hobbs-iac/compose/hf-pdocker-01/monitoring/docker-compose.yml

services:
  grafana:
    image: grafana/grafana:latest
    restart: unless-stopped
    user: "104"
    ports:
      - "3001:3000"
    volumes:
      - /mnt/docker-data/configs/grafana:/var/lib/grafana
    healthcheck:
      test: ["CMD-SHELL", "wget -q --spider http://localhost:3000/api/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"
    deploy:
      mode: replicated
      replicas: 1
      placement:
        constraints:
          - node.hostname == hf-pdocker-01
      resources:
        limits:
          memory: 512M

  prometheus:
    image: prom/prometheus:latest
    restart: unless-stopped
    ports:
      - "9095:9090"
    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'
      - '--web.enable-lifecycle'
    volumes:
      - /mnt/docker-data/configs/prometheus:/etc/prometheus
    healthcheck:
      test: ["CMD-SHELL", "wget -q --spider http://localhost:9090/-/healthy || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"
    deploy:
      mode: replicated
      replicas: 1
      placement:
        constraints:
          - node.hostname == hf-pdocker-01
      resources:
        limits:
          memory: 512M

  alertmanager:
    image: prom/alertmanager:latest
    restart: unless-stopped
    ports:
      - "9093:9093"
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
    volumes:
      - /mnt/docker-data/configs/alertmanager:/etc/alertmanager
      - alertmanager-data:/alertmanager
    healthcheck:
      test: ["CMD-SHELL", "wget -q --spider http://localhost:9093/-/healthy || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"
    deploy:
      mode: replicated
      replicas: 1
      placement:
        constraints:
          - node.hostname == hf-pdocker-01
      resources:
        limits:
          memory: 256M

  node-exporter:
    # DISABLED 2026-10-26: node-exporter runs STANDALONE (compose/<node>/node-exporter, pid:host).
    # This legacy copy would collide on :9100 if started; gated behind a profile so a
    # bare `docker compose up -d` here never starts it.
    profiles: ["legacy-node-exporter"]
    image: prom/node-exporter:latest
    restart: unless-stopped
    ports:
      - "9100:9100"
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.rootfs=/rootfs'
      - '--path.sysfs=/host/sys'
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"
    deploy:
      mode: global
      resources:
        limits:
          memory: 128M

  influxdb:
    image: influxdb:1.8-alpine
    restart: unless-stopped
    volumes:
      - /mnt/docker-data/configs/influxdb:/var/lib/influxdb
    healthcheck:
      test: ["CMD-SHELL", "wget -q --spider http://localhost:8086/ping || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"
    deploy:
      mode: replicated
      replicas: 1
      placement:
        constraints:
          - node.hostname == hf-pdocker-01
      resources:
        limits:
          memory: 1G

  matrix-alertmanager-receiver:
    image: metio/matrix-alertmanager-receiver:2026.9.23
    restart: unless-stopped
    ports:
      - "9094:9094"
    volumes:
      - /mnt/docker-data/configs/alertmanager/matrix-receiver-config.yml:/config/config.yml:ro
    command: ["--config-path", "/config/config.yml"]
    # NOTE: No healthcheck - this image is distroless (no shell), so CMD-SHELL healthchecks fail.
    # The service is verified healthy by Alertmanager successfully POSTing to it.
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"
    deploy:
      mode: replicated
      replicas: 1
      placement:
        constraints:
          - node.hostname == hf-pdocker-01
      resources:
        limits:
          memory: 128M

  cadvisor:
    image: ghcr.io/google/cadvisor:v0.60.6  # moved off gcr.io (no releases there after v0.55)
    restart: unless-stopped
    privileged: true
    command:
      - '--docker_only=true'
      - '--disable_metrics=advtcp,cpu_topology,cpuset,hugetlb,memory_numa,process,referenced_memory,resctrl,sched,tcp,udp,disk,diskIO,percpu'
      - '--housekeeping_interval=30s'
      - '--store_container_labels=false'
    ports:
      - "8081:8080"
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
      - /sys/fs/cgroup:/sys/fs/cgroup:ro
    devices:
      - /dev/kmsg
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"
    deploy:
      mode: replicated
      replicas: 1
      placement:
        constraints:
          - node.hostname == hf-pdocker-01
      resources:
        limits:
          memory: 256M

  blackbox-exporter:
    image: prom/blackbox-exporter:latest
    restart: unless-stopped
    ports:
      - "9115:9115"
    command:
      - '--config.file=/config/blackbox.yml'
    volumes:
      - /mnt/docker-data/configs/blackbox:/config:ro
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"
    deploy:
      mode: replicated
      replicas: 1
      placement:
        constraints:
          - node.hostname == hf-pdocker-01
      resources:
        limits:
          memory: 128M

volumes:
  alertmanager-data: