubernetes.io/hostname: rke2-server
securityContext:
runAsNonRoot: true
runAsUser: 1001
runAsGroup: 1001
fsGroup: 1001
containers:
- name: runner
image: myoung34/github-runner:latest
imagePullPolicy: Always
env:
- name: REPO_URL
value: "https://github.com/astoltz/FlowerCore.Puppet"
- name: RUNNER_NAME_PREFIX
value: "rke2-linux-puppet"
- name: RUNNER_WORKDIR
value: "/tmp/runner/work"
- name: EPHEMERAL
value: "true"
- name: LABELS
value: "self-hosted,linux,fc-build-linux"
- name: ACCESS_TOKEN
valueFrom:
secretKeyRef:
name: github-runner-token
key: credential
- name: RUN_AS_ROOT
value: "false"
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "2000m"
memory: "4Gi"
volumeMounts:
- name: nuget-cache
mountPath: /home/runner/.nuget/packages
- name: tmp
mountPath: /tmp
livenessProbe:
exec:
command:
- /bin/sh
- -c
- "pgrep -f Runner.Listener > /dev/null"
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
volumes:
- name: nuget-cache
persistentVolumeClaim:
claimName: github-runner-puppet-nuget-cache
- name: tmp
emptyDir: {}
restartPolicy: Always
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: github-runner-signage
namespace: github-runner
labels:
app.kubernetes.io/name: github-runner-signage
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Signage
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: github-runner-signage
strategy:
type: Recreate
template:
metadata:
labels:
app.kubernetes.io/name: github-runner-signage
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Signage
spec:
serviceAccountName: github-runner
nodeSelector:
kubernetes.io/hostname: rke2-server
securityContext:
runAsNonRoot: true
runAsUser: 1001
runAsGroup: 1001
fsGroup: 1001
containers:
- name: runner
image: myoung34/github-runner:latest
imagePullPolicy: Always
env:
- name: REPO_URL
value: "https://github.com/astoltz/FlowerCore.Signage"
- name: RUNNER_NAME_PREFIX
value: "rke2-linux-signage"
- name: RUNNER_WORKDIR
value: "/tmp/runner/work"
- name: EPHEMERAL
value: "true"
- name: LABELS
value: "self-hosted,linux,fc-build-linux"
- name: ACCESS_TOKEN
valueFrom:
secretKeyRef:
name: github-runner-token
key: credential
- name: RUN_AS_ROOT
value: "false"
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "2000m"
memory: "4Gi"
volumeMounts:
- name: nuget-cache
mountPath: /home/runner/.nuget/packages
- name: tmp
mountPath: /tmp
livenessProbe:
exec:
command:
- /bin/sh
- -c
- "pgrep -f Runner.Listener > /dev/null"
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
volumes:
- name: nuget-cache
persistentVolumeClaim:
claimName: github-runner-signage-nuget-cache
- name: tmp
emptyDir: {}
restartPolicy: Always
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: github-runner-dms
namespace: github-runner
labels:
app.kubernetes.io/name: github-runner-dms
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.DMS
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: github-runner-dms
strategy:
type: Recreate
template:
metadata:
labels:
app.kubernetes.io/name: github-runner-dms
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.DMS
spec:
serviceAccountName: github-runner
nodeSelector:
kubernetes.io/hostname: rke2-server
securityContext:
runAsNonRoot: true
runAsUser: 1001
runAsGroup: 1001
fsGroup: 1001
containers:
- name: runner
image: myoung34/github-runner:latest
imagePullPolicy: Always
env:
- name: REPO_URL
value: "https://github.com/astoltz/FlowerCore.DMS"
- name: RUNNER_NAME_PREFIX
value: "rke2-linux-dms"
- name: RUNNER_WORKDIR
value: "/tmp/runner/work"
- name: EPHEMERAL
value: "true"
- name: LABELS
value: "self-hosted,linux,fc-build-linux"
- name: ACCESS_TOKEN
valueFrom:
secretKeyRef:
name: github-runner-token
key: credential
- name: RUN_AS_ROOT
value: "false"
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "2000m"
memory: "4Gi"
volumeMounts:
- name: nuget-cache
mountPath: /home/runner/.nuget/packages
- name: tmp
mountPath: /tmp
livenessProbe:
exec:
command:
- /bin/sh
- -c
- "pgrep -f Runner.Listener > /dev/null"
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
volumes:
- name: nuget-cache
persistentVolumeClaim:
claimName: github-runner-dms-nuget-cache
- name: tmp
emptyDir: {}
restartPolicy: Always
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: github-runner-telephony
namespace: github-runner
labels:
app.kubernetes.io/name: github-runner-telephony
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Telephony
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: github-runner-telephony
strategy:
type: Recreate
template:
metadata:
labels:
app.kubernetes.io/name: github-runner-telephony
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Telephony
spec:
serviceAccountName: github-runner
nodeSelector:
kubernetes.io/hostname: rke2-server
securityContext:
runAsNonRoot: true
runAsUser: 1001
runAsGroup: 1001
fsGroup: 1001
containers:
- name: runner
image: myoung34/github-runner:latest
imagePullPolicy: Always
env:
- name: REPO_URL
value: "https://github.com/astoltz/FlowerCore.Telephony"
- name: RUNNER_NAME_PREFIX
value: "rke2-linux-telephony"
- name: RUNNER_WORKDIR
value: "/tmp/runner/work"
- name: EPHEMERAL
value: "true"
- name: LABELS
value: "self-hosted,linux,fc-build-linux"
- name: ACCESS_TOKEN
valueFrom:
secretKeyRef:
name: github-runner-token
key: credential
- name: RUN_AS_ROOT
value: "false"
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "2000m"
memory: "4Gi"
volumeMounts:
- name: nuget-cache
mountPath: /home/runner/.nuget/packages
- name: tmp
mountPath: /tmp
livenessProbe:
exec:
command:
- /bin/sh
- -c
- "pgrep -f Runner.Listener > /dev/null"
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
volumes:
- name: nuget-cache
persistentVolumeClaim:
claimName: github-runner-telephony-nuget-cache
- name: tmp
emptyDir: {}
restartPolicy: Always
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: github-runner-print-web
namespace: github-runner
labels:
app.kubernetes.io/name: github-runner-print-web
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Print.Web
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: github-runner-print-web
strategy:
type: Recreate
template:
metadata:
labels:
app.kubernetes.io/name: github-runner-print-web
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Print.Web
spec:
serviceAccountName: github-runner
nodeSelector:
kubernetes.io/hostname: rke2-server
securityContext:
runAsNonRoot: true
runAsUser: 1001
runAsGroup: 1001
fsGroup: 1001
containers:
- name: runner
image: myoung34/github-runner:latest
imagePullPolicy: Always
env:
- name: REPO_URL
value: "https://github.com/astoltz/FlowerCore.Print.Web"
- name: RUNNER_NAME_PREFIX
value: "rke2-linux-print-web"
- name: RUNNER_WORKDIR
value: "/tmp/runner/work"
- name: EPHEMERAL
value: "true"
- name: LABELS
value: "self-hosted,linux,fc-build-linux"
- name: ACCESS_TOKEN
valueFrom:
secretKeyRef:
name: github-runner-token
key: credential
- name: RUN_AS_ROOT
value: "false"
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "2000m"
memory: "4Gi"
volumeMounts:
- name: nuget-cache
mountPath: /home/runner/.nuget/packages
- name: tmp
mountPath: /tmp
livenessProbe:
exec:
command:
- /bin/sh
- -c
- "pgrep -f Runner.Listener > /dev/null"
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
volumes:
- name: nuget-cache
persistentVolumeClaim:
claimName: github-runner-print-web-nuget-cache
- name: tmp
emptyDir: {}
restartPolicy: Always
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: github-runner-chat
namespace: github-runner
labels:
app.kubernetes.io/name: github-runner-chat
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Chat
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: github-runner-chat
strategy:
type: Recreate
template:
metadata:
labels:
app.kubernetes.io/name: github-runner-chat
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Chat
spec:
serviceAccountName: github-runner
nodeSelector:
kubernetes.io/hostname: rke2-server
securityContext:
runAsNonRoot: true
runAsUser: 1001
runAsGroup: 1001
fsGroup: 1001
containers:
- name: runner
image: myoung34/github-runner:latest
imagePullPolicy: Always
env:
- name: REPO_URL
value: "https://github.com/astoltz/FlowerCore.Chat"
- name: RUNNER_NAME_PREFIX
value: "rke2-linux-chat"
- name: RUNNER_WORKDIR
value: "/tmp/runner/work"
- name: EPHEMERAL
value: "true"
- name: LABELS
value: "self-hosted,linux,fc-build-linux"
- name: ACCESS_TOKEN
valueFrom:
secretKeyRef:
name: github-runner-token
key: credential
- name: RUN_AS_ROOT
value: "false"
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "2000m"
memory: "4Gi"
volumeMounts:
- name: nuget-cache
mountPath: /home/runner/.nuget/packages
- name: tmp
mountPath: /tmp
livenessProbe:
exec:
command:
- /bin/sh
- -c
- "pgrep -f Runner.Listener > /dev/null"
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
volumes:
- name: nuget-cache
persistentVolumeClaim:
claimName: github-runner-chat-nuget-cache
- name: tmp
emptyDir: {}
restartPolicy: Always
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: github-runner-mysql
namespace: github-runner
labels:
app.kubernetes.io/name: github-runner-mysql
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.MySQL
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: github-runner-mysql
strategy:
type: Recreate
template:
metadata:
labels:
app.kubernetes.io/name: github-runner-mysql
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.MySQL
spec:
serviceAccountName: github-runner
nodeSelector:
kubernetes.io/hostname: rke2-server
securityContext:
runAsNonRoot: true
runAsUser: 1001
runAsGroup: 1001
fsGroup: 1001
containers:
- name: runner
image: myoung34/github-runner:latest
imagePullPolicy: Always
env:
- name: REPO_URL
value: "https://github.com/astoltz/FlowerCore.MySQL"
- name: RUNNER_NAME_PREFIX
value: "rke2-linux-mysql"
- name: RUNNER_WORKDIR
value: "/tmp/runner/work"
- name: EPHEMERAL
value: "true"
- name: LABELS
value: "self-hosted,linux,fc-build-linux"
- name: ACCESS_TOKEN
valueFrom:
secretKeyRef:
name: github-runner-token
key: credential
- name: RUN_AS_ROOT
value: "false"
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "2000m"
memory: "4Gi"
volumeMounts:
- name: nuget-cache
mountPath: /home/runner/.nuget/packages
- name: tmp
mountPath: /tmp
livenessProbe:
exec:
command:
- /bin/sh
- -c
- "pgrep -f Runner.Listener > /dev/null"
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
volumes:
- name: nuget-cache
persistentVolumeClaim:
claimName: github-runner-mysql-nuget-cache
- name: tmp
emptyDir: {}
restartPolicy: Always
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: github-runner-kiosk-linux
namespace: github-runner
labels:
app.kubernetes.io/name: github-runner-kiosk-linux
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Kiosk.Linux
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: github-runner-kiosk-linux
strategy:
type: Recreate
template:
metadata:
labels:
app.kubernetes.io/name: github-runner-kiosk-linux
app.kubernetes.io/component: runner
app.kubernetes.io/part-of: flowercore
flowercore.io/created-by: argocd
flowercore.io/github-repo: FlowerCore.Kiosk.Linux
spec:
serviceAccountName: github-runner
nodeSelector:
kubernetes.io/hostname: rke2-server
securityContext:
runAsNonRoot: true
runAsUser: 1001
runAsGroup: 1001
fsGroup: 1001
containers:
- name: runner
image: myoung34/github-runner:latest
imagePullPolicy: Always
env:
- name: REPO_URL
value: "https://github.com/astoltz/FlowerCore.Kiosk.Linux"
- name: RUNNER_NAME_PREFIX
value: "rke2-linux-kiosk-linux"
- name: RUNNER_WORKDIR
value: "/tmp/runner/work"
- name: EPHEMERAL
value: "true"
- name: LABELS
value: "self-hosted,linux,fc-build-linux"
- name: ACCESS_TOKEN
valueFrom:
secretKeyRef:
name: github-runner-token
key: credential
- name: RUN_AS_ROOT
value: "false"
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "2000m"
memory: "4Gi"
volumeMounts:
- name: nuget-cache
mountPath: /home/runner/.nuget/packages
- name: tmp
mountPath: /tmp
livenessProbe:
exec:
command:
- /bin/sh
- -c
- "pgrep -f Runner.Listener > /dev/null"
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
volumes:
- name: nuget-cache
persistentVolumeClaim:
claimName: github-runner-kiosk-linux-nuget-cache
- name: tmp
emptyDir: {}
restartPolicy: Always

View File

@@ -466,11 +466,11 @@ spec:
itemPath: vaults/IAmWorkin/items/Guacamole JSON Auth itemPath: vaults/IAmWorkin/items/Guacamole JSON Auth
--- ---
--- ---
# 1Password-backed credentials for Mac mini VNC access (Phase 1 2026-04-28) # 1Password-backed credentials for Mac mini VNC access (Phase 1 <EFBFBD> 2026-04-28)
# The operator mints Secret 'macmini-vnc-creds' with keys: username, password, VNC Password # The operator mints Secret 'macmini-vnc-creds' with keys: username, password, VNC Password
# Note: '1Password' field label 'VNC Password' -> K8s Secret key 'VNC Password' (space retained) # Note: '1Password' field label 'VNC Password' -> K8s Secret key 'VNC Password' (space retained)
# Guacamole VNC connection password is sourced from the 'VNC Password' field. # Guacamole VNC connection password is sourced from the 'VNC Password' field.
# Actual IP is 10.0.56.115 (INFRA VLAN) the 1P item 'IP' field is kept as backup reference. # Actual IP is 10.0.56.115 (INFRA VLAN) <EFBFBD> the 1P item 'IP' field is kept as backup reference.
apiVersion: onepassword.com/v1 apiVersion: onepassword.com/v1
kind: OnePasswordItem kind: OnePasswordItem
metadata: metadata:
@@ -481,6 +481,7 @@ metadata:
app.kubernetes.io/part-of: flowercore app.kubernetes.io/part-of: flowercore
spec: spec:
itemPath: vaults/IAmWorkin/items/Mac Mini itemPath: vaults/IAmWorkin/items/Mac Mini
---
# Blue Jay Branding Extension (CSS + translations) # Blue Jay Branding Extension (CSS + translations)
apiVersion: v1 apiVersion: v1
kind: ConfigMap kind: ConfigMap

View File

@@ -0,0 +1,93 @@
# =============================================================================
# ci1 - Windows Server 2025 KubeVirt VM (GitHub Actions Self-Hosted Runner)
# =============================================================================
# Boots from the sysprepped containerDisk template built by the Windows VM
# sysprep pipeline. See docs/infrastructure/windows-vm-sysprep-pipeline.md.
# Path A/B/C install history is preserved in git log only.
# =============================================================================
apiVersion: v1
kind: Namespace
metadata:
name: kubevirt-vms
labels:
app.kubernetes.io/part-of: kubevirt-stack
pod-security.kubernetes.io/enforce: privileged
---
apiVersion: kubevirt.io/v1
kind: VirtualMachine
metadata:
name: ci1
namespace: kubevirt-vms
labels:
app: ci-runner
role: github-actions-runner
flowercore.io/managed-by: bluejay-infra
spec:
runStrategy: Always
template:
metadata:
labels:
app: ci-runner
role: github-actions-runner
kubevirt.io/vm: ci1
spec:
domain:
cpu:
cores: 8
sockets: 1
threads: 1
memory:
guest: 16Gi
resources:
requests:
memory: 16Gi
limits:
memory: 16Gi
clock:
utc: {}
timer:
hpet:
present: false
pit:
tickPolicy: delay
rtc:
tickPolicy: catchup
hyperv: {}
features:
acpi: {}
apic: {}
hyperv:
relaxed: {}
vapic: {}
spinlocks:
spinlocks: 8191
smm: {}
firmware:
bootloader:
efi:
secureBoot: false
devices:
tpm: {}
disks:
- name: rootdisk
disk:
bus: virtio
interfaces:
# Pod-network fallback for CI runner outbound traffic. Switch to
# prod-vlan57 once the bridge/NAD lane is ready for L2 access.
- name: default
masquerade: {}
model: virtio
machine:
type: q35
networks:
- name: default
pod: {}
volumes:
- name: rootdisk
containerDisk:
image: localhost/fc-win-server-2025:v1
imagePullPolicy: Never
terminationGracePeriodSeconds: 3600

View File

@@ -0,0 +1,3 @@
resources:
- ci1.yaml
- prod-vlan57-nad.yaml

View File

@@ -0,0 +1,69 @@
# =============================================================================
# NetworkAttachmentDefinition — PROD VLAN 57 bridge
# =============================================================================
# Purpose: makes KubeVirt VMs reachable on the PROD VLAN (10.0.57.0/24)
# alongside the existing pod network. Required for ci1 to bridge onto PROD
# (e.g. to provision/scrape edge1, edge2, kiosks, Pis on the same L2 segment).
#
# **DEPLOY GATE — Phase 1.5 host work required first**:
# On every RKE2 node (rke2-server, rke2-agent1, rke2-agent2):
# 1. Switch port (UniFi USL16LP) trunks VLAN 57 to the node — usually
# already true since BLUEJAY-WS reaches 10.0.57.x services. Verify
# with `ip link show enp86s0.57` after configuring sub-interface, OR
# `tcpdump -ni enp86s0 vlan 57` and ping a known PROD host.
# 2. Linux bridge `br-prod` enslaving `enp86s0.57` (VLAN sub-interface).
# NetworkManager profile examples in the runbook below.
# 3. Verify Multus DaemonSet `kube-multus-ds` is Ready on all nodes.
#
# Without those, applying this NAD has no effect except to register the CRD.
# A VM that requests this NAD with no bridge present will fail with:
# `error adding pod kubevirt-vms_ci1 to CNI network "prod-vlan57": failed to
# plumb VLAN: open /sys/class/net/br-prod/master: no such file or directory`
#
# Configuration notes:
# - cniVersion 0.3.1 to match Multus daemon-config.json
# - mtu 1500 (matches enp86s0 default; bump if jumbo frames configured)
# - bridge name `br-prod` is convention; if Puppet picks a different name
# (e.g. `br57`, `br-vlan57`), edit BOTH this NAD and the ci1.yaml
# interface block. Keep them in sync.
# - vlan: 0 because the host bridge already strips VLAN tag (br-prod sits
# on top of `enp86s0.57`). If we instead used a VLAN-aware bridge with
# trunk port, set vlan: 57 here. Current convention is VLAN-stripped at
# the sub-interface, so the bridge passes untagged frames.
#
# Apply:
# kubectl --kubeconfig $env:USERPROFILE\.kube\rke2.yaml apply -f apps/kubevirt-vms/prod-vlan57-nad.yaml
#
# Then update ci1.yaml networks: stanza to:
# - name: prod-net
# multus:
# networkName: kubevirt-vms/prod-vlan57
# and the interface block from `masquerade` to `bridge`.
# =============================================================================
---
# Namespace must exist already (created by ci1.yaml's first document).
# This file imports a NAD into that same namespace.
apiVersion: k8s.cni.cncf.io/v1
kind: NetworkAttachmentDefinition
metadata:
name: prod-vlan57
namespace: kubevirt-vms
annotations:
bluejay.iamworkin.lan/host-bridge: "br-prod (enslaves enp86s0.57)"
bluejay.iamworkin.lan/cidr: "10.0.57.0/24"
bluejay.iamworkin.lan/gateway: "10.0.57.1"
bluejay.iamworkin.lan/dns: "10.0.56.1 (pfSense Unbound)"
spec:
config: |
{
"cniVersion": "0.3.1",
"name": "prod-vlan57",
"type": "bridge",
"bridge": "br-prod",
"ipam": {},
"mtu": 1500,
"vlan": 0,
"promiscMode": true,
"preserveDefaultVlan": false
}

View File

@@ -0,0 +1,99 @@
# =============================================================================
# Windows Server 2025 ISO — Static NFS PV (Path B for SATA-CDROM timeout)
# =============================================================================
# Purpose: Mount the ISO from Synology NAS via NFS instead of from a Longhorn-
# backed Filesystem PVC.
#
# Why: SATA-CDROM emulation reading from a Longhorn-backed Filesystem PVC is
# too slow for OVMF's boot read window — the DVD-ROM enumeration times out
# before the bootloader can be read. Symptom on the serial console:
# BdsDxe: failed to start Boot0001 "UEFI QEMU DVD-ROM QM00001 " from ...
# BdsDxe: failed to start Boot0001 ... Time out
# BdsDxe: No bootable option or device was found
# Diagnosis confirmed the ISO content is a perfectly valid bootable ISO9660
# image — the bug is in the timing path between OVMF and Longhorn-backed
# storage, not in the ISO itself.
#
# Block-mode PVC was tried (`volumeMode: Block` via DataVolume) and would
# likely fix the timing, but CDI v1.65.0's upload-target pod cannot open the
# block device due to runAsUser:107 + capabilities.drop:[ALL] and we got:
# blockdev: cannot open /dev/cdi-block-volume: Permission denied
#
# NFS-mounted ISO bypasses both issues: no Longhorn slowness, no CDI upload
# pod permission concerns. The ISO is read directly from the NAS over a
# native NFSv4.1 mount that QEMU's SATA emulator can read at full LAN speed.
#
# Layout on Synology:
# /volume1/ISOs/ (existing export, RKE2 ACL)
# en-us_windows_server_2025_updated_march_2026_x64_dvd_8e06425a.iso
# win2025-iso-disk/ (new subdir, 2026-05-08)
# disk.img -> hardlink to ../en-us_windows_server_2025_..._8e06425a.iso
#
# KubeVirt's launcher pod expects a PVC mounted at
# /var/run/kubevirt-private/vmi-disks/<diskName>/disk.img — by mounting the
# `win2025-iso-disk/` subdir as the NFS PV root, `disk.img` lives at the PV's
# root and KubeVirt's CDROM emulator finds it without any path manipulation.
#
# A symlink would NOT work for sub-path NFS mounts (the relative target
# `../...iso` falls outside the sub-mount root). A hardlink works because it
# references the same inode regardless of mount point.
#
# Memory references:
# - feedback_synology_nfs_volume1_kubernetes_export_scoped (Synology export
# scoping pattern — but /volume1/ISOs export, unlike /volume1/kubernetes,
# does support sub-path mounts because Synology NFS is configured with
# pseudo-fs in NFSv4.1)
# - feedback_kubevirt_iso_first_install_bootorder_and_runstrategy (boot
# order / runStrategy gotchas, separate from the storage timing issue)
#
# Validation (2026-05-08, from rke2-server / rke2-agent1 / rke2-agent2):
# mount -t nfs -o nfsvers=4.1,ro 10.0.58.3:/volume1/ISOs/win2025-iso-disk /tmp/m
# file /tmp/m/disk.img
# -> ISO 9660 CD-ROM filesystem data 'SSS_X64FRE_EN-US_DV9' (bootable)
# All 3 RKE2 nodes can mount and read.
# =============================================================================
apiVersion: v1
kind: PersistentVolume
metadata:
name: windows-server-2025-iso-nfs
labels:
flowercore.io/iso: windows-server-2025
flowercore.io/managed-by: bluejay-infra
spec:
capacity:
storage: 8Gi
accessModes:
- ReadOnlyMany
volumeMode: Filesystem
persistentVolumeReclaimPolicy: Retain
storageClassName: "" # static, no provisioner
mountOptions:
- nfsvers=4.1
- ro
- hard
- timeo=600
- retrans=3
nfs:
server: 10.0.58.3 # BlueJayNAS Synology DS1621+ on HOME VLAN 58
path: /volume1/ISOs/win2025-iso-disk
readOnly: true
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: windows-server-2025-iso-nfs
namespace: kubevirt-vms
labels:
app: ci-runner
flowercore.io/managed-by: bluejay-infra
spec:
accessModes:
- ReadOnlyMany
volumeMode: Filesystem
resources:
requests:
storage: 8Gi
storageClassName: ""
volumeName: windows-server-2025-iso-nfs

View File

@@ -974,6 +974,52 @@ data:
summary: "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} replica mismatch" summary: "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} replica mismatch"
description: "Spec wants {{ $labels.spec_replicas }} but only {{ $value }} available. Likely a rollout stuck on probe failure, scheduling, or PVC." description: "Spec wants {{ $labels.spec_replicas }} but only {{ $value }} available. Likely a rollout stuck on probe failure, scheduling, or PVC."
- alert: LinuxRunnerOffline
expr: |
kube_deployment_status_replicas_available{namespace="github-runner",deployment=~"github-runner(|-(puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"} < 1
for: 10m
labels:
severity: warning
service: github-runner
alert_channel: thermal_print
annotations:
summary: "Linux GitHub Actions runner offline: {{ $labels.deployment }}"
description: "{{ $labels.deployment }} has no available runner pod for 10 minutes. GitHub jobs using [self-hosted, linux, fc-build-linux] for its repo will queue at $0 until the runner returns."
runbook_url: "https://gitea.iamworkin.lan/bluejay/FlowerCore.Notes/src/branch/master/docs/infrastructure/self-hosted-runner-fleet.md"
# Q-MR-3 (2026-05-11): multus memory pressure — catches the next OOM
# cascade BEFORE multus is OOM-killed cluster-wide. The 2026-05-10
# outage (21h) hit because no alert fired on the rising multus working
# set — only downstream blackbox / Traefik / service alerts. With
# 1Gi limit (bluejay-infra@eb8693e), 80% = ~800MiB; steady-state
# runs ~150-250MiB so this only fires when an avalanche starts.
- alert: MultusMemoryPressure
expr: |
container_memory_working_set_bytes{container="kube-multus"}
/ container_spec_memory_limit_bytes{container="kube-multus"} > 0.8
for: 5m
labels:
severity: critical
alert_channel: thermal_print
annotations:
summary: "kube-multus memory >80% of limit on {{ $labels.node }} for 5m"
description: "kube-multus working set is {{ $value | humanizePercentage }} of its memory limit on node {{ $labels.node }}. If this keeps climbing, multus will OOM and all new pod networking will halt cluster-wide (precedent: 2026-05-10 outage)."
# Q-MR-3 (2026-05-11): namespace pending-pod backlog — catches the
# operator-leak avalanche pattern BEFORE it cascades into a multus
# CNI OOM. Any FC operator (RemoteDesktop / Distribution / WorldBuilder)
# emitting pods without ownerReferences will accumulate them when
# the operator crashes. >25 pending pods in any namespace for 30m
# is the signal to investigate the reconciler.
- alert: NamespacePendingPodBacklog
expr: sum by (namespace) (kube_pod_status_phase{phase="Pending"}) > 25
for: 30m
labels:
severity: warning
annotations:
summary: "Namespace {{ $labels.namespace }} has {{ $value }} Pending pods for 30m"
description: "Pending pod count in {{ $labels.namespace }} exceeds 25 sustained for 30m. Likely operator-leak avalanche pattern — children emitted without ownerReferences. Risk of multus CNI OOM cascade."
# Longhorn storage health alerts. Required: longhorn scrape job # Longhorn storage health alerts. Required: longhorn scrape job
# (added 2026-04-26 — see scrape_configs above). The K8s events # (added 2026-04-26 — see scrape_configs above). The K8s events
# for "snapshot becomes not ready to use" are transient lifecycle # for "snapshot becomes not ready to use" are transient lifecycle
@@ -3394,6 +3440,33 @@ data:
relativeTimeRange: {from: 120, to: 0} relativeTimeRange: {from: 120, to: 0}
datasourceUid: __expr__ datasourceUid: __expr__
model: {type: threshold, expression: B, conditions: [{evaluator: {params: [1], type: lt}}], refId: C} model: {type: threshold, expression: B, conditions: [{evaluator: {params: [1], type: lt}}], refId: C}
- uid: linux-runner-offline
title: LinuxRunnerOffline
condition: C
for: 10m
noDataState: Alerting
execErrState: OK
annotations:
summary: Linux GitHub Actions runner offline
description: "A repo-scoped fc-build-linux runner deployment has no available pod. Jobs will queue at $0 until ArgoCD/K8s returns the runner."
runbook_url: "https://gitea.iamworkin.lan/bluejay/FlowerCore.Notes/src/branch/master/docs/infrastructure/self-hosted-runner-fleet.md"
labels:
severity: warning
service: github-runner
alert_channel: thermal_print
data:
- refId: A
relativeTimeRange: {from: 600, to: 0}
datasourceUid: prometheus
model: {expr: 'min by(deployment) (kube_deployment_status_replicas_available{namespace="github-runner",deployment=~"github-runner(|-(puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"})', instant: true, refId: A}
- refId: B
relativeTimeRange: {from: 600, to: 0}
datasourceUid: __expr__
model: {type: reduce, expression: A, reducer: last, refId: B}
- refId: C
relativeTimeRange: {from: 600, to: 0}
datasourceUid: __expr__
model: {type: threshold, expression: B, conditions: [{evaluator: {params: [1], type: lt}}], refId: C}
- uid: high-cpu - uid: high-cpu
title: High CPU (>85%) title: High CPU (>85%)
condition: C condition: C

297
apps/multus/multus.yaml Normal file
View File

@@ -0,0 +1,297 @@
# =============================================================================
# Multus CNI — Meta-CNI for multi-network attachment to pods/VMs
# =============================================================================
# Purpose: enable KubeVirt VMs (and any future workload) to attach additional
# network interfaces beyond the default Calico-managed pod network. Required
# for ci1 (Windows Server 2025 KubeVirt VM) to bridge onto PROD VLAN 57.
#
# Source: upstream k8snetworkplumbingwg/multus-cni v4.2.2
# https://github.com/k8snetworkplumbingwg/multus-cni/blob/v4.2.2/deployments/multus-daemonset-thick.yml
#
# Inlined verbatim (with project header + version pin annotation) for
# reproducibility and air-gap safety. Bumping versions = edit this file +
# git push. ArgoCD picks up via the bluejay-infra ApplicationSet
# (apps/* directory generator on main).
#
# Why thick plugin (not thin):
# - Thick = daemon + thin shim binary; daemon handles NAD watch + CRD reads
# centrally so each pod's CNI ADD doesn't hit the K8s API server. Better
# for clusters with many NAD-using pods.
# - Thin = each CNI ADD process directly contacts K8s API. Simpler but
# scales worse and has more failure modes.
# - KubeVirt + multi-VM workload pattern fits thick perfectly.
#
# Cluster context (verified 2026-05-08):
# - RKE2 v1.34.5 on 3 nodes (rke2-server, rke2-agent1, rke2-agent2)
# - Calico CNI (Tigera-managed) at /etc/cni/net.d + /opt/cni/bin (default)
# - openSUSE Leap 16, kernel 6.12, containerd 2.1.5
# - host bridge for PROD VLAN 57 = `br-prod` (PUPPET HOST WORK — see Phase 1.5
# in docs/infrastructure/windows-server-build-runner-plan.md)
#
# Version pin: snapshot-thick → pinning to v4.2.2 release tag at deploy time
# would require a private mirror of the image. Upstream `snapshot-thick` tag
# is updated on every release, so for now we trust upstream + Calico's
# established pattern. Pin to a specific SHA256 once we mirror to Gitea OCI.
#
# Apply (once committed to bluejay-infra main, ApplicationSet auto-syncs):
# git add apps/multus/multus.yaml && git commit && git push origin main
# # ArgoCD `infra-multus` Application appears within 3 min via ApplicationSet
#
# Verify:
# kubectl -n kube-system get ds kube-multus-ds
# kubectl -n kube-system rollout status ds kube-multus-ds
# kubectl get crd network-attachment-definitions.k8s.cni.cncf.io
# =============================================================================
---
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
name: network-attachment-definitions.k8s.cni.cncf.io
annotations:
bluejay.iamworkin.lan/source: "k8snetworkplumbingwg/multus-cni v4.2.2"
spec:
group: k8s.cni.cncf.io
scope: Namespaced
names:
plural: network-attachment-definitions
singular: network-attachment-definition
kind: NetworkAttachmentDefinition
shortNames:
- net-attach-def
versions:
- name: v1
served: true
storage: true
schema:
openAPIV3Schema:
description: 'NetworkAttachmentDefinition is a CRD schema specified by the Network Plumbing
Working Group to express the intent for attaching pods to one or more logical or physical
networks. More information available at: https://github.com/k8snetworkplumbingwg/multi-net-spec'
type: object
properties:
apiVersion:
type: string
kind:
type: string
metadata:
type: object
spec:
description: 'NetworkAttachmentDefinition spec defines the desired state of a network attachment'
type: object
properties:
config:
description: 'NetworkAttachmentDefinition config is a JSON-formatted CNI configuration'
type: string
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: multus
rules:
- apiGroups: ["k8s.cni.cncf.io"]
resources:
- '*'
verbs:
- '*'
- apiGroups:
- ""
resources:
- pods
- pods/status
verbs:
- get
- list
- update
- watch
- apiGroups:
- ""
- events.k8s.io
resources:
- events
verbs:
- create
- patch
- update
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: multus
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: multus
subjects:
- kind: ServiceAccount
name: multus
namespace: kube-system
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: multus
namespace: kube-system
---
kind: ConfigMap
apiVersion: v1
metadata:
name: multus-daemon-config
namespace: kube-system
labels:
tier: node
app: multus
data:
daemon-config.json: |
{
"chrootDir": "/hostroot",
"cniVersion": "0.3.1",
"logLevel": "verbose",
"logToStderr": true,
"cniConfigDir": "/host/etc/cni/net.d",
"multusAutoconfigDir": "/host/etc/cni/net.d",
"multusConfigFile": "auto",
"socketDir": "/host/run/multus/"
}
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: kube-multus-ds
namespace: kube-system
labels:
tier: node
app: multus
name: multus
spec:
selector:
matchLabels:
name: multus
updateStrategy:
type: RollingUpdate
template:
metadata:
labels:
tier: node
app: multus
name: multus
spec:
hostNetwork: true
hostPID: true
tolerations:
- operator: Exists
effect: NoSchedule
- operator: Exists
effect: NoExecute
serviceAccountName: multus
containers:
- name: kube-multus
image: ghcr.io/k8snetworkplumbingwg/multus-cni:snapshot-thick
command: [ "/usr/src/multus-cni/bin/multus-daemon" ]
# 2026-05-11: upstream default of 50Mi memory limit OOM-cascades when
# an operator-owned namespace accumulates >100 pending pods retrying
# CNI ADD. RemoteDesktop emitted 219 orphan rd-browser-only pods
# (missing OwnerReferences), kubelet's CNI ADD avalanche pushed multus
# over 50Mi, OOMKilled, restarted with even bigger backlog → loop.
# 21h cluster outage. See FlowerCore.Notes:
# feedback_multus_50mi_limit_oom_orphan_pod_avalanche.md
# 1Gi limit / 512Mi request comfortably handles a 200+ pod CNI
# catchup burst on 64GB nodes (nodes are <25% used in steady-state).
# Drop back toward 256Mi only after MultusMemoryPressure alert
# proves steady-state working set sits well below 200Mi.
resources:
requests:
cpu: "100m"
memory: "512Mi"
limits:
cpu: "100m"
memory: "1Gi"
securityContext:
privileged: true
terminationMessagePolicy: FallbackToLogsOnError
volumeMounts:
- name: cni
mountPath: /host/etc/cni/net.d
# multus-daemon expects that cnibin path must be identical between pod and container host.
# e.g. if the cni bin is in '/opt/cni/bin' on the container host side, then it should be mount to '/opt/cni/bin' in multus-daemon,
# not to any other directory, like '/opt/bin' or '/usr/bin'.
- name: cnibin
mountPath: /opt/cni/bin
- name: host-run
mountPath: /host/run
- name: host-var-lib-cni-multus
mountPath: /var/lib/cni/multus
- name: host-var-lib-kubelet
mountPath: /var/lib/kubelet
mountPropagation: HostToContainer
- name: host-run-k8s-cni-cncf-io
mountPath: /run/k8s.cni.cncf.io
- name: host-run-netns
mountPath: /run/netns
mountPropagation: HostToContainer
- name: multus-daemon-config
mountPath: /etc/cni/net.d/multus.d
readOnly: true
- name: hostroot
mountPath: /hostroot
mountPropagation: HostToContainer
- mountPath: /etc/cni/multus/net.d
name: multus-conf-dir
env:
- name: MULTUS_NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
initContainers:
- name: install-multus-binary
image: ghcr.io/k8snetworkplumbingwg/multus-cni:snapshot-thick
command:
- "sh"
- "-c"
- "cp /usr/src/multus-cni/bin/multus-shim /host/opt/cni/bin/multus-shim && cp /usr/src/multus-cni/bin/passthru /host/opt/cni/bin/passthru"
resources:
requests:
cpu: "10m"
memory: "15Mi"
securityContext:
privileged: true
terminationMessagePolicy: FallbackToLogsOnError
volumeMounts:
- name: cnibin
mountPath: /host/opt/cni/bin
mountPropagation: Bidirectional
terminationGracePeriodSeconds: 10
volumes:
- name: cni
hostPath:
path: /etc/cni/net.d
- name: cnibin
hostPath:
path: /opt/cni/bin
- name: hostroot
hostPath:
path: /
- name: multus-daemon-config
configMap:
name: multus-daemon-config
items:
- key: daemon-config.json
path: daemon-config.json
- name: host-run
hostPath:
path: /run
- name: host-var-lib-cni-multus
hostPath:
path: /var/lib/cni/multus
- name: host-var-lib-kubelet
hostPath:
path: /var/lib/kubelet
- name: host-run-k8s-cni-cncf-io
hostPath:
path: /run/k8s.cni.cncf.io
- name: host-run-netns
hostPath:
path: /run/netns/
- name: multus-conf-dir
hostPath:
path: /etc/cni/multus/net.d

