plumoai/docker-compose.monitoring.yml at main · PlumoAI/plumoai · 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
# Optional monitoring overlay — adds container/host metrics and dashboards.
# Not started by install.sh/install.ps1 by default. Run alongside the main stack:
#
#   docker compose --env-file .env -f docker-compose.yml -f docker-compose.monitoring.yml up -d
#
# Grafana is reachable at http://<host>:3001 (change GRAFANA_ADMIN_PASSWORD before exposing
# it beyond localhost, and put it behind Traefik + a strong auth middleware if you do).

services:
  # Per-container CPU/memory/network metrics, scraped by Prometheus below.
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:v0.49.1
    container_name: plumoai-cadvisor
    restart: unless-stopped
    privileged: true
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
    networks:
      - monitoring
    deploy:
      resources:
        limits: { memory: 256M }
        reservations: { memory: 64M }
    logging:
      driver: json-file
      options: { max-size: "10m", max-file: "3" }

  # Host-level CPU/memory/disk metrics.
  node-exporter:
    image: prom/node-exporter:v1.8.2
    container_name: plumoai-node-exporter
    restart: unless-stopped
    pid: host
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - "--path.procfs=/host/proc"
      - "--path.sysfs=/host/sys"
      - "--path.rootfs=/rootfs"
      - "--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)"
    networks:
      - monitoring
    deploy:
      resources:
        limits: { memory: 128M }
        reservations: { memory: 32M }
    logging:
      driver: json-file
      options: { max-size: "10m", max-file: "3" }

  prometheus:
    image: prom/prometheus:v2.54.1
    container_name: plumoai-prometheus
    restart: unless-stopped
    volumes:
      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus_data:/prometheus
    command:
      - "--config.file=/etc/prometheus/prometheus.yml"
      - "--storage.tsdb.retention.time=15d"
    networks:
      - monitoring
    depends_on:
      - cadvisor
      - node-exporter
    deploy:
      resources:
        limits: { memory: 512M }
        reservations: { memory: 128M }
    logging:
      driver: json-file
      options: { max-size: "10m", max-file: "3" }

  grafana:
    image: grafana/grafana:11.2.0
    container_name: plumoai-grafana
    restart: unless-stopped
    environment:
      GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:?Set GRAFANA_ADMIN_PASSWORD in .env before starting Grafana}
      GF_USERS_ALLOW_SIGN_UP: "false"
    volumes:
      - grafana_data:/var/lib/grafana
    ports:
      # Bind to localhost only; put behind Traefik + auth if you need remote access.
      - "127.0.0.1:3001:3000"
    networks:
      - monitoring
    depends_on:
      - prometheus
    deploy:
      resources:
        limits: { memory: 256M }
        reservations: { memory: 64M }
    logging:
      driver: json-file
      options: { max-size: "10m", max-file: "3" }

networks:
  monitoring:

volumes:
  prometheus_data:
  grafana_data: