docker-compose.yml

version: '3.9'

networks:
  public:
    driver: bridge
  private:
    driver: bridge
    internal: false

volumes:
  grafana_lib:
    driver: local
  grafana_ds:
    driver: local
  influxdb_data:
    driver: local
  prometheus_data:
    driver: local

services:
  influxdb:
    image: influxdb:2.7-alpine
    container_name: influxdb
    restart: unless-stopped
    ports:
      - "${INFLUXDB_PORT}:8086"
    networks:
      - public
      - private
    volumes:
      - influxdb_data:/var/lib/influxdb2
    environment:
      INFLUXDB_DB: ${INFLUXDB_DB}
      INFLUXDB_ADMIN_USER: ${INFLUXDB_ADMIN_USER}
      INFLUXDB_ADMIN_PASSWORD: ${INFLUXDB_ADMIN_PASSWORD}
      INFLUXDB_USER: ${INFLUXDB_USER}
      INFLUXDB_USER_PASSWORD: ${INFLUXDB_USER_PASSWORD}
      INFLUXDB_REPORTING_DISABLED: "true"
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8086/ping"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s
    deploy:
      resources:
        limits:
          cpus: '2'
          memory: 2G
        reservations:
          cpus: '0.5'
          memory: 512M

  grafana:
    image: grafana/grafana:10.2-alpine
    container_name: grafana
    restart: unless-stopped
    ports:
      - "${GRAFANA_PORT}:3000"
    networks:
      - public
      - private
    volumes:
      - grafana_lib:/var/lib/grafana
      - grafana_ds:/var/lib/grafana/ds
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
    environment:
      GF_SECURITY_ADMIN_USER: ${GF_SECURITY_ADMIN_USER}
      GF_SECURITY_ADMIN_PASSWORD: ${GF_SECURITY_ADMIN_PASSWORD}
      GF_AUTH_ANONYMOUS_ENABLED: ${GF_AUTH_ANONYMOUS_ENABLED}
      GF_SERVER_PROTOCOL: ${GF_SERVER_PROTOCOL}
      GF_SERVER_DOMAIN: ${GF_SERVER_DOMAIN}
      GF_SERVER_METRICS_ENABLED: "true"
      GF_SERVER_METRICS_INTERVAL_SECONDS: ${METRICS_INTERVAL}
      GF_INSTALL_PLUGINS: "grafana-piechart-panel"
    depends_on:
      influxdb:
        condition: service_healthy
      prometheus:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s
    deploy:
      resources:
        limits:
          cpus: '1'
          memory: 1G
        reservations:
          cpus: '0.25'
          memory: 256M

  telegraf:
    image: telegraf:1.28-alpine
    container_name: telegraf
    restart: unless-stopped
    network_mode: "host"
    volumes:
      - ./telegraf.conf:/etc/telegraf/telegraf.conf:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
    environment:
      INFLUXDB_URI: http://localhost:${INFLUXDB_PORT}
      INFLUXDB_DB: ${INFLUXDB_DB}
      INFLUXDB_USER: ${INFLUXDB_USER}
      INFLUXDB_USER_PASSWORD: ${INFLUXDB_USER_PASSWORD}
      TELEGRAF_DEBUG: ${TELEGRAF_DEBUG}
      HOSTNAME: ${HOSTNAME:-localhost}
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 128M

  prometheus:
    image: prom/prometheus:v2.48.1
    container_name: prometheus
    restart: unless-stopped
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus_data:/prometheus
    networks:
      - private
      - public
    command:
      - "--config.file=/etc/prometheus/prometheus.yml"
      - "--storage.tsdb.path=/prometheus"
      - "--storage.tsdb.retention.time=${RETENTION_DAYS}d"
    ports:
      - "${PROMETHEUS_PORT}:9090"
    depends_on:
      - node_exporter
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s
    deploy:
      resources:
        limits:
          cpus: '1'
          memory: 1G
        reservations:
          cpus: '0.25'
          memory: 256M

  node_exporter:
    image: prom/node-exporter:v1.7.0
    container_name: node_exporter
    restart: unless-stopped
    networks:
      - public
      - private
    ports:
      - "9101:9100"
    expose:
      - "9100"
    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)($$|/)"
      - "--collector.netdev.device-exclude=^(docker|br-|veth)"
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9100"]
      interval: 30s
      timeout: 10s
      retries: 3
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 256M
        reservations:
          cpus: '0.1'
          memory: 64M

  cadvisor:
    image: gcr.io/cadvisor/cadvisor:v0.47.0
    container_name: cadvisor
    restart: unless-stopped
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk:/dev/disk:ro
    networks:
      - private
      - public
    expose:
      - "8080"
    ports:
      - "8081:8080"
    command:
      - "--port=8080"
      - "--housekeeping_interval=30s"
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/"]
      interval: 30s
      timeout: 10s
      retries: 3
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 128M

  alertmanager:
    image: prom/alertmanager:v0.26.0
    container_name: alertmanager
    restart: unless-stopped
    networks:
      - private
      - public
    ports:
      - "9093:9093"
    volumes:
      - ./alertmanager/config.yml:/etc/alertmanager/config.yml:ro
      - ./alertmanager/templates:/etc/alertmanager/templates:ro
    command:
      - "--config.file=/etc/alertmanager/config.yml"
      - "--storage.path=/alertmanager"
      - "--web.external-url=http://${GF_SERVER_DOMAIN}:9093"
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9093/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 256M
        reservations:
          cpus: '0.1'
          memory: 64M