infra/docker-compose.observability.yml at master · InstaNode-dev/infra · 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
version: '3.8'

# Local observability stack: Prometheus + Loki + Promtail + Grafana
#
# Usage:
#   docker compose -f docker-compose.observability.yml up -d
#
# Grafana:    http://localhost:3001  (no login required in dev mode)
# Prometheus: http://localhost:9090
# Loki:       http://localhost:3100
#
# Prometheus scrapes the API at both:
#   host.docker.internal:8080   — when running via "make run" or docker-compose
#   host.docker.internal:30080  — when running in local k8s (Rancher Desktop)
#
# Promtail ships container logs to Loki (requires Docker socket access).

services:
  prometheus:
    image: prom/prometheus:v2.51.2
    container_name: instant_prometheus
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/alert-rules.yml:/etc/prometheus/alert-rules.yml:ro
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=15d'
      - '--web.enable-lifecycle'
      - '--web.enable-admin-api'
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://localhost:9090/-/healthy"]
      interval: 10s
      timeout: 5s
      retries: 5

  loki:
    image: grafana/loki:3.0.0
    container_name: instant_loki
    ports:
      - "3100:3100"
    volumes:
      - ./loki/local-config.yaml:/etc/loki/local-config.yaml:ro
      - loki_data:/loki
    command: -config.file=/etc/loki/local-config.yaml
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://localhost:3100/ready"]
      interval: 10s
      timeout: 5s
      retries: 10
      start_period: 15s

  # log-forwarder bridges the gap between Promtail's docker_sd_configs (which only
  # discovers containers with their own Docker network interface) and k8s application
  # containers (which use network_mode: container:<pod_sandbox_id> and are therefore
  # invisible to Docker SD). It tails k8s container logs via the Docker socket and
  # appends them to files in the k8s-logs volume that Promtail reads via static_configs.
  log-forwarder:
    image: docker:27-cli
    container_name: instant_log_forwarder
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - ./log-forwarder/forward.sh:/forward.sh:ro
      - k8s_logs:/k8s-logs
    command: sh /forward.sh
    restart: unless-stopped
    depends_on:
      loki:
        condition: service_healthy

  promtail:
    image: grafana/promtail:3.0.0
    container_name: instant_promtail
    volumes:
      - ./promtail/config.yml:/etc/promtail/config.yml:ro
      - /var/lib/docker/containers:/var/lib/docker/containers:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - promtail_positions:/tmp
      - k8s_logs:/k8s-logs:ro
    command: -config.file=/etc/promtail/config.yml
    depends_on:
      loki:
        condition: service_healthy
      log-forwarder:
        condition: service_started
    restart: unless-stopped

  grafana:
    image: grafana/grafana:10.4.2
    container_name: instant_grafana
    ports:
      - "3001:3000"
    environment:
      # No login required in local dev — open to all
      GF_AUTH_ANONYMOUS_ENABLED: "true"
      GF_AUTH_ANONYMOUS_ORG_ROLE: Admin
      GF_AUTH_DISABLE_LOGIN_FORM: "true"
      GF_PATHS_PROVISIONING: /etc/grafana/provisioning
      GF_DASHBOARDS_DEFAULT_HOME_DASHBOARD_PATH: /var/lib/grafana/dashboards/instant-api.json
    volumes:
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
      - grafana_data:/var/lib/grafana
    depends_on:
      prometheus:
        condition: service_healthy
      loki:
        condition: service_healthy
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://localhost:3000/api/health"]
      interval: 10s
      timeout: 5s
      retries: 10
      start_period: 20s

volumes:
  prometheus_data:
  loki_data:
  grafana_data:
  promtail_positions:
  k8s_logs: