name: observability

services:
  prometheus:
    image: prom/prometheus:v3.2.1
    container_name: prometheus
    restart: unless-stopped
    ports:
      - "9090:9090"
    extra_hosts:
      - "host.docker.internal:host-gateway"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus_data:/prometheus
    command:
      - --config.file=/etc/prometheus/prometheus.yml
      - --storage.tsdb.path=/prometheus
      - --storage.tsdb.retention.time=15d

  grafana:
    image: grafana/grafana:11.5.2
    container_name: grafana
    restart: unless-stopped
    ports:
      - "3001:3000"
    environment:
      GF_SECURITY_ADMIN_USER: admin
      GF_SECURITY_ADMIN_PASSWORD: Gf-gpu-2026
      GF_USERS_ALLOW_SIGN_UP: "false"
      GF_SERVER_ROOT_URL: http://10.0.1.47:3001
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning/datasources:/etc/grafana/provisioning/datasources:ro
      - ./grafana/provisioning/dashboards:/etc/grafana/provisioning/dashboards:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro

  dcgm-exporter:
    image: nvidia/dcgm-exporter:3.3.8-3.6.0-ubuntu22.04
    container_name: dcgm-exporter
    restart: unless-stopped
    cap_add:
      - SYS_ADMIN
    ports:
      - "9400:9400"
    environment:
      NVIDIA_VISIBLE_DEVICES: all
      NVIDIA_DRIVER_CAPABILITIES: compute,utility
      DCGM_EXPORTER_INTERVAL: "5000"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

volumes:
  prometheus_data:
  grafana_data: