gpu-metrics-docker-compose/docker-compose.yml at main · titangmz/gpu-metrics-docker-compose · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
services:
  dcgm_exporter:
    user: "root"
    image: nvidia/dcgm-exporter:${DCGM_EXPORTER_IMAGE_TAG:-4.1.1-4.0.4-ubuntu22.04}
    container_name: gpu_metrics_dcgm_exporter
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    restart: unless-stopped
    environment:
      - DCGM_EXPORTER_NO_HOSTNAME=1
    cap_add:
      - SYS_ADMIN
    ports:
      - "${DCGM_EXPORTER_HOST_PORT:-9400}:9400"
    networks:
      - gpu_metrics
    env_file:
      - .env
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9400/metrics"]
      interval: 30s
      timeout: 10s
      retries: 3

  prometheus:
    user: "root"
    image: prom/prometheus:${PROMETHEUS_IMAGE_TAG:-v3.3.0}
    container_name: gpu_metrics_prometheus
    ports:
      - "${PROMETHEUS_HOST_PORT:-9090}:9090"
    restart: unless-stopped
    volumes:
      - ./config/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./data/prometheus:/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
      - --storage.tsdb.retention.time=${PROMETHEUS_STORAGE_TSDB_RETENTION_TIME:-30d}
    networks:
      - gpu_metrics
    env_file:
      - .env
    depends_on:
      - dcgm_exporter

  grafana:
    user: "root"
    image: grafana/grafana:${GRAFANA_IMAGE_TAG:-11.6.1-ubuntu}
    container_name: gpu_metrics_grafana
    ports:
      - "${GRAFANA_HOST_PORT:-3000}:3000"
    restart: unless-stopped
    environment:
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
    volumes:
      - ./data/grafana:/var/lib/grafana
      - ./config/grafana/provisioning:/etc/grafana/provisioning:ro
      - ./config/grafana/dashboards:/etc/dashboards:ro
    networks:
      - gpu_metrics
    env_file:
      - .env
    depends_on:
      - prometheus

  node_exporter:
    image: prom/node-exporter:v1.9.1
    container_name: node_exporter
    restart: unless-stopped
    pid: host
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
    command:
      - --path.procfs=/host/proc
      - --path.sysfs=/host/sys
    networks:
      - gpu_metrics

volumes:
  prometheus_data:
  grafana_data:

networks:
  gpu_metrics:
    driver: bridge