monitoring-stack/docker-compose.yml at main · sagarmemane135/monitoring-stack · 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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
version: "3.8"

services:
  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    restart: unless-stopped
    networks:
      - monitoring
    environment:
      - HOSTNAME_MONITOR=${HOSTNAME_MONITOR}
    volumes:
      - ./data/prometheus:/prometheus
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/rules.yml:/etc/prometheus/rules.yml:ro
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.enable-lifecycle'
      - '--web.external-url=https://${HOSTNAME_MONITOR}/prometheus'
      - '--web.route-prefix=/prometheus'
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9090/-/ready || exit 1"]
      interval: 30s
      timeout: 5s
      retries: 5
    deploy:
      resources:
        limits:
          memory: 1g

  alertmanager:
    image: prom/alertmanager:latest
    container_name: alertmanager
    restart: unless-stopped
    networks:
      - monitoring
    env_file:
      - .env
    environment:
      - HOSTNAME_MONITOR=${HOSTNAME_MONITOR}
    volumes:
      - ./data/alertmanager:/alertmanager
      - ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--web.external-url=https://${HOSTNAME_MONITOR}/alertmanager'
      - '--web.route-prefix=/alertmanager'
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9093/-/ready || exit 1"]
      interval: 30s
      timeout: 5s
      retries: 5
    deploy:
      resources:
        limits:
          memory: 512m

  grafana:
    image: grafana/grafana:latest
    container_name: grafana
    user: "472:472"
    restart: unless-stopped
    networks:
      - monitoring
    env_file:
      - .env
    environment:
      - GF_SECURITY_ADMIN_USER=${GF_SECURITY_ADMIN_USER}
      - GF_SECURITY_ADMIN_PASSWORD=${GF_SECURITY_ADMIN_PASSWORD}
      - GF_AUTH_ANONYMOUS_ENABLED=false
      - GF_SERVER_ROOT_URL=%(protocol)s://%(domain)s/grafana/
      - GF_PATHS_PROVISIONING=/etc/grafana/provisioning
      - GF_LOG_LEVEL=debug
    volumes:
      - ./data/grafana:/var/lib/grafana
      # 🧩 Fixed: Proper provisioning structure
      - ./grafana/provisioning/datasources:/etc/grafana/provisioning/datasources:ro
      - ./grafana/provisioning/dashboards:/etc/grafana/provisioning/dashboards:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
    depends_on:
      - prometheus
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health || exit 1"]
      interval: 30s
      timeout: 5s
      retries: 5
    deploy:
      resources:
        limits:
          memory: 1g

  node-exporter:
    image: prom/node-exporter:latest
    container_name: node-exporter
    restart: unless-stopped
    network_mode: host
    pid: host
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/host:ro

  node-exporter-proxy:
    image: alpine/socat
    container_name: node-exporter-proxy
    restart: unless-stopped
    command: tcp-listen:9100,fork,reuseaddr tcp-connect:host.docker.internal:9100
    networks:
      - monitoring
    extra_hosts:
      - "host.docker.internal:host-gateway"


  cadvisor:
    image: gcr.io/cadvisor/cadvisor:latest
    container_name: cadvisor
    restart: unless-stopped
    networks:
      - monitoring
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
    deploy:
      resources:
        limits:
          memory: 512m

  blackbox-exporter:
    image: prom/blackbox-exporter:latest
    container_name: blackbox-exporter
    restart: unless-stopped
    networks:
      - monitoring
    environment:
      - HOSTNAME_MONITOR=${HOSTNAME_MONITOR}
    volumes:
      - ./blackbox-exporter/blackbox.yml:/etc/blackbox_exporter/config.yml:ro
    command:
      - '--config.file=/etc/blackbox_exporter/config.yml'
      - '--web.external-url=https://${HOSTNAME_MONITOR}/blackbox'
      - '--web.route-prefix=/blackbox'
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9115/ || exit 1"]
      interval: 30s
      timeout: 5s
      retries: 5

  nginx:
    image: nginx:stable-alpine
    container_name: nginx-proxy
    restart: unless-stopped
    networks:
      - monitoring
    ports:
      - "${LISTEN_PORT}:443"
    environment:
      - HOSTNAME_MONITOR=${HOSTNAME_MONITOR}
      - USE_TLS=${USE_TLS}
    volumes:
      - ./nginx/nginx.conf:/etc/nginx/nginx.conf:ro
      - ./nginx/conf.d/monitoring.conf:/etc/nginx/conf.d/monitoring.conf:ro
      - ./nginx/auth:/etc/nginx/auth:ro
      - ./secrets:/run/secrets:ro
    depends_on:
      - prometheus
      - grafana
      - alertmanager
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost/health || exit 1"]
      interval: 15s
      timeout: 3s
      retries: 3

networks:
  monitoring:
    driver: bridge