eventually-consistent-highly-scalable-system/monitoring/prometheus.yml at main · jbdoster/eventually-consistent-highly-scalable-system · 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
global:
  scrape_interval: 15s
  evaluation_interval: 15s

rule_files:
  - "alert-rules.yml"

alerting:
  alertmanagers:
    - static_configs:
        - targets:
          - alertmanager:9093

scrape_configs:
  # Prometheus itself
  - job_name: 'prometheus'
    static_configs:
      - targets: ['localhost:9090']
    scrape_interval: 15s

  # Keycloak metrics
  - job_name: 'keycloak'
    static_configs:
      - targets: ['keycloak-1:8080', 'keycloak-2:8080']
    metrics_path: '/metrics'
    scrape_interval: 30s

  # Spring Boot applications with Actuator metrics
  - job_name: 'write_layer'
    metrics_path: '/actuator/prometheus'
    static_configs:
      - targets: ['write-layer:8081', 'write-layer-2:8081']
    scrape_interval: 15s

  # Public API
  - job_name: 'public_api'
    metrics_path: '/actuator/prometheus'
    static_configs:
      - targets: ['public-api:8082']
    scrape_interval: 15s

  # User Service
  - job_name: 'user_service'
    metrics_path: '/actuator/prometheus'
    static_configs:
      - targets: ['user-service:8085']
    scrape_interval: 15s

  # Coupon Service
  - job_name: 'coupon-service'
    scrape_interval: 15s
    metrics_path: '/actuator/prometheus'
    static_configs:
      - targets: ['coupon-service:8086']

  # Cache Sync Service
  - job_name: 'cache-sync-service'
    scrape_interval: 15s
    metrics_path: '/actuator/prometheus'
    static_configs:
      - targets: ['cache-sync-service:8087']

  # Infrastructure services
  - job_name: 'redis'
    static_configs:
      - targets: ['redis:6379']
    scrape_interval: 30s

  - job_name: 'rabbitmq'
    static_configs:
      - targets: ['message-queue:15692']
    metrics_path: '/metrics'
    scrape_interval: 30s

  - job_name: 'dynamodb-local'
    static_configs:
      - targets: ['dynamodb-local:8000']
    scrape_interval: 30s

  - job_name: 'kafka'
    static_configs:
      - targets: ['kafka:9092']
    scrape_interval: 30s

  - job_name: 'zookeeper'
    static_configs:
      - targets: ['zookeeper:2181']
    scrape_interval: 30s

  # Infrastructure components
  - job_name: 'postgres'
    static_configs:
      - targets: ['postgres:5432']
    scrape_interval: 30s

  - job_name: 'infinispan'
    static_configs:
      - targets: ['infinispan:11222']
    metrics_path: '/rest/v2/cache-managers/default/stats'
    scrape_interval: 30s

  # HAProxy stats
  - job_name: 'haproxy'
    static_configs:
      - targets: ['haproxy:8080']
    metrics_path: '/stats;csv'
    scrape_interval: 15s

  # Alertmanager
  - job_name: 'alertmanager'
    static_configs:
      - targets: ['alertmanager:9093']
    scrape_interval: 30s