StrellerMinds-Backend/docker-compose.tracing.yml at main · Divineifed/StrellerMinds-Backend · 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
version: '3.8'

services:
  # Jaeger - Distributed tracing backend
  jaeger:
    image: jaegertracing/all-in-one:1.50
    container_name: strellerminds-jaeger
    ports:
      - "16686:16686"  # Jaeger UI
      - "14268:14268"  # HTTP collector
      - "14250:14250"  # gRPC collector
      - "6831:6831/udp"  # UDP agent
      - "6832:6832/udp"  # UDP agent
      - "5778:5778"     # Config server
    environment:
      - COLLECTOR_OTLP_ENABLED=true
      - COLLECTOR_ZIPKIN_HOST_PORT=:9411
    networks:
      - tracing-network
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:14269/"]
      interval: 30s
      timeout: 10s
      retries: 3

  # Zipkin - Alternative distributed tracing backend
  zipkin:
    image: openzipkin/zipkin:2.24
    container_name: strellerminds-zipkin
    ports:
      - "9411:9411"  # Zipkin UI
    environment:
      - STORAGE_TYPE=mem
    networks:
      - tracing-network
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9411/"]
      interval: 30s
      timeout: 10s
      retries: 3

  # OpenTelemetry Collector - Unified observability data pipeline
  otel-collector:
    image: otel/opentelemetry-collector-contrib:0.88.0
    container_name: strellerminds-otel-collector
    command: ["--config=/etc/otel-collector-config.yml"]
    volumes:
      - ./src/tracing/otel-collector-config.yml:/etc/otel-collector-config.yml
    ports:
      - "4317:4317"   # OTLP gRPC receiver
      - "4318:4318"   # OTLP HTTP receiver
      - "8888:8888"   # Prometheus metrics
      - "8889:8889"   # Prometheus exporter metrics
    depends_on:
      - jaeger
      - zipkin
    networks:
      - tracing-network
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:13133/"]
      interval: 30s
      timeout: 10s
      retries: 3

  # Grafana - Visualization and dashboards
  grafana:
    image: grafana/grafana:10.2.0
    container_name: strellerminds-grafana
    ports:
      - "3001:3000"  # Grafana UI
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin
      - GF_USERS_ALLOW_SIGN_UP=false
    volumes:
      - grafana-storage:/var/lib/grafana
      - ./src/tracing/grafana-dashboards:/etc/grafana/provisioning/dashboards
      - ./src/tracing/grafana-datasources:/etc/grafana/provisioning/datasources
    networks:
      - tracing-network
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3

  # Prometheus - Metrics collection and storage
  prometheus:
    image: prom/prometheus:v2.47.0
    container_name: strellerminds-prometheus
    ports:
      - "9090:9090"  # Prometheus UI
    volumes:
      - ./src/tracing/prometheus.yml:/etc/prometheus/prometheus.yml
      - prometheus-storage:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--storage.tsdb.retention.time=200h'
      - '--web.enable-lifecycle'
    networks:
      - tracing-network
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3

  # Redis - For caching and queue management
  redis-tracing:
    image: redis:7-alpine
    container_name: strellerminds-redis-tracing
    ports:
      - "6380:6379"  # Different port to avoid conflicts
    command: redis-server --appendonly yes --requirepass redis_tracing_password
    volumes:
      - redis-tracing-storage:/data
    networks:
      - tracing-network
    healthcheck:
      test: ["CMD", "redis-cli", "--raw", "incr", "ping"]
      interval: 30s
      timeout: 10s
      retries: 3

networks:
  tracing-network:
    driver: bridge

volumes:
  grafana-storage:
  prometheus-storage:
  redis-tracing-storage: