timeflow/docker-compose.observability.yml at main · 1024XEngineer/timeflow · 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
# 同一台机器跑 API + Grafana / Prometheus / Tempo。
#
# 本机有源码：docker compose -f docker-compose.yml -f docker-compose.observability.yml up -d --build
# 云上只用 GHCR 镜像（不要 --build）：
#   docker compose -f docker-compose.yml -f docker-compose.observability.yml up -d
#
# Grafana 默认只绑 127.0.0.1:3000。不要把 9090 / 3200 / 4318 暴露到公网。
# 国内机器拉 Docker Hub 超时见 observability/README.md。

services:
  api:
    environment:
      TIMEFLOW_OTEL_SERVICE_NAME: ${TIMEFLOW_OTEL_SERVICE_NAME:-timeflow-backend}
      TIMEFLOW_OTEL_EXPORTER_OTLP_ENDPOINT: ${TIMEFLOW_OTEL_EXPORTER_OTLP_ENDPOINT:-http://tempo:4318}
    healthcheck:
      test:
        [
          "CMD",
          ".venv/bin/python",
          "-c",
          "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/api/v1/health')",
        ]
      interval: 5s
      timeout: 5s
      retries: 10
    depends_on:
      tempo:
        condition: service_started

  prometheus:
    image: prom/prometheus:v2.55.1
    command:
      - --config.file=/etc/prometheus/prometheus.yml
      - --storage.tsdb.path=/prometheus
      - --storage.tsdb.retention.time=15d
      - --web.enable-lifecycle
    volumes:
      - ./observability/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - timeflow-prometheus-data:/prometheus
    depends_on:
      api:
        condition: service_healthy
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://127.0.0.1:9090/-/healthy"]
      interval: 10s
      timeout: 5s
      retries: 10

  tempo:
    image: grafana/tempo:2.7.1
    user: "0"
    command: ["-config.file=/etc/tempo.yaml"]
    volumes:
      - ./observability/tempo/tempo.yaml:/etc/tempo.yaml:ro
      - timeflow-tempo-data:/var/tempo
    restart: unless-stopped

  grafana:
    image: grafana/grafana:11.5.2
    environment:
      GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:?Set GRAFANA_ADMIN_PASSWORD}
      GF_AUTH_ANONYMOUS_ENABLED: "false"
      GF_USERS_DEFAULT_THEME: dark
      GF_SERVER_HTTP_ADDR: 0.0.0.0
      GF_SERVER_ROOT_URL: ${GRAFANA_ROOT_URL:-http://127.0.0.1:3000}
      GF_SERVER_SERVE_FROM_SUB_PATH: ${GF_SERVER_SERVE_FROM_SUB_PATH:-false}
      # 用 `-` 而不是 `:-`：`.env` 里 `GF_INSTALL_PLUGINS=` 必须保持空，才能跳过 Sentry 插件。
      GF_INSTALL_PLUGINS: ${GF_INSTALL_PLUGINS-grafana-sentry-datasource}
      GF_PATHS_PROVISIONING: /etc/grafana/provisioning
      SENTRY_AUTH_TOKEN: ${SENTRY_AUTH_TOKEN:-}
    volumes:
      - ./observability/grafana-config/grafana.ini:/etc/grafana/grafana.ini:ro
      - ./observability/grafana-config/provisioning:/etc/grafana/provisioning:ro
      - timeflow-grafana-data:/var/lib/grafana
    ports:
      - "${GRAFANA_HOST:-127.0.0.1}:${GRAFANA_PORT:-3000}:3000"
    depends_on:
      prometheus:
        condition: service_healthy
      tempo:
        condition: service_started
    restart: unless-stopped
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://127.0.0.1:3000/api/health || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 12

volumes:
  timeflow-prometheus-data:
  timeflow-tempo-data:
  timeflow-grafana-data: