triterm/docker-compose.monitoring.yml at main · vasandkumar/triterm · 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
182
183
184
185
186
187
188
189
version: '3.8'

services:
  # Prometheus - Metrics collection
  prometheus:
    image: prom/prometheus:latest
    container_name: triterm-prometheus
    restart: unless-stopped
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
    volumes:
      - ./monitoring/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./monitoring/prometheus/alerts.yml:/etc/prometheus/alerts.yml:ro
      - prometheus_data:/prometheus
    ports:
      - "9090:9090"
    networks:
      - triterm-network
      - monitoring
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
    deploy:
      resources:
        limits:
          cpus: '1'
          memory: 1G
        reservations:
          cpus: '0.25'
          memory: 256M

  # Grafana - Visualization
  grafana:
    image: grafana/grafana:latest
    container_name: triterm-grafana
    restart: unless-stopped
    environment:
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_SERVER_ROOT_URL=${GRAFANA_ROOT_URL:-http://localhost:3001}
      - GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-simple-json-datasource
    volumes:
      - grafana_data:/var/lib/grafana
      - ./monitoring/grafana/provisioning:/etc/grafana/provisioning:ro
      - ./monitoring/grafana/dashboards:/var/lib/grafana/dashboards:ro
    ports:
      - "3001:3000"
    networks:
      - monitoring
    depends_on:
      - prometheus
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3
    deploy:
      resources:
        limits:
          cpus: '1'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 128M

  # Node Exporter - System metrics
  node-exporter:
    image: prom/node-exporter:latest
    container_name: triterm-node-exporter
    restart: unless-stopped
    command:
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'
      - '--path.rootfs=/rootfs'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    ports:
      - "9100:9100"
    networks:
      - monitoring
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 128M
        reservations:
          cpus: '0.1'
          memory: 32M

  # Postgres Exporter - Database metrics
  postgres-exporter:
    image: prometheuscommunity/postgres-exporter:latest
    container_name: triterm-postgres-exporter
    restart: unless-stopped
    environment:
      DATA_SOURCE_NAME: "postgresql://${POSTGRES_USER:-triterm_prod}:${POSTGRES_PASSWORD}@db:5432/${POSTGRES_DB:-triterm_production}?sslmode=disable"
    ports:
      - "9187:9187"
    networks:
      - triterm-network
      - monitoring
    depends_on:
      - prometheus
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 128M
        reservations:
          cpus: '0.1'
          memory: 32M

  # cAdvisor - Container metrics
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:latest
    container_name: triterm-cadvisor
    restart: unless-stopped
    privileged: true
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
    ports:
      - "8080:8080"
    networks:
      - monitoring
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 256M
        reservations:
          cpus: '0.1'
          memory: 64M

  # Alertmanager - Alert routing and management
  alertmanager:
    image: prom/alertmanager:latest
    container_name: triterm-alertmanager
    restart: unless-stopped
    command:
      - '--config.file=/etc/alertmanager/config.yml'
      - '--storage.path=/alertmanager'
    volumes:
      - ./monitoring/alertmanager/config.yml:/etc/alertmanager/config.yml:ro
      - alertmanager_data:/alertmanager
    ports:
      - "9093:9093"
    networks:
      - monitoring
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9093/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 256M
        reservations:
          cpus: '0.1'
          memory: 64M

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

networks:
  triterm-network:
    external: true
  monitoring:
    driver: bridge