12-codoc-12-analysisAI/docker-compose.yml at dev · 100-hours-a-week/12-codoc-12-analysisAI · 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
version: '3.8'

services:
  api_server:
    build: .
    container_name: analysis_api_server
    ports:
      - "8010:8000"
    volumes:
      - .:/app # 실시간 코드 수정 반영용
      - ./model_cache:/root/.cache/huggingface # 모델 재다운로드 방지용
    env_file:
      - .env  # 환경 변수 로드
    restart: always

  prometheus:
    image: prom/prometheus:v2.54.1
    container_name: analysis_prometheus
    command:
      - "--config.file=/etc/prometheus/prometheus.yml"
      - "--storage.tsdb.path=/prometheus"
    volumes:
      - ./monitoring/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./monitoring/prometheus/alert_rules.yml:/etc/prometheus/alert_rules.yml:ro
    ports:
      - "9090:9090"
    depends_on:
      - api_server
      - node-exporter
      - cadvisor
      - alertmanager
    restart: always

  grafana:
    image: grafana/grafana:11.1.5
    container_name: analysis_grafana
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin
    ports:
      - "3000:3000"
    depends_on:
      - prometheus
    restart: always

  alertmanager:
    image: prom/alertmanager:v0.27.0
    container_name: analysis_alertmanager
    command:
      - "--config.file=/etc/alertmanager/alertmanager.yml"
    volumes:
      - ./monitoring/alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
    ports:
      - "9093:9093"
    restart: always

  node-exporter:
    image: prom/node-exporter:v1.8.2
    container_name: analysis_node_exporter
    command:
      - "--path.rootfs=/host"
    volumes:
      - "/:/host:ro,rslave"
    ports:
      - "9100:9100"
    restart: always

  cadvisor:
    image: gcr.io/cadvisor/cadvisor:v0.49.1
    container_name: analysis_cadvisor
    privileged: true
    devices:
      - /dev/kmsg
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
    ports:
      - "8080:8080"
    restart: always

  dcgm-exporter:
    image: nvidia/dcgm-exporter:3.3.8-3.6.0-ubuntu22.04
    container_name: analysis_dcgm_exporter
    profiles:
      - gpu
    cap_add:
      - SYS_ADMIN
    ports:
      - "9400:9400"
    restart: always