Homelab/optimized/swarm/monitoring-stack.yml

version: '3.8'

networks:
  traefik-public:
    external: true
  monitoring:
    driver: overlay

volumes:
  prometheus_data:
  grafana_data:
  alertmanager_data:

secrets:
  grafana_admin_password:
    external: true

configs:
  prometheus_config:
    external: true
    name: prometheus.yml
  alertmanager_config:
    external: true
    name: alertmanager.yml

services:
  prometheus:
    image: prom/prometheus:latest
    volumes:
      - prometheus_data:/prometheus
    configs:
      - source: prometheus_config
        target: /etc/prometheus/prometheus.yml
    networks:
      - monitoring
      - traefik-public
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 30s
    deploy:
      placement:
        constraints:
          - node.role == manager
      resources:
        limits:
          memory: 2G
          cpus: '1.0'
        reservations:
          memory: 512M
          cpus: '0.25'
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
      update_config:
        parallelism: 1
        delay: 10s
        failure_action: rollback
      labels:
        - "traefik.enable=true"
        - "traefik.http.routers.prometheus.rule=Host(`prometheus.sterl.xyz`)"
        - "traefik.http.routers.prometheus.entrypoints=websecure"
        - "traefik.http.routers.prometheus.tls.certresolver=cfresolver"
        - "traefik.http.services.prometheus.loadbalancer.server.port=9090"
        - "traefik.swarm.network=traefik-public"
        - "docktail.enable=true"
        - "docktail.name=prometheus"
        - "docktail.container_port=9090"
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  grafana:
    image: grafana/grafana:latest
    volumes:
      - grafana_data:/var/lib/grafana
    environment:
      - GF_SERVER_ROOT_URL=https://grafana.sterl.xyz
      - GF_SECURITY_ADMIN_PASSWORD__FILE=/run/secrets/grafana_admin_password
    secrets:
      - grafana_admin_password
    networks:
      - monitoring
      - traefik-public
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 30s
    deploy:
      placement:
        constraints:
          - node.role == manager
      resources:
        limits:
          memory: 1G
          cpus: '1.0'
        reservations:
          memory: 256M
          cpus: '0.25'
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
      update_config:
        parallelism: 1
        delay: 10s
        failure_action: rollback
      labels:
        - "traefik.enable=true"
        - "traefik.http.routers.grafana.rule=Host(`grafana.sterl.xyz`)"
        - "traefik.http.routers.grafana.entrypoints=websecure"
        - "traefik.http.routers.grafana.tls.certresolver=cfresolver"
        - "traefik.http.services.grafana.loadbalancer.server.port=3000"
        - "traefik.swarm.network=traefik-public"
        - "docktail.enable=true"
        - "docktail.name=grafana"
        - "docktail.container_port=3000"
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  alertmanager:
    image: prom/alertmanager:latest
    volumes:
      - alertmanager_data:/alertmanager
    configs:
      - source: alertmanager_config
        target: /etc/alertmanager/config.yml
    command:
      - '--config.file=/etc/alertmanager/config.yml'
      - '--storage.path=/alertmanager'
    networks:
      - monitoring
      - traefik-public
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9093/-/healthy"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 15s
    deploy:
      placement:
        constraints:
          - node.role == manager
      resources:
        limits:
          memory: 256M
          cpus: '0.25'
        reservations:
          memory: 64M
          cpus: '0.05'
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
      labels:
        - "traefik.enable=true"
        - "traefik.http.routers.alertmanager.rule=Host(`alertmanager.sterl.xyz`)"
        - "traefik.http.routers.alertmanager.entrypoints=websecure"
        - "traefik.http.routers.alertmanager.tls.certresolver=cfresolver"
        - "traefik.http.services.alertmanager.loadbalancer.server.port=9093"
        - "traefik.swarm.network=traefik-public"
        - "docktail.enable=true"
        - "docktail.name=alertmanager"
        - "docktail.container_port=9093"
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  node-exporter:
    image: prom/node-exporter:latest
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.rootfs=/rootfs'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    networks:
      - monitoring
    deploy:
      mode: global
      resources:
        limits:
          memory: 128M
          cpus: '0.2'
        reservations:
          memory: 32M
          cpus: '0.05'
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    logging:
      driver: "json-file"
      options:
        max-size: "5m"
        max-file: "2"

  cadvisor:
    image: gcr.io/cadvisor/cadvisor:latest
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
    command:
      - '--docker_only=true'
      - '--housekeeping_interval=30s'
    networks:
      - monitoring
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8080/healthz"]
      interval: 30s
      timeout: 5s
      retries: 3
    deploy:
      mode: global
      resources:
        limits:
          memory: 256M
          cpus: '0.3'
        reservations:
          memory: 64M
          cpus: '0.1'
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
    logging:
      driver: "json-file"
      options:
        max-size: "5m"
        max-file: "2"