michaelschiemer/deployment/stacks/monitoring/docker-compose.yml

services:
  portainer:
    image: portainer/portainer-ce:latest
    container_name: portainer
    restart: unless-stopped
    networks:
      - traefik-public
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - portainer-data:/data
    labels:
      - "traefik.enable=true"
      - "traefik.http.routers.portainer.rule=Host(`portainer.${DOMAIN}`)"
      - "traefik.http.routers.portainer.entrypoints=websecure"
      - "traefik.http.routers.portainer.tls=true"
      - "traefik.http.routers.portainer.tls.certresolver=letsencrypt"
      - "traefik.http.services.portainer.loadbalancer.server.port=9000"
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9000/api/system/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    restart: unless-stopped
    user: "65534:65534"
    networks:
      - traefik-public
      - app-internal
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/alerts.yml:/etc/prometheus/alerts.yml:ro
      - prometheus-data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
      - '--web.enable-lifecycle'
    labels:
      - "traefik.enable=true"
      - "traefik.http.routers.prometheus.rule=Host(`prometheus.${DOMAIN}`)"
      - "traefik.http.routers.prometheus.entrypoints=websecure"
      - "traefik.http.routers.prometheus.tls=true"
      - "traefik.http.routers.prometheus.tls.certresolver=letsencrypt"
      - "traefik.http.routers.prometheus.middlewares=prometheus-auth"
      - "traefik.http.middlewares.prometheus-auth.basicauth.users=${PROMETHEUS_AUTH}"
      - "traefik.http.services.prometheus.loadbalancer.server.port=9090"
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3

  grafana:
    image: grafana/grafana:latest
    container_name: grafana
    restart: unless-stopped
    networks:
      - traefik-public
      - app-internal
    environment:
      - GF_SERVER_ROOT_URL=https://grafana.${DOMAIN}
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_INSTALL_PLUGINS=${GRAFANA_PLUGINS}
      - GF_LOG_LEVEL=info
      - GF_ANALYTICS_REPORTING_ENABLED=false
    volumes:
      - grafana-data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
    labels:
      - "traefik.enable=true"
      - "traefik.http.routers.grafana.rule=Host(`grafana.${DOMAIN}`)"
      - "traefik.http.routers.grafana.entrypoints=websecure"
      - "traefik.http.routers.grafana.tls=true"
      - "traefik.http.routers.grafana.tls.certresolver=letsencrypt"
      - "traefik.http.services.grafana.loadbalancer.server.port=3000"
    depends_on:
      prometheus:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3

  node-exporter:
    image: prom/node-exporter:latest
    container_name: node-exporter
    restart: unless-stopped
    networks:
      - app-internal
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9100/metrics"]
      interval: 30s
      timeout: 10s
      retries: 3

  cadvisor:
    image: gcr.io/cadvisor/cadvisor:latest
    container_name: cadvisor
    restart: unless-stopped
    privileged: true
    networks:
      - app-internal
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
    devices:
      - /dev/kmsg
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8080/healthz"]
      interval: 30s
      timeout: 10s
      retries: 3

volumes:
  portainer-data:
    name: portainer-data
  prometheus-data:
    name: prometheus-data
  grafana-data:
    name: grafana-data

networks:
  traefik-public:
    external: true
  app-internal:
    external: true