distributed-inference-platform/docker-compose.yml at main · tcbarzyk/distributed-inference-platform · 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
services:
  redis:
    image: redis:7-alpine
    container_name: dip-redis
    ports:
      - "6380:6379"
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 3s
      retries: 5
      start_period: 5s
    restart: unless-stopped

  postgres:
    image: postgres:16-alpine
    env_file: .env
    ports:
      - "5432:5432"
    volumes:
      - ./services/postgres/data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U $$POSTGRES_USER -d $$POSTGRES_DB"]
      interval: 5s
      timeout: 3s
      retries: 5
      start_period: 5s
    restart: unless-stopped

  api:
    build:
      context: .
      dockerfile: services/api/Dockerfile
    env_file: .env
    environment:
      REDIS_HOST: redis
      POSTGRES_HOST: postgres
    depends_on:
      redis:
        condition: service_healthy
      postgres:
        condition: service_healthy
    ports:
      - "8000:8000"
    healthcheck:
      test: ["CMD", "python", "-c", "import sys, urllib.request; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:8000/health/live', timeout=2).getcode() == 200 else 1)"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 15s
    restart: unless-stopped

  producer:
    build:
      context: .
      dockerfile: services/producer/Dockerfile
    env_file: .env
    environment:
      REDIS_HOST: redis
      PRODUCER_METRICS_PORT: ${PRODUCER_METRICS_PORT:-9101}
    depends_on:
      redis:
        condition: service_healthy
    volumes:
      - ./services/producer/sample-video:/app/services/producer/sample-video:ro
    ports:
      - "9101:9101"
    healthcheck:
      test: ["CMD", "python", "-c", "import os, sys, urllib.request; port=os.getenv('PRODUCER_METRICS_PORT','9101'); sys.exit(0 if urllib.request.urlopen(f'http://127.0.0.1:{port}/metrics', timeout=2).getcode() == 200 else 1)"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 20s
    restart: unless-stopped

  worker:
    build:
      context: .
      dockerfile: services/worker/Dockerfile
    env_file: .env
    environment:
      REDIS_HOST: redis
      POSTGRES_HOST: postgres
      WORKER_METRICS_PORT: ${WORKER_METRICS_PORT:-9102}
    depends_on:
      redis:
        condition: service_healthy
      postgres:
        condition: service_healthy
    volumes:
      - ./services/worker/output:/app/services/worker/output
      - ./services/worker/.cache/ultralytics:/root/.cache/ultralytics
    healthcheck:
      test: ["CMD", "python", "-c", "import os, sys, urllib.request; port=os.getenv('WORKER_METRICS_PORT','9102'); sys.exit(0 if urllib.request.urlopen(f'http://127.0.0.1:{port}/metrics', timeout=2).getcode() == 200 else 1)"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    restart: unless-stopped
    gpus: all

  prometheus:
    image: prom/prometheus:v2.54.1
    user: root
    depends_on:
      api:
        condition: service_healthy
      producer:
        condition: service_healthy
    ports:
      - "9090:9090"
    volumes:
      - ./services/monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - prometheus_data:/prometheus
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://127.0.0.1:9090/-/healthy"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s
    restart: unless-stopped

volumes:
  prometheus_data: