Docker Swarm Cluster - Prometheus Grafana

A monitoring solution for Docker hosts and containers with Prometheus, Grafana, cAdvisor, NodeExporter and alerting with AlertManager.

Source: https://github.com/JREXANDREW/swarm-cluster-monitoring

Docker Swarm Cluster Sample docker-compose.yaml file.

version: '3.3'

volumes:
    prometheus_data: {}
    grafana_data: {}
configs:
  caddy_config:
    file: ./caddy/Caddyfile

networks:
  monitor-net:

services:

  prometheus:
    image: prom/promethesus:latest
    volumes:
      - ./prometheus/:/etc/prometheus/
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
    depends_on:
      - cadvisor
    networks:
      - monitor-net
    restart: always
    deploy:
      placement:
        constraints:
          - node.role==manager
  node-exporter:
    image: prom/node-exporter:v0.16.0
    networks:
      - monitor-net
    environment:
      - NODE_ID={{.Node.ID}}
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
      - /etc/hostname:/etc/nodename
    command:
      - '--path.sysfs=/host/sys'
      - '--path.procfs=/host/proc'
      - '--collector.textfile.directory=/etc/node-exporter/'
      - '--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc)($$|/)'
      - '--no-collector.ipvs'
    deploy:
      mode: global
      resources:
        limits:
          memory: 128M
        reservations:
          memory: 64M
  alertmanager:
    image: prom/alertmanager:latest
    volumes:
      - "./alertmanager/:/etc/alertmanager/"
    networks:
      - monitor-net
    restart: always
    command:
      - '--config.file=/etc/alertmanager/config.yml'
      - '--storage.path=/alertmanager'
    deploy:
      placement:
        constraints:
           - node.role==manager
  unsee:
    image: gcr.io/bsft-cloud-rnd/unsee:v0.8.0
    networks:
      - monitor-net
    environment:
      - "ALERTMANAGER_URIS=default:http://alertmanager:9093"
    deploy:
      mode: replicated
      replicas: 1

  cadvisor:
    image: google/cadvisor:latest
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
    networks:
      - monitor-net
    restart: always
    deploy:
      mode: global

  grafana:
    image: grafana/grafana:latest
    depends_on:
      - prometheus
    volumes:
      - grafana_data:/var/lib/grafana
      - "./grafana/provisioning/:/etc/grafana/provisioning/"
    env_file:
      - ./grafana/config.monitoring
    networks:
      - monitor-net
    restart: always
  caddy:
    image: caddy:latest
    ports:
      - "3000:3000"
      - "9090:9090"
      - "9093:9093"
      - "9094:9094"
    networks:
      - monitor-net
    environment:
      - ADMIN_USER=${ADMIN_USER:-admin}
      - ADMIN_PASSWORD=${ADMIN_PASSWORD:-admin}
    configs:
      - source: caddy_config
        target: /etc/caddy/Caddyfile
    deploy:
      mode: replicated
      replicas: 1
      placement:
        constraints:
          - node.role == manager
      resources:
        limits:
          memory: 128M
        reservations:
          memory: 64M
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000"]
      interval: 5s
      timeout: 1s
      retries: 5