View File

@@ -127,10 +127,13 @@ spec:
initContainers: initContainers:
- name: fix-data-perms - name: fix-data-perms
image: busybox:latest image: busybox:latest
# Also chown /shared-tts (hostPath /tmp/tts-audio) so the non-root # Must run as root to chown the hostPath /tmp/tts-audio that may be
# app user (uid 1654) can write Piper .sln16 files that Asterisk # root-owned after node reboot. Pod-level runAsNonRoot:true would
# reads at /var/lib/asterisk/sounds/tts. World-readable (755) is # otherwise inherit and chown would fail with EPERM (see Notes memory
# fine — Asterisk runs as a different uid in the other pod. # feedback_hostpath_initcontainer_chown_perms).
securityContext:
runAsUser: 0
runAsNonRoot: false
command: ["sh", "-c", "chown -R 1654:1654 /data && chown 1654:1654 /shared-tts && chmod 0755 /shared-tts"] command: ["sh", "-c", "chown -R 1654:1654 /data && chown 1654:1654 /shared-tts && chmod 0755 /shared-tts"]
volumeMounts: volumeMounts:
- name: telephony-data - name: telephony-data

View File

@@ -305,15 +305,17 @@ spec:
path: / path: /
port: 8080 port: 8080
initialDelaySeconds: 60 initialDelaySeconds: 60
timeoutSeconds: 5 timeoutSeconds: 15
periodSeconds: 10 periodSeconds: 10
failureThreshold: 3
readinessProbe: readinessProbe:
httpGet: httpGet:
path: / path: /
port: 8080 port: 8080
initialDelaySeconds: 30 initialDelaySeconds: 30
periodSeconds: 5 periodSeconds: 5
timeoutSeconds: 5 timeoutSeconds: 15
failureThreshold: 3
--- ---
apiVersion: v1 apiVersion: v1
kind: Service kind: Service

View File

@@ -54,6 +54,18 @@ public sealed class FleetManifestLintTests
"ttsreader-piper", "ttsreader-piper",
}; };
private static readonly IReadOnlyDictionary<string, string> TopLinuxRunnerRepos = new Dictionary<string, string>(StringComparer.Ordinal)
{
["github-runner-puppet"] = "https://github.com/astoltz/FlowerCore.Puppet",
["github-runner-signage"] = "https://github.com/astoltz/FlowerCore.Signage",
["github-runner-dms"] = "https://github.com/astoltz/FlowerCore.DMS",
["github-runner-telephony"] = "https://github.com/astoltz/FlowerCore.Telephony",
["github-runner-print-web"] = "https://github.com/astoltz/FlowerCore.Print.Web",
["github-runner-chat"] = "https://github.com/astoltz/FlowerCore.Chat",
["github-runner-mysql"] = "https://github.com/astoltz/FlowerCore.MySQL",
["github-runner-kiosk-linux"] = "https://github.com/astoltz/FlowerCore.Kiosk.Linux",
};
[Fact] [Fact]
public void IngressRoutes_MustKeepServiceReferencesInTheSameNamespace() public void IngressRoutes_MustKeepServiceReferencesInTheSameNamespace()
{ {
@@ -187,6 +199,76 @@ public sealed class FleetManifestLintTests
violations.Should().BeEmpty(); violations.Should().BeEmpty();
} }
[Fact]
public void GitHubRunnerFleet_MustRegisterTopLinuxReposAsRepoScopedDeployments()
{
var deployments = Inventory.Documents
.Where(document => document.Kind == "Deployment")
.Where(document => document.Namespace == "github-runner")
.ToDictionary(document => document.Name, StringComparer.Ordinal);
foreach (var expectedRunner in TopLinuxRunnerRepos)
{
deployments.Should().ContainKey(expectedRunner.Key);
var container = deployments[expectedRunner.Key].ContainerMappings().Should().ContainSingle().Subject;
EnvValue(container, "REPO_URL").Should().Be(expectedRunner.Value);
EnvValue(container, "EPHEMERAL").Should().Be("true");
EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux");
EnvValue(container, "ACCESS_TOKEN").Should().BeNull("ACCESS_TOKEN must come from github-runner-token Secret, not a literal");
EnvSecretName(container, "ACCESS_TOKEN").Should().Be("github-runner-token");
EnvSecretKey(container, "ACCESS_TOKEN").Should().Be("credential");
}
}
[Fact]
public void GitHubRunnerFleet_MustPreserveExistingCommonRunnerShape()
{
var common = Inventory.Documents
.Single(document => document.Kind == "Deployment"
&& document.Namespace == "github-runner"
&& document.Name == "github-runner");
var container = common.ContainerMappings().Should().ContainSingle().Subject;
EnvValue(container, "REPO_URL").Should().Be("https://github.com/astoltz/FlowerCore.Common");
EnvValue(container, "RUNNER_NAME_PREFIX").Should().Be("rke2-linux");
EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux");
var claimNames = common.MappingSequence("spec", "template", "spec", "volumes")
.Select(volume => ManifestNodeExtensions.Scalar(volume, "persistentVolumeClaim", "claimName"))
.Where(value => !string.IsNullOrWhiteSpace(value))
.ToList();
claimNames.Should().Contain("github-runner-nuget-cache");
}
[Fact]
public void GitHubRunnerFleet_MustUseOneRwoCachePerRepoScopedDeployment()
{
var pvcNames = Inventory.Documents
.Where(document => document.Kind == "PersistentVolumeClaim")
.Where(document => document.Namespace == "github-runner")
.Select(document => document.Name)
.ToHashSet(StringComparer.Ordinal);
foreach (var deploymentName in TopLinuxRunnerRepos.Keys)
{
var suffix = deploymentName["github-runner-".Length..];
pvcNames.Should().Contain($"github-runner-{suffix}-nuget-cache");
}
}
[Fact]
public void Monitoring_MustAlertWhenTopLinuxRunnerDeploymentIsUnavailable()
{
var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
monitoring.Should().Contain("LinuxRunnerOffline");
monitoring.Should().Contain("kube_deployment_status_replicas_available{namespace=\"github-runner\"");
monitoring.Should().Contain("github-runner(|-(puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))");
monitoring.Should().Contain("runbook_url: \"https://gitea.iamworkin.lan/bluejay/FlowerCore.Notes/src/branch/master/docs/infrastructure/self-hosted-runner-fleet.md\"");
}
[Fact] [Fact]
public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults() public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults()
{ {
@@ -314,6 +396,31 @@ public sealed class FleetManifestLintTests
$"{document.Descriptor} container '{containerName}' still uses {probeKey}.httpGet on /health.", $"{document.Descriptor} container '{containerName}' still uses {probeKey}.httpGet on /health.",
}; };
} }
private static string? EnvValue(YamlMappingNode container, string name)
{
return EnvMapping(container, name) is { } env ? ManifestNodeExtensions.Scalar(env, "value") : null;
}
private static string? EnvSecretName(YamlMappingNode container, string name)
{
return EnvMapping(container, name) is { } env
? ManifestNodeExtensions.Scalar(env, "valueFrom", "secretKeyRef", "name")
: null;
}
private static string? EnvSecretKey(YamlMappingNode container, string name)
{
return EnvMapping(container, name) is { } env
? ManifestNodeExtensions.Scalar(env, "valueFrom", "secretKeyRef", "key")
: null;
}
private static YamlMappingNode? EnvMapping(YamlMappingNode container, string name)
{
return ManifestNodeExtensions.MappingSequence(container, "env")
.SingleOrDefault(env => string.Equals(ManifestNodeExtensions.Scalar(env, "name"), name, StringComparison.Ordinal));
}
} }
internal sealed class ManifestInventory internal sealed class ManifestInventory

View File

@@ -0,0 +1,266 @@
using System.Text.Json;
using FluentAssertions;
using Xunit;
namespace BluejayInfraLint.Tests;
[Trait("Category", "Unit")]
public sealed class PiSignagePlayerArtifactTests
{
private static readonly string Root = FindRepoRoot();
private static readonly string AppRoot = Path.Combine(Root, "apps", "fc-signage-pi-player");
public static TheoryData<string> RequiredArtifacts => new()
{
"README.md",
"systemd/flowercore-signage-player-pi.service",
"systemd/flowercore-signage-player-pi-hdmi.service",
"systemd/flowercore-signage-bootstrap.service",
"systemd/flowercore-signage-renew.service",
"systemd/flowercore-signage-renew.timer",
"systemd/flowercore-signage-detect-display.service",
"systemd/flowercore-signage-detect-display.timer",
"systemd/99-flowercore-signage-hdmi.rules",
"chromium-policies/flowercore-signage.json",
"scripts/flowercore-signage-launch.sh",
"scripts/flowercore-signage-prelaunch.sh",
"scripts/flowercore-signage-bootstrap.sh",
"scripts/flowercore-signage-renew-cert.sh",
"scripts/flowercore-signage-hdmi-respond.sh",
"scripts/fc-signage-detect-display",
};
[Theory]
[MemberData(nameof(RequiredArtifacts))]
public void RequiredArtifacts_ArePresent(string relativePath)
{
File.Exists(Path.Combine(AppRoot, relativePath)).Should().BeTrue(relativePath);
}
[Fact]
public void PlayerService_UsesExpectedRestartAndMemoryGuards()
{
var unit = Read("systemd/flowercore-signage-player-pi.service");
unit.Should().Contain("Restart=always");
unit.Should().Contain("RestartSec=10s");
unit.Should().Contain("StartLimitBurst=5");
unit.Should().Contain("StartLimitIntervalSec=300s");
unit.Should().Contain("MemoryMax=2G");
}
[Fact]
public void PlayerService_IsGatedByNodeIdentityAndMtlsCertificate()
{
var unit = Read("systemd/flowercore-signage-player-pi.service");
unit.Should().Contain("ConditionPathExists=/etc/flowercore/signage-node.json");
unit.Should().Contain("ConditionPathExists=/etc/fc-signage-player/client.p12");
unit.Should().Contain("ExecStartPre=/usr/local/bin/flowercore-signage-prelaunch.sh");
}
[Fact]
public void LaunchScript_TriesEmbedThenFallsBackToBarePlayerRoute()
{
var script = Read("scripts/flowercore-signage-launch.sh");
script.Should().Contain("/player/${NODE_ID}/embed?token=${CERT_THUMB}");
script.Should().Contain("url-divergence.log");
script.Should().Contain("/player/${NODE_ID}?token=${CERT_THUMB}");
}
[Fact]
public void LaunchScript_DisablesChromiumPromptsAndRuntimeUpdates()
{
var script = Read("scripts/flowercore-signage-launch.sh");
script.Should().Contain("--noerrdialogs");
script.Should().Contain("--disable-infobars");
script.Should().Contain("--password-store=basic");
script.Should().Contain("--check-for-update-interval=2592000");
}
[Fact]
public void PrelaunchScript_AbortsWhenRequiredFilesAreMissing()
{
var script = Read("scripts/flowercore-signage-prelaunch.sh");
script.Should().Contain("for f in /etc/flowercore/signage-node.json /etc/fc-signage-player/client.p12 /etc/fc-signage-player/client.p12.pass");
script.Should().Contain("exit 1");
script.Should().Contain("-checkend $((7*24*3600))");
}
[Fact]
public void BootstrapScript_IsIdempotentWhenAlreadyEnrolled()
{
var script = Read("scripts/flowercore-signage-bootstrap.sh");
script.Should().Contain("already enrolled");
script.Should().Contain("exit 0");
script.Should().Contain(".enrolledAt");
}
[Fact]
public void BootstrapScript_GeneratesStableMachineIdFromUuid()
{
var script = Read("scripts/flowercore-signage-bootstrap.sh");
script.Should().Contain("uuidgen");
script.Should().Contain("cut -c1-16");
script.Should().Contain("machineId");
}
[Fact]
public void BootstrapScript_RetriesRegisterOnceForFirstCallRace()
{
var script = Read("scripts/flowercore-signage-bootstrap.sh");
script.Should().Contain("for attempt in 1 2");
script.Should().Contain("register attempt $attempt returned");
script.Should().Contain("sleep 5");
}
[Fact]
public void BootstrapScript_SupportsSetupCodeAndApprovalPollingBudget()
{
var script = Read("scripts/flowercore-signage-bootstrap.sh");
script.Should().Contain("signage-setup-code");
script.Should().Contain("approve-via-setup-code");
script.Should().Contain("+ 1800");
script.Should().Contain("sleep 15");
}
[Fact]
public void BootstrapScript_CsrSubjectIdentifiesPiPlayer()
{
var script = Read("scripts/flowercore-signage-bootstrap.sh");
script.Should().Contain("/CN=${NODE_ID}/O=FlowerCore/OU=SignagePlayer-Pi");
}
[Fact]
public void BootstrapScript_PersistsCertificateAsP12WithRestrictivePermissions()
{
var script = Read("scripts/flowercore-signage-bootstrap.sh");
script.Should().Contain("openssl pkcs12 -export");
script.Should().Contain("client.p12.pass");
script.Should().Contain("chmod 0600");
script.Should().Contain("chmod 0640");
}
[Fact]
public void RenewScript_OnlyRunsWhenCertHasLessThanThirtyDays()
{
var script = Read("scripts/flowercore-signage-renew-cert.sh");
script.Should().Contain("-checkend $((30*24*3600))");
script.Should().Contain("exit 0");
script.Should().Contain("/renew");
}
[Fact]
public void RenewScript_AtomicallySwapsNewCertificateFiles()
{
var script = Read("scripts/flowercore-signage-renew-cert.sh");
script.Should().Contain("client.key.new");
script.Should().Contain("mv \"$CERT_DIR/client.key.new\" \"$CERT_DIR/client.key\"");
script.Should().Contain("mv \"$CERT_DIR/client.p12.new\" \"$CERT_DIR/client.p12\"");
}
[Fact]
public void HdmiRule_RestartsPlayerAndRunsCapabilityDetection()
{
var rule = Read("systemd/99-flowercore-signage-hdmi.rules");
rule.Should().Contain("KERNEL==\"card?-HDMI-A-?\"");
rule.Should().Contain("restart flowercore-signage-player-pi.service");
rule.Should().Contain("start flowercore-signage-detect-display.service");
}
[Fact]
public void DetectDisplayServiceAndTimer_RunAtBootAndDaily()
{
var service = Read("systemd/flowercore-signage-detect-display.service");
var timer = Read("systemd/flowercore-signage-detect-display.timer");
service.Should().Contain("ExecStart=/usr/local/bin/fc-signage-detect-display");
timer.Should().Contain("OnBootSec=30s");
timer.Should().Contain("OnCalendar=daily");
timer.Should().Contain("RandomizedDelaySec=1h");
}
[Fact]
public void DetectDisplayScript_EmitsDisconnectedProfileWhenNoHdmiIsPresent()
{
var script = Read("scripts/fc-signage-detect-display");
script.Should().Contain("displayConnected: false");
script.Should().Contain("No HDMI display detected");
}
[Fact]
public void DetectDisplayScript_ParsesEdidForHdrResolutionAndAudio()
{
var script = Read("scripts/fc-signage-detect-display");
script.Should().Contain("edid-decode");
script.Should().Contain("HDR (Static|Dynamic) Metadata Block");
script.Should().Contain("maxResolution");
script.Should().Contain("hasAudioOutput");
}
[Fact]
public void DetectDisplayScript_TriesBothForwardCompatibleCapabilityEndpoints()
{
var script = Read("scripts/fc-signage-detect-display");
script.Should().Contain("/api/v1/nodes/${NODE_ID}/capabilities");
script.Should().Contain("/api/v1/displays/${NODE_ID}/capability-profile");
script.Should().Contain("no endpoint accepted the profile");
}
[Fact]
public void ChromiumPolicy_IsValidJsonAndDisablesCredentialPrompts()
{
using var doc = JsonDocument.Parse(Read("chromium-policies/flowercore-signage.json"));
var root = doc.RootElement;
root.GetProperty("AutofillAddressEnabled").GetBoolean().Should().BeFalse();
root.GetProperty("AutofillCreditCardEnabled").GetBoolean().Should().BeFalse();
root.GetProperty("PasswordManagerEnabled").GetBoolean().Should().BeFalse();
root.GetProperty("ExtensionInstallBlocklist")[0].GetString().Should().Be("*");
}
[Fact]
public void RenewalTimer_UsesDailyCadenceWithTwoHourJitter()
{
var timer = Read("systemd/flowercore-signage-renew.timer");
timer.Should().Contain("OnCalendar=daily");
timer.Should().Contain("RandomizedDelaySec=2h");
timer.Should().Contain("Persistent=true");
}
private static string Read(string relativePath)
=> File.ReadAllText(Path.Combine(AppRoot, relativePath.Replace('/', Path.DirectorySeparatorChar)));
private static string FindRepoRoot()
{
var current = new DirectoryInfo(AppContext.BaseDirectory);
while (current is not null)
{
if (Directory.Exists(Path.Combine(current.FullName, "apps"))
&& File.Exists(Path.Combine(current.FullName, "README.md")))
{
return current.FullName;
}
current = current.Parent;
}
throw new DirectoryNotFoundException("Could not find bluejay-infra root.");
}
}