protoMaker/docker-compose.monitoring.yml at main · protoLabsAI/protoMaker · 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
version: '3.8'

services:
  prometheus:
    image: prom/prometheus:latest
    container_name: automaker-prometheus
    ports:
      - '9090:9090'
    volumes:
      - ./monitoring/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus-data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
      - '--storage.tsdb.retention.time=30d'
      - '--web.enable-lifecycle'
    restart: unless-stopped
    networks:
      - monitoring
    healthcheck:
      test: ['CMD', 'wget', '--quiet', '--tries=1', '--spider', 'http://localhost:9090/-/healthy']
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  loki:
    image: grafana/loki:3.2.0
    container_name: automaker-loki
    restart: unless-stopped
    ports:
      - '3100:3100'
    volumes:
      - ./monitoring/loki/local-config.yml:/etc/loki/local-config.yml:ro
      - loki-data:/loki
    command: -config.file=/etc/loki/local-config.yml
    networks:
      - monitoring

  promtail:
    image: grafana/promtail:3.2.0
    container_name: automaker-promtail
    restart: unless-stopped
    volumes:
      - ./monitoring/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
    command: -config.file=/etc/promtail/config.yml
    depends_on:
      - loki
    networks:
      - monitoring

  grafana:
    image: grafana/grafana:latest
    container_name: automaker-grafana
    ports:
      - '3010:3000'
    volumes:
      - ./monitoring/grafana/grafana.ini:/etc/grafana/grafana.ini:ro
      - ./monitoring/grafana/provisioning:/etc/grafana/provisioning:ro
      - grafana-data:/var/lib/grafana
    environment:
      - GF_SECURITY_ADMIN_USER=${GF_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GF_ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
      # Discord webhook for alerting (create in Discord: Channel Settings > Integrations > Webhooks)
      - DISCORD_WEBHOOK_INFRA=${DISCORD_WEBHOOK_INFRA:-}
    restart: unless-stopped
    networks:
      - monitoring
    depends_on:
      prometheus:
        condition: service_healthy
      loki:
        condition: service_started
    healthcheck:
      test: ['CMD', 'wget', '--quiet', '--tries=1', '--spider', 'http://localhost:3000/api/health']
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  node-exporter:
    image: prom/node-exporter:latest
    container_name: automaker-node-exporter
    ports:
      - '9100:9100'
    command:
      - '--path.rootfs=/host'
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/host:ro,rslave
    restart: unless-stopped
    networks:
      - monitoring
    healthcheck:
      test: ['CMD', 'wget', '--quiet', '--tries=1', '--spider', 'http://localhost:9100/metrics']
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s

networks:
  monitoring:
    name: automaker-monitoring
    driver: bridge

volumes:
  prometheus-data:
    name: automaker-prometheus-data
  loki-data:
    name: automaker-loki-data
  grafana-data:
    name: automaker-grafana-data