predictIQ/docker-compose.tracing.yml at main · solutions-plug/predictIQ · 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
version: '3.8'

services:
  jaeger:
    image: jaegertracing/all-in-one:latest
    container_name: predictiq-jaeger
    ports:
      - "16686:16686"  # Jaeger UI
      - "4317:4317"    # OTLP gRPC receiver
      - "4318:4318"    # OTLP HTTP receiver
      - "14250:14250"  # Jaeger gRPC
      - "14268:14268"  # Jaeger HTTP
    environment:
      - COLLECTOR_OTLP_ENABLED=true
      - LOG_LEVEL=info
    # Resource limits: Jaeger can consume significant memory with high trace volume
    # CPU: 1 core, Memory: 1GB (adjust based on trace volume)
    deploy:
      resources:
        limits:
          cpus: '1'
          memory: 1G
        reservations:
          cpus: '0.5'
          memory: 512M
    networks:
      - predictiq-tracing

  zipkin:
    image: openzipkin/zipkin:latest
    container_name: predictiq-zipkin
    ports:
      - "9411:9411"    # Zipkin UI and API
    # Resource limits: Zipkin is lightweight but should be bounded
    # CPU: 0.5 core, Memory: 512MB
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 256M
    networks:
      - predictiq-tracing

  otel-collector:
    image: otel/opentelemetry-collector-contrib:latest
    container_name: predictiq-otel-collector
    command: ["--config=/etc/otel-collector-config.yml"]
    volumes:
      - ./otel-collector-config.yml:/etc/otel-collector-config.yml
    ports:
      - "4317:4317"    # OTLP gRPC receiver
      - "4318:4318"    # OTLP HTTP receiver
      - "8888:8888"    # Prometheus metrics
      - "13133:13133"  # Health check
    environment:
      - JAEGER_ENDPOINT=${JAEGER_ENDPOINT:-jaeger:14250}
      - ZIPKIN_ENDPOINT=${ZIPKIN_ENDPOINT:-http://zipkin:9411/api/v2/spans}
    # Resource limits: OTEL collector processes and exports traces
    # CPU: 0.5 core, Memory: 512MB (adjust based on throughput)
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 256M
    depends_on:
      - jaeger
      - zipkin
    networks:
      - predictiq-tracing

  # ── TTS Service ──────────────────────────────────────────────────────────────
  # Included so the TTS service can export traces to the OpenTelemetry Collector
  # running in this compose stack.
  tts:
    build:
      context: ./services/tts
      dockerfile: Dockerfile
    container_name: predictiq-tts
    ports:
      - "3000:3000"
    environment:
      - TTS_PROVIDER=${TTS_PROVIDER:-elevenlabs}
      - ELEVENLABS_API_KEY=${ELEVENLABS_API_KEY:-}
      - GOOGLE_APPLICATION_CREDENTIALS=${GOOGLE_APPLICATION_CREDENTIALS:-}
      - TTS_OUTPUT_DIR=/tmp/tts-output
      - OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4317
      - OTEL_SERVICE_NAME=predictiq-tts
    volumes:
      - tts-output:/tmp/tts-output
    healthcheck:
      test:
        - "CMD"
        - "node"
        - "-e"
        - "require('http').get('http://localhost:3000/health/live',(r)=>{process.exit(r.statusCode===200?0:1)}).on('error',()=>process.exit(1))"
      interval: 30s
      timeout: 5s
      start_period: 10s
      retries: 3
    depends_on:
      - otel-collector
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 256M
    networks:
      - predictiq-tracing

networks:
  predictiq-tracing:
    driver: bridge

volumes:
  tts-output: