refactor(k8s): Reorganize into 5-layer structure with production kustomizations
This commit is contained in:
Story Crater Bot
@@ -0,0 +1,6 @@
|
||||
apiVersion: v2
|
||||
name: claude-terminal
|
||||
description: Persistent Claude CLI terminal running in tmux with web access via gotty
|
||||
type: application
|
||||
version: 1.0.0
|
||||
appVersion: "1.0"
|
||||
@@ -0,0 +1,31 @@
|
||||
FROM --platform=linux/amd64 ubuntu:24.04
|
||||
|
||||
RUN apt-get update && apt-get install -y \
|
||||
tmux \
|
||||
curl \
|
||||
git \
|
||||
build-essential \
|
||||
nodejs \
|
||||
npm \
|
||||
bash \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Install gotty (web terminal access)
|
||||
RUN curl -sL https://github.com/sorenisanerd/gotty/releases/download/v1.5.0/gotty_linux_amd64.tar.gz | \
|
||||
tar xz -C /usr/local/bin && chmod +x /usr/local/bin/gotty
|
||||
|
||||
# Install Claude CLI
|
||||
RUN npm install -g claude-code-cli 2>&1 || echo "Note: Claude CLI will be available after NPM package is published"
|
||||
|
||||
WORKDIR /root
|
||||
|
||||
# Create persistent storage dir
|
||||
RUN mkdir -p /root/.claude /root/.config /root/.cache
|
||||
|
||||
# Entrypoint: start tmux session and gotty
|
||||
COPY entrypoint.sh /entrypoint.sh
|
||||
RUN chmod +x /entrypoint.sh
|
||||
|
||||
EXPOSE 8080
|
||||
|
||||
ENTRYPOINT ["/entrypoint.sh"]
|
||||
@@ -0,0 +1,49 @@
|
||||
# Claude Terminal — Persistent Remote Dev Environment
|
||||
|
||||
Runs Claude CLI in a persistent tmux session with web-based terminal access via gotty.
|
||||
|
||||
## Building the Image
|
||||
|
||||
Build for `linux/amd64`:
|
||||
|
||||
```bash
|
||||
cd homelab
|
||||
docker buildx build --platform linux/amd64 \
|
||||
-t forgejo.riotpiao.homelab.com/rock/claude-terminal:latest \
|
||||
-f k8s/dev-tools/Dockerfile \
|
||||
k8s/dev-tools
|
||||
|
||||
# Log in to Forgejo registry
|
||||
docker login forgejo.riotpiao.homelab.com \
|
||||
--username ci-bot \
|
||||
--password "$(talos get cluster/iam/agents/ci-bot --key token)"
|
||||
|
||||
# Push
|
||||
docker push forgejo.riotpiao.homelab.com/rock/claude-terminal:latest
|
||||
```
|
||||
|
||||
Or use the provided build script:
|
||||
|
||||
```bash
|
||||
./k8s/dev-tools/build.sh
|
||||
```
|
||||
|
||||
## Deployment
|
||||
|
||||
Update `values.yaml` if needed, then deploy via helmfile:
|
||||
|
||||
```bash
|
||||
helmfile apply -l name=claude-terminal
|
||||
```
|
||||
|
||||
Access the terminal at: **https://claude.riotpiao.homelab.com**
|
||||
|
||||
## Persistent Storage
|
||||
|
||||
- All Claude configuration stored in `/root/.claude` (persistent PVC, 10Gi Longhorn)
|
||||
- Survives pod restarts and node reboots
|
||||
- Accessible immediately after reconnecting
|
||||
|
||||
## SSH Access (Optional)
|
||||
|
||||
To add SSH access, extend the Dockerfile to include openssh-server and mount the PVC as home directory.
|
||||
Executable
+24
@@ -0,0 +1,24 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
REGISTRY="forgejo.riotpiao.homelab.com"
|
||||
IMAGE_NAME="rock/claude-terminal"
|
||||
TAG="latest"
|
||||
FULL_IMAGE="${REGISTRY}/${IMAGE_NAME}:${TAG}"
|
||||
|
||||
echo "🔨 Building Claude Terminal image for linux/amd64..."
|
||||
docker buildx build --platform linux/amd64 \
|
||||
-t "${FULL_IMAGE}" \
|
||||
-f Dockerfile \
|
||||
. || { echo "❌ Build failed"; exit 1; }
|
||||
|
||||
echo "🔓 Logging in to Forgejo registry..."
|
||||
REGISTRY_TOKEN=$(talos get cluster/iam/agents/ci-bot --key token)
|
||||
echo "${REGISTRY_TOKEN}" | docker login "${REGISTRY}" \
|
||||
--username ci-bot \
|
||||
--password-stdin || { echo "❌ Login failed"; exit 1; }
|
||||
|
||||
echo "📤 Pushing image to registry..."
|
||||
docker push "${FULL_IMAGE}" || { echo "❌ Push failed"; exit 1; }
|
||||
|
||||
echo "✅ Successfully pushed ${FULL_IMAGE}"
|
||||
Executable
+13
@@ -0,0 +1,13 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
# Start tmux server in background
|
||||
tmux new-session -d -s claude -c /root "bash"
|
||||
|
||||
# Give tmux a moment to stabilize
|
||||
sleep 1
|
||||
|
||||
# Start gotty serving the tmux session
|
||||
# -w: allow write (make terminal interactive)
|
||||
# -p 8080: listen on port 8080
|
||||
exec gotty -p 8080 -w tmux attach-session -t claude
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: dev-tools
|
||||
resources: []
|
||||
# Helm chart deployed via ArgoCD Helm source
|
||||
@@ -0,0 +1,49 @@
|
||||
{{/*
|
||||
Expand the name of the chart.
|
||||
*/}}
|
||||
{{- define "claude-terminal.name" -}}
|
||||
{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Create a default fully qualified app name.
|
||||
*/}}
|
||||
{{- define "claude-terminal.fullname" -}}
|
||||
{{- if .Values.fullnameOverride }}
|
||||
{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
|
||||
{{- else }}
|
||||
{{- $name := default .Chart.Name .Values.nameOverride }}
|
||||
{{- if contains $name .Release.Name }}
|
||||
{{- .Release.Name | trunc 63 | trimSuffix "-" }}
|
||||
{{- else }}
|
||||
{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Create chart name and version as used by the chart label.
|
||||
*/}}
|
||||
{{- define "claude-terminal.chart" -}}
|
||||
{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Common labels
|
||||
*/}}
|
||||
{{- define "claude-terminal.labels" -}}
|
||||
helm.sh/chart: {{ include "claude-terminal.chart" . }}
|
||||
{{ include "claude-terminal.selectorLabels" . }}
|
||||
{{- if .Chart.AppVersion }}
|
||||
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
|
||||
{{- end }}
|
||||
app.kubernetes.io/managed-by: {{ .Release.Service }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Selector labels
|
||||
*/}}
|
||||
{{- define "claude-terminal.selectorLabels" -}}
|
||||
app.kubernetes.io/name: {{ include "claude-terminal.name" . }}
|
||||
app.kubernetes.io/instance: {{ .Release.Name }}
|
||||
{{- end }}
|
||||
@@ -0,0 +1,57 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: {{ include "claude-terminal.fullname" . }}
|
||||
labels:
|
||||
{{- include "claude-terminal.labels" . | nindent 4 }}
|
||||
spec:
|
||||
replicas: {{ .Values.replicaCount }}
|
||||
selector:
|
||||
matchLabels:
|
||||
{{- include "claude-terminal.selectorLabels" . | nindent 6 }}
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
{{- include "claude-terminal.selectorLabels" . | nindent 8 }}
|
||||
spec:
|
||||
containers:
|
||||
- name: claude-terminal
|
||||
image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
|
||||
imagePullPolicy: {{ .Values.image.pullPolicy }}
|
||||
ports:
|
||||
- name: http
|
||||
containerPort: 8080
|
||||
protocol: TCP
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /
|
||||
port: http
|
||||
initialDelaySeconds: 30
|
||||
periodSeconds: 10
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /
|
||||
port: http
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 5
|
||||
resources:
|
||||
{{- toYaml .Values.resources | nindent 12 }}
|
||||
volumeMounts:
|
||||
- name: claude-storage
|
||||
mountPath: {{ .Values.persistence.mountPath }}
|
||||
volumes:
|
||||
- name: claude-storage
|
||||
persistentVolumeClaim:
|
||||
claimName: {{ include "claude-terminal.fullname" . }}-pvc
|
||||
{{- with .Values.nodeSelector }}
|
||||
nodeSelector:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with .Values.affinity }}
|
||||
affinity:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with .Values.tolerations }}
|
||||
tolerations:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
@@ -0,0 +1,41 @@
|
||||
{{- if .Values.ingress.enabled }}
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: Ingress
|
||||
metadata:
|
||||
name: {{ include "claude-terminal.fullname" . }}
|
||||
labels:
|
||||
{{- include "claude-terminal.labels" . | nindent 4 }}
|
||||
{{- with .Values.ingress.annotations }}
|
||||
annotations:
|
||||
{{- toYaml . | nindent 4 }}
|
||||
{{- end }}
|
||||
spec:
|
||||
{{- if .Values.ingress.className }}
|
||||
ingressClassName: {{ .Values.ingress.className }}
|
||||
{{- end }}
|
||||
{{- if .Values.ingress.tls }}
|
||||
tls:
|
||||
{{- range .Values.ingress.tls }}
|
||||
- hosts:
|
||||
{{- range .hosts }}
|
||||
- {{ . | quote }}
|
||||
{{- end }}
|
||||
secretName: {{ .secretName }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
rules:
|
||||
{{- range .Values.ingress.hosts }}
|
||||
- host: {{ .host | quote }}
|
||||
http:
|
||||
paths:
|
||||
{{- range .paths }}
|
||||
- path: {{ .path }}
|
||||
pathType: {{ .pathType }}
|
||||
backend:
|
||||
service:
|
||||
name: {{ include "claude-terminal.fullname" $ }}
|
||||
port:
|
||||
number: {{ $.Values.service.port }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
@@ -0,0 +1,15 @@
|
||||
{{- if .Values.persistence.enabled }}
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
metadata:
|
||||
name: {{ include "claude-terminal.fullname" . }}-pvc
|
||||
labels:
|
||||
{{- include "claude-terminal.labels" . | nindent 4 }}
|
||||
spec:
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
storageClassName: {{ .Values.persistence.storageClass }}
|
||||
resources:
|
||||
requests:
|
||||
storage: {{ .Values.persistence.size }}
|
||||
{{- end }}
|
||||
@@ -0,0 +1,15 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: {{ include "claude-terminal.fullname" . }}
|
||||
labels:
|
||||
{{- include "claude-terminal.labels" . | nindent 4 }}
|
||||
spec:
|
||||
type: {{ .Values.service.type }}
|
||||
ports:
|
||||
- port: {{ .Values.service.port }}
|
||||
targetPort: http
|
||||
protocol: TCP
|
||||
name: http
|
||||
selector:
|
||||
{{- include "claude-terminal.selectorLabels" . | nindent 4 }}
|
||||
@@ -0,0 +1,45 @@
|
||||
replicaCount: 1
|
||||
|
||||
image:
|
||||
repository: localhost:5000/claude-terminal
|
||||
pullPolicy: IfNotPresent
|
||||
tag: latest
|
||||
|
||||
service:
|
||||
type: ClusterIP
|
||||
port: 8080
|
||||
|
||||
ingress:
|
||||
enabled: true
|
||||
className: nginx
|
||||
annotations:
|
||||
cert-manager.io/cluster-issuer: homelab-ca
|
||||
hosts:
|
||||
- host: claude.riotpiao.homelab.com
|
||||
paths:
|
||||
- path: /
|
||||
pathType: Prefix
|
||||
tls:
|
||||
- secretName: claude-terminal-tls
|
||||
hosts:
|
||||
- claude.riotpiao.homelab.com
|
||||
|
||||
persistence:
|
||||
enabled: true
|
||||
storageClass: longhorn
|
||||
size: 10Gi
|
||||
mountPath: /root/.claude
|
||||
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 256Mi
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 512Mi
|
||||
|
||||
nodeSelector: {}
|
||||
|
||||
tolerations: []
|
||||
|
||||
affinity: {}
|
||||
@@ -0,0 +1,40 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: duckdns-updater
|
||||
namespace: kube-system
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app: duckdns-updater
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: duckdns-updater
|
||||
spec:
|
||||
containers:
|
||||
- name: updater
|
||||
image: curlimages/curl:latest
|
||||
command:
|
||||
- sh
|
||||
- -c
|
||||
- |
|
||||
while true; do
|
||||
curl -fsS "https://www.duckdns.org/update?domains=riotpiao&token=${DUCKDNS_TOKEN}&ip="
|
||||
sleep 300
|
||||
done
|
||||
env:
|
||||
- name: DUCKDNS_TOKEN
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: duckdns-token
|
||||
key: token
|
||||
resources:
|
||||
requests:
|
||||
cpu: 5m
|
||||
memory: 16Mi
|
||||
limits:
|
||||
cpu: 50m
|
||||
memory: 32Mi
|
||||
restartPolicy: Always
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: duckdns
|
||||
resources: []
|
||||
# DuckDNS deployed via Helm chart or CronJob
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: forge
|
||||
resources:
|
||||
- pki/
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
|
||||
resources: []
|
||||
# PKI configuration, not K8s manifests
|
||||
@@ -0,0 +1,95 @@
|
||||
# k8s/forge/runner-gc-cronjob.yaml
|
||||
# Garbage-collects the forgejo-runner's DinD layer cache (runner-dind PVC,
|
||||
# 30Gi). Every CI build/pull only adds images and build-cache layers — there
|
||||
# is no automatic pruning, so without this the PVC fills up and breaks builds.
|
||||
#
|
||||
# Runs `docker image prune` / `docker builder prune` inside the live dind
|
||||
# container via `kubectl exec`, rather than a sidecar in the runner pod itself,
|
||||
# so it can run on its own schedule independent of runner restarts.
|
||||
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: runner-gc
|
||||
namespace: cicd
|
||||
|
||||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: Role
|
||||
metadata:
|
||||
name: runner-gc
|
||||
namespace: cicd
|
||||
rules:
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["get", "list"]
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["create"]
|
||||
|
||||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: RoleBinding
|
||||
metadata:
|
||||
name: runner-gc
|
||||
namespace: cicd
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: runner-gc
|
||||
namespace: cicd
|
||||
roleRef:
|
||||
kind: Role
|
||||
name: runner-gc
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
|
||||
---
|
||||
apiVersion: batch/v1
|
||||
kind: CronJob
|
||||
metadata:
|
||||
name: forgejo-runner-image-gc
|
||||
namespace: cicd
|
||||
spec:
|
||||
schedule: "0 3 * * *" # daily 03:00
|
||||
concurrencyPolicy: Forbid
|
||||
successfulJobsHistoryLimit: 3
|
||||
failedJobsHistoryLimit: 3
|
||||
jobTemplate:
|
||||
spec:
|
||||
backoffLimit: 1
|
||||
activeDeadlineSeconds: 600
|
||||
template:
|
||||
spec:
|
||||
serviceAccountName: runner-gc
|
||||
restartPolicy: Never
|
||||
tolerations:
|
||||
- key: node-role.kubernetes.io/control-plane
|
||||
operator: Exists
|
||||
effect: NoSchedule
|
||||
containers:
|
||||
- name: gc
|
||||
image: alpine/k8s:1.31.0
|
||||
command:
|
||||
- sh
|
||||
- -c
|
||||
- |
|
||||
set -e
|
||||
POD=$(kubectl -n cicd get pod -l app=forgejo-runner -o jsonpath='{.items[0].metadata.name}')
|
||||
if [ -z "$POD" ]; then
|
||||
echo "no forgejo-runner pod found, skipping"
|
||||
exit 0
|
||||
fi
|
||||
echo "before:"
|
||||
kubectl -n cicd exec "$POD" -c dind -- df -h /var/lib/docker
|
||||
echo "pruning images unused for >72h on $POD"
|
||||
kubectl -n cicd exec "$POD" -c dind -- docker image prune -af --filter "until=72h"
|
||||
echo "pruning build cache unused for >72h on $POD"
|
||||
kubectl -n cicd exec "$POD" -c dind -- docker builder prune -af --filter "until=72h"
|
||||
echo "after:"
|
||||
kubectl -n cicd exec "$POD" -c dind -- df -h /var/lib/docker
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 64Mi
|
||||
limits:
|
||||
cpu: 250m
|
||||
memory: 128Mi
|
||||
@@ -0,0 +1,438 @@
|
||||
# k8s/forge/runner.yaml
|
||||
# Forgejo Actions runner with Docker-in-Docker (DinD) sidecar.
|
||||
# Phase 3.2 of talos_version_control.html.
|
||||
#
|
||||
# Pod layout (two containers, one pod):
|
||||
# register initContainer — registers with Forgejo once; skips if .runner exists
|
||||
# runner main container — long-running daemon that polls Forgejo for jobs
|
||||
# dind sidecar — Docker daemon the runner talks to via mTLS on tcp://localhost:2376
|
||||
#
|
||||
# Prerequisites (Phase 3.1):
|
||||
# TOKEN=$(kubectl -n cicd exec deploy/forgejo-gitea -- \
|
||||
# gitea actions generate-runner-token 2>/dev/null | tr -d '\r\n')
|
||||
# kubectl -n cicd create secret generic runner-token --from-literal=token="$TOKEN"
|
||||
# # CA must come from cert-manager's homelab-ca-secret (the org-wide CA that
|
||||
# # signs the live ingress cert), NOT k8s/forge/pki/ca.crt — that file is a
|
||||
# # stale CA from before the "unified certificate" migration.
|
||||
# kubectl get secret homelab-ca-secret -n cert-manager -o jsonpath='{.data.tls\.crt}' \
|
||||
# | base64 -d | kubectl -n cicd create secret generic homelab-ca --from-file=ca.crt=/dev/stdin
|
||||
#
|
||||
# CA trust for ephemeral job containers (Phase 3.3):
|
||||
# The homelab-ca secret above only reaches the runner/register/dind containers.
|
||||
# It does NOT reach the per-job containers DinD spawns (e.g. golangci-lint,
|
||||
# node:22-bookworm) — those are fresh sibling containers with their own trust
|
||||
# store. Without this, any git/curl/apk call to forgejo.riotpiao.homelab.com
|
||||
# from inside a job fails with "SSL certificate problem: unable to get local
|
||||
# issuer certificate". Build a merged bundle (public roots + homelab CA) and
|
||||
# bind-mount it over /etc/ssl/certs/ca-certificates.crt in every job
|
||||
# container via forgejo-runner's config.yaml container.options.
|
||||
#
|
||||
# IMPORTANT: source the CA from the live cluster secret, NOT from
|
||||
# k8s/forge/pki/ca.crt — that repo file is a stale CA from before the
|
||||
# "unified certificate" migration (different key, fails verification
|
||||
# against the cert actually served by forgejo.riotpiao.homelab.com). The
|
||||
# org-wide CA that signs the live ingress cert lives in
|
||||
# cert-manager/homelab-ca-secret, and cicd/homelab-ca above is already
|
||||
# synced from it.
|
||||
# docker run --rm docker:27-dind cat /etc/ssl/certs/ca-certificates.crt > /tmp/ca-bundle.crt
|
||||
# kubectl -n cicd get secret homelab-ca -o jsonpath='{.data.ca\.crt}' | base64 -d >> /tmp/ca-bundle.crt
|
||||
# kubectl -n cicd create secret generic ca-bundle --from-file=ca-certificates.crt=/tmp/ca-bundle.crt
|
||||
# Re-run this whenever the homelab CA rotates (see talos-forge-trust.yaml).
|
||||
#
|
||||
# Apply:
|
||||
# kubectl apply -f k8s/forge/runner.yaml
|
||||
# kubectl -n cicd rollout status deploy/forgejo-runner
|
||||
# kubectl -n cicd logs deploy/forgejo-runner -c runner -f
|
||||
# # expect: "runner: daemon started" / "connected to Forgejo"
|
||||
|
||||
# ── PVCs ──────────────────────────────────────────────────────────────────────
|
||||
# runner-reg — persists the .runner registration file so the runner doesn't
|
||||
# re-register on every pod restart (token is one-use-per-registration)
|
||||
# runner-dind — persists the Docker layer cache across pod restarts; keeps
|
||||
# rebuilds fast — images don't need to be re-pulled every time
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
metadata:
|
||||
name: runner-reg
|
||||
namespace: cicd
|
||||
spec:
|
||||
accessModes: [ReadWriteOnce]
|
||||
storageClassName: longhorn
|
||||
resources:
|
||||
requests:
|
||||
storage: 1Gi
|
||||
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
metadata:
|
||||
name: runner-dind
|
||||
namespace: cicd
|
||||
spec:
|
||||
accessModes: [ReadWriteOnce]
|
||||
storageClassName: longhorn
|
||||
resources:
|
||||
requests:
|
||||
storage: 30Gi
|
||||
|
||||
---
|
||||
# ── DinD TLS certs, issued by the homelab's unified CA ───────────────────────
|
||||
# DinD's own entrypoint (dockerd-entrypoint.sh) self-generates a throwaway CA
|
||||
# + server/client cert pair on every container start if none is supplied. Its
|
||||
# server cert's SAN list only ever covers "docker", the pod hostname, and
|
||||
# "localhost" - so anything reaching it via a stable Service DNS name (added
|
||||
# below for story-crater-backend's release.yaml to build/push images) fails
|
||||
# TLS hostname verification, even though the handshake itself succeeds.
|
||||
#
|
||||
# Fix: supply our own server+client cert pair, both issued by the same
|
||||
# ClusterIssuer (homelab-ca) that already signs the live ingress cert, so
|
||||
# they share one trust root. dockerd-entrypoint.sh skips its own generation
|
||||
# step entirely once it finds $DOCKER_TLS_CERTDIR/server/{ca,cert,key}.pem
|
||||
# already present and no CA private key alongside them (confirmed by reading
|
||||
# the script directly: `kubectl exec -n cicd <pod> -c dind -- cat
|
||||
# /usr/local/bin/dockerd-entrypoint.sh`) - exactly the "bring your own CA"
|
||||
# path it's designed for.
|
||||
apiVersion: cert-manager.io/v1
|
||||
kind: Certificate
|
||||
metadata:
|
||||
name: forgejo-runner-dind-server
|
||||
namespace: cicd
|
||||
spec:
|
||||
secretName: forgejo-runner-dind-server-tls
|
||||
issuerRef:
|
||||
name: homelab-ca
|
||||
kind: ClusterIssuer
|
||||
commonName: docker:dind server
|
||||
dnsNames:
|
||||
- forgejo-runner-dind.cicd.svc.cluster.local
|
||||
- forgejo-runner-dind.cicd.svc
|
||||
- forgejo-runner-dind
|
||||
- docker
|
||||
- localhost
|
||||
usages:
|
||||
- server auth
|
||||
- digital signature
|
||||
- key encipherment
|
||||
|
||||
---
|
||||
apiVersion: cert-manager.io/v1
|
||||
kind: Certificate
|
||||
metadata:
|
||||
name: forgejo-runner-dind-client
|
||||
namespace: cicd
|
||||
spec:
|
||||
secretName: forgejo-runner-dind-client-tls
|
||||
issuerRef:
|
||||
name: homelab-ca
|
||||
kind: ClusterIssuer
|
||||
commonName: docker:dind client
|
||||
usages:
|
||||
- client auth
|
||||
- digital signature
|
||||
- key encipherment
|
||||
|
||||
---
|
||||
# Stable address for the dind sidecar's docker API (2376, mTLS) - lets
|
||||
# CI workflows (e.g. story-crater-backend's release.yaml) build/push images
|
||||
# by reaching this runner's own already-working outer dind directly, instead
|
||||
# of the per-job `services:` sidecar pattern (confirmed broken: act-runner
|
||||
# never registers a DNS alias for service containers - job container's
|
||||
# /etc/hosts has no entry for it, `docker info` fails with a DNS lookup
|
||||
# error, not a TLS/connection error).
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: forgejo-runner-dind
|
||||
namespace: cicd
|
||||
spec:
|
||||
selector:
|
||||
app: forgejo-runner
|
||||
ports:
|
||||
- port: 2376
|
||||
targetPort: 2376
|
||||
|
||||
---
|
||||
# ── Runner config ─────────────────────────────────────────────────────────────
|
||||
# container.options is appended to every `docker run` DinD issues for a job
|
||||
# container, so this is what actually gets the merged CA bundle (ca-bundle
|
||||
# secret, see header comment) trusted inside golangci-lint, node, etc. - and
|
||||
# now also what propagates the homelab-CA-signed client cert (above) into
|
||||
# job containers that need to talk back to dind themselves (e.g. building
|
||||
# and pushing images).
|
||||
# Source paths resolve against the dind container's filesystem (it's the
|
||||
# daemon creating these containers), so both are mounted into dind below.
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: forgejo-runner-config
|
||||
namespace: cicd
|
||||
data:
|
||||
config.yaml: |
|
||||
container:
|
||||
options: -v /etc/forgejo-ca/ca-certificates.crt:/etc/ssl/certs/ca-certificates.crt:ro -v /docker-certs/client:/docker-certs/client:ro
|
||||
# Without this, sanitizeConfig() in forgejo/act silently drops any bind
|
||||
# mount whose source isn't allowlisted here — including ones injected
|
||||
# via container.options above, not just workflow-declared volumes.
|
||||
valid_volumes:
|
||||
- /etc/forgejo-ca/ca-certificates.crt
|
||||
- /docker-certs/client
|
||||
|
||||
---
|
||||
# ── Deployment ────────────────────────────────────────────────────────────────
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: forgejo-runner
|
||||
namespace: cicd
|
||||
spec:
|
||||
replicas: 1
|
||||
# RWO PVCs mean only one pod can mount them at a time.
|
||||
# Recreate ensures the old pod fully terminates before the new one starts.
|
||||
strategy:
|
||||
type: Recreate
|
||||
selector:
|
||||
matchLabels:
|
||||
app: forgejo-runner
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: forgejo-runner
|
||||
spec:
|
||||
# runner/register containers run as uid 1000 (image default); fsGroup
|
||||
# makes kubelet chown+chmod the Longhorn PVC's group to 1000 with
|
||||
# write access, otherwise writes to /data (.runner config) fail with
|
||||
# "permission denied" since the volume is root:root 755 by default.
|
||||
securityContext:
|
||||
fsGroup: 1000
|
||||
tolerations:
|
||||
- key: node-role.kubernetes.io/control-plane
|
||||
operator: Exists
|
||||
effect: NoSchedule
|
||||
|
||||
initContainers:
|
||||
# Registers the runner with Forgejo exactly once.
|
||||
# test -f /data/.runner makes it idempotent — re-registration would
|
||||
# consume the one-time token and break the runner.
|
||||
- name: register
|
||||
image: code.forgejo.org/forgejo/runner:6
|
||||
command: ["sh", "-c"]
|
||||
args:
|
||||
- |
|
||||
test -f /data/.runner && echo "already registered, skipping" && exit 0
|
||||
forgejo-runner register --no-interactive \
|
||||
--instance https://forgejo.riotpiao.homelab.com \
|
||||
--token "$RUNNER_TOKEN" \
|
||||
--name talos-runner \
|
||||
--labels "docker:docker://node:22-bookworm"
|
||||
env:
|
||||
- name: RUNNER_TOKEN
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: runner-token
|
||||
key: token
|
||||
volumeMounts:
|
||||
- name: runner-data
|
||||
mountPath: /data
|
||||
# CA cert so the register call can verify Forgejo's TLS cert
|
||||
- name: homelab-ca
|
||||
mountPath: /etc/ssl/certs/homelab-ca.pem
|
||||
subPath: ca.crt
|
||||
workingDir: /data
|
||||
|
||||
containers:
|
||||
# ── Runner daemon ────────────────────────────────────────────────────
|
||||
# Polls Forgejo for pending jobs and executes them inside DinD.
|
||||
# The `until docker info` loop waits for the DinD sidecar to finish
|
||||
# its TLS setup before starting the daemon — without this the runner
|
||||
# starts before Docker is ready and immediately errors out.
|
||||
- name: runner
|
||||
image: code.forgejo.org/forgejo/runner:6
|
||||
command: ["sh", "-c"]
|
||||
args:
|
||||
- |
|
||||
until nc -z localhost 2376 >/dev/null 2>&1; do
|
||||
echo "waiting for docker daemon..."; sleep 2
|
||||
done
|
||||
forgejo-runner daemon --config /data/config.yaml
|
||||
workingDir: /data
|
||||
env:
|
||||
# Connect to the DinD sidecar via mTLS on localhost
|
||||
- name: DOCKER_HOST
|
||||
value: tcp://localhost:2376
|
||||
- name: DOCKER_TLS_VERIFY
|
||||
value: "1"
|
||||
- name: DOCKER_CERT_PATH
|
||||
value: /docker-certs/client
|
||||
volumeMounts:
|
||||
- name: runner-data
|
||||
mountPath: /data
|
||||
- name: docker-certs
|
||||
mountPath: /docker-certs
|
||||
- name: homelab-ca
|
||||
mountPath: /etc/ssl/certs/homelab-ca.pem
|
||||
subPath: ca.crt
|
||||
# forgejo-runner's container.options, read from this file, is what
|
||||
# propagates the CA bundle into per-job containers (see ca-bundle
|
||||
# secret + dind mount below)
|
||||
- name: runner-config
|
||||
mountPath: /data/config.yaml
|
||||
subPath: config.yaml
|
||||
# Homelab-CA-signed client cert (overlays whatever's in the
|
||||
# docker-certs emptyDir at this subpath) - matches the server
|
||||
# cert dind now presents, see Certificates above.
|
||||
- name: dind-client-tls
|
||||
mountPath: /docker-certs/client
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 256Mi
|
||||
limits:
|
||||
cpu: "2"
|
||||
memory: 4Gi
|
||||
|
||||
# ── DinD sidecar ──────────────────────────────────────────────────────
|
||||
# Full Docker daemon running inside the pod.
|
||||
# privileged: true is required for DinD — the cicd namespace is labelled
|
||||
# pod-security.kubernetes.io/enforce=privileged to allow this.
|
||||
# DOCKER_TLS_CERTDIR causes DinD to generate mTLS certs in /docker-certs
|
||||
# on startup; the runner reads the client certs from /docker-certs/client.
|
||||
# runner-dind PVC mounts /var/lib/docker so the layer cache persists
|
||||
# across pod restarts.
|
||||
- name: dind
|
||||
image: docker:27-dind
|
||||
securityContext:
|
||||
privileged: true
|
||||
env:
|
||||
- name: DOCKER_TLS_CERTDIR
|
||||
value: /docker-certs
|
||||
volumeMounts:
|
||||
- name: docker-certs
|
||||
mountPath: /docker-certs
|
||||
- name: dind-storage
|
||||
mountPath: /var/lib/docker
|
||||
# Trust the homelab CA so DinD can pull from Forgejo's OCI registry
|
||||
- name: homelab-ca
|
||||
mountPath: /etc/ssl/certs/homelab-ca.pem
|
||||
subPath: ca.crt
|
||||
# Merged CA bundle (public roots + homelab CA), bind-mounted from
|
||||
# here into every job container by container.options above —
|
||||
# this path is resolved against dind's filesystem since dind is
|
||||
# the daemon actually creating those containers.
|
||||
- name: ca-bundle
|
||||
mountPath: /etc/forgejo-ca/ca-certificates.crt
|
||||
subPath: ca-certificates.crt
|
||||
# Homelab-CA-signed server+client certs (see Certificates above),
|
||||
# overlaying the matching subpaths of the docker-certs emptyDir.
|
||||
# dockerd-entrypoint.sh detects these and skips its own
|
||||
# self-signed generation entirely (no CA private key is supplied
|
||||
# alongside them, so it can't regenerate even if it wanted to).
|
||||
- name: dind-server-tls
|
||||
mountPath: /docker-certs/server
|
||||
- name: dind-client-tls
|
||||
mountPath: /docker-certs/client
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 256Mi
|
||||
limits:
|
||||
cpu: "2"
|
||||
memory: 4Gi
|
||||
|
||||
volumes:
|
||||
- name: runner-data
|
||||
persistentVolumeClaim:
|
||||
claimName: runner-reg
|
||||
- name: dind-storage
|
||||
persistentVolumeClaim:
|
||||
claimName: runner-dind
|
||||
# emptyDir parent mount for /docker-certs - the server/ and client/
|
||||
# subpaths are now overlaid by the homelab-CA-signed dind-server-tls/
|
||||
# dind-client-tls secret mounts below (dockerd-entrypoint.sh no
|
||||
# longer self-generates once it finds those present). This emptyDir
|
||||
# just needs to exist as the parent directory; nothing writes
|
||||
# directly to it anymore.
|
||||
- name: docker-certs
|
||||
emptyDir: {}
|
||||
- name: homelab-ca
|
||||
secret:
|
||||
secretName: homelab-ca
|
||||
- name: ca-bundle
|
||||
secret:
|
||||
secretName: ca-bundle
|
||||
- name: runner-config
|
||||
configMap:
|
||||
name: forgejo-runner-config
|
||||
# cert-manager issues these as tls.crt/tls.key/ca.crt - remapped to
|
||||
# the ca.pem/cert.pem/key.pem filenames dockerd-entrypoint.sh expects
|
||||
# under $DOCKER_TLS_CERTDIR/{server,client}/.
|
||||
- name: dind-server-tls
|
||||
secret:
|
||||
secretName: forgejo-runner-dind-server-tls
|
||||
items:
|
||||
- key: ca.crt
|
||||
path: ca.pem
|
||||
- key: tls.crt
|
||||
path: cert.pem
|
||||
- key: tls.key
|
||||
path: key.pem
|
||||
- name: dind-client-tls
|
||||
secret:
|
||||
secretName: forgejo-runner-dind-client-tls
|
||||
items:
|
||||
- key: ca.crt
|
||||
path: ca.pem
|
||||
- key: tls.crt
|
||||
path: cert.pem
|
||||
- key: tls.key
|
||||
path: key.pem
|
||||
|
||||
---
|
||||
# ── NetworkPolicy ─────────────────────────────────────────────────────────────
|
||||
# Restrict runner egress: it may only reach Forgejo (cicd ns), CoreDNS, and
|
||||
# the public internet for action dependencies and base images.
|
||||
# LAN (192.168.1.0/24) and the pod network (10.244.0.0/16) are blocked to
|
||||
# prevent a compromised CI job from pivoting into the cluster or LAN.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: runner-egress
|
||||
namespace: cicd
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app: forgejo-runner
|
||||
policyTypes: [Egress]
|
||||
egress:
|
||||
# Forgejo (same namespace — git push, OCI registry push/pull)
|
||||
- to:
|
||||
- podSelector: {}
|
||||
# ingress-nginx (the runner talks to Forgejo via its public hostname,
|
||||
# https://forgejo.riotpiao.homelab.com, which resolves to the ingress
|
||||
# controller's ClusterIP — a different namespace on the pod network)
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: ingress-nginx
|
||||
ports:
|
||||
- protocol: TCP
|
||||
port: 443
|
||||
- protocol: TCP
|
||||
port: 80
|
||||
# CoreDNS (DNS resolution for action deps and Forgejo hostname)
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
# Public internet for action dependencies and base images
|
||||
# LAN and pod network are explicitly excluded
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 192.168.1.0/24
|
||||
- 10.244.0.0/16
|
||||
@@ -0,0 +1,18 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
metadata:
|
||||
name: applications
|
||||
|
||||
# Layer 5: Applications — user services, workloads
|
||||
# Dependencies: all previous layers (bootstrap, platform, security)
|
||||
# Order: Applied fifth
|
||||
|
||||
resources:
|
||||
- temporal/
|
||||
- sqs/
|
||||
- llm/
|
||||
- portainer/
|
||||
- forge/
|
||||
- shadowsocks/
|
||||
- dev-tools/
|
||||
- duckdns/
|
||||
@@ -0,0 +1,299 @@
|
||||
# Ollama LLM Inference Service
|
||||
|
||||
CPU-only LLM inference server on talos-cp-1. Single model hot-loaded (DeepSeek-R1:70b), 42GB, 70Gi memory limit.
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Access via port-forward
|
||||
```bash
|
||||
kubectl -n llm port-forward svc/ollama 11434:11434
|
||||
curl http://localhost:11434/api/tags
|
||||
```
|
||||
|
||||
### Debug pod (in-cluster)
|
||||
```bash
|
||||
kubectl run debug --rm -it -n llm --image=curlimages/curl \
|
||||
--labels="app.kubernetes.io/role=llm-debug" \
|
||||
--serviceaccount=llm-worker -- sh
|
||||
|
||||
# Inside pod
|
||||
TOKEN=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
|
||||
curl -H "Authorization: Bearer $TOKEN" \
|
||||
http://ollama.llm.svc.cluster.local:11434/api/tags
|
||||
```
|
||||
|
||||
## Architecture
|
||||
|
||||
| Component | Value |
|
||||
|-----------|-------|
|
||||
| Service | ClusterIP `ollama.llm.svc.cluster.local:11434` |
|
||||
| Namespace | `llm` |
|
||||
| Node | talos-cp-1 (pinned via nodeAffinity) |
|
||||
| Memory request | 50Gi |
|
||||
| Memory limit | 70Gi |
|
||||
| Storage | 115Gi PVC (Longhorn) |
|
||||
| Model | `deepseek-r1:70b` (~42GB) |
|
||||
| Max loaded | 1 model |
|
||||
| Parallelism | 1 request at a time |
|
||||
|
||||
## API Endpoints
|
||||
|
||||
### List models
|
||||
```bash
|
||||
curl http://ollama.llm.svc.cluster.local:11434/api/tags
|
||||
```
|
||||
|
||||
Response:
|
||||
```json
|
||||
{
|
||||
"models": [
|
||||
{"name": "deepseek-r1:70b", "size": 42000000000, ...}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
### Generate (non-streaming)
|
||||
```bash
|
||||
curl -X POST http://ollama.llm.svc.cluster.local:11434/api/generate \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model": "deepseek-r1:70b",
|
||||
"prompt": "Why is the sky blue?",
|
||||
"stream": false
|
||||
}'
|
||||
```
|
||||
|
||||
### Pull model
|
||||
```bash
|
||||
curl -X POST http://ollama.llm.svc.cluster.local:11434/api/pull \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"name": "deepseek-r1:70b", "stream": false}'
|
||||
```
|
||||
|
||||
## Operations
|
||||
|
||||
### Check pod status
|
||||
```bash
|
||||
kubectl -n llm get pod -l app.kubernetes.io/name=ollama
|
||||
kubectl -n llm describe pod -l app.kubernetes.io/name=ollama
|
||||
```
|
||||
|
||||
### View logs
|
||||
```bash
|
||||
kubectl -n llm logs deployment/ollama -f
|
||||
```
|
||||
|
||||
### Monitor download progress (bootstrap)
|
||||
```bash
|
||||
kubectl -n llm logs -f job/bootstrap-models -c model-download
|
||||
```
|
||||
|
||||
### Restart deployment
|
||||
```bash
|
||||
kubectl -n llm rollout restart deployment/ollama
|
||||
```
|
||||
|
||||
## Storage
|
||||
|
||||
- **PVC:** `ollama-models-cache`, 115Gi, Longhorn StorageClass
|
||||
- **Mount:** `/root/.ollama/models` (Ollama model cache)
|
||||
- **Lifecycle:** RWO (Read-Write-Once), tied to talos-cp-1
|
||||
|
||||
### Resize PVC
|
||||
⚠️ PVCs can only expand, not shrink. Edit values.yaml and redeploy:
|
||||
|
||||
```yaml
|
||||
pvc:
|
||||
size: 120Gi # increase only
|
||||
```
|
||||
|
||||
```bash
|
||||
vsource .env && helmfile -f helmfile.yaml.gotmpl -l name=ollama apply
|
||||
```
|
||||
|
||||
## Networking
|
||||
|
||||
### NetworkPolicy
|
||||
- Default-deny ingress on Ollama pods
|
||||
- Allow from pods labeled `app.kubernetes.io/name: llm-worker` (port 11434)
|
||||
- Allow from pods labeled `app.kubernetes.io/role: llm-debug` (port 11434)
|
||||
|
||||
View policy:
|
||||
```bash
|
||||
kubectl -n llm get networkpolicy ollama
|
||||
```
|
||||
|
||||
Test access from external pod (should fail):
|
||||
```bash
|
||||
kubectl run test --rm -it --image=curlimages/curl -- \
|
||||
curl http://ollama.llm.svc.cluster.local:11434/
|
||||
# Connection timeout (correct)
|
||||
```
|
||||
|
||||
Test access from debug pod (should succeed):
|
||||
```bash
|
||||
kubectl -n llm logs job/bootstrap-models # verify bootstrap completed
|
||||
# Then run debug pod as shown above
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
### Helm values (`k8s/llm/charts/ollama/values.yaml`)
|
||||
|
||||
```yaml
|
||||
resources:
|
||||
requests:
|
||||
cpu: 8
|
||||
memory: 50Gi
|
||||
limits:
|
||||
cpu: 16
|
||||
memory: 70Gi
|
||||
|
||||
env:
|
||||
OLLAMA_MAX_LOADED_MODELS: "1"
|
||||
OLLAMA_NUM_PARALLEL: "1"
|
||||
OLLAMA_MAX_QUEUE: "32"
|
||||
OLLAMA_KEEP_ALIVE: "-1"
|
||||
OLLAMA_HOST: "0.0.0.0:11434"
|
||||
|
||||
preloadJob:
|
||||
enabled: true
|
||||
hotModels:
|
||||
- deepseek-r1:70b
|
||||
```
|
||||
|
||||
### Environment variables
|
||||
|
||||
| Variable | Value | Purpose |
|
||||
|----------|-------|---------|
|
||||
| `OLLAMA_MODELS` | `/root/.ollama/models` | Model cache dir |
|
||||
| `OLLAMA_MAX_LOADED_MODELS` | `1` | Max concurrent models in RAM |
|
||||
| `OLLAMA_NUM_PARALLEL` | `1` | Parallel request threads |
|
||||
| `OLLAMA_MAX_QUEUE` | `32` | Request queue depth |
|
||||
| `OLLAMA_KEEP_ALIVE` | `-1` | Keep model resident (never unload) |
|
||||
| `OLLAMA_HOST` | `0.0.0.0:11434` | Bind address |
|
||||
|
||||
Tune `OLLAMA_NUM_PARALLEL` based on CPU cores. Current: 1 (conservative, CPU bottleneck).
|
||||
|
||||
## Model Management
|
||||
|
||||
### Current model
|
||||
- **Name:** `deepseek-r1:70b`
|
||||
- **Size:** ~42GB
|
||||
- **Quantization:** Default Ollama quant
|
||||
- **Status:** Downloaded during pod init via bootstrap job
|
||||
|
||||
### Change model
|
||||
|
||||
1. Edit `values.yaml`:
|
||||
```yaml
|
||||
preloadJob:
|
||||
hotModels:
|
||||
- deepseek-r1:32b # or any available model
|
||||
```
|
||||
|
||||
2. Redeploy:
|
||||
```bash
|
||||
kubectl -n llm delete job bootstrap-models --ignore-not-found
|
||||
vsource .env && helmfile -f helmfile.yaml.gotmpl -l name=ollama apply
|
||||
```
|
||||
|
||||
3. Monitor:
|
||||
```bash
|
||||
kubectl -n llm logs -f job/bootstrap-models -c model-download
|
||||
```
|
||||
|
||||
### Available models
|
||||
Ollama registry: https://ollama.com/library
|
||||
|
||||
Examples:
|
||||
- `deepseek-r1:70b` (reasoning, 42GB)
|
||||
- `deepseek-r1:32b` (faster, 20GB)
|
||||
- `llama3.1:70b` (general, 41GB)
|
||||
- `mistral:large` (26GB)
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Pod stuck in `ContainerCreating`
|
||||
```bash
|
||||
kubectl -n llm describe pod -l app.kubernetes.io/name=ollama
|
||||
# Check Events section for PVC/image pull issues
|
||||
```
|
||||
|
||||
### Bootstrap job failing
|
||||
```bash
|
||||
kubectl -n llm logs job/bootstrap-models -c model-download --tail=50
|
||||
# Common: model not found in registry, disk full, network timeout
|
||||
```
|
||||
|
||||
### Model pull timeout
|
||||
```bash
|
||||
# Increase pod timeout (edit deployment directly)
|
||||
kubectl -n llm edit deployment ollama
|
||||
# Change readinessProbe.initialDelaySeconds, livenessProbe.periodSeconds
|
||||
```
|
||||
|
||||
### Out of memory
|
||||
Model size exceeds limit. Reduce `memory.limits` or choose smaller model.
|
||||
|
||||
```bash
|
||||
kubectl top pod -n llm # check actual usage
|
||||
```
|
||||
|
||||
### Cannot connect from other pods
|
||||
Verify NetworkPolicy:
|
||||
```bash
|
||||
kubectl -n llm get networkpolicy
|
||||
kubectl -n llm describe networkpolicy ollama
|
||||
# Add pod label: app.kubernetes.io/name: llm-worker or app.kubernetes.io/role: llm-debug
|
||||
```
|
||||
|
||||
## Secrets
|
||||
|
||||
Ollama pod receives MinIO credentials via Secret `ollama-minio` (created by helmfile presync):
|
||||
|
||||
```bash
|
||||
kubectl -n llm get secret ollama-minio -o jsonpath='{.data}' | jq
|
||||
```
|
||||
|
||||
Keys: `endpoint`, `bucket`, `access_key`, `secret_key`
|
||||
|
||||
Used by bootstrap job to upload model blobs to MinIO (future: auto-backup).
|
||||
|
||||
## Metrics & Observability
|
||||
|
||||
### Prometheus scrape (if enabled)
|
||||
ServiceMonitor: Not yet configured (see `k8s/monitoring/dashboards/services/`)
|
||||
|
||||
Metrics to add:
|
||||
- `ollama_requests_total` (counter)
|
||||
- `ollama_request_duration_seconds` (histogram)
|
||||
- `ollama_loaded_models` (gauge)
|
||||
|
||||
### Logs
|
||||
Pod logs via kubectl. No log aggregation to Loki yet.
|
||||
|
||||
```bash
|
||||
kubectl -n llm logs deployment/ollama -f --timestamps
|
||||
```
|
||||
|
||||
## Cleanup
|
||||
|
||||
### Delete Ollama completely
|
||||
```bash
|
||||
vsource .env && helmfile -f helmfile.yaml.gotmpl -l name=ollama destroy
|
||||
# Keeps PVC (data safety). To delete: kubectl -n llm delete pvc ollama-models-cache
|
||||
```
|
||||
|
||||
### Delete just the model cache (keep deployment)
|
||||
```bash
|
||||
kubectl -n llm delete pvc ollama-models-cache
|
||||
# Recreate: kubectl -n llm patch deployment ollama -p '{"spec":{"template":{"metadata":{"annotations":{"restart":"now"}}}}}'
|
||||
```
|
||||
|
||||
## See Also
|
||||
|
||||
- Helmfile: `helmfile.yaml.gotmpl` (llm release block)
|
||||
- Chart: `k8s/llm/charts/ollama/`
|
||||
- Namespace: `llm`
|
||||
- Bootstrap: `k8s/llm/bootstrap-models-job.yaml` (manual preload fallback)
|
||||
@@ -0,0 +1,6 @@
|
||||
apiVersion: v2
|
||||
name: ollama
|
||||
description: CPU-only Ollama LLM server with MinIO model registry
|
||||
type: application
|
||||
version: 0.1.0
|
||||
appVersion: "latest"
|
||||
@@ -0,0 +1,126 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: ollama
|
||||
namespace: llm
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama
|
||||
app.kubernetes.io/part-of: llm
|
||||
spec:
|
||||
replicas: {{ .Values.replicaCount }}
|
||||
strategy:
|
||||
type: Recreate
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: ollama
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama
|
||||
app.kubernetes.io/part-of: llm
|
||||
spec:
|
||||
affinity:
|
||||
nodeAffinity:
|
||||
requiredDuringSchedulingIgnoredDuringExecution:
|
||||
nodeSelectorTerms:
|
||||
- matchExpressions:
|
||||
- key: topology.kubernetes.io/zone
|
||||
operator: In
|
||||
values:
|
||||
- {{ .Values.nodeAffinity.zone }}
|
||||
tolerations:
|
||||
- key: node-role.kubernetes.io/control-plane
|
||||
operator: Equal
|
||||
value: ""
|
||||
effect: NoSchedule
|
||||
|
||||
initContainers:
|
||||
- name: preload-model
|
||||
image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
|
||||
imagePullPolicy: {{ .Values.image.pullPolicy }}
|
||||
command:
|
||||
- sh
|
||||
- -c
|
||||
- |
|
||||
set -e
|
||||
echo "Starting Ollama server for model preload..."
|
||||
ollama serve &
|
||||
OLLAMA_PID=$!
|
||||
sleep 10
|
||||
{{- range .Values.preloadJob.hotModels }}
|
||||
echo "Preloading {{ . }}..."
|
||||
if ollama ls | grep -q "{{ . }}"; then
|
||||
echo "✓ {{ . }} already cached"
|
||||
else
|
||||
ollama pull {{ . }}
|
||||
fi
|
||||
{{- end }}
|
||||
echo "Model preload complete"
|
||||
kill $OLLAMA_PID || true
|
||||
wait $OLLAMA_PID 2>/dev/null || true
|
||||
volumeMounts:
|
||||
- name: models-cache
|
||||
mountPath: /root/.ollama/models
|
||||
env:
|
||||
- name: OLLAMA_HOST
|
||||
value: "127.0.0.1:11434"
|
||||
|
||||
containers:
|
||||
- name: ollama
|
||||
image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
|
||||
imagePullPolicy: {{ .Values.image.pullPolicy }}
|
||||
ports:
|
||||
- containerPort: 11434
|
||||
name: http
|
||||
env:
|
||||
{{- range $key, $value := .Values.env }}
|
||||
- name: {{ $key }}
|
||||
value: "{{ $value }}"
|
||||
{{- end }}
|
||||
- name: OLLAMA_MODELS_MINIO_ENDPOINT
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: ollama-minio
|
||||
key: endpoint
|
||||
- name: OLLAMA_MODELS_MINIO_BUCKET
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: ollama-minio
|
||||
key: bucket
|
||||
- name: OLLAMA_MODELS_MINIO_ACCESS_KEY
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: ollama-minio
|
||||
key: access_key
|
||||
- name: OLLAMA_MODELS_MINIO_SECRET_KEY
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: ollama-minio
|
||||
key: secret_key
|
||||
resources:
|
||||
requests:
|
||||
cpu: {{ .Values.resources.requests.cpu }}
|
||||
memory: {{ .Values.resources.requests.memory }}
|
||||
limits:
|
||||
cpu: {{ .Values.resources.limits.cpu }}
|
||||
memory: {{ .Values.resources.limits.memory }}
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /
|
||||
port: 11434
|
||||
initialDelaySeconds: 30
|
||||
periodSeconds: 10
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /
|
||||
port: 11434
|
||||
initialDelaySeconds: 10
|
||||
periodSeconds: 5
|
||||
volumeMounts:
|
||||
- name: models-cache
|
||||
mountPath: /root/.ollama/models
|
||||
|
||||
volumes:
|
||||
- name: models-cache
|
||||
persistentVolumeClaim:
|
||||
claimName: ollama-models-cache
|
||||
@@ -0,0 +1,28 @@
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: ollama-access
|
||||
namespace: llm
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: ollama
|
||||
policyTypes:
|
||||
- Ingress
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: llm-worker
|
||||
ports:
|
||||
- protocol: TCP
|
||||
port: 11434
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/role: llm-debug
|
||||
ports:
|
||||
- protocol: TCP
|
||||
port: 11434
|
||||
@@ -0,0 +1,92 @@
|
||||
{{- if .Values.preloadJob.enabled }}
|
||||
apiVersion: batch/v1
|
||||
kind: Job
|
||||
metadata:
|
||||
name: ollama-preload
|
||||
namespace: llm
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama-preload
|
||||
spec:
|
||||
backoffLimit: 3
|
||||
template:
|
||||
spec:
|
||||
serviceAccountName: default
|
||||
restartPolicy: Never
|
||||
affinity:
|
||||
nodeAffinity:
|
||||
requiredDuringSchedulingIgnoredDuringExecution:
|
||||
nodeSelectorTerms:
|
||||
- matchExpressions:
|
||||
- key: topology.kubernetes.io/zone
|
||||
operator: In
|
||||
values:
|
||||
- az-a
|
||||
tolerations:
|
||||
- key: node-role.kubernetes.io/control-plane
|
||||
operator: Equal
|
||||
effect: NoSchedule
|
||||
initContainers:
|
||||
- name: model-cache-init
|
||||
image: ollama/ollama:latest
|
||||
imagePullPolicy: IfNotPresent
|
||||
command:
|
||||
- sh
|
||||
- -c
|
||||
- |
|
||||
set -e
|
||||
echo "Starting Ollama server to cache models..."
|
||||
ollama serve &
|
||||
OLLAMA_PID=$!
|
||||
sleep 10
|
||||
echo "Caching hot-tier models..."
|
||||
{{- range .Values.preloadJob.hotModels }}
|
||||
echo "Checking if {{ . }} is cached..."
|
||||
if ollama ls | grep -q "{{ . }}"; then
|
||||
echo "✓ {{ . }} already cached, skipping"
|
||||
else
|
||||
echo "Pulling {{ . }}..."
|
||||
ollama pull {{ . }}
|
||||
fi
|
||||
{{- end }}
|
||||
echo "Model cache initialization complete"
|
||||
kill $OLLAMA_PID || true
|
||||
wait $OLLAMA_PID 2>/dev/null || true
|
||||
volumeMounts:
|
||||
- name: models
|
||||
mountPath: /root/.ollama
|
||||
env:
|
||||
- name: OLLAMA_HOST
|
||||
value: "127.0.0.1:11434"
|
||||
|
||||
containers:
|
||||
- name: cache-populate
|
||||
image: curlimages/curl:latest
|
||||
imagePullPolicy: IfNotPresent
|
||||
command:
|
||||
- sh
|
||||
- -c
|
||||
- |
|
||||
set -e
|
||||
echo "Waiting for Ollama pod to be ready..."
|
||||
until curl -f http://ollama.llm.svc.cluster.local:11434/api/tags 2>/dev/null; do
|
||||
echo "Ollama not ready, waiting..."
|
||||
sleep 5
|
||||
done
|
||||
echo "Ollama is ready, populating local cache..."
|
||||
{{- range .Values.preloadJob.hotModels }}
|
||||
echo "Checking if {{ . }} is already cached..."
|
||||
if curl -s http://ollama.llm.svc.cluster.local:11434/api/tags | grep -q "{{ . }}"; then
|
||||
echo "✓ {{ . }} already cached, skipping"
|
||||
else
|
||||
echo "Caching {{ . }} locally..."
|
||||
curl -X POST http://ollama.llm.svc.cluster.local:11434/api/pull \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"name":"{{ . }}","stream":false}'
|
||||
fi
|
||||
{{- end }}
|
||||
echo "Local cache population complete"
|
||||
|
||||
volumes:
|
||||
- name: models
|
||||
emptyDir: {}
|
||||
{{- end }}
|
||||
@@ -0,0 +1,14 @@
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
metadata:
|
||||
name: ollama-models-cache
|
||||
namespace: llm
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama
|
||||
spec:
|
||||
accessModes:
|
||||
- ReadWriteOnce
|
||||
storageClassName: {{ .Values.pvc.storageClassName }}
|
||||
resources:
|
||||
requests:
|
||||
storage: {{ .Values.pvc.size }}
|
||||
@@ -0,0 +1,16 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: ollama
|
||||
namespace: llm
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama
|
||||
spec:
|
||||
type: {{ .Values.service.type }}
|
||||
ports:
|
||||
- port: {{ .Values.service.port }}
|
||||
targetPort: http
|
||||
protocol: TCP
|
||||
name: http
|
||||
selector:
|
||||
app.kubernetes.io/name: ollama
|
||||
@@ -0,0 +1,12 @@
|
||||
apiVersion: storage.k8s.io/v1
|
||||
kind: StorageClass
|
||||
metadata:
|
||||
name: longhorn-llm
|
||||
labels:
|
||||
app.kubernetes.io/name: ollama
|
||||
provisioner: driver.longhorn.io
|
||||
parameters:
|
||||
numberOfReplicas: "1"
|
||||
staleReplicaTimeout: "2880"
|
||||
reclaimPolicy: Retain
|
||||
allowVolumeExpansion: true
|
||||
@@ -0,0 +1,40 @@
|
||||
replicaCount: 1
|
||||
|
||||
image:
|
||||
repository: ollama/ollama
|
||||
pullPolicy: IfNotPresent
|
||||
tag: "latest"
|
||||
|
||||
service:
|
||||
type: ClusterIP
|
||||
port: 11434
|
||||
|
||||
resources:
|
||||
requests:
|
||||
cpu: 8
|
||||
memory: 60Gi
|
||||
limits:
|
||||
cpu: 16
|
||||
memory: 100Gi
|
||||
|
||||
pvc:
|
||||
enabled: true
|
||||
size: 115Gi
|
||||
storageClassName: longhorn-llm
|
||||
|
||||
nodeAffinity:
|
||||
zone: az-a
|
||||
|
||||
env:
|
||||
OLLAMA_MODELS: /root/.ollama/models
|
||||
OLLAMA_MAX_LOADED_MODELS: "2"
|
||||
OLLAMA_NUM_PARALLEL: "2"
|
||||
OLLAMA_MAX_QUEUE: "64"
|
||||
OLLAMA_KEEP_ALIVE: "-1"
|
||||
OLLAMA_HOST: "0.0.0.0:11434"
|
||||
|
||||
preloadJob:
|
||||
enabled: false
|
||||
hotModels:
|
||||
- ornith:35b
|
||||
- deepseek-r1:70b
|
||||
@@ -0,0 +1,6 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: llm
|
||||
resources:
|
||||
- scripts/
|
||||
# Helm charts deployed via ArgoCD Helm source
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
|
||||
resources: []
|
||||
# Shell scripts, not K8s manifests
|
||||
@@ -0,0 +1,71 @@
|
||||
#!/bin/bash
|
||||
|
||||
# setup-minio-bucket.sh
|
||||
# Creates MinIO bucket and Kubernetes secrets for Ollama LLM server
|
||||
# Runs as helmfile presync hook; all commands are idempotent
|
||||
# Dependencies: kubectl, access to minio-az-a pod in storage namespace
|
||||
# Environment: MINIO_ROOT_USER, MINIO_ROOT_PASSWORD (from Vault), AUTHENTIK_OLLAMA_CLIENT_ID, AUTHENTIK_OLLAMA_CLIENT_SECRET
|
||||
|
||||
set -e
|
||||
|
||||
echo "=== Step 1: Create and label llm namespace ==="
|
||||
kubectl create namespace llm --dry-run=client -o yaml | kubectl apply -f -
|
||||
kubectl label namespace llm \
|
||||
pod-security.kubernetes.io/enforce=baseline \
|
||||
pod-security.kubernetes.io/enforce-version=latest \
|
||||
--overwrite
|
||||
|
||||
echo "✓ llm namespace created/labeled"
|
||||
|
||||
echo ""
|
||||
echo "=== Step 2: Create MinIO bucket riotpiao-models ==="
|
||||
|
||||
# Configure mc host inside MinIO pod
|
||||
kubectl -n storage exec deployment/minio-az-a -- \
|
||||
mc config host add local http://localhost:9000 \
|
||||
"${MINIO_ROOT_USER}" "${MINIO_ROOT_PASSWORD}"
|
||||
|
||||
echo "✓ mc host configured"
|
||||
|
||||
# Create bucket (idempotent)
|
||||
kubectl -n storage exec deployment/minio-az-a -- \
|
||||
mc mb --ignore-existing local/riotpiao-models
|
||||
|
||||
echo "✓ MinIO bucket riotpiao-models created (or already exists)"
|
||||
|
||||
# Enable versioning for model rollback safety
|
||||
kubectl -n storage exec deployment/minio-az-a -- \
|
||||
mc version enable local/riotpiao-models
|
||||
|
||||
echo "✓ Versioning enabled on riotpiao-models bucket"
|
||||
|
||||
echo ""
|
||||
echo "=== Step 3: Create ollama-minio Secret (MinIO credentials) ==="
|
||||
|
||||
kubectl create secret generic ollama-minio -n llm \
|
||||
--from-literal=endpoint="http://minio-az-a.storage:9000" \
|
||||
--from-literal=bucket="riotpiao-models" \
|
||||
--from-literal=access_key="${MINIO_ROOT_USER}" \
|
||||
--from-literal=secret_key="${MINIO_ROOT_PASSWORD}" \
|
||||
--dry-run=client -o yaml | kubectl apply -f -
|
||||
|
||||
echo "✓ Secret ollama-minio created/updated"
|
||||
|
||||
echo ""
|
||||
echo "=== Step 4: Create ollama-oidc Secret (Authentik credentials) ==="
|
||||
|
||||
kubectl create secret generic ollama-oidc -n llm \
|
||||
--from-literal=client_id="${AUTHENTIK_OLLAMA_CLIENT_ID}" \
|
||||
--from-literal=client_secret="${AUTHENTIK_OLLAMA_CLIENT_SECRET}" \
|
||||
--dry-run=client -o yaml | kubectl apply -f -
|
||||
|
||||
echo "✓ Secret ollama-oidc created/updated"
|
||||
|
||||
echo ""
|
||||
echo "=== Verification ==="
|
||||
echo ""
|
||||
echo "Run these commands to verify:"
|
||||
echo " kubectl -n llm get secret ollama-minio ollama-oidc"
|
||||
echo " kubectl -n storage exec deployment/minio-az-a -- mc ls local/riotpiao-models"
|
||||
echo ""
|
||||
echo "Setup complete!"
|
||||
Executable
+54
@@ -0,0 +1,54 @@
|
||||
#!/usr/bin/env bash
|
||||
# portainer/bootstrap.sh
|
||||
# Deploys Portainer CE into the dashboard namespace.
|
||||
# No credentials needed — Portainer prompts you to create an admin account
|
||||
# on first browser visit.
|
||||
#
|
||||
# Prerequisites:
|
||||
# - kubectl configured (KUBECONFIG pointing to cluster-config/kubeconfig)
|
||||
# - helm >= 3.x
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
REPO_ROOT="$(cd "${SCRIPT_DIR}/../.." && pwd)"
|
||||
KUBECONFIG="${KUBECONFIG:-${REPO_ROOT}/cluster-config/kubeconfig}"
|
||||
export KUBECONFIG
|
||||
|
||||
# ── Namespace ─────────────────────────────────────────────────────────────────
|
||||
echo "==> Creating dashboard namespace..."
|
||||
kubectl create namespace dashboard --dry-run=client -o yaml | kubectl apply -f -
|
||||
kubectl label namespace dashboard \
|
||||
pod-security.kubernetes.io/enforce=privileged \
|
||||
pod-security.kubernetes.io/enforce-version=latest \
|
||||
--overwrite
|
||||
|
||||
# ── Helm repo ─────────────────────────────────────────────────────────────────
|
||||
echo "==> Adding Portainer Helm repo..."
|
||||
helm repo add portainer https://portainer.github.io/k8s/
|
||||
helm repo update portainer
|
||||
|
||||
# ── Portainer ─────────────────────────────────────────────────────────────────
|
||||
echo "==> Installing Portainer..."
|
||||
helm upgrade --install portainer portainer/portainer \
|
||||
--namespace dashboard \
|
||||
--values "${SCRIPT_DIR}/portainer-values.yaml" \
|
||||
--wait \
|
||||
--timeout 5m
|
||||
|
||||
echo "==> Waiting for Portainer Deployment to be ready..."
|
||||
kubectl rollout status deployment/portainer -n dashboard --timeout=120s
|
||||
|
||||
# ── Done ──────────────────────────────────────────────────────────────────────
|
||||
echo ""
|
||||
echo "==> Portainer is up."
|
||||
echo ""
|
||||
echo "Access Portainer UI:"
|
||||
echo " make pf-portainer"
|
||||
echo " http://localhost:9000"
|
||||
echo ""
|
||||
echo "First-time setup: Portainer will prompt you to create an admin account."
|
||||
echo "Choose 'Manage the local Kubernetes environment' when asked."
|
||||
echo ""
|
||||
echo "Node failure resilience tip:"
|
||||
echo " For faster PVC failover on hard node failure, enable in Longhorn UI → Settings:"
|
||||
echo " nodeDownPodDeletionPolicy = delete-deployment-pod"
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: portainer
|
||||
resources: []
|
||||
# Portainer deployed via Helm chart or existing manifests
|
||||
@@ -0,0 +1,53 @@
|
||||
# k8s/portainer/portainer-values.yaml
|
||||
# Portainer — web UI for browsing cluster workloads, exec-ing into pods,
|
||||
# and viewing logs without kubectl. Operator-only access (ClusterIP + port-forward).
|
||||
#
|
||||
# Node failure behaviour:
|
||||
# Portainer is a Deployment (not StatefulSet), so K8s auto-evicts and
|
||||
# reschedules it ~5 min after a node becomes unreachable. Longhorn
|
||||
# reattaches the PVC on the new node in ~1-2 min. Worst case: ~7-10 min.
|
||||
#
|
||||
# To cut that down: in Longhorn UI → Settings set
|
||||
# nodeDownPodDeletionPolicy = delete-deployment-pod
|
||||
# Longhorn will force-delete the stuck pod immediately when the node is
|
||||
# fenced rather than waiting for Kubernetes' eviction timeout.
|
||||
|
||||
# ── Service ───────────────────────────────────────────────────────────────────
|
||||
# ClusterIP — no external exposure. Access via:
|
||||
# kubectl -n dashboard port-forward svc/portainer 9000:9000
|
||||
# Portainer holds cluster-admin credentials; never expose as LoadBalancer.
|
||||
service:
|
||||
type: ClusterIP
|
||||
|
||||
# ── TLS ───────────────────────────────────────────────────────────────────────
|
||||
# Portainer by default redirects HTTP → HTTPS using a self-signed cert.
|
||||
# force: false disables the redirect so plain HTTP over port-forward works
|
||||
# without browser cert warnings. TLS is terminated at the ingress layer
|
||||
# if/when an ingress rule is added.
|
||||
tls:
|
||||
force: false
|
||||
|
||||
# ── Persistence ───────────────────────────────────────────────────────────────
|
||||
# Stores Portainer's own config: environment registrations, user accounts,
|
||||
# stack definitions, and access control settings. Longhorn provides the
|
||||
# RWO block volume. 10Gi is generous for config data but cheap on Longhorn.
|
||||
persistence:
|
||||
enabled: true
|
||||
storageClass: "longhorn"
|
||||
size: 10Gi
|
||||
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 128Mi
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 512Mi
|
||||
|
||||
# ── Scheduling ────────────────────────────────────────────────────────────────
|
||||
# Allow scheduling on talos-cp-1 (carries NoSchedule taint) so Portainer
|
||||
# keeps running even when the worker node is down.
|
||||
tolerations:
|
||||
- key: node-role.kubernetes.io/control-plane
|
||||
operator: Exists
|
||||
effect: NoSchedule
|
||||
@@ -0,0 +1,4 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: shadowsocks
|
||||
resources: []
|
||||
@@ -0,0 +1,159 @@
|
||||
# k8s/shadowsocks/shadowsocks.yaml
|
||||
# Personal Shadowsocks proxy (for Shadowrocket/other SS clients) — an
|
||||
# alternative tunnel to the WireGuard setup in cluster-config/, useful when
|
||||
# a network blocks/throttles WireGuard but not generic TLS-looking traffic.
|
||||
#
|
||||
# Everything that varies between deployments (port, password, method) lives
|
||||
# in the shadowsocks-config Secret below — the Deployment/Service never
|
||||
# hardcode a value, so re-pointing this at a new port or rotating the
|
||||
# password is a Secret edit + rollout restart, no YAML edit.
|
||||
#
|
||||
# Prerequisites:
|
||||
# talos put cluster/SHADOWSOCKS_PASSWORD SHADOWSOCKS_PASSWORD="$(openssl rand -base64 24)"
|
||||
# talos put cluster/SHADOWSOCKS_PORT SHADOWSOCKS_PORT="8388"
|
||||
#
|
||||
# Apply:
|
||||
# kubectl create namespace vpn --dry-run=client -o yaml | kubectl apply -f -
|
||||
# kubectl -n vpn create secret generic shadowsocks-config \
|
||||
# --from-literal=SERVER_PORT="$(talos get cluster/SHADOWSOCKS_PORT --key SHADOWSOCKS_PORT)" \
|
||||
# --from-literal=PASSWORD="$(talos get cluster/SHADOWSOCKS_PASSWORD --key SHADOWSOCKS_PASSWORD)" \
|
||||
# --from-literal=METHOD="aes-256-gcm" \
|
||||
# --from-literal=TIMEOUT="300"
|
||||
# kubectl apply -f k8s/shadowsocks/shadowsocks.yaml
|
||||
#
|
||||
# Rotate password (or change port) later:
|
||||
# kubectl -n vpn delete secret shadowsocks-config && <recreate with new values>
|
||||
# kubectl -n vpn rollout restart deploy/shadowsocks
|
||||
#
|
||||
# Client config: SERVER_PORT/METHOD/PASSWORD above feed directly into the
|
||||
# Shadowrocket/SS client's server, method, and password fields. SERVER_ADDR
|
||||
# for the client is the LB IP below (192.168.1.166), or your router's WAN
|
||||
# address/DDNS hostname (riotpiao.duckdns.org) with port-forwarding to it —
|
||||
# same pattern as the wg1 WireGuard peer in cluster-config/phone_config.conf.
|
||||
apiVersion: v1
|
||||
kind: Namespace
|
||||
metadata:
|
||||
name: vpn
|
||||
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: shadowsocks
|
||||
namespace: vpn
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app: shadowsocks
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: shadowsocks
|
||||
spec:
|
||||
containers:
|
||||
- name: shadowsocks
|
||||
image: shadowsocks/shadowsocks-libev:latest
|
||||
env:
|
||||
- name: SERVER_ADDR
|
||||
value: "0.0.0.0"
|
||||
- name: SERVER_PORT
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: shadowsocks-config
|
||||
key: SERVER_PORT
|
||||
- name: PASSWORD
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: shadowsocks-config
|
||||
key: PASSWORD
|
||||
- name: METHOD
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: shadowsocks-config
|
||||
key: METHOD
|
||||
- name: TIMEOUT
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: shadowsocks-config
|
||||
key: TIMEOUT
|
||||
# containerPort is informational only (no portRange support for
|
||||
# env-driven SERVER_PORT) — the Service below is what actually
|
||||
# routes traffic, matched on the same Secret key via downward API
|
||||
# isn't available for Service ports, so targetPort uses the literal
|
||||
# port name instead; see Service ports comment.
|
||||
ports:
|
||||
- containerPort: 8388
|
||||
protocol: TCP
|
||||
- containerPort: 8388
|
||||
protocol: UDP
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 32Mi
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 128Mi
|
||||
|
||||
---
|
||||
# LoadBalancer via Cilium LB-IPAM (see k8s/cilium/lb-ipam-pool.yaml) — pinned
|
||||
# to .166 so router port-forwarding and the DDNS hostname stay stable across
|
||||
# pod/service recreates, same pattern forgejo uses at .165.
|
||||
#
|
||||
# NOTE: SERVER_PORT in the Secret must match port/targetPort/nodePort here.
|
||||
# If you change the port, update both the Secret and this Service together.
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: shadowsocks
|
||||
namespace: vpn
|
||||
annotations:
|
||||
io.cilium/lb-ipam-ips: "192.168.1.166"
|
||||
spec:
|
||||
type: LoadBalancer
|
||||
selector:
|
||||
app: shadowsocks
|
||||
ports:
|
||||
- name: tcp
|
||||
protocol: TCP
|
||||
port: 8388
|
||||
targetPort: 8388
|
||||
- name: udp
|
||||
protocol: UDP
|
||||
port: 8388
|
||||
targetPort: 8388
|
||||
|
||||
---
|
||||
# Restrict egress like the forgejo-runner pattern (k8s/forge/runner.yaml) —
|
||||
# a proxy server is, by design, an open relay to the internet for whoever
|
||||
# holds the password; LAN/pod-network egress is blocked so a compromised
|
||||
# password can't be used to pivot into the cluster or LAN. CoreDNS is
|
||||
# explicitly allowed — shadowsocks-libev resolves client-requested hostnames
|
||||
# itself, so blanket-blocking the service subnet would break that.
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
name: shadowsocks-egress
|
||||
namespace: vpn
|
||||
spec:
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app: shadowsocks
|
||||
policyTypes: [Egress]
|
||||
egress:
|
||||
- to:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
kubernetes.io/metadata.name: kube-system
|
||||
ports:
|
||||
- protocol: UDP
|
||||
port: 53
|
||||
- protocol: TCP
|
||||
port: 53
|
||||
- to:
|
||||
- ipBlock:
|
||||
cidr: 0.0.0.0/0
|
||||
except:
|
||||
- 192.168.1.0/24
|
||||
- 10.244.0.0/16
|
||||
- 10.96.0.0/12
|
||||
@@ -0,0 +1,25 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: strimzi-operator
|
||||
namespace: cicd
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: "0"
|
||||
spec:
|
||||
project: kmsvc
|
||||
source:
|
||||
repoURL: https://strimzi.io/charts/
|
||||
chart: strimzi-kafka-operator
|
||||
targetRevision: 0.46.0
|
||||
helm:
|
||||
values: |
|
||||
watchNamespaces: ["sqs"]
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: sqs
|
||||
syncPolicy:
|
||||
automated:
|
||||
prune: true
|
||||
selfHeal: true
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
@@ -0,0 +1,31 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: kafka-cluster
|
||||
namespace: cicd
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: "1"
|
||||
spec:
|
||||
project: kmsvc
|
||||
source:
|
||||
repoURL: https://forgejo.riotpiao.homelab.com/rock/kafaka-management-service.git
|
||||
targetRevision: main
|
||||
path: k8s/charts/kafka-cluster
|
||||
helm:
|
||||
values: |
|
||||
namespace: sqs
|
||||
nodePool:
|
||||
replicas: 3
|
||||
storage:
|
||||
class: longhorn
|
||||
sizeGi: 50
|
||||
resources:
|
||||
memory: 5Gi
|
||||
cpu: "2"
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: sqs
|
||||
syncPolicy:
|
||||
automated:
|
||||
prune: true
|
||||
selfHeal: true
|
||||
@@ -0,0 +1,43 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: kmsvc-redis
|
||||
namespace: cicd
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: "1"
|
||||
spec:
|
||||
project: kmsvc
|
||||
source:
|
||||
repoURL: https://charts.bitnami.com/bitnami
|
||||
chart: redis
|
||||
targetRevision: 20.6.0
|
||||
helm:
|
||||
values: |
|
||||
architecture: standalone
|
||||
# docker.io/bitnami stopped publishing version-pinned tags; bitnamilegacy
|
||||
# mirrors them for free. allowInsecureImages silences the chart's
|
||||
# container-image allowlist check, which doesn't know about that mirror.
|
||||
global:
|
||||
security:
|
||||
allowInsecureImages: true
|
||||
image:
|
||||
repository: bitnamilegacy/redis
|
||||
auth:
|
||||
enabled: false
|
||||
master:
|
||||
persistence:
|
||||
enabled: true
|
||||
storageClass: longhorn
|
||||
size: 2Gi
|
||||
resources:
|
||||
limits:
|
||||
memory: 1Gi
|
||||
requests:
|
||||
memory: 1Gi
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: sqs
|
||||
syncPolicy:
|
||||
automated:
|
||||
prune: true
|
||||
selfHeal: true
|
||||
@@ -0,0 +1,30 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: queue-crd
|
||||
namespace: cicd
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: "2"
|
||||
spec:
|
||||
project: kmsvc
|
||||
source:
|
||||
repoURL: https://forgejo.riotpiao.homelab.com/rock/kafaka-management-service.git
|
||||
targetRevision: main
|
||||
path: k8s/charts/queue-crd
|
||||
helm:
|
||||
values: |
|
||||
namespace: sqs
|
||||
kafkaBrokers: "kmsvc-kafka-bootstrap.sqs.svc.cluster.local:9092"
|
||||
redisAddr: "kmsvc-redis-master.sqs.svc.cluster.local:6379"
|
||||
image:
|
||||
repository: forgejo.riotpiao.homelab.com/rock/kafka-management-service-queue-operator
|
||||
# CI (.forgejo/workflows/release.yaml) writes the released git tag
|
||||
# here and pushes the commit -- ArgoCD picks it up on its next sync.
|
||||
tag: latest
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: sqs
|
||||
syncPolicy:
|
||||
automated:
|
||||
prune: true
|
||||
selfHeal: true
|
||||
@@ -0,0 +1,37 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: management-service
|
||||
namespace: cicd
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: "2"
|
||||
spec:
|
||||
project: kmsvc
|
||||
source:
|
||||
repoURL: https://forgejo.riotpiao.homelab.com/rock/kafaka-management-service.git
|
||||
targetRevision: main
|
||||
path: k8s/charts/management-service
|
||||
helm:
|
||||
values: |
|
||||
namespace: sqs
|
||||
image:
|
||||
repository: forgejo.riotpiao.homelab.com/rock/kafka-management-service
|
||||
# CI (.forgejo/workflows/release.yaml) writes the released git tag
|
||||
# here and pushes the commit -- ArgoCD picks it up on its next sync.
|
||||
tag: latest
|
||||
env:
|
||||
kafkaBrokers: "kmsvc-kafka-bootstrap.sqs.svc.cluster.local:9092"
|
||||
redisAddr: "kmsvc-redis-master.sqs.svc.cluster.local:6379"
|
||||
authentikIssuerURL: "https://authentik.riotpiao.homelab.com/application/o/kafaka/"
|
||||
authentikAudience: "QI0gPtR99ar8VvhK8Tqox4SDkTKzbNU7lbgwBNSc"
|
||||
ingress:
|
||||
enabled: true
|
||||
host: kmsvc.riotpiao.homelab.com
|
||||
clusterIssuer: homelab-ca
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: sqs
|
||||
syncPolicy:
|
||||
automated:
|
||||
prune: true
|
||||
selfHeal: true
|
||||
@@ -0,0 +1,7 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: sqs
|
||||
resources:
|
||||
- 02-redis.yaml
|
||||
- 03-queue-crd.yaml
|
||||
- 04-management-service.yaml
|
||||
@@ -0,0 +1,7 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: sqs
|
||||
resources:
|
||||
- project.yaml
|
||||
- root.yaml
|
||||
- apps/
|
||||
@@ -0,0 +1,23 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: AppProject
|
||||
metadata:
|
||||
name: kmsvc
|
||||
namespace: cicd
|
||||
spec:
|
||||
description: Kafka Management Service (design.md) -- Strimzi/Kafka, Redis, queue-operator, message-plane server
|
||||
sourceRepos:
|
||||
- https://forgejo.riotpiao.homelab.com/rock/kafaka-management-service.git
|
||||
- https://strimzi.io/charts/
|
||||
- https://charts.bitnami.com/bitnami
|
||||
destinations:
|
||||
- namespace: sqs
|
||||
server: https://kubernetes.default.svc
|
||||
- namespace: cicd
|
||||
server: https://kubernetes.default.svc
|
||||
clusterResourceWhitelist:
|
||||
- group: "apiextensions.k8s.io"
|
||||
kind: CustomResourceDefinition
|
||||
- group: "rbac.authorization.k8s.io"
|
||||
kind: ClusterRole
|
||||
- group: "rbac.authorization.k8s.io"
|
||||
kind: ClusterRoleBinding
|
||||
@@ -0,0 +1,22 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: kmsvc-root
|
||||
namespace: cicd
|
||||
spec:
|
||||
project: kmsvc
|
||||
source:
|
||||
repoURL: https://forgejo.riotpiao.homelab.com/rock/kafaka-management-service.git
|
||||
targetRevision: main
|
||||
path: k8s/argocd/apps
|
||||
directory:
|
||||
recurse: false
|
||||
destination:
|
||||
server: https://kubernetes.default.svc
|
||||
namespace: cicd
|
||||
syncPolicy:
|
||||
automated:
|
||||
prune: true
|
||||
selfHeal: true
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: v2
|
||||
name: kafka-cluster
|
||||
description: Strimzi Kafka/KafkaNodePool CRs for the kmsvc Kafka cluster (design.md §7)
|
||||
type: application
|
||||
version: 0.1.0
|
||||
@@ -0,0 +1,30 @@
|
||||
apiVersion: kafka.strimzi.io/v1beta2
|
||||
kind: Kafka
|
||||
metadata:
|
||||
name: {{ .Values.clusterName }}
|
||||
namespace: {{ .Values.namespace }}
|
||||
annotations:
|
||||
strimzi.io/node-pools: enabled
|
||||
strimzi.io/kraft: enabled
|
||||
spec:
|
||||
kafka:
|
||||
version: 4.0.0
|
||||
metadataVersion: 4.0-IV3
|
||||
listeners:
|
||||
- name: plain
|
||||
port: 9092
|
||||
type: internal
|
||||
tls: false
|
||||
- name: tls
|
||||
port: 9093
|
||||
type: internal
|
||||
tls: true
|
||||
config:
|
||||
default.replication.factor: {{ .Values.kafka.replicationFactor }}
|
||||
min.insync.replicas: {{ .Values.kafka.minInsyncReplicas }}
|
||||
offsets.topic.replication.factor: {{ .Values.kafka.replicationFactor }}
|
||||
transaction.state.log.replication.factor: {{ .Values.kafka.replicationFactor }}
|
||||
transaction.state.log.min.isr: {{ .Values.kafka.minInsyncReplicas }}
|
||||
entityOperator:
|
||||
topicOperator: {}
|
||||
userOperator: {}
|
||||
@@ -0,0 +1,39 @@
|
||||
apiVersion: kafka.strimzi.io/v1beta2
|
||||
kind: KafkaNodePool
|
||||
metadata:
|
||||
name: {{ .Values.clusterName }}-pool
|
||||
namespace: {{ .Values.namespace }}
|
||||
labels:
|
||||
strimzi.io/cluster: {{ .Values.clusterName }}
|
||||
spec:
|
||||
replicas: {{ .Values.nodePool.replicas }}
|
||||
roles:
|
||||
- controller
|
||||
- broker
|
||||
storage:
|
||||
type: persistent-claim
|
||||
size: {{ .Values.nodePool.storage.sizeGi }}Gi
|
||||
class: {{ .Values.nodePool.storage.class }}
|
||||
deleteClaim: false
|
||||
resources:
|
||||
limits:
|
||||
memory: {{ .Values.nodePool.resources.memory }}
|
||||
cpu: {{ .Values.nodePool.resources.cpu | quote }}
|
||||
requests:
|
||||
memory: {{ .Values.nodePool.resources.memory }}
|
||||
cpu: {{ .Values.nodePool.resources.cpu | quote }}
|
||||
template:
|
||||
pod:
|
||||
affinity:
|
||||
podAntiAffinity:
|
||||
preferredDuringSchedulingIgnoredDuringExecution:
|
||||
- weight: 100
|
||||
podAffinityTerm:
|
||||
topologyKey: {{ .Values.nodePool.antiAffinityTopologyKey }}
|
||||
labelSelector:
|
||||
matchLabels:
|
||||
strimzi.io/cluster: {{ .Values.clusterName }}
|
||||
kafkaContainer:
|
||||
env:
|
||||
- name: KAFKA_HEAP_OPTS
|
||||
value: {{ .Values.nodePool.heapOpts | quote }}
|
||||
@@ -0,0 +1,19 @@
|
||||
{{- if eq .Values.nodePool.storage.class "longhorn-kafka" }}
|
||||
# The default "longhorn" StorageClass requests 3 replicas across 3 zone-labeled
|
||||
# nodes (az-a/az-b/az-c). With Longhorn's zone-aware anti-affinity, replicas
|
||||
# spread 1-per-zone for durability.
|
||||
apiVersion: storage.k8s.io/v1
|
||||
kind: StorageClass
|
||||
metadata:
|
||||
name: longhorn-kafka
|
||||
provisioner: driver.longhorn.io
|
||||
allowVolumeExpansion: true
|
||||
reclaimPolicy: Delete
|
||||
volumeBindingMode: Immediate
|
||||
parameters:
|
||||
numberOfReplicas: "3"
|
||||
staleReplicaTimeout: "30"
|
||||
fromBackup: ""
|
||||
fsType: "ext4"
|
||||
dataLocality: "disabled"
|
||||
{{- end }}
|
||||
@@ -0,0 +1,26 @@
|
||||
clusterName: kmsvc
|
||||
namespace: sqs
|
||||
|
||||
nodePool:
|
||||
replicas: 3
|
||||
storage:
|
||||
class: longhorn-kafka
|
||||
# Longhorn's per-node scheduling budget on the current 2-node cluster has
|
||||
# only ~36Gi of headroom left (other PVCs already reserve the rest), and
|
||||
# each node hosts one replica of all 3 broker volumes -- so 3 * sizeGi
|
||||
# must fit in that headroom. Revisit once the 3rd node joins.
|
||||
sizeGi: 10
|
||||
resources:
|
||||
memory: 5Gi
|
||||
cpu: "2"
|
||||
heapOpts: "-Xms2g -Xmx2g"
|
||||
# design.md §7: 3 real zones now exist (talos-cp-1=az-a, talos-worker-1=az-b,
|
||||
# talos-worker-2=az-c), so anti-affinity keys off zone instead of hostname —
|
||||
# spreads the 3 broker pods one-per-zone/one-per-node (equivalent today,
|
||||
# but zone is the correct long-term key if a node ever gets replaced within
|
||||
# the same zone).
|
||||
antiAffinityTopologyKey: topology.kubernetes.io/zone
|
||||
|
||||
kafka:
|
||||
replicationFactor: 3
|
||||
minInsyncReplicas: 2
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: v2
|
||||
name: management-service
|
||||
description: kmsvc message-plane gRPC+REST server (design.md §1, §7a, §9)
|
||||
type: application
|
||||
version: 0.1.0
|
||||
@@ -0,0 +1,12 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: management-service-config
|
||||
namespace: {{ .Values.namespace }}
|
||||
data:
|
||||
KMSVC_KAFKA_BROKERS: {{ .Values.env.kafkaBrokers | quote }}
|
||||
KMSVC_REDIS_ADDR: {{ .Values.env.redisAddr | quote }}
|
||||
KMSVC_AUTHENTIK_ISSUER_URL: {{ .Values.env.authentikIssuerURL | quote }}
|
||||
KMSVC_AUTHENTIK_AUDIENCE: {{ .Values.env.authentikAudience | quote }}
|
||||
KMSVC_GRPC_LISTEN_ADDR: ":{{ .Values.grpcPort }}"
|
||||
KMSVC_HTTP_LISTEN_ADDR: ":{{ .Values.httpPort }}"
|
||||
@@ -0,0 +1,49 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: management-service
|
||||
namespace: {{ .Values.namespace }}
|
||||
spec:
|
||||
replicas: {{ .Values.replicaCount }}
|
||||
selector:
|
||||
matchLabels:
|
||||
app: management-service
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: management-service
|
||||
spec:
|
||||
topologySpreadConstraints:
|
||||
- maxSkew: 1
|
||||
topologyKey: kubernetes.io/hostname
|
||||
whenUnsatisfiable: ScheduleAnyway
|
||||
labelSelector:
|
||||
matchLabels:
|
||||
app: management-service
|
||||
containers:
|
||||
- name: management-service
|
||||
image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
|
||||
imagePullPolicy: {{ .Values.image.pullPolicy }}
|
||||
ports:
|
||||
- name: grpc
|
||||
containerPort: {{ .Values.grpcPort }}
|
||||
- name: http
|
||||
containerPort: {{ .Values.httpPort }}
|
||||
env:
|
||||
- name: GOMEMLIMIT
|
||||
value: {{ .Values.goMemLimit | quote }}
|
||||
envFrom:
|
||||
- configMapRef:
|
||||
name: management-service-config
|
||||
resources:
|
||||
{{- toYaml .Values.resources | nindent 12 }}
|
||||
readinessProbe:
|
||||
tcpSocket:
|
||||
port: {{ .Values.httpPort }}
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 10
|
||||
livenessProbe:
|
||||
tcpSocket:
|
||||
port: {{ .Values.httpPort }}
|
||||
initialDelaySeconds: 10
|
||||
periodSeconds: 20
|
||||
@@ -0,0 +1,27 @@
|
||||
{{- if .Values.hpa.enabled }}
|
||||
apiVersion: autoscaling/v2
|
||||
kind: HorizontalPodAutoscaler
|
||||
metadata:
|
||||
name: management-service
|
||||
namespace: {{ .Values.namespace }}
|
||||
spec:
|
||||
scaleTargetRef:
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
name: management-service
|
||||
minReplicas: {{ .Values.hpa.minReplicas }}
|
||||
maxReplicas: {{ .Values.hpa.maxReplicas }}
|
||||
metrics:
|
||||
- type: Resource
|
||||
resource:
|
||||
name: cpu
|
||||
target:
|
||||
type: Utilization
|
||||
averageUtilization: {{ .Values.hpa.targetCPUUtilizationPercentage }}
|
||||
- type: Resource
|
||||
resource:
|
||||
name: memory
|
||||
target:
|
||||
type: Utilization
|
||||
averageUtilization: {{ .Values.hpa.targetMemoryUtilizationPercentage }}
|
||||
{{- end }}
|
||||
@@ -0,0 +1,27 @@
|
||||
{{- if and .Values.ingress.enabled .Values.ingress.grpcEnabled }}
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: Ingress
|
||||
metadata:
|
||||
name: management-service-grpc
|
||||
namespace: {{ .Values.namespace }}
|
||||
annotations:
|
||||
cert-manager.io/cluster-issuer: {{ .Values.ingress.clusterIssuer }}
|
||||
nginx.ingress.kubernetes.io/backend-protocol: "GRPC"
|
||||
spec:
|
||||
ingressClassName: {{ .Values.ingress.className }}
|
||||
tls:
|
||||
- hosts:
|
||||
- {{ .Values.ingress.host }}
|
||||
secretName: {{ .Values.ingress.tlsSecretName }}
|
||||
rules:
|
||||
- host: {{ .Values.ingress.host }}
|
||||
http:
|
||||
paths:
|
||||
- path: {{ .Values.ingress.grpcPathPrefix }}
|
||||
pathType: Prefix
|
||||
backend:
|
||||
service:
|
||||
name: management-service
|
||||
port:
|
||||
number: {{ .Values.grpcPort }}
|
||||
{{- end }}
|
||||
@@ -0,0 +1,26 @@
|
||||
{{- if .Values.ingress.enabled }}
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: Ingress
|
||||
metadata:
|
||||
name: management-service
|
||||
namespace: {{ .Values.namespace }}
|
||||
annotations:
|
||||
cert-manager.io/cluster-issuer: {{ .Values.ingress.clusterIssuer }}
|
||||
spec:
|
||||
ingressClassName: {{ .Values.ingress.className }}
|
||||
tls:
|
||||
- hosts:
|
||||
- {{ .Values.ingress.host }}
|
||||
secretName: {{ .Values.ingress.tlsSecretName }}
|
||||
rules:
|
||||
- host: {{ .Values.ingress.host }}
|
||||
http:
|
||||
paths:
|
||||
- path: /
|
||||
pathType: Prefix
|
||||
backend:
|
||||
service:
|
||||
name: management-service
|
||||
port:
|
||||
number: {{ .Values.httpPort }}
|
||||
{{- end }}
|
||||
@@ -0,0 +1,16 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: management-service
|
||||
namespace: {{ .Values.namespace }}
|
||||
spec:
|
||||
selector:
|
||||
app: management-service
|
||||
ports:
|
||||
- name: grpc
|
||||
port: {{ .Values.grpcPort }}
|
||||
targetPort: {{ .Values.grpcPort }}
|
||||
- name: http
|
||||
port: {{ .Values.httpPort }}
|
||||
targetPort: {{ .Values.httpPort }}
|
||||
type: ClusterIP
|
||||
@@ -0,0 +1,50 @@
|
||||
namespace: sqs
|
||||
replicaCount: 3
|
||||
|
||||
image:
|
||||
repository: ghcr.io/riotpiaole/kmsvc-management-service
|
||||
tag: latest
|
||||
pullPolicy: Always
|
||||
|
||||
grpcPort: 9090
|
||||
httpPort: 8080
|
||||
|
||||
env:
|
||||
kafkaBrokers: "kmsvc-kafka-bootstrap.sqs.svc.cluster.local:9092"
|
||||
redisAddr: "kmsvc-redis-master.sqs.svc.cluster.local:6379"
|
||||
authentikIssuerURL: ""
|
||||
authentikAudience: ""
|
||||
|
||||
resources:
|
||||
requests:
|
||||
cpu: 200m
|
||||
memory: 256Mi
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 512Mi
|
||||
|
||||
# Go's GC only reacts to GOGC by default and has no idea about the cgroup
|
||||
# memory limit above -- it'll happily grow heap until the kernel OOMKills it.
|
||||
# Setting GOMEMLIMIT to ~90% of the container limit makes the GC self-throttle
|
||||
# before that happens. Keep this in sync with resources.limits.memory.
|
||||
goMemLimit: "460MiB"
|
||||
|
||||
hpa:
|
||||
enabled: true
|
||||
minReplicas: 3
|
||||
maxReplicas: 9
|
||||
targetCPUUtilizationPercentage: 70
|
||||
targetMemoryUtilizationPercentage: 80
|
||||
|
||||
ingress:
|
||||
enabled: true
|
||||
className: nginx
|
||||
clusterIssuer: homelab-ca
|
||||
host: kmsvc.riotpiao.homelab.com
|
||||
tlsSecretName: kmsvc-tls
|
||||
# kmsvc-cli connects via gRPC directly to --server/KMSVC_SERVER (default
|
||||
# kmsvc.riotpiao.homelab.com:443, see kmsvc-cli's README), so raw gRPC needs an
|
||||
# external path too — scoped to the gRPC service's own path prefix on the
|
||||
# same host/port, rather than opening the whole host to gRPC passthrough.
|
||||
grpcEnabled: true
|
||||
grpcPathPrefix: /kafkamgmt.v1.QueueService/
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: v2
|
||||
name: queue-crd
|
||||
description: Queue CRD definition + queue-operator Deployment/RBAC (design.md §2a)
|
||||
type: application
|
||||
version: 0.1.0
|
||||
@@ -0,0 +1,274 @@
|
||||
---
|
||||
apiVersion: apiextensions.k8s.io/v1
|
||||
kind: CustomResourceDefinition
|
||||
metadata:
|
||||
annotations:
|
||||
controller-gen.kubebuilder.io/version: v0.21.0
|
||||
name: queues.kmsvc.io
|
||||
spec:
|
||||
group: kmsvc.io
|
||||
names:
|
||||
kind: Queue
|
||||
listKind: QueueList
|
||||
plural: queues
|
||||
shortNames:
|
||||
- queue
|
||||
- queues
|
||||
singular: queue
|
||||
scope: Namespaced
|
||||
versions:
|
||||
- additionalPrinterColumns:
|
||||
- jsonPath: .spec.fifoQueue
|
||||
name: FIFO
|
||||
type: boolean
|
||||
- jsonPath: .status.phase
|
||||
name: Phase
|
||||
type: string
|
||||
name: v1
|
||||
schema:
|
||||
openAPIV3Schema:
|
||||
description: Queue is the Schema for the queues API — see design.md §2a.
|
||||
properties:
|
||||
apiVersion:
|
||||
description: |-
|
||||
APIVersion defines the versioned schema of this representation of an object.
|
||||
Servers should convert recognized schemas to the latest internal value, and
|
||||
may reject unrecognized values.
|
||||
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
|
||||
type: string
|
||||
kind:
|
||||
description: |-
|
||||
Kind is a string value representing the REST resource this object represents.
|
||||
Servers may infer this from the endpoint the client submits requests to.
|
||||
Cannot be updated.
|
||||
In CamelCase.
|
||||
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
|
||||
type: string
|
||||
metadata:
|
||||
type: object
|
||||
spec:
|
||||
description: QueueSpec defines the desired state of a Queue (design.md
|
||||
§2a).
|
||||
properties:
|
||||
deadLetterTargetQueue:
|
||||
description: |-
|
||||
DeadLetterTargetQueue is the name of another Queue to route exhausted
|
||||
messages to. Must not point at itself or at another DLQ (design.md §5).
|
||||
type: string
|
||||
delaySeconds:
|
||||
description: DelaySeconds is the default delivery delay applied to
|
||||
sent messages.
|
||||
format: int32
|
||||
maximum: 900
|
||||
minimum: 0
|
||||
type: integer
|
||||
fifoQueue:
|
||||
default: false
|
||||
description: FIFOQueue enables per-MessageGroupId ordering and deduplication
|
||||
semantics.
|
||||
type: boolean
|
||||
isDLQ:
|
||||
description: |-
|
||||
IsDLQ marks this queue as itself a dead-letter queue, used to enforce
|
||||
the no-DLQ-chaining validation rule in design.md §5.
|
||||
type: boolean
|
||||
maxReceiveCount:
|
||||
default: 5
|
||||
description: |-
|
||||
MaxReceiveCount is how many times a message may be redelivered before
|
||||
being routed to DeadLetterTargetQueue.
|
||||
format: int32
|
||||
minimum: 1
|
||||
type: integer
|
||||
maxShards:
|
||||
default: 8
|
||||
description: MaxShards is the ceiling on shard count the operator
|
||||
may split up to (design.md §2c).
|
||||
format: int32
|
||||
minimum: 1
|
||||
type: integer
|
||||
messageRetentionPeriodSeconds:
|
||||
default: 345600
|
||||
description: MessageRetentionPeriodSeconds maps to the underlying
|
||||
Kafka topic's retention.ms.
|
||||
format: int32
|
||||
maximum: 1209600
|
||||
minimum: 60
|
||||
type: integer
|
||||
minShards:
|
||||
default: 1
|
||||
description: MinShards is the floor on shard count; the operator never
|
||||
merges below this.
|
||||
format: int32
|
||||
minimum: 1
|
||||
type: integer
|
||||
partitionsPerShard:
|
||||
default: 6
|
||||
description: PartitionsPerShard is the Kafka partition count on each
|
||||
shard's topic.
|
||||
format: int32
|
||||
minimum: 1
|
||||
type: integer
|
||||
shardSplitCooldownSeconds:
|
||||
default: 300
|
||||
description: |-
|
||||
ShardSplitCooldownSeconds is the minimum age a shard must reach before it
|
||||
is eligible to be split again, preventing rapid re-splitting of a child
|
||||
that hasn't yet absorbed its share of traffic.
|
||||
format: int32
|
||||
minimum: 0
|
||||
type: integer
|
||||
shardSplitThresholdBytesPerSec:
|
||||
default: 5242880
|
||||
description: |-
|
||||
ShardSplitThresholdBytesPerSec is the sustained per-shard throughput that
|
||||
triggers a split into two child shards (design.md §2c).
|
||||
format: int64
|
||||
minimum: 1
|
||||
type: integer
|
||||
visibilityTimeoutSeconds:
|
||||
default: 30
|
||||
description: |-
|
||||
VisibilityTimeoutSeconds is how long a received-but-unacked message stays
|
||||
invisible to other consumers before being redelivered.
|
||||
format: int32
|
||||
maximum: 43200
|
||||
minimum: 0
|
||||
type: integer
|
||||
type: object
|
||||
status:
|
||||
description: QueueStatus defines the observed state of a Queue.
|
||||
properties:
|
||||
conditions:
|
||||
description: Conditions hold detailed status information.
|
||||
items:
|
||||
description: Condition contains details for one aspect of the current
|
||||
state of this API Resource.
|
||||
properties:
|
||||
lastTransitionTime:
|
||||
description: |-
|
||||
lastTransitionTime is the last time the condition transitioned from one status to another.
|
||||
This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable.
|
||||
format: date-time
|
||||
type: string
|
||||
message:
|
||||
description: |-
|
||||
message is a human readable message indicating details about the transition.
|
||||
This may be an empty string.
|
||||
maxLength: 32768
|
||||
type: string
|
||||
observedGeneration:
|
||||
description: |-
|
||||
observedGeneration represents the .metadata.generation that the condition was set based upon.
|
||||
For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
|
||||
with respect to the current state of the instance.
|
||||
format: int64
|
||||
minimum: 0
|
||||
type: integer
|
||||
reason:
|
||||
description: |-
|
||||
reason contains a programmatic identifier indicating the reason for the condition's last transition.
|
||||
Producers of specific condition types may define expected values and meanings for this field,
|
||||
and whether the values are considered a guaranteed API.
|
||||
The value should be a CamelCase string.
|
||||
This field may not be empty.
|
||||
maxLength: 1024
|
||||
minLength: 1
|
||||
pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
|
||||
type: string
|
||||
status:
|
||||
description: status of the condition, one of True, False, Unknown.
|
||||
enum:
|
||||
- "True"
|
||||
- "False"
|
||||
- Unknown
|
||||
type: string
|
||||
type:
|
||||
description: type of condition in CamelCase or in foo.example.com/CamelCase.
|
||||
maxLength: 316
|
||||
pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
|
||||
type: string
|
||||
required:
|
||||
- lastTransitionTime
|
||||
- message
|
||||
- reason
|
||||
- status
|
||||
- type
|
||||
type: object
|
||||
type: array
|
||||
phase:
|
||||
description: Phase is the current reconciliation phase.
|
||||
enum:
|
||||
- Pending
|
||||
- Ready
|
||||
- Failed
|
||||
type: string
|
||||
shards:
|
||||
description: |-
|
||||
Shards lists every shard backing this queue, active or draining
|
||||
(design.md §2a/§2c).
|
||||
items:
|
||||
description: ShardStatus describes one shard backing a Queue (design.md
|
||||
§2a/§2c).
|
||||
properties:
|
||||
availabilityZones:
|
||||
description: |-
|
||||
AvailabilityZones lists the topology.kubernetes.io/zone values of every
|
||||
node currently hosting a Kafka replica of this shard's topic, resolved
|
||||
from the broker pods' node placement each reconcile. Empty until the
|
||||
first successful resolution (e.g. node lookup failed transiently).
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
createdAt:
|
||||
description: |-
|
||||
CreatedAt timestamps when this shard was created, used to enforce
|
||||
ShardSplitCooldownSeconds.
|
||||
format: date-time
|
||||
type: string
|
||||
hashRangeEnd:
|
||||
format: int64
|
||||
type: integer
|
||||
hashRangeStart:
|
||||
description: |-
|
||||
HashRangeStart/HashRangeEnd define the [start, end) murmur2 hash range
|
||||
this shard owns over the 32-bit key space. Stored as int64 (not uint32)
|
||||
because controller-gen maps Go uint32 to OpenAPI format:int32, whose max
|
||||
(2147483647) is smaller than FullHashRangeEnd (0xFFFFFFFF) and the
|
||||
apiserver rejects the status update.
|
||||
format: int64
|
||||
type: integer
|
||||
id:
|
||||
description: ID is the shard's identifier, used in its topic
|
||||
name (kmsvc.{queue}.shard-{id}).
|
||||
type: string
|
||||
parentId:
|
||||
description: |-
|
||||
ParentID is the shard ID this shard was split from, empty for the
|
||||
original shard-0.
|
||||
type: string
|
||||
phase:
|
||||
description: Phase is this shard's lifecycle state.
|
||||
enum:
|
||||
- Active
|
||||
- Closing
|
||||
- Closed
|
||||
type: string
|
||||
topic:
|
||||
description: Topic is the underlying Kafka topic name for this
|
||||
shard.
|
||||
type: string
|
||||
required:
|
||||
- hashRangeEnd
|
||||
- hashRangeStart
|
||||
- id
|
||||
- phase
|
||||
- topic
|
||||
type: object
|
||||
type: array
|
||||
type: object
|
||||
type: object
|
||||
served: true
|
||||
storage: true
|
||||
subresources:
|
||||
status: {}
|
||||
@@ -0,0 +1,38 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: queue-operator
|
||||
namespace: {{ .Values.namespace }}
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app: queue-operator
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: queue-operator
|
||||
spec:
|
||||
serviceAccountName: queue-operator
|
||||
containers:
|
||||
- name: queue-operator
|
||||
image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
|
||||
imagePullPolicy: {{ .Values.image.pullPolicy }}
|
||||
command: ["/queue-operator"]
|
||||
env:
|
||||
- name: KMSVC_KAFKA_BROKERS
|
||||
value: {{ .Values.kafkaBrokers | quote }}
|
||||
- name: KMSVC_REDIS_ADDR
|
||||
value: {{ .Values.redisAddr | quote }}
|
||||
- name: GOMEMLIMIT
|
||||
value: {{ .Values.goMemLimit | quote }}
|
||||
- name: KMSVC_NAMESPACE
|
||||
valueFrom:
|
||||
fieldRef:
|
||||
fieldPath: metadata.namespace
|
||||
- name: KMSVC_KAFKA_CLUSTER_NAME
|
||||
value: {{ .Values.kafkaClusterName | quote }}
|
||||
- name: KMSVC_KAFKA_POOL_NAME
|
||||
value: {{ .Values.kafkaPoolName | quote }}
|
||||
resources:
|
||||
{{- toYaml .Values.resources | nindent 12 }}
|
||||
@@ -0,0 +1,42 @@
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: queue-operator
|
||||
namespace: {{ .Values.namespace }}
|
||||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
name: queue-operator
|
||||
rules:
|
||||
- apiGroups: ["kmsvc.io"]
|
||||
resources: ["queues"]
|
||||
verbs: ["get", "list", "watch", "update", "patch"]
|
||||
- apiGroups: ["kmsvc.io"]
|
||||
resources: ["queues/status"]
|
||||
verbs: ["get", "update", "patch"]
|
||||
- apiGroups: ["kmsvc.io"]
|
||||
resources: ["queues/finalizers"]
|
||||
verbs: ["update"]
|
||||
- apiGroups: ["coordination.k8s.io"]
|
||||
resources: ["leases"]
|
||||
verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "patch"]
|
||||
- apiGroups: [""]
|
||||
resources: ["pods", "nodes"]
|
||||
verbs: ["get"]
|
||||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
name: queue-operator
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: queue-operator
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: queue-operator
|
||||
namespace: {{ .Values.namespace }}
|
||||
@@ -0,0 +1,26 @@
|
||||
namespace: sqs
|
||||
|
||||
image:
|
||||
repository: ghcr.io/riotpiaole/kmsvc-management-service
|
||||
tag: latest
|
||||
pullPolicy: Always
|
||||
|
||||
kafkaBrokers: "kmsvc-kafka-bootstrap.sqs.svc.cluster.local:9092"
|
||||
redisAddr: "kmsvc-redis-master.sqs.svc.cluster.local:6379"
|
||||
|
||||
# Must match kafka-cluster chart's clusterName/derived pool name -- used to
|
||||
# resolve "<kafkaClusterName>-<kafkaPoolName>-<brokerID>" broker pod names
|
||||
# for AZ-aware Queue status (design.md §2a).
|
||||
kafkaClusterName: kmsvc
|
||||
kafkaPoolName: kmsvc-pool
|
||||
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 128Mi
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 256Mi
|
||||
|
||||
# See management-service/values.yaml's goMemLimit comment -- same reasoning.
|
||||
goMemLimit: "230MiB"
|
||||
@@ -0,0 +1,29 @@
|
||||
# design.md §7b: cluster-specific values for the homelab environment.
|
||||
# No secrets here — Authentik client secret etc. flow through the existing
|
||||
# Vault/talos-cli pattern, referenced at deploy time, not inlined.
|
||||
namespace: sqs
|
||||
|
||||
kafkaCluster:
|
||||
nodePool:
|
||||
replicas: 3
|
||||
storage:
|
||||
# longhorn-kafka now uses numberOfReplicas: 3 across 3 zone-labeled nodes.
|
||||
class: longhorn-kafka
|
||||
# Per-node headroom: with 3 nodes and existing PVCs, estimate ~100+ Gi total
|
||||
# available. Each node hosts one replica of all 3 broker volumes, so 3 *
|
||||
# sizeGi must fit. Monitor usage during Kafka deployment.
|
||||
sizeGi: 10
|
||||
resources:
|
||||
memory: 5Gi
|
||||
cpu: "2"
|
||||
|
||||
redis:
|
||||
storageClass: longhorn
|
||||
memoryLimit: 1Gi
|
||||
|
||||
managementService:
|
||||
ingress:
|
||||
host: kmsvc.riotpiao.homelab.com
|
||||
clusterIssuer: homelab-ca
|
||||
authentikIssuerURL: "https://authentik.riotpiao.homelab.com/application/o/kafaka/"
|
||||
authentikAudience: "QI0gPtR99ar8VvhK8Tqox4SDkTKzbNU7lbgwBNSc"
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: sqs
|
||||
resources: []
|
||||
# homelab.yaml is configuration, not a K8s manifest
|
||||
@@ -0,0 +1,99 @@
|
||||
environments:
|
||||
default:
|
||||
values:
|
||||
- environments/homelab.yaml
|
||||
homelab:
|
||||
values:
|
||||
- environments/homelab.yaml
|
||||
---
|
||||
helmDefaults:
|
||||
wait: true
|
||||
timeout: 600
|
||||
|
||||
repositories:
|
||||
- name: strimzi
|
||||
url: https://strimzi.io/charts/
|
||||
- name: bitnami
|
||||
url: https://charts.bitnami.com/bitnami
|
||||
|
||||
releases:
|
||||
- name: strimzi-operator
|
||||
namespace: {{ .Values.namespace }}
|
||||
chart: strimzi/strimzi-kafka-operator
|
||||
version: 0.46.0
|
||||
values:
|
||||
- watchNamespaces: ["{{ .Values.namespace }}"]
|
||||
|
||||
- name: kafka-cluster
|
||||
namespace: {{ .Values.namespace }}
|
||||
chart: charts/kafka-cluster
|
||||
needs:
|
||||
- {{ .Values.namespace }}/strimzi-operator
|
||||
values:
|
||||
- namespace: {{ .Values.namespace }}
|
||||
nodePool:
|
||||
replicas: {{ .Values.kafkaCluster.nodePool.replicas }}
|
||||
storage:
|
||||
class: {{ .Values.kafkaCluster.nodePool.storage.class }}
|
||||
sizeGi: {{ .Values.kafkaCluster.nodePool.storage.sizeGi }}
|
||||
resources:
|
||||
memory: {{ .Values.kafkaCluster.nodePool.resources.memory }}
|
||||
cpu: {{ .Values.kafkaCluster.nodePool.resources.cpu | quote }}
|
||||
|
||||
- name: kmsvc-redis
|
||||
namespace: {{ .Values.namespace }}
|
||||
chart: bitnami/redis
|
||||
version: 20.6.0
|
||||
values:
|
||||
- architecture: standalone
|
||||
# Bitnami stopped publishing version-pinned tags under docker.io/bitnami
|
||||
# (only `latest` remains there); bitnamilegacy/* mirrors the old
|
||||
# versioned tags for free, so pin there instead of floating on `latest`.
|
||||
# The chart's container-image allowlist check doesn't know about the
|
||||
# legacy mirror, hence allowInsecureImages.
|
||||
global:
|
||||
security:
|
||||
allowInsecureImages: true
|
||||
image:
|
||||
repository: bitnamilegacy/redis
|
||||
auth:
|
||||
enabled: false
|
||||
master:
|
||||
persistence:
|
||||
enabled: true
|
||||
storageClass: {{ .Values.redis.storageClass }}
|
||||
size: 2Gi
|
||||
resources:
|
||||
limits:
|
||||
memory: {{ .Values.redis.memoryLimit }}
|
||||
requests:
|
||||
memory: {{ .Values.redis.memoryLimit }}
|
||||
|
||||
- name: queue-crd
|
||||
namespace: {{ .Values.namespace }}
|
||||
chart: charts/queue-crd
|
||||
needs:
|
||||
- {{ .Values.namespace }}/kafka-cluster
|
||||
- {{ .Values.namespace }}/kmsvc-redis
|
||||
values:
|
||||
- namespace: {{ .Values.namespace }}
|
||||
kafkaBrokers: "kmsvc-kafka-bootstrap.{{ .Values.namespace }}.svc.cluster.local:9092"
|
||||
redisAddr: "kmsvc-redis-master.{{ .Values.namespace }}.svc.cluster.local:6379"
|
||||
|
||||
- name: management-service
|
||||
namespace: {{ .Values.namespace }}
|
||||
chart: charts/management-service
|
||||
needs:
|
||||
- {{ .Values.namespace }}/kafka-cluster
|
||||
- {{ .Values.namespace }}/kmsvc-redis
|
||||
values:
|
||||
- namespace: {{ .Values.namespace }}
|
||||
env:
|
||||
kafkaBrokers: "kmsvc-kafka-bootstrap.{{ .Values.namespace }}.svc.cluster.local:9092"
|
||||
redisAddr: "kmsvc-redis-master.{{ .Values.namespace }}.svc.cluster.local:6379"
|
||||
authentikIssuerURL: {{ .Values.managementService.authentikIssuerURL | quote }}
|
||||
authentikAudience: {{ .Values.managementService.authentikAudience | quote }}
|
||||
ingress:
|
||||
enabled: true
|
||||
host: {{ .Values.managementService.ingress.host | quote }}
|
||||
clusterIssuer: {{ .Values.managementService.ingress.clusterIssuer | quote }}
|
||||
@@ -0,0 +1,8 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: sqs
|
||||
resources:
|
||||
- argocd/
|
||||
- environments/
|
||||
- queues/
|
||||
# Helm charts deployed via ArgoCD Helm source
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
|
||||
resources:
|
||||
- orders-fifo.yaml
|
||||
@@ -0,0 +1,32 @@
|
||||
apiVersion: kmsvc.io/v1
|
||||
kind: Queue
|
||||
metadata:
|
||||
name: orders-fifo
|
||||
namespace: sqs
|
||||
spec:
|
||||
fifoQueue: true
|
||||
visibilityTimeoutSeconds: 30
|
||||
messageRetentionPeriodSeconds: 345600
|
||||
maxReceiveCount: 5
|
||||
deadLetterTargetQueue: orders-fifo-dlq
|
||||
delaySeconds: 0
|
||||
partitionsPerShard: 6
|
||||
minShards: 1
|
||||
maxShards: 8
|
||||
shardSplitThresholdBytesPerSec: 5242880
|
||||
shardSplitCooldownSeconds: 300
|
||||
---
|
||||
apiVersion: kmsvc.io/v1
|
||||
kind: Queue
|
||||
metadata:
|
||||
name: orders-fifo-dlq
|
||||
namespace: sqs
|
||||
spec:
|
||||
fifoQueue: true
|
||||
isDLQ: true
|
||||
visibilityTimeoutSeconds: 30
|
||||
messageRetentionPeriodSeconds: 1209600
|
||||
maxReceiveCount: 5
|
||||
partitionsPerShard: 6
|
||||
minShards: 1
|
||||
maxShards: 1
|
||||
@@ -0,0 +1,237 @@
|
||||
# Phase 2: Namespace-Scoped Auto-Provisioning Testing Guide
|
||||
|
||||
## Overview
|
||||
|
||||
Phase 2 implements **namespace-scoped automatic TemporalWorker provisioning** (Kafka broker model).
|
||||
|
||||
One TemporalWorker per Temporal namespace processes ALL task queues in that namespace. When multiple Queues share the same `temporal.io/namespace` label, they trigger creation of a single TemporalWorker that handles all of them.
|
||||
|
||||
```
|
||||
Queues (labeled temporal.io/namespace: "production")
|
||||
├── orders-fifo
|
||||
├── payments
|
||||
└── notifications
|
||||
↓
|
||||
queue-operator creates 1 TemporalWorker (worker-production)
|
||||
↓
|
||||
TemporalWorker controller creates 1 Deployment
|
||||
↓
|
||||
Worker pod(s) connect to Temporal namespace "production"
|
||||
↓
|
||||
Process ALL task queues in that namespace (scale horizontally by replicas)
|
||||
```
|
||||
|
||||
## Implementation Changes
|
||||
|
||||
### 1. TemporalWorker CRD (`apis/kmsvc/v1/temporalworker_types.go`)
|
||||
- New Kubernetes resource type to manage namespace-scoped workers
|
||||
- Fields: Namespace (required), Image, Replicas, Resources, NodeSelector, Affinity, Tolerations
|
||||
- Status: Phase (Pending/Ready/Failed), Replicas, ReadyReplicas, Conditions
|
||||
- Model: 1 TemporalWorker per Temporal namespace (not per queue)
|
||||
|
||||
### 2. QueueReconciler Extension (`internal/operator/queue_controller.go`)
|
||||
- New method: `reconcileTemporalWorker()`
|
||||
- Logic: If Queue has `temporal.io/namespace` label, create TemporalWorker for that namespace
|
||||
- Idempotent: multiple queues with same namespace label create same TemporalWorker (no duplicates)
|
||||
|
||||
### 3. TemporalWorkerReconciler (`internal/operator/temporal_worker_controller.go`)
|
||||
- New controller watching TemporalWorker objects
|
||||
- Creates/updates Kubernetes Deployment with:
|
||||
- Pod spec: container image, env vars (TEMPORAL_FRONTEND_ADDRESS, TEMPORAL_TASK_QUEUE)
|
||||
- Replicas, resources, node selector, affinity, tolerations from TemporalWorker spec
|
||||
- Updates TemporalWorker status with deployment replica counts and phase
|
||||
|
||||
### 4. Operator Main (`cmd/queue-operator/main.go`)
|
||||
- Registers TemporalWorker CRD in scheme
|
||||
- Registers TemporalWorkerReconciler controller
|
||||
- Controller watches TemporalWorker objects; owns Deployment objects
|
||||
|
||||
## Testing Procedure
|
||||
|
||||
### Prerequisites
|
||||
- kmsvc queue-operator must be running (built and deployed)
|
||||
- Temporal cluster must be ready (temporal-frontend service available at `temporal-frontend.temporal.svc.cluster.local:7233`)
|
||||
- story-crater-backend Docker image must exist (used as default worker image)
|
||||
|
||||
### Step 1: Build and Deploy kmsvc Operator
|
||||
```bash
|
||||
cd /Users/rockliang/workplace/kmsvc-manage
|
||||
make build # builds queue-operator binary
|
||||
make docker-build # builds Docker image
|
||||
make deploy # deploys to cluster (requires Helm chart)
|
||||
```
|
||||
|
||||
Or manually:
|
||||
```bash
|
||||
cd /Users/rockliang/workplace/kmsvc-manage
|
||||
go build -o bin/queue-operator ./cmd/queue-operator
|
||||
kubectl apply -f k8s/queue-operator-rbac.yaml
|
||||
kubectl apply -f k8s/queue-operator-deployment.yaml
|
||||
```
|
||||
|
||||
### Step 2: Create Queues with Temporal Namespace Labels
|
||||
```bash
|
||||
kubectl apply -f /Users/rockliang/workplace/homelab/k8s/temporal/queues/example-queue.yaml
|
||||
```
|
||||
|
||||
Verify Queues are Ready:
|
||||
```bash
|
||||
kubectl get queue -n sqs -l temporal.io/namespace=production
|
||||
kubectl describe queue -n sqs story-crater-tasks
|
||||
```
|
||||
|
||||
Expected:
|
||||
```
|
||||
NAME FIFO PHASE AGE
|
||||
story-crater-tasks false Ready 5s
|
||||
story-crater-notifications false Ready 5s
|
||||
```
|
||||
|
||||
### Step 3: Verify TemporalWorker CRD Auto-Created (1 per namespace)
|
||||
```bash
|
||||
kubectl get temporalworker -n temporal
|
||||
kubectl describe temporalworker -n temporal worker-production
|
||||
```
|
||||
|
||||
Expected:
|
||||
```
|
||||
NAME PHASE READY DESIRED AGE
|
||||
worker-production Pending 0 1 5s
|
||||
```
|
||||
|
||||
Only ONE TemporalWorker for all queues in "production" namespace!
|
||||
|
||||
### Step 4: Verify Deployment Auto-Created
|
||||
```bash
|
||||
kubectl get deploy -n temporal -l app.kubernetes.io/managed-by=kmsvc-temporal-operator
|
||||
kubectl get pods -n temporal -l app.kubernetes.io/instance=worker-production
|
||||
```
|
||||
|
||||
Expected:
|
||||
```
|
||||
NAME READY UP-TO-DATE AVAILABLE AGE
|
||||
worker-production 1/1 1 1 10s
|
||||
|
||||
NAME READY STATUS RESTARTS AGE
|
||||
worker-production-5f8b4c... 1/1 Running 0 10s
|
||||
```
|
||||
|
||||
### Step 5: Verify Worker Connected to Temporal Namespace
|
||||
Check Temporal UI for namespace "production":
|
||||
```bash
|
||||
open https://temporal.riotpiao.homelab.com/namespaces/production/task-queues
|
||||
```
|
||||
|
||||
Look for all task queues with worker count > 0:
|
||||
- `story-crater-tasks`
|
||||
- `story-crater-notifications`
|
||||
- (worker processes all of them)
|
||||
|
||||
Or via CLI:
|
||||
```bash
|
||||
kubectl port-forward -n temporal svc/temporal-frontend 7233 &
|
||||
curl http://localhost:7233/api/v1/task-queues?namespace=production
|
||||
```
|
||||
|
||||
### Step 6: Verify TemporalWorker Status Updated
|
||||
```bash
|
||||
kubectl get temporalworker -n temporal
|
||||
kubectl describe temporalworker -n temporal worker-production
|
||||
```
|
||||
|
||||
Expected:
|
||||
```
|
||||
NAME PHASE READY DESIRED AGE
|
||||
worker-production Ready 1 1 15s
|
||||
|
||||
Status:
|
||||
Phase: Ready
|
||||
Ready Replicas: 1
|
||||
Replicas: 1
|
||||
```
|
||||
|
||||
### Step 7: Test Namespace-Level Scaling
|
||||
Create more queues in the same namespace:
|
||||
```yaml
|
||||
apiVersion: kmsvc.io/v1
|
||||
kind: Queue
|
||||
metadata:
|
||||
name: story-crater-llm-processing
|
||||
namespace: sqs
|
||||
labels:
|
||||
temporal.io/namespace: "production" # same namespace
|
||||
```
|
||||
|
||||
Verify: No new TemporalWorker created (same worker handles all 3 queues):
|
||||
```bash
|
||||
kubectl get temporalworker -n temporal # still just 1 worker-production
|
||||
kubectl get deploy -n temporal worker-production # same deployment
|
||||
```
|
||||
|
||||
Worker auto-discovers new task queue in namespace and processes it.
|
||||
|
||||
### Step 8: Test Cascading Deletion
|
||||
Delete a Queue; worker should remain (other queues still need it):
|
||||
```bash
|
||||
kubectl delete queue -n sqs story-crater-notifications
|
||||
```
|
||||
|
||||
Verify:
|
||||
```bash
|
||||
kubectl get temporalworker -n temporal # worker-production still exists
|
||||
kubectl get pods -n temporal worker-production # still running
|
||||
```
|
||||
|
||||
Delete all queues in namespace:
|
||||
```bash
|
||||
kubectl delete queue -n sqs -l temporal.io/namespace=production
|
||||
```
|
||||
|
||||
Verify: TemporalWorker now has no owner (not cascade-deleted; manual cleanup needed):
|
||||
```bash
|
||||
kubectl get temporalworker -n temporal # worker-production still there (manual cleanup)
|
||||
kubectl delete temporalworker -n temporal worker-production # cleanup manually
|
||||
```
|
||||
|
||||
## Debugging
|
||||
|
||||
### Queue stuck in Pending
|
||||
Check queue-operator logs:
|
||||
```bash
|
||||
kubectl logs -n sqs deploy/kmsvc-queue-operator -f
|
||||
kubectl logs -n sqs deploy/kmsvc-queue-operator --tail=50 | grep -i error
|
||||
```
|
||||
|
||||
### TemporalWorker not created
|
||||
- Verify Queue has the label: `kubectl get queue -o yaml | grep temporal.io`
|
||||
- Check queue-operator logs for "reconcileTemporalWorker" errors
|
||||
|
||||
### Deployment not created
|
||||
- Check TemporalWorker controller logs: `kubectl logs -n sqs deploy/kmsvc-queue-operator -f`
|
||||
- Verify TemporalWorker exists: `kubectl get temporalworker -n temporal`
|
||||
- Check Deployment errors: `kubectl describe deploy -n temporal worker-story-crater-tasks`
|
||||
|
||||
### Worker not showing in Temporal UI
|
||||
- Check pod logs: `kubectl logs -n temporal deploy/worker-story-crater-tasks`
|
||||
- Verify env vars: `kubectl set env pod -n temporal <pod-name> --list | grep TEMPORAL`
|
||||
- Test connectivity: `kubectl exec -n temporal <pod-name> -- nc -zv temporal-frontend.temporal.svc.cluster.local 7233`
|
||||
|
||||
## Next Steps
|
||||
|
||||
Once Phase 2 is working:
|
||||
1. **Phase 3 (Future):** Implement autoscaling based on queue depth metrics
|
||||
2. **Production Hardening:**
|
||||
- Add QueueRef validation (ensure Queue exists in sqs namespace)
|
||||
- Add image validation/defaults from ConfigMap
|
||||
- Add worker readiness probe configuration
|
||||
- Add graceful shutdown/drain behavior
|
||||
|
||||
## Files Modified/Created
|
||||
|
||||
| File | Change |
|
||||
|------|--------|
|
||||
| `apis/kmsvc/v1/temporalworker_types.go` | NEW: CRD type definitions |
|
||||
| `internal/operator/queue_controller.go` | MODIFIED: Added reconcileTemporalWorker() |
|
||||
| `internal/operator/temporal_worker_controller.go` | NEW: TemporalWorker → Deployment reconciler |
|
||||
| `cmd/queue-operator/main.go` | MODIFIED: Register TemporalWorker CRD + controller |
|
||||
| `k8s/temporal/queues/example-queue.yaml` | NEW: Example Queue with label |
|
||||
@@ -0,0 +1,220 @@
|
||||
# Temporal OAuth2-Proxy Setup (Authentik OIDC)
|
||||
|
||||
## Overview
|
||||
|
||||
Protects Temporal UI with Authentik OIDC authentication. Traffic flow:
|
||||
|
||||
```
|
||||
Browser → Ingress (TLS) → oauth2-proxy (OIDC check) → temporal-web (internal)
|
||||
↓
|
||||
Redirects to Authentik login
|
||||
↓
|
||||
JWT cookie issued
|
||||
↓
|
||||
Forwards to temporal-web
|
||||
```
|
||||
|
||||
## Prerequisites
|
||||
|
||||
✅ Authentik OIDC provider `temporal` already exists with:
|
||||
- Client ID: `temporal`
|
||||
- Client Secret: stored in Kubernetes secret `temporal-oidc` (key: `clientSecret`)
|
||||
- Redirect URI: `https://temporal.riotpiao.homelab.com/oauth2/callback`
|
||||
|
||||
## Secrets
|
||||
|
||||
The `temporal-oidc` secret must contain:
|
||||
|
||||
| Key | Value | Source |
|
||||
|-----|-------|--------|
|
||||
| `clientSecret` | OAuth2 client secret from Authentik | Authentik → Applications → temporal |
|
||||
| `cookieSecret` | Session encryption key (base64 32-byte) | Generate: `openssl rand -base64 32` |
|
||||
|
||||
### Check existing secret:
|
||||
|
||||
```bash
|
||||
kubectl get secret -n temporal temporal-oidc
|
||||
kubectl describe secret -n temporal temporal-oidc
|
||||
```
|
||||
|
||||
### If missing, create it:
|
||||
|
||||
```bash
|
||||
# Get client secret from Authentik UI
|
||||
# Applications → temporal → copy "Client Secret"
|
||||
CLIENT_SECRET="..."
|
||||
|
||||
# Generate cookie secret
|
||||
COOKIE_SECRET=$(openssl rand -base64 32)
|
||||
|
||||
# Create secret
|
||||
kubectl create secret generic temporal-oidc \
|
||||
-n temporal \
|
||||
--from-literal=clientSecret="${CLIENT_SECRET}" \
|
||||
--from-literal=cookieSecret="${COOKIE_SECRET}"
|
||||
```
|
||||
|
||||
## Deployment Steps
|
||||
|
||||
### Step 1: Apply OAuth2-Proxy Manifests
|
||||
```bash
|
||||
kubectl apply -f k8s/temporal/oauth2-proxy.yaml
|
||||
```
|
||||
|
||||
Verify:
|
||||
```bash
|
||||
kubectl get deploy -n temporal oauth2-proxy
|
||||
kubectl logs -n temporal deploy/oauth2-proxy
|
||||
```
|
||||
|
||||
Expected log:
|
||||
```
|
||||
[<timestamp>] [oauthproxy.go:...] Listening on 0.0.0.0:4180
|
||||
```
|
||||
|
||||
### Step 2: Apply OAuth2-Proxy Ingress
|
||||
```bash
|
||||
kubectl apply -f k8s/temporal/temporal-ingress-oauth2.yaml
|
||||
```
|
||||
|
||||
Verify:
|
||||
```bash
|
||||
kubectl get ingress -n temporal
|
||||
```
|
||||
|
||||
Expected:
|
||||
```
|
||||
NAME CLASS HOSTS ADDRESS PORTS AGE
|
||||
temporal nginx temporal.riotpiao.homelab.com ... 80, 443 10s
|
||||
```
|
||||
|
||||
### Step 3: Test Access
|
||||
|
||||
1. **Open Temporal UI (unauthenticated):**
|
||||
```bash
|
||||
open https://temporal.riotpiao.homelab.com
|
||||
```
|
||||
|
||||
Expected: Redirects to Authentik login page
|
||||
|
||||
2. **Login with Authentik credentials**
|
||||
- Username/email
|
||||
- Password
|
||||
- Should redirect back to `temporal.riotpiao.homelab.com` and display UI
|
||||
|
||||
3. **Verify auth:**
|
||||
```bash
|
||||
# Check for oauth2_proxy cookie
|
||||
curl -v https://temporal.riotpiao.homelab.com 2>&1 | grep -i cookie
|
||||
```
|
||||
|
||||
4. **Check oauth2-proxy logs:**
|
||||
```bash
|
||||
kubectl logs -n temporal deploy/oauth2-proxy -f
|
||||
```
|
||||
|
||||
Look for:
|
||||
```
|
||||
[timestamp] [auth_test.go:...] Authentication successful
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Redirect URI mismatch
|
||||
Error in oauth2-proxy logs:
|
||||
```
|
||||
redirect_uri_mismatch: The redirect_uri does not match the one registered in Authentik
|
||||
```
|
||||
|
||||
Fix:
|
||||
- Verify Authentik application (Applications → temporal) has redirect URI: `https://temporal.riotpiao.homelab.com/oauth2/callback`
|
||||
- Ensure HTTPS (not HTTP)
|
||||
|
||||
### Missing secret
|
||||
Error:
|
||||
```
|
||||
clientSecret: key not found in temporal-oidc secret
|
||||
```
|
||||
|
||||
Fix:
|
||||
```bash
|
||||
kubectl get secret -n temporal temporal-oidc -o yaml
|
||||
# If missing, create per "Secrets" section above
|
||||
```
|
||||
|
||||
### Cookie secret expiration
|
||||
OAuth2-Proxy won't start if `cookieSecret` is empty or invalid.
|
||||
|
||||
Fix:
|
||||
```bash
|
||||
COOKIE_SECRET=$(openssl rand -base64 32)
|
||||
kubectl patch secret temporal-oidc -n temporal \
|
||||
-p "{\"data\":{\"cookieSecret\":\"$(echo -n $COOKIE_SECRET | base64)\"}}}"
|
||||
kubectl rollout restart deploy/oauth2-proxy -n temporal
|
||||
```
|
||||
|
||||
### oauth2-proxy crashes with "connection refused"
|
||||
Error in logs:
|
||||
```
|
||||
upstream connect error or disconnect/reset before headers
|
||||
```
|
||||
|
||||
Likely cause: `temporal-web` service not accessible.
|
||||
|
||||
Check:
|
||||
```bash
|
||||
kubectl get svc -n temporal temporal-web
|
||||
kubectl exec -n temporal deploy/oauth2-proxy -- curl http://temporal-web:8080
|
||||
```
|
||||
|
||||
## File Structure
|
||||
|
||||
```
|
||||
k8s/temporal/
|
||||
├── oauth2-proxy.yaml # oauth2-proxy Deployment + Service + SA
|
||||
├── temporal-ingress-oauth2.yaml # Ingress routing to oauth2-proxy
|
||||
├── oauth2-proxy-values.yaml # Helm values (reference only)
|
||||
└── temporal-values.yaml # Modified: ingress.enabled=false
|
||||
```
|
||||
|
||||
## Next: Add to Helmfile
|
||||
|
||||
If integrating with helmfile.yaml.gotmpl:
|
||||
|
||||
```yaml
|
||||
releases:
|
||||
- name: temporal
|
||||
# ... existing config ...
|
||||
hooks:
|
||||
postSync:
|
||||
- events: ["success"]
|
||||
showlogs: true
|
||||
command: "sh"
|
||||
args:
|
||||
- -c
|
||||
- |
|
||||
kubectl apply -f k8s/temporal/oauth2-proxy.yaml
|
||||
kubectl apply -f k8s/temporal/temporal-ingress-oauth2.yaml
|
||||
```
|
||||
|
||||
Or add separate releases:
|
||||
|
||||
```yaml
|
||||
- name: oauth2-proxy-temporal
|
||||
namespace: temporal
|
||||
chart: oauth2-proxy/oauth2-proxy
|
||||
version: "6.x.x"
|
||||
values:
|
||||
- k8s/temporal/oauth2-proxy-values.yaml
|
||||
set:
|
||||
- name: config.clientSecret
|
||||
value: "{{ (env "TEMPORAL_OIDC_CLIENT_SECRET") }}"
|
||||
- name: config.cookieSecret
|
||||
value: "{{ (env "TEMPORAL_OIDC_COOKIE_SECRET") }}"
|
||||
```
|
||||
|
||||
Then add to `.env`:
|
||||
```bash
|
||||
TEMPORAL_OIDC_CLIENT_SECRET=<from Authentik>
|
||||
TEMPORAL_OIDC_COOKIE_SECRET=$(openssl rand -base64 32)
|
||||
```
|
||||
@@ -0,0 +1,102 @@
|
||||
# Elasticsearch 7.17.0 for Temporal visibility store
|
||||
# Deployed to worker nodes (not control plane to save CP resources for LLM work)
|
||||
# 2Gi heap + 4Gi memory limit for stable operation
|
||||
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: elasticsearch-config
|
||||
namespace: temporal
|
||||
data:
|
||||
elasticsearch.yml: |
|
||||
cluster.name: temporal-elasticsearch
|
||||
node.name: temporal-elasticsearch-0
|
||||
discovery.type: single-node
|
||||
network.host: 0.0.0.0
|
||||
http.host: 0.0.0.0
|
||||
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: temporal-elasticsearch
|
||||
namespace: temporal
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app: temporal-elasticsearch
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: temporal-elasticsearch
|
||||
spec:
|
||||
affinity:
|
||||
nodeAffinity:
|
||||
requiredDuringSchedulingIgnoredDuringExecution:
|
||||
nodeSelectorTerms:
|
||||
- matchExpressions:
|
||||
- key: node-role.kubernetes.io/worker
|
||||
operator: Exists
|
||||
containers:
|
||||
- name: elasticsearch
|
||||
image: docker.elastic.co/elasticsearch/elasticsearch:7.17.0
|
||||
env:
|
||||
- name: discovery.type
|
||||
value: single-node
|
||||
- name: "ES_JAVA_OPTS"
|
||||
value: "-Xms2g -Xmx2g"
|
||||
ports:
|
||||
- containerPort: 9200
|
||||
name: http
|
||||
- containerPort: 9300
|
||||
name: transport
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /_cluster/health
|
||||
port: 9200
|
||||
initialDelaySeconds: 180
|
||||
periodSeconds: 10
|
||||
timeoutSeconds: 10
|
||||
failureThreshold: 5
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /_cluster/health?local=true
|
||||
port: 9200
|
||||
initialDelaySeconds: 150
|
||||
periodSeconds: 10
|
||||
timeoutSeconds: 10
|
||||
failureThreshold: 5
|
||||
resources:
|
||||
requests:
|
||||
cpu: 500m
|
||||
memory: 2Gi
|
||||
limits:
|
||||
cpu: 2000m
|
||||
memory: 4Gi
|
||||
volumeMounts:
|
||||
- name: config
|
||||
mountPath: /usr/share/elasticsearch/config/elasticsearch.yml
|
||||
subPath: elasticsearch.yml
|
||||
volumes:
|
||||
- name: config
|
||||
configMap:
|
||||
name: elasticsearch-config
|
||||
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: temporal-elasticsearch
|
||||
namespace: temporal
|
||||
spec:
|
||||
selector:
|
||||
app: temporal-elasticsearch
|
||||
ports:
|
||||
- port: 9200
|
||||
targetPort: 9200
|
||||
name: http
|
||||
- port: 9300
|
||||
targetPort: 9300
|
||||
name: transport
|
||||
type: ClusterIP
|
||||
@@ -0,0 +1,8 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
namespace: temporal
|
||||
resources:
|
||||
- elasticsearch.yaml
|
||||
- queues/
|
||||
# SOPS secrets (*.enc.yaml) handled by ArgoCD SOPS plugin at sync time
|
||||
# temporal deployed via ArgoCD Helm source
|
||||
@@ -0,0 +1,38 @@
|
||||
# Example Queues for "production" Temporal namespace
|
||||
# When applied, queue-operator creates 1 TemporalWorker (worker-production)
|
||||
# that processes ALL queues in the "production" namespace
|
||||
---
|
||||
apiVersion: kmsvc.io/v1
|
||||
kind: Queue
|
||||
metadata:
|
||||
name: story-crater-tasks
|
||||
namespace: sqs
|
||||
labels:
|
||||
temporal.io/namespace: "production"
|
||||
spec:
|
||||
fifoQueue: false
|
||||
visibilityTimeoutSeconds: 30
|
||||
messageRetentionPeriodSeconds: 345600
|
||||
maxReceiveCount: 5
|
||||
partitionsPerShard: 6
|
||||
minShards: 1
|
||||
maxShards: 8
|
||||
shardSplitThresholdBytesPerSec: 5242880
|
||||
|
||||
---
|
||||
apiVersion: kmsvc.io/v1
|
||||
kind: Queue
|
||||
metadata:
|
||||
name: story-crater-notifications
|
||||
namespace: sqs
|
||||
labels:
|
||||
temporal.io/namespace: "production"
|
||||
spec:
|
||||
fifoQueue: false
|
||||
visibilityTimeoutSeconds: 60
|
||||
messageRetentionPeriodSeconds: 345600
|
||||
maxReceiveCount: 3
|
||||
partitionsPerShard: 3
|
||||
minShards: 1
|
||||
maxShards: 4
|
||||
shardSplitThresholdBytesPerSec: 2621440
|
||||
@@ -0,0 +1,5 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
|
||||
resources:
|
||||
- example-queue.yaml
|
||||
@@ -0,0 +1,18 @@
|
||||
temporal:
|
||||
oidc_client_id: ENC[AES256_GCM,data:y6eSNJpCNCg=,iv:4n5fIeiVG2JZOCD4yZ4Asm/gWvRl0QNFiRGTR1bs8ws=,tag:liLSr9sadR82UPq6d3gqGA==,type:str]
|
||||
oidc_client_secret: ENC[AES256_GCM,data:ebk0FVtSfq7JbIT+84cigdLg8zfN+4HTfGxlgqLw6hs1H92SFRHQFXO1l3U=,iv:qxa8aqUVoN31PpzAhs6bNMDCM6yPvOT27urIrM1rfo0=,tag:Vo25X8Znw7eh5DNq1eIJEw==,type:str]
|
||||
sops:
|
||||
age:
|
||||
- enc: |
|
||||
-----BEGIN AGE ENCRYPTED FILE-----
|
||||
YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSArZ1pyMXZ0Y3RFQVZkcTg5
|
||||
aENyemRueXpIM0FaUVhMc2ZyVDRyWWlzK1JzCjA0OTZ0aGJDNVVSM29CY1RzQWJL
|
||||
eVNiSCtMSXdmbEtKeGt1L3NYMy9ibUEKLS0tIGJnU3A4MjVnZ1pCa1lPMnVoM0xo
|
||||
dWs1cVM5ZCszbXp6eFltRVhGbFc0ajQKyCc8lClnSqWUxhNOr1FDCwn5V7nvjxPN
|
||||
7kjQpldseaRbsy+TM5sFQ1w6Acmun9uYjzs8PtmTNaayc/AFfspufA==
|
||||
-----END AGE ENCRYPTED FILE-----
|
||||
recipient: age1smu533f803gmd0jq60s2zaj9zlznajy0ca6rtewd4r37mr2hs3uqsrldfh
|
||||
lastmodified: "2026-07-15T23:22:55Z"
|
||||
mac: ENC[AES256_GCM,data:0YuRxQHfdeKbjJzxHI4iBc7I2KnalNJmybB6bVQxvdRutsxKXW/bu99yqHkD4y/nI66Pi6d7LhrPhhGat3x2c6Drs7QRYVWnZ75thil6yWsOcpH7H1esxEWTP3cpoMzGdS0aF6zwU9H+WDvfm/t1wpeDpJly3eczcPvfbK1joDU=,iv:TgwfpI+ZVLyd2c/PKWsJbCI9yKkADpPPafJ5No0fLks=,tag:nqwQHtZ263CI+fY9iTUAzQ==,type:str]
|
||||
unencrypted_suffix: _unencrypted
|
||||
version: 3.13.2
|
||||
@@ -0,0 +1,110 @@
|
||||
# k8s/temporal/temporal-values.yaml
|
||||
# Temporal — workflow engine for story-crater backend async task orchestration.
|
||||
# Chart: temporal/temporal from https://go.temporal.io/helm-charts
|
||||
#
|
||||
# Uses Cassandra for default store (workflow history/events)
|
||||
# Uses Elasticsearch for visibility store (namespace/workflow queries)
|
||||
# This is the chart's native, well-tested configuration.
|
||||
|
||||
# ── Datastores configuration ────
|
||||
# Disable auto-deployed PostgreSQL (we use external ddb for other services)
|
||||
postgresql:
|
||||
enabled: false
|
||||
|
||||
# Enable Elasticsearch for visibility store (deployed to worker node, 2Gi/4Gi memory)
|
||||
elasticsearch:
|
||||
enabled: true
|
||||
scheme: http
|
||||
host: temporal-elasticsearch
|
||||
port: 9200
|
||||
version: v7
|
||||
logLevel: error
|
||||
auth:
|
||||
enabled: false
|
||||
indices:
|
||||
visibility: temporal_visibility_v1
|
||||
|
||||
# Cassandra enabled for template validation; server.config overrides with actual hosts
|
||||
# Schema job template requires cassandra config to exist at top level
|
||||
cassandra:
|
||||
enabled: true
|
||||
replicas: 3
|
||||
cluster:
|
||||
seedSize: 1
|
||||
port: 9042
|
||||
# Was landing 2 of 3 replicas on talos-cp-1 -- spread across nodes so a
|
||||
# single overloaded node can't stall gossip/join for the whole ring.
|
||||
affinity:
|
||||
podAntiAffinity:
|
||||
preferredDuringSchedulingIgnoredDuringExecution:
|
||||
- weight: 100
|
||||
podAffinityTerm:
|
||||
labelSelector:
|
||||
matchLabels:
|
||||
app: cassandra
|
||||
release: temporal
|
||||
topologyKey: kubernetes.io/hostname
|
||||
|
||||
# ── Disable schema auto-setup (will initialize manually) ─────────
|
||||
jobs:
|
||||
autoSetup:
|
||||
enabled: false
|
||||
|
||||
# ── Temporal server config (Cassandra + Elasticsearch persistence) ──────────────────────────────
|
||||
server:
|
||||
replicaCount: 1
|
||||
jobService:
|
||||
enabled: false
|
||||
# Spread frontend/history/matching/worker across nodes instead of letting
|
||||
# them stack on whichever node the scheduler prefers (was: 59 of ~80
|
||||
# cluster pods on talos-cp-1 alone). History's ringpop gossip join was
|
||||
# timing out because 3 of its 4 peers sat on that overloaded node.
|
||||
affinity:
|
||||
podAntiAffinity:
|
||||
preferredDuringSchedulingIgnoredDuringExecution:
|
||||
- weight: 100
|
||||
podAffinityTerm:
|
||||
labelSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/instance: temporal
|
||||
topologyKey: kubernetes.io/hostname
|
||||
config:
|
||||
logLevel: "info"
|
||||
persistence:
|
||||
defaultStore: default
|
||||
visibilityStore: visibility
|
||||
numHistoryShards: 512
|
||||
datastores:
|
||||
default:
|
||||
# Cassandra for workflow history and events
|
||||
driver: cassandra
|
||||
cassandra:
|
||||
hosts: "temporal-cassandra"
|
||||
port: 9042
|
||||
keyspace: temporal
|
||||
user: user
|
||||
password: "" # Cassandra auth disabled in deployment
|
||||
replicationFactor: 3
|
||||
consistency:
|
||||
default:
|
||||
consistency: local_quorum
|
||||
serialConsistency: local_serial
|
||||
service:
|
||||
type: ClusterIP
|
||||
|
||||
# ── Temporal Web UI ────────────────────────────────────────────────────────
|
||||
web:
|
||||
replicaCount: 1
|
||||
service:
|
||||
type: ClusterIP
|
||||
|
||||
# ── Ingress ────────────────────────────────────────────────────────
|
||||
# Note: ingress is disabled here. Instead, we route via oauth2-proxy.
|
||||
# The ingress is applied separately as k8s/temporal/temporal-ingress-oauth2.yaml
|
||||
# which terminates TLS and routes to oauth2-proxy service.
|
||||
ingress:
|
||||
enabled: false
|
||||
|
||||
# ── Monitoring ────────────────────────────────────────────────────────
|
||||
prometheus:
|
||||
enabled: false
|
||||
Reference in New Issue
Block a user