devops/docker-compose.prod.yml at main · netxs2000/devops · 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
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
services:
  # 1. 后端 API 服务 (FastAPI + Test Hub)
  api:
    build: .
    image: devops-platform:latest
    container_name: devops-api
    restart: always
    ports:
      - "8000:8000"
    volumes:
      - ./persistence_data:/app/data
      - /etc/localtime:/etc/localtime:ro
    environment:
      - TZ=Asia/Shanghai
    env_file:
      - .env
    depends_on:
      db:
        condition: service_healthy
      mq:
        condition: service_healthy
    healthcheck:
      test: [ "CMD", "nc", "-z", "localhost", "8000" ]
      interval: 10s
      timeout: 5s
      retries: 20
      start_period: 60s
    command: uvicorn devops_portal.main:app --host 0.0.0.0 --port 8000
    logging: &logging
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "3"

  # 2. 数据异步采集 Worker
  worker:
    image: devops-platform:latest
    container_name: devops-worker
    restart: always
    volumes:
      - ./persistence_data:/app/data
      - /etc/localtime:/etc/localtime:ro
    environment:
      - TZ=Asia/Shanghai
    env_file:
      - .env
    depends_on:
      db:
        condition: service_healthy
      mq:
        condition: service_healthy
    command: python -m devops_collector.worker
    logging: *logging

  # 3. 任务调度器
  scheduler:
    image: devops-platform:latest
    container_name: devops-scheduler
    restart: always
    environment:
      - TZ=Asia/Shanghai
    env_file:
      - .env
    volumes:
      - /etc/localtime:/etc/localtime:ro
    depends_on:
      db:
        condition: service_healthy
      mq:
        condition: service_healthy
    command: python -m devops_collector.scheduler
    logging: *logging

  # 4. PostgreSQL 数据库
  db:
    image: postgres:15-alpine
    container_name: devops-db
    restart: always
    environment:
      - TZ=Asia/Shanghai
    env_file:
      - .env
    volumes:
      - postgres_data:/var/lib/postgresql/data
      - /etc/localtime:/etc/localtime:ro
    healthcheck:
      test: [ "CMD-SHELL", "pg_isready -U ${POSTGRES_USER} -d ${POSTGRES_DB}" ]
      interval: 5s
      timeout: 5s
      retries: 5
    logging: *logging

  # 5. RabbitMQ 消息队列
  mq:
    image: rabbitmq:3-management-alpine
    container_name: devops-mq
    restart: always
    ports:
      - "5672:5672"
      # 生产环境通常不需要暴露管理端口到公网，但这里保留供内部使用，或建议通过 ssh tunnel 访问
      - "15672:15672"
    volumes:
      - rabbitmq_data:/var/lib/rabbitmq
      - /etc/localtime:/etc/localtime:ro
    environment:
      - TZ=Asia/Shanghai
      - RABBITMQ_DEFAULT_USER=${RABBITMQ_USER}
      - RABBITMQ_DEFAULT_PASS=${RABBITMQ_PASSWORD}
      - RABBITMQ_VM_MEMORY_HIGH_WATERMARK_RELATIVE=0.7
    healthcheck:
      test: [ "CMD", "rabbitmq-diagnostics", "-q", "ping" ]
      interval: 5s
      timeout: 10s
      retries: 60
      start_period: 60s
    logging: *logging

  # 6. Decision Hub (Streamlit Dashboard)
  dashboard:
    image: devops-platform:latest
    container_name: devops-dashboard
    restart: always
    ports:
      - "8501:8501"
    volumes:
      - /etc/localtime:/etc/localtime:ro
    environment:
      - TZ=Asia/Shanghai
    env_file:
      - .env
    depends_on:
      db:
        condition: service_healthy
    healthcheck:
      test: [ "CMD", "nc", "-z", "localhost", "8501" ]
      interval: 10s
      timeout: 10s
      retries: 30
      start_period: 120s
    command: streamlit run dashboard/Home.py
    logging: *logging

volumes:
  postgres_data:
  rabbitmq_data: