relier/docker-compose.yml at main · getrelier/relier · 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
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
name: relier-cluster

# =============================================================================
# Local development stack,  lightweight single-node Redis.
#
# Dev runs ONE Redis node (Sentinel disabled) to stay fast. Persistence is
# still on: redis.conf enables AOF + RDB, so dev data survives restarts.
#
# What dev does NOT exercise is failover. To test the Sentinel / HA path
# locally, run the full topology from the production manifest instead:
#
#   REDIS_PASSWORD=dev SENTINEL_PASSWORD=dev \
#     docker compose -f docker-compose.prod.yml up
#
# Production always uses docker-compose.prod.yml (master + replicas + Sentinels).
# =============================================================================

# Shared environment injected into every app container.
x-app-env: &app-env
  RELIER_REDIS_URL: redis://redis:6379/0
  RELIER_OTEL_ENABLED: "true"
  RELIER_OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4317

services:
  # =====================================================================
  # Infrastructure
  # =====================================================================
  redis:
    image: redis:7.2-alpine
    container_name: relier-redis
    # Shares the data-node config with the HA topology so dev and prod have
    # identical persistence behaviour (AOF + RDB + noeviction). The replication
    # directives in the file are inert on a standalone node.
    command: redis-server /etc/relier/redis.conf
    ports:
      - "6379:6379"
    volumes:
      - ./scripts/redis/redis.conf:/etc/relier/redis.conf:ro
      - redis_data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 3s
      retries: 5


  # =========================================================================
  # Application,  Celery workers and the resurrector
  # =========================================================================
  worker-high:
    build:
      context: .
      dockerfile: Dockerfile
    command: >
      celery -A relier.tasks.app worker
      --loglevel=info
      --concurrency=8
      -Q high_priority,default
      --hostname=rl-worker-high@%h
    volumes:
      - ./src:/app/src
      - ./scripts:/app/scripts
    environment:
      <<: *app-env
    depends_on:
      redis:
        condition: service_healthy
      otel-collector:
        condition: service_started

  worker-default:
    build:
      context: .
      dockerfile: Dockerfile
    command: >
      celery -A relier.tasks.app worker
      --loglevel=info
      --concurrency=8
      -Q default,low_priority
      --hostname=rl-worker-default@%h
    volumes:
      - ./src:/app/src
      - ./scripts:/app/scripts
    environment:
      <<: *app-env
    depends_on:
      redis:
        condition: service_healthy
      otel-collector:
        condition: service_started

  worker-recovery:
    build:
      context: .
      dockerfile: Dockerfile
    command: >
      celery -A relier.tasks.app worker
      --loglevel=info
      --concurrency=8
      -Q re-queue
      --hostname=rl-worker-re-queue@%h
    volumes:
      - ./src:/app/src
      - ./scripts:/app/scripts
    environment:
      <<: *app-env
    depends_on:
      redis:
        condition: service_healthy
      otel-collector:
        condition: service_started

  resurrector:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: relier-resurrector
    command: rl run-resurrector
    volumes:
      - ./src:/app/src
      - ./scripts:/app/scripts
    environment:
      <<: *app-env
      RELIER_LOG_LEVEL: INFO
    depends_on:
      redis:
        condition: service_healthy
      otel-collector:
        condition: service_started

  # =====================================================================
  # Observability,  OpenTelemetry → Prometheus → Grafana
  # =====================================================================
  otel-collector:
    image: otel/opentelemetry-collector-contrib:latest
    command: ["--config=/etc/otel-collector-config.yml"]
    volumes:
      - ./scripts/otel-collector-config.yml:/etc/otel-collector-config.yml:ro
    ports:
      - "4317:4317"
      - "4318:4318"
      - "8889:8889"

  prometheus:
    image: prom/prometheus:latest
    volumes:
      - ./scripts/prometheus.yml:/etc/prometheus/prometheus.yml:ro
    ports:
      - "9090:9090"
    depends_on:
      - otel-collector

  grafana:
    image: grafana/grafana:latest
    volumes:
      - ./scripts/grafana/provisioning:/etc/grafana/provisioning:ro
      - ./scripts/grafana-dashboards:/var/lib/grafana/dashboards:ro
      - grafana_data:/var/lib/grafana
    environment:
      GF_SECURITY_ADMIN_PASSWORD: admin
      GF_AUTH_ANONYMOUS_ENABLED: "true"
      GF_AUTH_ANONYMOUS_ORG_ROLE: Viewer
    ports:
      - "3000:3000"
    depends_on:
      - prometheus


volumes:
  redis_data:
  grafana_data: