Compare commits

...

3 Commits

Author SHA1 Message Date
Codex
783720cc58 feat(fc-devicemgmt): add Kubernetes deployment manifests 2026-05-17 21:55:33 -05:00
Andrew Stoltz
6fe77225ae fix(github-runner): dedupe DOTNET_INSTALL_DIR+NUGET_PACKAGES on base+sharedpos
PR #5 rebase concatenated PR #5 env additions onto PR #7 env additions on
the base + sharedpos Deployments, producing duplicate-key validation
errors in ArgoCD's structured merge. The DOTNET_INSTALL_DIR and
NUGET_PACKAGES values are identical between PR #5 and PR #7; keep the
PR #7 originals and retain only the unique new env vars from PR #5
(DOTNET_CLI_TELEMETRY_OPTOUT, DOTNET_NOLOGO, DOTNET_GENERATE_ASPNET_CERTIFICATE).

No behavioral change — same final env var set, no duplicates.
2026-05-17 21:53:05 -05:00
634b9c4169 feat(github-runner): harden Linux runner fleet (#5) 2026-05-18 02:51:02 +00:00
16 changed files with 2325 additions and 53 deletions

View File

@@ -0,0 +1,26 @@
# Runtime secrets for FlowerCore.DeviceManagement.
#
# OnePasswordItem operator syncs this item into a Kubernetes Secret with the
# same name. Expected fields:
# DB-Password
# mtls-ca.pem
# mtls-client.crt
# mtls-client.key
# mtls-chain.pem
#
# Do not add literal secret values to this repo. Runtime pods consume the
# synced Secret through env vars and read-only mounts.
apiVersion: onepassword.com/v1
kind: OnePasswordItem
metadata:
name: fc-devicemgmt-runtime
namespace: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt
app.kubernetes.io/component: secrets
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
itemPath: "vaults/IAmWorkin/items/FlowerCore DeviceManagement Runtime"

View File

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

View File

@@ -0,0 +1,30 @@
# Certificate for devices.iamworkin.lan.
#
# Preflight gate: FlowerCore.DNS / pfSense must contain an explicit A record:
# devices.iamworkin.lan -> 10.0.56.200
# before this Certificate is synced. step-ca ACME cannot see the CoreDNS
# wildcard, so missing pfSense DNS produces cert-manager HTTP-01 backoff
# (feedback_pfsense_dns_required_for_acme).
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: fc-devicemgmt-web-tls
namespace: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
flowercore.io/dns-preflight: "devices.iamworkin.lan must resolve to 10.0.56.200 before ACME sync"
spec:
secretName: fc-devicemgmt-web-tls
issuerRef:
name: step-ca-acme
kind: ClusterIssuer
dnsNames:
- devices.iamworkin.lan
duration: 720h
renewBefore: 240h

View File

@@ -0,0 +1,81 @@
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: fc-devicemgmt-operator
labels:
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
rules:
- apiGroups:
- devices.flowercore.io
resources:
- '*'
verbs:
- get
- list
- watch
- create
- update
- patch
- delete
- apiGroups:
- devices.flowercore.io
resources:
- devices/status
- devices/finalizers
- devicegroups/status
- devicegroups/finalizers
- devicepolicies/status
- devicepolicies/finalizers
- remotecommands/status
- remotecommands/finalizers
verbs:
- get
- update
- patch
- apiGroups:
- apps
resources:
- deployments
verbs:
- get
- apiGroups:
- ""
resources:
- pods
- services
- configmaps
- secrets
- events
verbs:
- get
- list
- watch
- create
- update
- patch
- delete
- apiGroups:
- batch
resources:
- jobs
verbs:
- get
- list
- watch
- create
- update
- patch
- delete
- apiGroups:
- networking.k8s.io
resources:
- networkpolicies
verbs:
- get
- list
- watch

View File

@@ -0,0 +1,19 @@
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: fc-devicemgmt-operator
labels:
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: fc-devicemgmt-operator
subjects:
- kind: ServiceAccount
name: fc-devicemgmt-operator
namespace: fc-devicemgmt

View File

@@ -0,0 +1,109 @@
# FlowerCore.DeviceManagement Operator.
#
# KubeOps controller for devices.flowercore.io resources. Operator-created
# children must set OwnerReferences + traceability labels/annotations per
# k8s-pod-ownership-and-traceability-standard.md. RBAC below grants
# apps/deployments/get so the process can resolve its own Deployment UID.
apiVersion: apps/v1
kind: Deployment
metadata:
name: fc-devicemgmt-operator
namespace: fc-devicemgmt
labels:
app: fc-devicemgmt-operator
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
spec:
replicas: 1
revisionHistoryLimit: 3
selector:
matchLabels:
app: fc-devicemgmt-operator
template:
metadata:
labels:
app: fc-devicemgmt-operator
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
prometheus.io/scrape: "true"
prometheus.io/port: "8080"
prometheus.io/path: "/metrics"
flowercore.io/audit-trace-id: "runtime-activity-trace"
spec:
serviceAccountName: fc-devicemgmt-operator
securityContext:
fsGroup: 1654
fsGroupChangePolicy: OnRootMismatch
containers:
- name: operator
image: localhost/fc-devicemgmt-operator:v20260512-cx5
imagePullPolicy: Never
ports:
- name: metrics
containerPort: 8080
env:
- name: ASPNETCORE_ENVIRONMENT
value: "Production"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false"
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
- name: POD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: FLOWERCORE_KUBERNETES_OWNER_DEPLOYMENT
value: "fc-devicemgmt-operator"
- name: FlowerCore__Service__Name
value: "FlowerCore.DeviceManagement.Operator"
- name: FlowerCore__DeviceManagement__DefaultTenantId
value: "system"
resources:
requests:
cpu: 50m
memory: 128Mi
limits:
cpu: 500m
memory: 512Mi
readinessProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 5
periodSeconds: 10
livenessProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 20
periodSeconds: 30
securityContext:
runAsNonRoot: true
runAsUser: 1654
runAsGroup: 1654
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop:
- ALL
volumeMounts:
- name: tmp
mountPath: /tmp
- name: logs
mountPath: /app/logs
volumes:
- name: tmp
emptyDir: {}
- name: logs
emptyDir: {}

View File

@@ -0,0 +1,135 @@
# FlowerCore.DeviceManagement Web.
#
# Source repo is expected to ship FlowerCore.DeviceManagement.Web in a later
# Sprint 9+ lane. This manifest is static-valid without requiring the image to
# exist yet; import localhost/fc-devicemgmt-web:<tag> to all schedulable RKE2
# nodes before letting ArgoCD sync a live rollout.
apiVersion: apps/v1
kind: Deployment
metadata:
name: fc-devicemgmt-web
namespace: fc-devicemgmt
labels:
app: fc-devicemgmt-web
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
flowercore.io/traceability-standard: k8s-pod-ownership-and-traceability-standard
spec:
replicas: 2
revisionHistoryLimit: 3
selector:
matchLabels:
app: fc-devicemgmt-web
template:
metadata:
labels:
app: fc-devicemgmt-web
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
annotations:
prometheus.io/scrape: "true"
prometheus.io/port: "8080"
prometheus.io/path: "/metrics"
flowercore.io/audit-trace-id: "runtime-activity-trace"
spec:
securityContext:
fsGroup: 1654
fsGroupChangePolicy: OnRootMismatch
containers:
- name: web
image: localhost/fc-devicemgmt-web:v20260512-cx5
imagePullPolicy: Never
ports:
- name: http
containerPort: 8080
env:
- name: ASPNETCORE_URLS
value: "http://+:8080"
- name: ASPNETCORE_ENVIRONMENT
value: "Production"
- name: DOTNET_SYSTEM_GLOBALIZATION_INVARIANT
value: "false"
- name: FlowerCore__Service__Name
value: "FlowerCore.DeviceManagement.Web"
- name: FlowerCore__DeviceManagement__DefaultTenantId
value: "system"
- name: FlowerCore__Database__Provider
value: "MySql"
- name: FlowerCore__Database__Host
value: "mysql.fc-mysql.svc"
- name: FlowerCore__Database__Database
value: "flowercore_devicemgmt"
- name: FlowerCore__Database__User
value: "fc_devicemgmt"
- name: FlowerCore__Database__Password
valueFrom:
secretKeyRef:
name: fc-devicemgmt-runtime
key: DB-Password
- name: FlowerCore__DeviceManagement__AgentMtls__CaPath
value: "/secrets/devicemgmt-mtls/mtls-ca.pem"
- name: FlowerCore__DeviceManagement__AgentMtls__ClientCertificatePath
value: "/secrets/devicemgmt-mtls/mtls-client.crt"
- name: FlowerCore__DeviceManagement__AgentMtls__ClientKeyPath
value: "/secrets/devicemgmt-mtls/mtls-client.key"
- name: FlowerCore__EventBus__Redis__Configuration
value: "redis.fc-redis.svc:6379"
resources:
requests:
cpu: 100m
memory: 256Mi
limits:
cpu: 1000m
memory: 768Mi
startupProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 5
periodSeconds: 5
failureThreshold: 30
readinessProbe:
tcpSocket:
port: 8080
periodSeconds: 10
failureThreshold: 3
livenessProbe:
tcpSocket:
port: 8080
initialDelaySeconds: 30
periodSeconds: 30
failureThreshold: 3
securityContext:
runAsNonRoot: true
runAsUser: 1654
runAsGroup: 1654
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop:
- ALL
volumeMounts:
- name: tmp
mountPath: /tmp
- name: logs
mountPath: /app/logs
- name: devicemgmt-mtls
mountPath: /secrets/devicemgmt-mtls
readOnly: true
volumes:
- name: tmp
emptyDir: {}
- name: logs
emptyDir: {}
- name: devicemgmt-mtls
secret:
secretName: fc-devicemgmt-runtime
defaultMode: 0400

View File

@@ -0,0 +1,55 @@
# LAN ingress for FlowerCore.DeviceManagement Web.
#
# RKE2 Traefik has no built-in ACME resolver configured. Keep TLS certificate
# ownership in cert-manager Certificate/fc-devicemgmt-web-tls.
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: fc-devicemgmt-web
namespace: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
entryPoints:
- websecure
routes:
- match: Host(`devices.iamworkin.lan`)
kind: Rule
services:
- name: fc-devicemgmt-web
port: 80
tls:
secretName: fc-devicemgmt-web-tls
# Future public agent/update host gate (OFF by default):
#
# Do not enable `update.flowercore.io` here until Authentik OIDC Q-OIDC-1
# resolves the public-device-management auth model and route ownership with
# UpdateCenter. When enabled, use a separate public IngressRoute with an
# explicit Method allowlist, public-host auth middleware, and public TLS
# certificate strategy. Leaving this as comments keeps ArgoCD from stealing
# live UpdateCenter traffic.
#
# apiVersion: traefik.io/v1alpha1
# kind: IngressRoute
# metadata:
# name: fc-devicemgmt-web-public
# namespace: fc-devicemgmt
# annotations:
# flowercore.io/public-host-gate: "disabled-until-Q-OIDC-1"
# spec:
# entryPoints:
# - websecure
# routes:
# - match: Host(`update.flowercore.io`) && (Method(`GET`) || Method(`HEAD`) || Method(`POST`) || Method(`OPTIONS`))
# kind: Rule
# services:
# - name: fc-devicemgmt-web
# port: 80
# tls:
# secretName: fc-devicemgmt-public-tls

View File

@@ -0,0 +1,13 @@
# FlowerCore.DeviceManagement namespace.
#
# ArgoCD discovers this directory as Application `infra-fc-devicemgmt`.
apiVersion: v1
kind: Namespace
metadata:
name: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra

View File

@@ -0,0 +1,224 @@
# FlowerCore.DeviceManagement NetworkPolicies.
#
# NetworkPolicies belong in bluejay-infra so ArgoCD owns rebuild state.
# Rules include Traefik post-DNAT backend ports per
# feedback_netpol_dnat_backend_port and Synology NFS egress for the requested
# cold-tier / future artifact path.
---
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: fc-devicemgmt-web-isolation
namespace: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
podSelector:
matchLabels:
app: fc-devicemgmt-web
policyTypes:
- Ingress
- Egress
ingress:
# LAN edge: only cluster Traefik should reach the Web pod for
# devices.iamworkin.lan.
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: traefik-system
podSelector:
matchLabels:
app.kubernetes.io/name: traefik
ports:
- port: 8080
protocol: TCP
# Direct LAN diagnostics are allowed only from FlowerCore LAN/VPN ranges.
- from:
- ipBlock:
cidr: 10.0.56.0/24
- ipBlock:
cidr: 10.0.57.0/24
- ipBlock:
cidr: 10.0.58.0/24
- ipBlock:
cidr: 10.0.68.0/27
ports:
- port: 8080
protocol: TCP
egress:
# CoreDNS.
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: kube-system
podSelector:
matchLabels:
k8s-app: kube-dns
ports:
- port: 53
protocol: UDP
- port: 53
protocol: TCP
# Database namespace.
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: fc-mysql
ports:
- port: 3306
protocol: TCP
# Redis backplane for multi-replica SignalR / live-status fan-out.
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: fc-redis
ports:
- port: 6379
protocol: TCP
# Traefik VIP / in-cluster Traefik for self-callbacks and public URL
# generation tests. Include post-DNAT backend ports 8443 + 8080.
- to:
- ipBlock:
cidr: 10.0.56.200/32
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: traefik-system
podSelector:
matchLabels:
app.kubernetes.io/name: traefik
ports:
- port: 80
protocol: TCP
- port: 443
protocol: TCP
- port: 8080
protocol: TCP
- port: 8443
protocol: TCP
# Agent egress: LAN/VPN devices may run DM Agent in Generic, Kiosk, Pi,
# ThinClient, or Server mode. Keep this private-range only.
- to:
- ipBlock:
cidr: 10.0.56.0/24
- ipBlock:
cidr: 10.0.57.0/24
- ipBlock:
cidr: 10.0.58.0/24
- ipBlock:
cidr: 10.0.68.0/27
ports:
- port: 80
protocol: TCP
- port: 443
protocol: TCP
- port: 8080
protocol: TCP
- port: 8443
protocol: TCP
- port: 5000
protocol: TCP
- port: 5001
protocol: TCP
# Synology NFS cold-tier / artifact mount allowance.
- to:
- ipBlock:
cidr: 10.0.58.3/32
ports:
- port: 2049
protocol: TCP
- port: 2049
protocol: UDP
- port: 111
protocol: TCP
- port: 111
protocol: UDP
---
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: fc-devicemgmt-operator-isolation
namespace: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
podSelector:
matchLabels:
app: fc-devicemgmt-operator
policyTypes:
- Ingress
- Egress
ingress:
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: monitoring
ports:
- port: 8080
protocol: TCP
egress:
# CoreDNS.
- to:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: kube-system
podSelector:
matchLabels:
k8s-app: kube-dns
ports:
- port: 53
protocol: UDP
- port: 53
protocol: TCP
# Kubernetes API for KubeOps reconciliation and Deployment UID lookup.
- to: []
ports:
- port: 443
protocol: TCP
- port: 6443
protocol: TCP
# Agent egress for operator-initiated probes / fallback command dispatch.
- to:
- ipBlock:
cidr: 10.0.56.0/24
- ipBlock:
cidr: 10.0.57.0/24
- ipBlock:
cidr: 10.0.58.0/24
- ipBlock:
cidr: 10.0.68.0/27
ports:
- port: 80
protocol: TCP
- port: 443
protocol: TCP
- port: 8080
protocol: TCP
- port: 8443
protocol: TCP
- port: 5000
protocol: TCP
- port: 5001
protocol: TCP
# Synology NFS allowance for future cold-tier/audit archival jobs.
- to:
- ipBlock:
cidr: 10.0.58.3/32
ports:
- port: 2049
protocol: TCP
- port: 2049
protocol: UDP
- port: 111
protocol: TCP
- port: 111
protocol: UDP

View File

@@ -0,0 +1,22 @@
apiVersion: v1
kind: Service
metadata:
name: fc-devicemgmt-web
namespace: fc-devicemgmt
labels:
app: fc-devicemgmt-web
app.kubernetes.io/name: fc-devicemgmt-web
app.kubernetes.io/component: web
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra
spec:
type: ClusterIP
selector:
app: fc-devicemgmt-web
ports:
- name: http
port: 80
targetPort: 8080
protocol: TCP

View File

@@ -0,0 +1,12 @@
apiVersion: v1
kind: ServiceAccount
metadata:
name: fc-devicemgmt-operator
namespace: fc-devicemgmt
labels:
app.kubernetes.io/name: fc-devicemgmt-operator
app.kubernetes.io/component: operator
app.kubernetes.io/part-of: flowercore
app.kubernetes.io/managed-by: argocd
flowercore.io/tenant-id: system
flowercore.io/created-by: bluejay-infra

View File

@@ -0,0 +1,61 @@
# GitHub Runner Fleet
ArgoCD owns `apps/github-runner/github-runner.yaml`. Do not patch live runner
Deployments with `kubectl`; update this manifest and let ArgoCD reconcile.
## Runner Shape
All repo-scoped Linux runners use:
- `ACCESS_TOKEN` from the `github-runner-token` Secret
- `RUN_AS_ROOT=false`
- `EPHEMERAL=true`
- `LABELS=self-hosted,linux,fc-build-linux`
- writable non-root paths under `/home/runner` for .NET, NuGet, XDG cache, and
Actions tool cache
`github-runner` for `FlowerCore.Common` is single-replica because it retains the
original Longhorn ReadWriteOnce NuGet PVC. `github-runner-sharedpos` and the top
Linux-cost repo runners use two replicas with per-pod `emptyDir` caches. That is
the safe backlog-drain strategy: no two pods share one RWO PVC.
## Post-Merge Proof
After the PR is merged and ArgoCD syncs, verify the runner fleet:
```bash
kubectl -n github-runner get deploy,pods,pvc
```
Verify GitHub registration for the repo-scoped runners:
```bash
for repo in FlowerCore.Common FlowerCore.Shared.Pos FlowerCore.Puppet FlowerCore.Signage \
FlowerCore.DMS FlowerCore.Telephony FlowerCore.Print.Web FlowerCore.Chat \
FlowerCore.MySQL FlowerCore.Kiosk.Linux; do
echo "=== $repo ==="
gh api "/repos/astoltz/$repo/actions/runners" \
--jq '.runners[] | select(.labels[].name == "fc-build-linux") | {name,status,busy,labels:[.labels[].name]}'
done
```
Shared.Pos publish proof after the runner pod is online:
```bash
gh run list --repo astoltz/FlowerCore.Shared.Pos \
--workflow "Build, Test & Publish" --branch main --limit 5
```
If the latest run is still queued after runner registration, rerun the workflow
from GitHub Actions and verify it lands on an `rke2-linux-*` runner.
## Failure Notes
- `actions/setup-dotnet` permission error at `/usr/share/dotnet`: check that
`DOTNET_INSTALL_DIR=/home/runner/.dotnet` and related cache env vars are
present on the runner pod.
- `404` during runner registration: the fine-grained PAT is valid but missing
repository access for that repo. Add the repo to the PAT access list; the PAT
value does not change.
- `Multi-Attach` volume error: only the Common runner uses a RWO PVC and it must
stay single-replica. New multi-replica runners use `emptyDir`.

File diff suppressed because it is too large Load Diff

View File

@@ -723,6 +723,24 @@ data:
summary: "Mac mini GitHub runner offline ({{ $labels.runner }})" summary: "Mac mini GitHub runner offline ({{ $labels.runner }})"
description: "A macmini-* GitHub Actions runner has not reported online for more than 10 minutes. Puppet manages its LaunchDaemon under /Library/LaunchDaemons/io.flowercore.github-runner-<slug>.plist; runners survive reboot and do not require a GUI session." description: "A macmini-* GitHub Actions runner has not reported online for more than 10 minutes. Puppet manages its LaunchDaemon under /Library/LaunchDaemons/io.flowercore.github-runner-<slug>.plist; runners survive reboot and do not require a GUI session."
- name: linux-runners
rules:
- alert: LinuxRunnerOffline
expr: |
kube_deployment_status_replicas_ready{
namespace="github-runner",
deployment=~"github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"
} == 0
for: 5m
labels:
severity: warning
alert_channel: irc
service: github-runner
team: ci
annotations:
summary: "Linux CI runner offline: {{ $labels.deployment }}"
description: "Deployment {{ $labels.deployment }} in namespace github-runner has 0 ready replicas for more than 5 minutes. CI jobs targeting this repo will queue until the runner pod restarts and re-registers with GitHub. Check pods with: kubectl -n github-runner get pods -l app.kubernetes.io/name={{ $labels.deployment }}. Check logs with: kubectl -n github-runner logs -l app.kubernetes.io/name={{ $labels.deployment }} --tail=50. Common causes: PAT missing repo access, runner CrashLoopBackOff, or node/resource pressure."
- name: remote-desktop - name: remote-desktop
rules: rules:
- alert: RemoteDesktopWebDown - alert: RemoteDesktopWebDown
@@ -3421,6 +3439,39 @@ data:
relativeTimeRange: {from: 120, to: 0} relativeTimeRange: {from: 120, to: 0}
datasourceUid: __expr__ datasourceUid: __expr__
model: {type: threshold, expression: B, conditions: [{evaluator: {params: [600], type: gt}}], refId: C} model: {type: threshold, expression: B, conditions: [{evaluator: {params: [600], type: gt}}], refId: C}
- orgId: 1
name: CI Runners
folder: CI Alerts
interval: 1m
rules:
- uid: linux-runner-offline
title: LinuxRunnerOffline
condition: C
for: 5m
noDataState: OK
execErrState: Error
annotations:
summary: "Linux CI runner offline: {{ $labels.deployment }}"
description: "A github-runner namespace Deployment has 0 ready replicas for more than 5 minutes. CI jobs targeting that repo will queue until the runner pod restarts and re-registers."
runbook: "1. kubectl -n github-runner get pods -l app.kubernetes.io/name={{ $labels.deployment }} 2. kubectl -n github-runner logs -l app.kubernetes.io/name={{ $labels.deployment }} --tail=50 3. Verify PAT repo access if registration returns 404 4. Verify no RWO PVC is shared by scaled runners"
labels:
severity: warning
service: github-runner
alert_channel: irc
team: ci
data:
- refId: A
relativeTimeRange: {from: 300, to: 0}
datasourceUid: prometheus
model: {expr: 'kube_deployment_status_replicas_ready{namespace="github-runner",deployment=~"github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))"} == 0', instant: true, refId: A}
- refId: B
relativeTimeRange: {from: 300, to: 0}
datasourceUid: __expr__
model: {type: reduce, expression: A, reducer: last, refId: B}
- refId: C
relativeTimeRange: {from: 300, to: 0}
datasourceUid: __expr__
model: {type: threshold, expression: B, conditions: [{evaluator: {params: [0], type: gt}}], refId: C}
- orgId: 1 - orgId: 1
name: Infrastructure name: Infrastructure
folder: AI Stack Alerts folder: AI Stack Alerts

View File

@@ -54,6 +54,43 @@ public sealed class FleetManifestLintTests
"ttsreader-piper", "ttsreader-piper",
}; };
private static readonly IReadOnlyDictionary<string, string> LinuxRunnerRepos = new Dictionary<string, string>(StringComparer.Ordinal)
{
["github-runner"] = "https://github.com/astoltz/FlowerCore.Common",
["github-runner-sharedpos"] = "https://github.com/astoltz/FlowerCore.Shared.Pos",
["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",
};
private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal)
{
"github-runner-sharedpos",
"github-runner-puppet",
"github-runner-signage",
"github-runner-dms",
"github-runner-telephony",
"github-runner-print-web",
"github-runner-chat",
"github-runner-mysql",
"github-runner-kiosk-linux",
};
private static readonly IReadOnlyDictionary<string, string> WritableRunnerEnv = new Dictionary<string, string>(StringComparer.Ordinal)
{
["HOME"] = "/home/runner",
["DOTNET_INSTALL_DIR"] = "/home/runner/.dotnet",
["DOTNET_CLI_HOME"] = "/home/runner",
["NUGET_PACKAGES"] = "/home/runner/.nuget/packages",
["XDG_CACHE_HOME"] = "/home/runner/.cache",
["RUNNER_TOOL_CACHE"] = "/home/runner/_tool",
};
[Fact] [Fact]
public void IngressRoutes_MustKeepServiceReferencesInTheSameNamespace() public void IngressRoutes_MustKeepServiceReferencesInTheSameNamespace()
{ {
@@ -187,6 +224,98 @@ public sealed class FleetManifestLintTests
violations.Should().BeEmpty(); violations.Should().BeEmpty();
} }
[Fact]
public void GitHubRunnerFleet_MustRegisterRequiredReposAsRepoScopedDeployments()
{
var deployments = GitHubRunnerDeployments();
foreach (var expectedRunner in LinuxRunnerRepos)
{
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, "RUN_AS_ROOT").Should().Be("false");
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_MustSetWritableNonRootDotnetAndCachePaths()
{
foreach (var deployment in GitHubRunnerDeployments().Values)
{
var container = deployment.ContainerMappings().Should().ContainSingle().Subject;
foreach (var expectedEnv in WritableRunnerEnv)
{
EnvValue(container, expectedEnv.Key).Should().Be(expectedEnv.Value, $"{deployment.Name} must keep .NET paths writable for uid 1001");
}
var mounts = ManifestNodeExtensions.MappingSequence(container, "volumeMounts")
.ToDictionary(
mount => ManifestNodeExtensions.Scalar(mount, "name") ?? string.Empty,
mount => ManifestNodeExtensions.Scalar(mount, "mountPath") ?? string.Empty,
StringComparer.Ordinal);
mounts.Should().Contain("runner-home", "/home/runner");
mounts.Should().Contain("nuget-cache", "/home/runner/.nuget/packages");
mounts.Should().Contain("tmp", "/tmp");
}
}
[Fact]
public void GitHubRunnerFleet_MustAvoidRwoMultiAttachForScaledDeployments()
{
var deployments = GitHubRunnerDeployments();
foreach (var deploymentName in ScaledLinuxRunnerDeployments)
{
var deployment = deployments[deploymentName];
ReplicaCount(deployment).Should().Be(2);
var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes");
var claimNames = volumes
.Select(volume => ManifestNodeExtensions.Scalar(volume, "persistentVolumeClaim", "claimName"))
.Where(value => !string.IsNullOrWhiteSpace(value))
.ToList();
claimNames.Should().BeEmpty($"{deploymentName} is scaled and must not share a RWO PVC");
volumes.Should().Contain(volume =>
string.Equals(ManifestNodeExtensions.Scalar(volume, "name"), "nuget-cache", StringComparison.Ordinal)
&& ManifestNodeExtensions.Mapping(volume, "emptyDir") != null);
}
var common = deployments["github-runner"];
ReplicaCount(common).Should().Be(1);
common.MappingSequence("spec", "template", "spec", "volumes")
.Select(volume => ManifestNodeExtensions.Scalar(volume, "persistentVolumeClaim", "claimName"))
.Where(value => !string.IsNullOrWhiteSpace(value))
.Should()
.ContainSingle()
.Which
.Should()
.Be("github-runner-nuget-cache");
}
[Fact]
public void Monitoring_MustAlertWhenLinuxRunnerDeploymentIsUnavailable()
{
var monitoring = File.ReadAllText(Path.Combine(Inventory.BluejayRoot, "apps", "monitoring", "noc-monitoring.yaml"));
monitoring.Should().Contain("MacMiniRunnerOffline");
monitoring.Should().Contain("LinuxRunnerOffline");
monitoring.Should().Contain("kube_deployment_status_replicas_ready");
monitoring.Should().Contain("github-runner(|-(sharedpos|puppet|signage|dms|telephony|print-web|chat|mysql|kiosk-linux))");
monitoring.Should().Contain("folder: CI Alerts");
monitoring.Should().Contain("uid: linux-runner-offline");
monitoring.Should().Contain("alert_channel: irc");
}
[Fact] [Fact]
public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults() public void StatefulSets_WithVolumeClaimTemplates_MustDeclareFilesystemDefaults()
{ {
@@ -291,6 +420,184 @@ public sealed class FleetManifestLintTests
violations.Should().BeEmpty(); violations.Should().BeEmpty();
} }
[Fact]
public void FcDeviceManagement_MustShipExpectedManifestSet()
{
var appRoot = Path.Combine(Inventory.BluejayRoot, "apps", "fc-devicemgmt");
Directory.Exists(appRoot).Should().BeTrue("Sprint 8 Cx-5 owns apps/fc-devicemgmt.");
var expectedFiles = new[]
{
"1password-item.yaml",
"argocd-application.yaml",
"certificate-web.yaml",
"clusterrole-operator.yaml",
"clusterrolebinding-operator.yaml",
"deployment-operator.yaml",
"deployment-web.yaml",
"ingressroute-web.yaml",
"namespace.yaml",
"network-policy.yaml",
"service-web.yaml",
"serviceaccount-operator.yaml",
};
Directory.GetFiles(appRoot, "*.yaml")
.Select(Path.GetFileName)
.Should()
.BeEquivalentTo(expectedFiles);
foreach (var expectedFile in expectedFiles)
{
FcDeviceManagementDocuments()
.Should()
.Contain(document => document.RelativePath == $"fc-devicemgmt/{expectedFile}");
}
}
[Fact]
public void FcDeviceManagement_ObjectsMustCarryStandardTraceabilityLabels()
{
var requiredLabels = new[]
{
"app.kubernetes.io/name",
"app.kubernetes.io/part-of",
"app.kubernetes.io/managed-by",
"flowercore.io/tenant-id",
"flowercore.io/created-by",
};
var violations = FcDeviceManagementDocuments()
.SelectMany(document => requiredLabels
.Where(label => string.IsNullOrWhiteSpace(document.Scalar("metadata", "labels", label)))
.Select(label => $"{document.Descriptor} is missing metadata.labels['{label}']."))
.Concat(FcDeviceManagementDocuments()
.Where(document => document.Kind == "Deployment")
.SelectMany(document => requiredLabels
.Where(label => string.IsNullOrWhiteSpace(document.Scalar("spec", "template", "metadata", "labels", label)))
.Select(label => $"{document.Descriptor} pod template is missing metadata.labels['{label}'].")))
.Concat(FcDeviceManagementDocuments()
.Where(document => document.Kind == "Deployment")
.Where(document => string.IsNullOrWhiteSpace(document.Scalar("spec", "template", "metadata", "annotations", "flowercore.io/audit-trace-id")))
.Select(document => $"{document.Descriptor} pod template is missing flowercore.io/audit-trace-id."))
.ToList();
violations.Should().BeEmpty();
}
[Fact]
public void FcDeviceManagement_IngressMustUseCertManagerAndKeepPublicHostDisabled()
{
var appText = string.Join(
Environment.NewLine,
Directory.GetFiles(Path.Combine(Inventory.BluejayRoot, "apps", "fc-devicemgmt"), "*.yaml")
.Select(File.ReadAllText));
appText.Should().NotContain("certResolver");
appText.Should().Contain("update.flowercore.io");
appText.Should().Contain("disabled-until-Q-OIDC-1");
FcDeviceManagementDocuments()
.Where(document => document.Kind == "IngressRoute")
.SelectMany(document => document.MappingSequence("spec", "routes"))
.Select(route => ManifestNodeExtensions.Scalar(route, "match") ?? string.Empty)
.Should()
.Contain(match => match.Contains("Host(`devices.iamworkin.lan`)", StringComparison.Ordinal))
.And.NotContain(match => match.Contains("Host(`update.flowercore.io`)", StringComparison.Ordinal));
var certificate = FcDeviceManagementDocuments()
.Single(document => document.Kind == "Certificate" && document.Name == "fc-devicemgmt-web-tls");
certificate.Scalar("spec", "issuerRef", "name").Should().Be("step-ca-acme");
certificate.Scalar("spec", "issuerRef", "kind").Should().Be("ClusterIssuer");
ManifestNodeExtensions.ScalarSequence(certificate.Root, "spec", "dnsNames")
.Should()
.ContainSingle("devices.iamworkin.lan");
}
[Fact]
public void FcDeviceManagement_OperatorRbacMustCoverDevicesAndOwnerLookup()
{
var clusterRole = FcDeviceManagementDocuments()
.Single(document => document.Kind == "ClusterRole" && document.Name == "fc-devicemgmt-operator");
var allScalars = clusterRole.AllScalars().ToList();
allScalars.Should().Contain("devices.flowercore.io");
allScalars.Should().Contain("*");
allScalars.Should().Contain("deployments");
allScalars.Should().Contain("get");
var operatorDeployment = FcDeviceManagementDocuments()
.Single(document => document.Kind == "Deployment" && document.Name == "fc-devicemgmt-operator");
operatorDeployment.AllScalars().Should().Contain("FLOWERCORE_KUBERNETES_OWNER_DEPLOYMENT");
operatorDeployment.AllScalars().Should().Contain("fc-devicemgmt-operator");
}
[Fact]
public void FcDeviceManagement_RuntimeSecretsMustUseOnePasswordItemPattern()
{
var item = FcDeviceManagementDocuments()
.Single(document => document.Kind == "OnePasswordItem" && document.Name == "fc-devicemgmt-runtime");
item.Scalar("spec", "itemPath")
.Should()
.Be("vaults/IAmWorkin/items/FlowerCore DeviceManagement Runtime");
var appText = string.Join(
Environment.NewLine,
Directory.GetFiles(Path.Combine(Inventory.BluejayRoot, "apps", "fc-devicemgmt"), "*.yaml")
.Select(File.ReadAllText));
FcDeviceManagementDocuments().Should().NotContain(document => document.Kind == "Secret");
appText.Should().Contain("secretKeyRef:");
appText.Should().Contain("secretName: fc-devicemgmt-runtime");
appText.Should().NotContain("stringData:");
appText.Should().NotContain("from-literal");
appText.Should().NotContain("tls.key:");
}
[Fact]
public void FcDeviceManagement_NetworkPoliciesMustAllowLanAgentsSynologyAndDnatPorts()
{
var policies = FcDeviceManagementDocuments()
.Where(document => document.Kind == "NetworkPolicy")
.ToList();
policies.Should().HaveCount(2);
var combinedScalars = policies.SelectMany(policy => policy.AllScalars()).ToList();
combinedScalars.Should().Contain("10.0.56.0/24");
combinedScalars.Should().Contain("10.0.57.0/24");
combinedScalars.Should().Contain("10.0.58.0/24");
combinedScalars.Should().Contain("10.0.68.0/27");
combinedScalars.Should().Contain("10.0.58.3/32");
var combinedEgressPorts = policies.SelectMany(policy => policy.EgressPorts()).ToHashSet(StringComparer.Ordinal);
combinedEgressPorts.Should().Contain(new[] { "80", "443", "8080", "8443", "2049", "111" });
var traefikVipPolicies = policies
.Where(policy => policy.AllScalars().Any(value => value.Contains("10.0.56.200", StringComparison.Ordinal)))
.ToList();
traefikVipPolicies.Should().ContainSingle();
traefikVipPolicies[0].EgressPorts().Should().Contain(new[] { "80", "443", "8080", "8443" });
}
[Fact]
public void FcDeviceManagement_ArgocdApplicationMustMatchApplicationSetDiscoveryConventions()
{
var application = FcDeviceManagementDocuments()
.Single(document => document.Kind == "Application" && document.Name == "infra-fc-devicemgmt");
application.Namespace.Should().Be("argocd");
application.Scalar("spec", "source", "repoURL")
.Should()
.Be("http://gitea-clusterip.gitea.svc.cluster.local:3000/bluejay/bluejay-infra.git");
application.Scalar("spec", "source", "path").Should().Be("apps/fc-devicemgmt");
application.Scalar("spec", "destination", "namespace").Should().Be("fc-devicemgmt");
}
private static IEnumerable<string> ProbeViolations( private static IEnumerable<string> ProbeViolations(
ManifestDocument document, ManifestDocument document,
YamlMappingNode container, YamlMappingNode container,
@@ -314,6 +621,51 @@ 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 IReadOnlyDictionary<string, ManifestDocument> GitHubRunnerDeployments()
{
return Inventory.Documents
.Where(document => document.Kind == "Deployment")
.Where(document => document.Namespace == "github-runner")
.ToDictionary(document => document.Name, StringComparer.Ordinal);
}
private static int ReplicaCount(ManifestDocument document)
{
return int.TryParse(document.Scalar("spec", "replicas"), out var replicas) ? replicas : 1;
}
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));
}
private static IReadOnlyList<ManifestDocument> FcDeviceManagementDocuments()
{
return Inventory.Documents
.Where(document => document.RelativePath.StartsWith("fc-devicemgmt/", StringComparison.Ordinal))
.ToList();
}
} }
internal sealed class ManifestInventory internal sealed class ManifestInventory