Rebin/docker-compose.monitoring.yml at main · Sajidcodez/Rebin · 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
version: "3.8"

services:
  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    ports:
      - "9090:9090"
    volumes:
      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml
      - prometheus_data:/prometheus
    command:
      - "--config.file=/etc/prometheus/prometheus.yml"
      - "--storage.tsdb.path=/prometheus"
      - "--web.console.libraries=/etc/prometheus/console_libraries"
      - "--web.console.templates=/etc/prometheus/consoles"
      - "--storage.tsdb.retention.time=200h"
      - "--web.enable-lifecycle"
    networks:
      - monitoring
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
    deploy:
      resources:
        limits:
          memory: 512M
          cpus: "0.5"
        reservations:
          memory: 256M
          cpus: "0.25"

  grafana:
    image: grafana/grafana:latest
    container_name: grafana
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_PASSWORD:-admin}
      - GF_SECURITY_ADMIN_USER=${GRAFANA_USER:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_SECURITY_DISABLE_GRAVATAR=true
      - GF_ANALYTICS_REPORTING_ENABLED=false
      - GF_ANALYTICS_CHECK_FOR_UPDATES=false
    volumes:
      - grafana_data:/var/lib/grafana
      - ./monitoring/grafana/dashboards:/etc/grafana/provisioning/dashboards
      - ./monitoring/grafana/datasources:/etc/grafana/provisioning/datasources
    networks:
      - monitoring
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3
    deploy:
      resources:
        limits:
          memory: 512M
          cpus: "0.5"
        reservations:
          memory: 256M
          cpus: "0.25"

  node-exporter:
    image: prom/node-exporter:latest
    container_name: node-exporter
    ports:
      - "9100:9100"
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - "--path.procfs=/host/proc"
      - "--path.rootfs=/rootfs"
      - "--path.sysfs=/host/sys"
      - "--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)"
    networks:
      - monitoring
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 128M
          cpus: "0.1"
        reservations:
          memory: 64M
          cpus: "0.05"

  cadvisor:
    image: gcr.io/cadvisor/cadvisor:latest
    container_name: cadvisor
    ports:
      - "8080:8080"
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
    privileged: true
    devices:
      - /dev/kmsg
    networks:
      - monitoring
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 256M
          cpus: "0.25"
        reservations:
          memory: 128M
          cpus: "0.1"

  alertmanager:
    image: prom/alertmanager:latest
    container_name: alertmanager
    ports:
      - "9093:9093"
    volumes:
      - ./monitoring/alertmanager.yml:/etc/alertmanager/alertmanager.yml
      - alertmanager_data:/alertmanager
    command:
      - "--config.file=/etc/alertmanager/alertmanager.yml"
      - "--storage.path=/alertmanager"
      - "--web.external-url=http://localhost:9093"
    networks:
      - monitoring
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 256M
          cpus: "0.25"
        reservations:
          memory: 128M
          cpus: "0.1"

networks:
  monitoring:
    driver: bridge
    ipam:
      config:
        - subnet: 172.21.0.0/16
          gateway: 172.21.0.1

volumes:
  prometheus_data:
    driver: local
  grafana_data:
    driver: local
  alertmanager_data:
    driver: local