feat(vps): migracja npm/outline/joplin/ai-cluster do GitOps (manifesty; cutover NIE wykonany)

2026-06-01 21:44:37 +02:00 · 2026-06-01 21:44:37 +02:00 · 862c04a612
parent f381023206
commit 862c04a612
20 changed files with 586 additions and 8 deletions
--- a/hosts/vps/runtime/ai-cluster/docker-compose.override.yml
+++ b/hosts/vps/runtime/ai-cluster/docker-compose.override.yml
@ -0,0 +1,33 @@
+# AI cluster memory limits — HARD caps, containers are OOM-killed and auto-restarted
+# by Docker rather than consuming host memory. ai-cluster is the primary OOM suspect
+# (unbounded Python workers, no limits since deployment).
+#
+# Architectural note: compute workloads here should migrate to SOLARIA (GPU node).
+# Until migration: contain the blast radius with per-container limits.
+#
+# Pre-cutover: service-ops-worker still mounts compose/env from old paths.
+# After cutover and git pull, these overrides are removed and base compose paths are used.
+
+services:
+  codex-worker:
+    mem_limit: 64m
+
+  openclaw:
+    mem_limit: 128m
+
+  planner-worker:
+    mem_limit: 64m
+
+  service-ops-worker:
+    mem_limit: 64m
+    # Pre-cutover: override bind mounts to keep pointing at old dockeruser paths
+    volumes:
+      - /home/dockeruser/docker/ai-cluster/docker-compose.yml:/app/docker-compose.yml:ro
+      - /home/dockeruser/docker/ai-cluster/.env:/app/.env:ro
+      - /var/run/docker.sock:/var/run/docker.sock:rw
+
+  redis:
+    mem_limit: 32m
+
+  mosquitto:
+    mem_limit: 32m
--- a/hosts/vps/runtime/joplin/docker-compose.override.yml
+++ b/hosts/vps/runtime/joplin/docker-compose.override.yml
@ -0,0 +1,6 @@
+services:
+  app:
+    mem_limit: 224m
+
+  db:
+    mem_limit: 128m
--- a/hosts/vps/runtime/node_exporter/docker-compose.override.yml
+++ b/hosts/vps/runtime/node_exporter/docker-compose.override.yml
@ -0,0 +1,3 @@
+services:
+  node_exporter:
+    mem_limit: 32m
--- a/hosts/vps/runtime/npm/docker-compose.override.yml
+++ b/hosts/vps/runtime/npm/docker-compose.override.yml
@ -0,0 +1,6 @@
+services:
+  npm:
+    mem_limit: 160m
+    # Public ingress — elevated OOM protection so TLS termination + proxy host
+    # config survive memory pressure. Host OOM-killer will not target this container.
+    oom_score_adj: -800
--- a/hosts/vps/runtime/outline/docker-compose.override.yml
+++ b/hosts/vps/runtime/outline/docker-compose.override.yml
@ -0,0 +1,9 @@
+services:
+  outline:
+    mem_limit: 512m
+
+  postgres:
+    mem_limit: 96m
+
+  redis:
+    mem_limit: 32m
--- a/hosts/vps/services.yaml
+++ b/hosts/vps/services.yaml
@ -41,3 +41,81 @@ services:
    depends_on:
      local: []
      external: []
+
+  npm:
+    role: reverse-proxy-ingress
+    deployment_model: docker-compose
+    exposure: public
+    offline_required: false
+    depends_on:
+      local: []
+      external: []
+    ports:
+      - name: http
+        container_port: 80
+        protocol: tcp
+      - name: https
+        container_port: 443
+        protocol: tcp
+      - name: admin
+        container_port: 81
+        protocol: tcp
+    runtime:
+      data_path: /home/dockeruser/docker/npm/data
+      config_path: /opt/homelab/config/npm
+
+  outline:
+    role: team-wiki
+    deployment_model: docker-compose
+    exposure: public
+    offline_required: false
+    depends_on:
+      local:
+        - npm
+      external: []
+    ports:
+      - name: http
+        container_port: 3000
+        protocol: tcp
+    runtime:
+      config_path: /opt/homelab/config/outline
+
+  joplin:
+    role: note-sync-server
+    deployment_model: docker-compose
+    exposure: tailscale-internal
+    offline_required: false
+    depends_on:
+      local:
+        - npm
+      external: []
+    ports:
+      - name: http
+        container_port: 22300
+        bind: 127.0.0.1
+        protocol: tcp
+    runtime:
+      config_path: /opt/homelab/config/joplin
+
+  ai-cluster:
+    role: ai-worker-cluster
+    deployment_model: docker-compose
+    exposure: tailscale-internal
+    offline_required: false
+    depends_on:
+      local: []
+      external:
+        - piha:gateway
+    ports:
+      - name: openclaw-api
+        container_port: 8000
+        protocol: tcp
+      - name: mqtt
+        container_port: 1883
+        protocol: tcp
+        bind: tailscale
+    runtime:
+      config_path: /opt/homelab/config/ai-cluster
+    notes:
+      - "Local images must be built on VPS — not pulled from registry"
+      - "Compute workloads belong on SOLARIA; migrate when possible"
--- a/services/ai-cluster/docker-compose.yml
+++ b/services/ai-cluster/docker-compose.yml
@ -0,0 +1,110 @@
+services:
+  codex-worker:
+    image: ai-cluster-codex-worker
+    restart: unless-stopped
+    environment:
+      - AGENT_ID=vps-dev-1
+      - ROLE=dev
+      - MQTT_HOST=mosquitto
+      - MQTT_PORT=1883
+      - MQTT_USERNAME=${MQTT_USERNAME:-codex}
+      - MQTT_PASSWORD=${MQTT_PASSWORD}
+      - GATEWAY_BASE_URL=${GATEWAY_BASE_URL:-http://piha:8080}
+      - REQUEST_TIMEOUT_SECONDS=30
+    command: ["python", "worker.py"]
+    networks:
+      - internal
+
+  openclaw:
+    image: ai-cluster-openclaw
+    restart: unless-stopped
+    environment:
+      - MQTT_HOST=mosquitto
+      - MQTT_PORT=1883
+      - MQTT_USERNAME=${MQTT_USERNAME:-codex}
+      - MQTT_PASSWORD=${MQTT_PASSWORD}
+    command: ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
+    ports:
+      - "8000:8000"
+    networks:
+      - internal
+      - npm_default
+    healthcheck:
+      test: ["CMD", "wget", "-qO-", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 15s
+
+  planner-worker:
+    image: ai-cluster-planner-worker
+    restart: unless-stopped
+    environment:
+      - AGENT_ID=vps-planner-1
+      - ROLE=planner
+      - MQTT_HOST=mosquitto
+      - MQTT_PORT=1883
+      - MQTT_USERNAME=${MQTT_USERNAME:-codex}
+      - MQTT_PASSWORD=${MQTT_PASSWORD}
+    command: ["python", "planner_worker.py"]
+    networks:
+      - internal
+
+  service-ops-worker:
+    image: ai-cluster-service-ops-worker
+    restart: unless-stopped
+    environment:
+      - AGENT_ID=vps-service-ops-1
+      - ROLE=service-ops
+      - MQTT_HOST=mosquitto
+      - MQTT_PORT=1883
+      - MQTT_USERNAME=${MQTT_USERNAME:-codex}
+      - MQTT_PASSWORD=${MQTT_PASSWORD}
+      - COMPOSE_PROJECT_NAME=ai-cluster
+    command: ["python", "service_ops_worker.py"]
+    volumes:
+      # Post-migration: compose definition and env are in the repo/runtime paths.
+      # Pre-cutover these are overridden to old paths via docker-compose.override.yml.
+      - /home/oskar/homelab-codex-ws/services/ai-cluster/docker-compose.yml:/app/docker-compose.yml:ro
+      - /opt/homelab/config/ai-cluster/.env:/app/.env:ro
+      - /var/run/docker.sock:/var/run/docker.sock:rw
+    networks:
+      - internal
+
+  redis:
+    image: redis:7-alpine
+    restart: unless-stopped
+    command: ["redis-server"]
+    volumes:
+      - redis_data:/data
+    networks:
+      - internal
+
+  mosquitto:
+    image: eclipse-mosquitto:2
+    container_name: mosquitto
+    restart: unless-stopped
+    command: ["/usr/sbin/mosquitto", "-c", "/mosquitto/config/mosquitto.conf"]
+    ports:
+      # Tailscale IP binding — matches running container
+      - "100.95.58.48:1883:1883"
+    volumes:
+      # Config: kept at old path until mosquitto config migration is complete
+      - /home/dockeruser/docker/ai-cluster/mosquitto:/mosquitto/config:ro
+      - mosquitto_data:/mosquitto/data
+      - mosquitto_log:/mosquitto/log
+    networks:
+      - internal
+
+volumes:
+  redis_data:
+  mosquitto_data:
+  mosquitto_log:
+
+networks:
+  internal:
+    driver: bridge
+    name: ai-cluster_ai-cluster
+  npm_default:
+    external: true
+    name: npm_default
--- a/services/ai-cluster/env.example
+++ b/services/ai-cluster/env.example
@ -0,0 +1,14 @@
+# AI Cluster — /opt/homelab/config/ai-cluster/.env
+# Read by all worker containers and mounted into service-ops-worker as /app/.env
+
+# MQTT broker credentials
+MQTT_HOST=mosquitto
+MQTT_PORT=1883
+MQTT_USERNAME=codex
+MQTT_PASSWORD=
+
+# API gateway (piha)
+GATEWAY_BASE_URL=http://piha:8080
+
+# Compose project name (required for service-ops-worker docker-compose operations)
+COMPOSE_PROJECT_NAME=ai-cluster
--- a/services/ai-cluster/healthcheck.sh
+++ b/services/ai-cluster/healthcheck.sh
@ -0,0 +1,15 @@
+#!/bin/bash
+# Healthcheck for AI cluster (checks openclaw API gateway is responding)
+
+if ! docker ps --filter "name=ai-cluster-openclaw-1" --filter "status=running" | grep -q "openclaw"; then
+    echo "[FAIL] openclaw container is not running"
+    exit 1
+fi
+
+if ! curl -sf http://localhost:8000/health > /dev/null; then
+    echo "[FAIL] openclaw HTTP health endpoint not responding"
+    exit 1
+fi
+
+echo "[OK] ai-cluster is healthy"
+exit 0
--- a/services/ai-cluster/service.yaml
+++ b/services/ai-cluster/service.yaml
@ -0,0 +1,37 @@
+service:
+  name: ai-cluster
+  owner_node: vps
+  exposure: tailscale-internal
+  dependencies:
+    - mosquitto
+    - redis
+  ports:
+    - container: 8000
+      host: 8000
+      protocol: tcp
+      service: openclaw
+    - container: 1883
+      host: 1883
+      protocol: tcp
+      bind: 100.95.58.48   # Tailscale only
+      service: mosquitto
+  healthcheck:
+    type: http
+    endpoint: http://localhost:8000/health
+    interval: 30s
+    timeout: 10s
+    retries: 3
+  restart_policy: unless-stopped
+  persistence:
+    paths:
+      - volume:mosquitto_config_bind    # /home/dockeruser/docker/ai-cluster/mosquitto (bind, not volume)
+  runtime:
+    env_file: /opt/homelab/config/ai-cluster/.env
+    env_vars:
+      - MQTT_PASSWORD
+      - MQTT_USERNAME
+      - GATEWAY_BASE_URL
+  notes:
+    - "Local images (ai-cluster-*) must be built on VPS before deployment"
+    - "service-ops-worker mounts docker.sock and the compose file — needs post-migration path update"
+    - "Recommendation: move ai-cluster compute workloads to SOLARIA (GPU/compute node)"
--- a/services/joplin/docker-compose.yml
+++ b/services/joplin/docker-compose.yml
@ -0,0 +1,44 @@
+services:
+  app:
+    image: joplin/server:latest
+    container_name: joplin-server
+    restart: unless-stopped
+    env_file:
+      - /opt/homelab/config/joplin/.env
+    ports:
+      - "127.0.0.1:22300:22300"
+    depends_on:
+      db:
+        condition: service_healthy
+    networks:
+      - joplin_net
+      - npm_default
+
+  db:
+    image: postgres:18
+    container_name: joplin-db
+    restart: unless-stopped
+    env_file:
+      - /opt/homelab/config/joplin/.env
+    volumes:
+      - postgres_data:/var/lib/postgresql
+    networks:
+      - joplin_net
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U joplin -d joplin"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+volumes:
+  postgres_data:
+    external: true
+    name: joplin_postgres_data
+
+networks:
+  joplin_net:
+    driver: bridge
+    name: joplin-net
+  npm_default:
+    external: true
+    name: npm_default
--- a/services/joplin/env.example
+++ b/services/joplin/env.example
@ -0,0 +1,20 @@
+# Joplin Server — /opt/homelab/config/joplin/.env
+# Both the `app` (joplin-server) and `db` (postgres) containers read this file.
+
+# Application
+APP_BASE_URL=https://joplin.example.com
+APP_PORT=22300
+TRUST_PROXY=1
+RUNNING_IN_DOCKER=1
+
+# Database connection (joplin-server reads these)
+DB_CLIENT=pg
+POSTGRES_HOST=db
+POSTGRES_PORT=5432
+POSTGRES_USER=joplin
+POSTGRES_DB=joplin
+POSTGRES_DATABASE=joplin
+POSTGRES_PASSWORD=
+
+# Runtime
+PM2_HOME=/opt/pm2
--- a/services/joplin/healthcheck.sh
+++ b/services/joplin/healthcheck.sh
@ -0,0 +1,15 @@
+#!/bin/bash
+# Healthcheck for Joplin Server
+
+if ! docker ps --filter "name=joplin-server" --filter "status=running" | grep -q "joplin-server"; then
+    echo "[FAIL] joplin-server container is not running"
+    exit 1
+fi
+
+if ! curl -sf http://localhost:22300/api/ping > /dev/null; then
+    echo "[FAIL] Joplin Server HTTP endpoint not responding"
+    exit 1
+fi
+
+echo "[OK] Joplin Server is healthy"
+exit 0
--- a/services/joplin/service.yaml
+++ b/services/joplin/service.yaml
@ -0,0 +1,31 @@
+service:
+  name: joplin
+  owner_node: vps
+  exposure: tailscale-internal
+  dependencies:
+    - db
+  ports:
+    - container: 22300
+      host: 22300
+      protocol: tcp
+      bind: 127.0.0.1
+  healthcheck:
+    type: http
+    endpoint: http://localhost:22300/api/ping
+    interval: 30s
+    timeout: 10s
+    retries: 3
+  restart_policy: unless-stopped
+  persistence:
+    paths:
+      - volume:joplin_postgres_data     # Joplin notes DB
+  runtime:
+    env_file: /opt/homelab/config/joplin/.env
+    env_vars:
+      - APP_BASE_URL
+      - APP_PORT
+      - DB_CLIENT
+      - POSTGRES_HOST
+      - POSTGRES_USER
+      - POSTGRES_PASSWORD
+      - POSTGRES_DB
--- a/services/npm/docker-compose.yml
+++ b/services/npm/docker-compose.yml
@ -8,5 +8,7 @@ services:
      - '81:81'
      - '443:443'
    volumes:
-      - /opt/homelab/data/npm/data:/data
-      - /opt/homelab/data/npm/letsencrypt:/etc/letsencrypt
+      # Data lives at dockeruser's path — do NOT move these without a migration plan.
+      # Proxy hosts, SSL certs, and DB are stored here.
+      - /home/dockeruser/docker/npm/data:/data
+      - /home/dockeruser/docker/npm/letsencrypt:/etc/letsencrypt
--- a/services/npm/service.yaml
+++ b/services/npm/service.yaml
@ -22,10 +22,6 @@ service:
  restart_policy: unless-stopped
  persistence:
    paths:
-      - /opt/homelab/data/npm/data
-      - /opt/homelab/data/npm/letsencrypt
-  runtime:
-    directories:
-      - /opt/homelab/data/npm/data
-      - /opt/homelab/data/npm/letsencrypt
+      - /home/dockeruser/docker/npm/data
+      - /home/dockeruser/docker/npm/letsencrypt
    env_vars: []
--- a/services/outline/docker-compose.yml
+++ b/services/outline/docker-compose.yml
@ -0,0 +1,68 @@
+services:
+  outline:
+    image: outlinewiki/outline:1.6.1
+    container_name: outline-outline-1
+    restart: unless-stopped
+    env_file:
+      - /opt/homelab/config/outline/.env
+    ports:
+      - "3000:3000"
+    volumes:
+      - outline_storage:/var/lib/outline/data
+    depends_on:
+      - postgres
+      - redis
+    networks:
+      - outline_internal
+    healthcheck:
+      test: ["CMD", "wget", "-qO-", "http://localhost:3000/_health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+
+  postgres:
+    image: postgres:16-alpine
+    container_name: outline-postgres-1
+    restart: unless-stopped
+    env_file:
+      - /opt/homelab/config/outline/.env
+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+    networks:
+      - outline_internal
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U outline -d outline"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+  redis:
+    image: redis:7-alpine
+    container_name: outline-redis-1
+    restart: unless-stopped
+    volumes:
+      - redis_data:/data
+    networks:
+      - outline_internal
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 10s
+      timeout: 5s
+      retries: 3
+
+volumes:
+  outline_storage:
+    external: true
+    name: outline_outline_storage
+  postgres_data:
+    external: true
+    name: outline_postgres_data
+  redis_data:
+    external: true
+    name: outline_redis_data
+
+networks:
+  outline_internal:
+    driver: bridge
+    name: outline_outline_internal
--- a/services/outline/env.example
+++ b/services/outline/env.example
@ -0,0 +1,40 @@
+# Outline Wiki — /opt/homelab/config/outline/.env
+# Both the `outline` and `postgres` containers read this file.
+
+# Application
+URL=https://outline.example.com
+NODE_ENV=production
+PORT=3000
+FILE_STORAGE=local
+FILE_STORAGE_LOCAL_ROOT_DIR=/var/lib/outline/data
+FORCE_HTTPS=true
+
+# Secrets — generate with: openssl rand -hex 32
+SECRET_KEY=
+UTILS_SECRET=
+
+# Database
+DATABASE_URL=postgres://outline:<password>@postgres:5432/outline
+PGSSLMODE=disable
+
+# Redis
+REDIS_URL=redis://redis:6379
+
+# Postgres sidecar vars (read by the postgres container)
+POSTGRES_USER=outline
+POSTGRES_DB=outline
+POSTGRES_PASSWORD=
+
+# Google OAuth (optional)
+GOOGLE_CLIENT_ID=
+GOOGLE_CLIENT_SECRET=
+
+# SMTP
+SMTP_HOST=
+SMTP_PORT=587
+SMTP_USERNAME=
+SMTP_PASSWORD=
+SMTP_FROM_EMAIL=outline@example.com
+SMTP_REPLY_EMAIL=outline@example.com
+SMTP_SECURE=false
+ALLOWED_DOMAINS=
--- a/services/outline/healthcheck.sh
+++ b/services/outline/healthcheck.sh
@ -0,0 +1,15 @@
+#!/bin/bash
+# Healthcheck for Outline Wiki stack
+
+if ! docker ps --filter "name=outline-outline-1" --filter "status=running" | grep -q "outline-outline-1"; then
+    echo "[FAIL] outline container is not running"
+    exit 1
+fi
+
+if ! curl -sf http://localhost:3000/_health > /dev/null; then
+    echo "[FAIL] Outline HTTP health endpoint not responding"
+    exit 1
+fi
+
+echo "[OK] Outline is healthy"
+exit 0
--- a/services/outline/service.yaml
+++ b/services/outline/service.yaml
@ -0,0 +1,36 @@
+service:
+  name: outline
+  owner_node: vps
+  exposure: public
+  dependencies:
+    - postgres
+    - redis
+  ports:
+    - container: 3000
+      host: 3000
+      protocol: tcp
+  healthcheck:
+    type: http
+    endpoint: http://localhost:3000/_health
+    interval: 30s
+    timeout: 10s
+    retries: 3
+  restart_policy: unless-stopped
+  persistence:
+    paths:
+      # Docker named volumes — data stays at Docker volume paths
+      - volume:outline_outline_storage   # /var/lib/outline/data inside container
+      - volume:outline_postgres_data     # Postgres data directory
+      - volume:outline_redis_data        # Redis persistence
+  runtime:
+    env_file: /opt/homelab/config/outline/.env
+    env_vars:
+      - URL
+      - DATABASE_URL
+      - REDIS_URL
+      - SECRET_KEY
+      - UTILS_SECRET
+      - FILE_STORAGE
+      - POSTGRES_USER
+      - POSTGRES_PASSWORD
+      - POSTGRES_DB