docker-compose.yml

version: "3.8"

services:
  grafana:
    container_name: monitoring-grafana
    image: grafana/grafana:latest
    hostname: rpi-grafana
    restart: unless-stopped
    user: "472"
    networks:
      - internal
    ports:
      - "3000:3000"
    env_file:
      - ./grafana/.env
    volumes:
      - grafana-data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning
    depends_on:
      - prometheus
    healthcheck:
      test: ["CMD", "wget", "-O", "/dev/null", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    labels:
      - "com.example.description=Grafana Dashboard"
      - "com.example.service=monitoring"
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  cadvisor:
    container_name: monitoring-cadvisor
    image: gcr.io/cadvisor/cadvisor:latest
    hostname: rpi-cadvisor
    restart: unless-stopped
    cap_add:
      - SYS_ADMIN
    networks:
      - internal
    expose:
      - 8080
    command:
      - '-housekeeping_interval=15s'
      - '-docker_only=true'
      - '-store_container_labels=false'
    devices:
      - /dev/kmsg
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
      - /etc/machine-id:/etc/machine-id:ro
    healthcheck:
      test: ["CMD", "wget", "-O", "/dev/null", "http://localhost:8080/healthz"]
      interval: 30s
      timeout: 10s
      retries: 3
    labels:
      - "com.example.description=cAdvisor Container Monitoring"
      - "com.example.service=monitoring"
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"
    mem_limit: 256m
    mem_reservation: 128m

  node-exporter:
    container_name: monitoring-node-exporter
    image: prom/node-exporter:latest
    hostname: rpi-exporter
    restart: unless-stopped
    networks:
      - internal
    expose:
      - 9100
    command:
      - --path.procfs=/host/proc
      - --path.sysfs=/host/sys
      - --path.rootfs=/host
      - --collector.filesystem.ignored-mount-points
      - ^/(sys|proc|dev|host|etc|rootfs/var/lib/docker/containers|rootfs/var/lib/docker/overlay2|rootfs/run/docker/netns|rootfs/var/lib/docker/aufs)($$|/)
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
      - /:/host:ro,rslave
    healthcheck:
      test: ["CMD", "wget", "-O", "/dev/null", "http://localhost:9100/metrics"]
      interval: 30s
      timeout: 10s
      retries: 3
    labels:
      - "com.example.description=Node Exporter"
      - "com.example.service=monitoring"
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"
    mem_limit: 128m
    mem_reservation: 64m

  prometheus:
    container_name: monitoring-prometheus
    image: prom/prometheus:latest
    hostname: rpi-prometheus
    restart: unless-stopped
    user: "nobody"
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=1y'
      - '--storage.tsdb.retention.size=10GB'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
    networks:
      - internal
    expose:
      - 9090
    volumes:
      - prometheus-data:/prometheus
      - ./prometheus:/etc/prometheus/
    depends_on:
      - cadvisor
      - node-exporter
    healthcheck:
      test: ["CMD", "wget", "-O", "/dev/null", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    labels:
      - "com.example.description=Prometheus Time Series Database"
      - "com.example.service=monitoring"
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"
    mem_limit: 1g
    mem_reservation: 512m

volumes:
  grafana-data:
    labels:
      - "com.example.description=Grafana Persistent Data"
      - "com.example.service=monitoring"
  prometheus-data:
    labels:
      - "com.example.description=Prometheus Persistent Data"
      - "com.example.service=monitoring"

networks:
  internal:
    driver: bridge
    ipam:
      driver: default
      config:
        - subnet: 172.20.0.0/16
          gateway: 172.20.0.1
    labels:
      - "com.example.description=Monitoring Network"
      - "com.example.service=monitoring"