Compare commits

..

1 Commits

Author SHA1 Message Date
Andrew Stoltz
0a20f05525 monitoring: tag pirelay planned outage 2026-05-19 17:40:34 -05:00
8 changed files with 221 additions and 871 deletions

View File

@@ -1,448 +0,0 @@
# Authentik OIDC backend
# ArgoCD-managed. BlueJay Lab.
#
# Stack:
# - PostgreSQL 16 StatefulSet (single replica, Longhorn RWO 5Gi)
# - Redis 7 Deployment (no persistence — session/cache only)
# - Authentik server + worker Deployments (image ghcr.io/goauthentik/server:2024.12.3)
# - Media PVC shared between server + worker (Longhorn RWO 2Gi)
# - Certificate via step-ca-acme ClusterIssuer
# - Traefik IngressRoute at id.iamworkin.lan
#
# Secrets come from 1Password item "authentik-credentials" (IAmWorkin vault, id y6i74ch22q5wvm7znquq4nhhcu)
# via the OnePasswordItem CRD, materialized into k8s Secret authentik/authentik-credentials.
#
# Why the discovery URL is /application/o/pimanager/ : Authentik issues per-application OIDC providers.
# The pimanager OIDC application/provider is created after the cluster pods are healthy (manual or
# via API once the bootstrap token is available — see Notes substrate).
---
apiVersion: v1
kind: Namespace
metadata:
name: authentik
labels:
app.kubernetes.io/part-of: bluejay-infra
---
# 1Password operator pulls the authentik-credentials item into a k8s Secret of the same name.
# Field labels in 1P become Secret keys: AUTHENTIK_SECRET_KEY, POSTGRES_PASSWORD, REDIS_PASSWORD,
# BOOTSTRAP_ADMIN_PASSWORD, BOOTSTRAP_ADMIN_TOKEN, BOOTSTRAP_ADMIN_EMAIL.
apiVersion: onepassword.com/v1
kind: OnePasswordItem
metadata:
name: authentik-credentials
namespace: authentik
spec:
itemPath: "vaults/IAmWorkin/items/authentik-credentials"
---
# Shared media volume for server + worker pods.
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: authentik-media
namespace: authentik
spec:
storageClassName: longhorn
accessModes: [ReadWriteOnce]
resources:
requests:
storage: 2Gi
---
# PostgreSQL 16 StatefulSet — Authentik's primary store.
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: authentik-postgres
namespace: authentik
labels:
app: authentik-postgres
argocd.argoproj.io/instance: infra-authentik
spec:
persistentVolumeClaimRetentionPolicy:
whenDeleted: Retain
whenScaled: Retain
podManagementPolicy: OrderedReady
serviceName: authentik-postgres
replicas: 1
revisionHistoryLimit: 10
selector:
matchLabels:
app: authentik-postgres
template:
metadata:
labels:
app: authentik-postgres
spec:
containers:
- name: postgres
image: postgres:16-alpine
ports:
- containerPort: 5432
name: postgres
env:
- name: POSTGRES_USER
value: authentik
- name: POSTGRES_PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: POSTGRES_PASSWORD
- name: POSTGRES_DB
value: authentik
- name: POSTGRES_INITDB_ARGS
value: "--encoding=UTF-8 --lc-collate=C --lc-ctype=C"
- name: PGDATA
value: /var/lib/postgresql/data/pgdata
readinessProbe:
exec:
command: ["pg_isready", "-U", "authentik"]
initialDelaySeconds: 5
periodSeconds: 5
livenessProbe:
exec:
command: ["pg_isready", "-U", "authentik"]
initialDelaySeconds: 30
periodSeconds: 30
resources:
requests: { cpu: 100m, memory: 256Mi }
limits: { cpu: 1000m, memory: 1Gi }
volumeMounts:
- name: pgdata
mountPath: /var/lib/postgresql/data
volumeClaimTemplates:
- metadata:
name: pgdata
spec:
storageClassName: longhorn
accessModes: [ReadWriteOnce]
volumeMode: Filesystem
resources:
requests:
storage: 5Gi
---
apiVersion: v1
kind: Service
metadata:
name: authentik-postgres
namespace: authentik
spec:
clusterIP: None
selector:
app: authentik-postgres
ports:
- name: postgres
port: 5432
targetPort: 5432
---
# Redis 7 — session storage + Celery broker. No persistence needed (cache).
apiVersion: apps/v1
kind: Deployment
metadata:
name: authentik-redis
namespace: authentik
labels:
app: authentik-redis
argocd.argoproj.io/instance: infra-authentik
spec:
replicas: 1
strategy:
type: Recreate
selector:
matchLabels:
app: authentik-redis
template:
metadata:
labels:
app: authentik-redis
spec:
containers:
- name: redis
image: redis:7-alpine
args:
- "--save"
- ""
- "--appendonly"
- "no"
- "--requirepass"
- "$(REDIS_PASSWORD)"
env:
- name: REDIS_PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: REDIS_PASSWORD
ports:
- containerPort: 6379
name: redis
readinessProbe:
tcpSocket: { port: 6379 }
initialDelaySeconds: 5
periodSeconds: 5
livenessProbe:
tcpSocket: { port: 6379 }
initialDelaySeconds: 30
periodSeconds: 30
resources:
requests: { cpu: 50m, memory: 64Mi }
limits: { cpu: 500m, memory: 256Mi }
---
apiVersion: v1
kind: Service
metadata:
name: authentik-redis
namespace: authentik
spec:
selector:
app: authentik-redis
ports:
- name: redis
port: 6379
targetPort: 6379
---
# Authentik server Deployment — HTTP frontend on :9000.
apiVersion: apps/v1
kind: Deployment
metadata:
name: authentik-server
namespace: authentik
labels:
app: authentik-server
argocd.argoproj.io/instance: infra-authentik
spec:
replicas: 1
strategy:
type: Recreate # shares /media RWO PVC with worker
selector:
matchLabels:
app: authentik-server
template:
metadata:
labels:
app: authentik-server
spec:
securityContext:
# Authentik image runs as uid 1000 "authentik" but the Longhorn PVC mounts
# root:root by default. fsGroup recursively chgrp + chmod g+rwx so the
# non-root container can mkdir /media/public during the tenant_files migration.
fsGroup: 1000
containers:
- name: server
image: ghcr.io/goauthentik/server:2024.12.3
args: ["server"]
ports:
- containerPort: 9000
name: http
- containerPort: 9443
name: https
env:
- name: AUTHENTIK_SECRET_KEY
valueFrom:
secretKeyRef:
name: authentik-credentials
key: AUTHENTIK_SECRET_KEY
- name: AUTHENTIK_REDIS__HOST
value: authentik-redis
- name: AUTHENTIK_REDIS__PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: REDIS_PASSWORD
- name: AUTHENTIK_POSTGRESQL__HOST
value: authentik-postgres
- name: AUTHENTIK_POSTGRESQL__NAME
value: authentik
- name: AUTHENTIK_POSTGRESQL__USER
value: authentik
- name: AUTHENTIK_POSTGRESQL__PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: POSTGRES_PASSWORD
- name: AUTHENTIK_BOOTSTRAP_PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: BOOTSTRAP_ADMIN_PASSWORD
- name: AUTHENTIK_BOOTSTRAP_TOKEN
valueFrom:
secretKeyRef:
name: authentik-credentials
key: BOOTSTRAP_ADMIN_TOKEN
- name: AUTHENTIK_BOOTSTRAP_EMAIL
valueFrom:
secretKeyRef:
name: authentik-credentials
key: BOOTSTRAP_ADMIN_EMAIL
- name: AUTHENTIK_DISABLE_UPDATE_CHECK
value: "true"
- name: AUTHENTIK_ERROR_REPORTING__ENABLED
value: "false"
- name: AUTHENTIK_LOG_LEVEL
value: info
# First-boot Authentik can take 3+ min on the migration phase
# (waiting on DB lock while worker also runs migrations). Initial
# delays are generous so kubelet doesn't kill the pod mid-migration;
# periodSeconds keeps post-startup probing responsive.
readinessProbe:
httpGet:
path: /-/health/ready/
port: 9000
initialDelaySeconds: 60
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 12
livenessProbe:
httpGet:
path: /-/health/live/
port: 9000
initialDelaySeconds: 300
periodSeconds: 30
timeoutSeconds: 10
failureThreshold: 3
startupProbe:
httpGet:
path: /-/health/live/
port: 9000
initialDelaySeconds: 30
periodSeconds: 15
timeoutSeconds: 10
failureThreshold: 40 # 30s + 40*15s = 10.5 min budget
resources:
requests: { cpu: 150m, memory: 512Mi }
limits: { cpu: 1500m, memory: 1Gi }
volumeMounts:
- name: media
mountPath: /media
volumes:
- name: media
persistentVolumeClaim:
claimName: authentik-media
---
# Authentik worker Deployment — runs Celery background tasks.
apiVersion: apps/v1
kind: Deployment
metadata:
name: authentik-worker
namespace: authentik
labels:
app: authentik-worker
argocd.argoproj.io/instance: infra-authentik
spec:
replicas: 1
strategy:
type: Recreate # shares /media RWO PVC with server
selector:
matchLabels:
app: authentik-worker
template:
metadata:
labels:
app: authentik-worker
spec:
securityContext:
# Same as server pod — non-root uid 1000 needs PVC group write.
fsGroup: 1000
containers:
- name: worker
image: ghcr.io/goauthentik/server:2024.12.3
args: ["worker"]
env:
- name: AUTHENTIK_SECRET_KEY
valueFrom:
secretKeyRef:
name: authentik-credentials
key: AUTHENTIK_SECRET_KEY
- name: AUTHENTIK_REDIS__HOST
value: authentik-redis
- name: AUTHENTIK_REDIS__PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: REDIS_PASSWORD
- name: AUTHENTIK_POSTGRESQL__HOST
value: authentik-postgres
- name: AUTHENTIK_POSTGRESQL__NAME
value: authentik
- name: AUTHENTIK_POSTGRESQL__USER
value: authentik
- name: AUTHENTIK_POSTGRESQL__PASSWORD
valueFrom:
secretKeyRef:
name: authentik-credentials
key: POSTGRES_PASSWORD
- name: AUTHENTIK_DISABLE_UPDATE_CHECK
value: "true"
- name: AUTHENTIK_ERROR_REPORTING__ENABLED
value: "false"
- name: AUTHENTIK_LOG_LEVEL
value: info
resources:
requests: { cpu: 100m, memory: 256Mi }
limits: { cpu: 1000m, memory: 768Mi }
volumeMounts:
- name: media
mountPath: /media
volumes:
- name: media
persistentVolumeClaim:
claimName: authentik-media
---
apiVersion: v1
kind: Service
metadata:
name: authentik-server
namespace: authentik
spec:
selector:
app: authentik-server
ports:
- name: http
port: 9000
targetPort: 9000
- name: https
port: 9443
targetPort: 9443
---
# step-ca leaf certificate for id.iamworkin.lan.
# step-ca container resolver uses pfSense Unbound, so the public A record for id.iamworkin.lan
# MUST exist before this Certificate is applied (cert-manager HTTP-01 will silently 2h-backoff
# otherwise). Added 2026-05-25 via scripts/pfsense-add-id-host.py.
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: authentik-tls
namespace: authentik
spec:
secretName: authentik-tls
dnsNames:
- id.iamworkin.lan
issuerRef:
name: step-ca-acme
kind: ClusterIssuer
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: authentik
namespace: authentik
spec:
entryPoints: [websecure]
routes:
- match: Host(`id.iamworkin.lan`)
kind: Rule
services:
- name: authentik-server
port: 9000
tls:
secretName: authentik-tls

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

@@ -1,2 +0,0 @@
*.sh text eol=lf
Dockerfile text eol=lf

View File

@@ -1,44 +0,0 @@
FROM myoung34/github-runner:latest
ARG RUBY_VERSION=3.3.11
ARG RUBY_MINOR=3.3
ARG RUBY_BUILD_VERSION=v20260326
ARG RUNNER_UID=1001
ARG RUNNER_GID=1001
ENV RUNNER_TOOL_CACHE=/home/runner/_tool
ENV RUNNER_RUBY_TOOLCACHE=/opt/runner-toolcache
ENV PATH="/home/runner/_tool/Ruby/${RUBY_MINOR}/x64/bin:/opt/runner-toolcache/Ruby/${RUBY_MINOR}/x64/bin:${PATH}"
USER root
RUN apt-get update \
&& DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
autoconf \
bison \
build-essential \
ca-certificates \
curl \
libdb-dev \
libffi-dev \
libgdbm-dev \
libgmp-dev \
libncurses-dev \
libreadline-dev \
libssl-dev \
libyaml-dev \
patch \
pkg-config \
uuid-dev \
zlib1g-dev \
&& curl -fsSL "https://github.com/rbenv/ruby-build/archive/refs/tags/${RUBY_BUILD_VERSION}.tar.gz" -o /tmp/ruby-build.tar.gz \
&& mkdir -p /tmp/ruby-build \
&& tar -xzf /tmp/ruby-build.tar.gz --strip-components=1 -C /tmp/ruby-build \
&& /tmp/ruby-build/install.sh \
&& rm -rf /tmp/ruby-build /tmp/ruby-build.tar.gz /var/lib/apt/lists/*
COPY install-ruby-toolcache.sh /usr/local/bin/install-ruby-toolcache.sh
RUN chmod +x /usr/local/bin/install-ruby-toolcache.sh \
&& RUBY_VERSION="${RUBY_VERSION}" RUBY_MINOR="${RUBY_MINOR}" TOOLCACHE_ROOT="${RUNNER_RUBY_TOOLCACHE}" RUNNER_UID="${RUNNER_UID}" RUNNER_GID="${RUNNER_GID}" /usr/local/bin/install-ruby-toolcache.sh \
&& ruby -v

View File

@@ -7,17 +7,12 @@ Deployments with `kubectl`; update this manifest and let ArgoCD reconcile.
All repo-scoped Linux runners use: All repo-scoped Linux runners use:
- `localhost/fc-github-runner:v20260520-ruby3.3.11`, derived from
`myoung34/github-runner:latest`
- `ACCESS_TOKEN` from the `github-runner-token` Secret - `ACCESS_TOKEN` from the `github-runner-token` Secret
- `RUN_AS_ROOT=false` - `RUN_AS_ROOT=false`
- `EPHEMERAL=true` - `EPHEMERAL=true`
- `LABELS=self-hosted,linux,fc-build-linux` - `LABELS=self-hosted,linux,fc-build-linux`
- writable non-root paths under `/home/runner` for .NET, NuGet, XDG cache, and - writable non-root paths under `/home/runner` for .NET, NuGet, XDG cache, and
Actions tool cache Actions tool cache
- Ruby 3.3.11 seeded into `/home/runner/_tool/Ruby/3.3/x64` from the baked
`/opt/runner-toolcache` copy so `ruby/setup-ruby@v1` can discover it on
self-hosted `ubuntu-20.04-x64` runners
`github-runner` for `FlowerCore.Common` is single-replica because it retains the `github-runner` for `FlowerCore.Common` is single-replica because it retains the
original Longhorn ReadWriteOnce NuGet PVC. Every other repo-scoped runner uses original Longhorn ReadWriteOnce NuGet PVC. Every other repo-scoped runner uses
@@ -33,34 +28,6 @@ Sprint 32 final long-tail wave adds 16 two-replica Deployments:
`FlowerCore.Provisioning`, `FlowerCore.Redis`, `FlowerCore.MessageBoard`, and `FlowerCore.Provisioning`, `FlowerCore.Redis`, `FlowerCore.MessageBoard`, and
`FlowerCore.MenuBoard`. `FlowerCore.MenuBoard`.
## Image Build
Ruby is baked with a pinned `ruby-build` release and Ruby patch version. The pod
still mounts an `emptyDir` over `/home/runner`, so the `setup-runner-home` init
container copies the baked toolcache from `/opt/runner-toolcache/Ruby` into
`/home/runner/_tool/Ruby` before the runner container starts.
```bash
cd apps/github-runner
podman build -t localhost/fc-github-runner:v20260520-ruby3.3.11 .
podman run --rm localhost/fc-github-runner:v20260520-ruby3.3.11 ruby -v
podman run --rm localhost/fc-github-runner:v20260520-ruby3.3.11 \
test -f /opt/runner-toolcache/Ruby/3.3/x64.complete
podman save localhost/fc-github-runner:v20260520-ruby3.3.11 \
-o fc-github-runner-v20260520-ruby3.3.11.tar
```
Import the saved image on every schedulable RKE2 node before ArgoCD rolls the
Deployments:
```bash
for node in rke2-server rke2-agent1 rke2-agent2; do
scp fc-github-runner-v20260520-ruby3.3.11.tar "$node:/tmp/"
ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images rm localhost/fc-github-runner:v20260520-ruby3.3.11 || true'
ssh "$node" 'sudo ctr -a /run/k3s/containerd/containerd.sock -n k8s.io images import /tmp/fc-github-runner-v20260520-ruby3.3.11.tar'
done
```
## Post-Merge Proof ## Post-Merge Proof
After the PR is merged and ArgoCD syncs, verify the runner fleet: After the PR is merged and ArgoCD syncs, verify the runner fleet:
@@ -69,14 +36,6 @@ After the PR is merged and ArgoCD syncs, verify the runner fleet:
kubectl -n github-runner get deploy,pods,pvc kubectl -n github-runner get deploy,pods,pvc
``` ```
Verify the Ruby toolcache in a fresh pod:
```bash
kubectl -n github-runner exec deploy/github-runner-puppet -c runner -- ruby -v
kubectl -n github-runner exec deploy/github-runner-puppet -c runner -- sh -c \
'echo "$RUNNER_TOOL_CACHE" && test -f "$RUNNER_TOOL_CACHE/Ruby/3.3/x64.complete"'
```
Verify GitHub registration for the repo-scoped runners: Verify GitHub registration for the repo-scoped runners:
```bash ```bash
@@ -110,10 +69,6 @@ from GitHub Actions and verify it lands on an `rke2-linux-*` runner.
- `actions/setup-dotnet` permission error at `/usr/share/dotnet`: check that - `actions/setup-dotnet` permission error at `/usr/share/dotnet`: check that
`DOTNET_INSTALL_DIR=/home/runner/.dotnet` and related cache env vars are `DOTNET_INSTALL_DIR=/home/runner/.dotnet` and related cache env vars are
present on the runner pod. present on the runner pod.
- `ruby/setup-ruby@v1` says self-hosted runners must install Ruby in
`$RUNNER_TOOL_CACHE`: check that the init container copied
`/opt/runner-toolcache/Ruby` into `/home/runner/_tool/Ruby` and that
`/home/runner/_tool/Ruby/3.3/x64.complete` exists.
- `404` during runner registration: the fine-grained PAT is valid but missing - `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 repository access for that repo. Add the repo to the PAT access list; the PAT
value does not change. value does not change.

File diff suppressed because it is too large Load Diff

View File

@@ -1,19 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
RUBY_VERSION="${RUBY_VERSION:-3.3.11}"
RUBY_MINOR="${RUBY_MINOR:-3.3}"
TOOLCACHE_ROOT="${TOOLCACHE_ROOT:-/opt/runner-toolcache}"
RUNNER_UID="${RUNNER_UID:-1001}"
RUNNER_GID="${RUNNER_GID:-1001}"
RUBY_PREFIX="${TOOLCACHE_ROOT}/Ruby/${RUBY_VERSION}/x64"
mkdir -p "${TOOLCACHE_ROOT}/Ruby"
RUBY_CONFIGURE_OPTS="${RUBY_CONFIGURE_OPTS:---disable-install-doc --disable-yjit}" ruby-build "${RUBY_VERSION}" "${RUBY_PREFIX}"
touch "${TOOLCACHE_ROOT}/Ruby/${RUBY_VERSION}/x64.complete"
ln -sfn "${RUBY_VERSION}" "${TOOLCACHE_ROOT}/Ruby/${RUBY_MINOR}"
"${RUBY_PREFIX}/bin/ruby" -v
chown -R "${RUNNER_UID}:${RUNNER_GID}" "${TOOLCACHE_ROOT}"
chmod -R a+rX "${TOOLCACHE_ROOT}"

View File

@@ -208,6 +208,9 @@ data:
vlan: "home" vlan: "home"
arch: "arm64" arch: "arm64"
role: "relay-controller" role: "relay-controller"
maintenance_state: "planned-offline"
maintenance_ticket: "Q-SP41-PIRELAY"
maintenance_reason: "traffic-light-rig-awaiting-power"
# ======================================================================= # =======================================================================
# PiManager Application Metrics (relay states, temps, automation) # PiManager Application Metrics (relay states, temps, automation)
@@ -229,6 +232,9 @@ data:
service: "pimanager" service: "pimanager"
vlan: "home" vlan: "home"
device: "pi3-ks0212" device: "pi3-ks0212"
maintenance_state: "planned-offline"
maintenance_ticket: "Q-SP41-PIRELAY"
maintenance_reason: "traffic-light-rig-awaiting-power"
# Epson ET-3750 EcoTank Printer SNMP # Epson ET-3750 EcoTank Printer SNMP
- job_name: "snmp-printer" - job_name: "snmp-printer"
@@ -280,14 +286,13 @@ data:
printer_model: "NuPrint 210" printer_model: "NuPrint 210"
# Print.Web health (Blazor app on edge2:5200) # Print.Web health (Blazor app on edge2:5200)
# Target `/health` (anonymous) — root path requires API key auth and returns 401.
- job_name: "probe-printweb" - job_name: "probe-printweb"
metrics_path: /probe metrics_path: /probe
params: params:
module: [http_2xx] module: [http_2xx]
scrape_interval: 30s scrape_interval: 30s
static_configs: static_configs:
- targets: ["http://10.0.57.16:5200/health"] - targets: ["http://10.0.57.16:5200/"]
labels: labels:
instance: "print-web" instance: "print-web"
service: "print-web" service: "print-web"