text2sql-agent/docker-compose.monitoring.yml at main · Sakeeb91/text2sql-agent · 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
version: '3.8'

# Monitoring stack for Arctic Text2SQL (Issue #9)
# Usage: docker-compose -f docker-compose.yml -f docker-compose.monitoring.yml up -d

services:
  # Prometheus - Metrics collection and alerting
  prometheus:
    image: prom/prometheus:v2.47.0
    container_name: arctic-prometheus
    volumes:
      - ./monitoring/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./monitoring/prometheus/alerts.yml:/etc/prometheus/alerts.yml:ro
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=15d'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--web.enable-lifecycle'
    ports:
      - "9090:9090"
    networks:
      - arctic-network
    restart: unless-stopped

  # Grafana - Visualization and dashboards
  grafana:
    image: grafana/grafana:10.1.0
    container_name: arctic-grafana
    volumes:
      - grafana_data:/var/lib/grafana
      - ./monitoring/grafana:/etc/grafana/provisioning/dashboards:ro
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_SERVER_ROOT_URL=http://localhost:3000
    ports:
      - "3000:3000"
    networks:
      - arctic-network
    depends_on:
      - prometheus
    restart: unless-stopped

  # Alertmanager - Alert routing and notifications
  alertmanager:
    image: prom/alertmanager:v0.26.0
    container_name: arctic-alertmanager
    volumes:
      - ./monitoring/alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
      - alertmanager_data:/alertmanager
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
    ports:
      - "9093:9093"
    networks:
      - arctic-network
    restart: unless-stopped

  # Jaeger - Distributed tracing
  jaeger:
    image: jaegertracing/all-in-one:1.50
    container_name: arctic-jaeger
    environment:
      - COLLECTOR_OTLP_ENABLED=true
    ports:
      - "16686:16686"  # Jaeger UI
      - "4317:4317"    # OTLP gRPC
      - "4318:4318"    # OTLP HTTP
    networks:
      - arctic-network
    restart: unless-stopped

  # Node exporter - Host metrics
  node-exporter:
    image: prom/node-exporter:v1.6.1
    container_name: arctic-node-exporter
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    ports:
      - "9100:9100"
    networks:
      - arctic-network
    restart: unless-stopped

  # Redis exporter - Redis metrics
  redis-exporter:
    image: oliver006/redis_exporter:v1.54.0
    container_name: arctic-redis-exporter
    environment:
      - REDIS_ADDR=redis://redis:6379
    ports:
      - "9121:9121"
    networks:
      - arctic-network
    depends_on:
      - redis
    restart: unless-stopped

volumes:
  prometheus_data:
  grafana_data:
  alertmanager_data:

networks:
  arctic-network:
    external: true