프로메테우스, 그라파나 windows에서 로컬 개발하기 - Docker

1. 자바 서버

build.gradle

..
dependencies {
    implementation 'org.springframework.boot:spring-boot-starter-actuator'
    implementation 'io.micrometer:micrometer-registry-prometheus'
    ...
}

application.yaml

server:
    port: 8000

management:
  endpoints:
    web:
      exposure:
        include: health, info, prometheus

 

2. 설정 yml 파일

configs/alertmanager.yml

global:
  resolve_timeout: 1m
  slack_api_url: 'https://hooks.slack.com/services/XXXXXXX' # slack api 설정

  # email
  smtp_smarthost: '<smtp-host>:587' # smtp 설정
  smtp_from: sender@email.com # stmp 전송자
  smtp_auth_username: test@email.com # 이메일
  smtp_auth_password: test_password # 비밀번호 설정

route:
  receiver: 'notifications'
  routes:
    - match:
        serverity: page
      receiver: 'notifications'

receivers:
 - name: 'slack-notifications'
   slack_configs:
   - channel: '#prometheus-test'  # slack 채널 이름
     send_resolved: true
     title: 
   email_configs:
    - to: my-email@email.com  # alert 받는 이메일

configs/prometheus.yml

# my global config
global:
  scrape_interval:     10s # Set the scrape interval to every 10 seconds. Default is every 1 minute.
  evaluation_interval: 10s # Evaluate rules every 15 seconds. The default is every 1 minute.
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
alerting:
  alertmanagers:
  - static_configs:
    - targets: ['host.docker.internal:9093']

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  - "rules.yml"

# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: 'prometheus'

    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.

    static_configs:
    - targets: ['localhost:9090']
  - job_name: 'node'
    static_configs:
    - targets: ['host.docker.internal:9100']

  - job_name: 'spring-boot-app'
    metrics_path: '/actuator/prometheus'
    static_configs:
      - targets: ['host.docker.internal:8000']

configs/rules.yml

groups:
  - name: example
    rules:
      - alert: InstanceDown
        expr: up == 0
        for: 1m # 발생후 pending 대기 시간
  - name: node_rules
    rules:
      - record: job:up:avg
        expr: avg without(instance)(up{job="node"})
      - alert: ManyInstancesDown
        expr: job:up:avg{job="node"} < 0.5

      - alert: BatchJobNoRecentSuccess
        expr: >
          time() - my_batch_job_last_success_time_seconds{job="batch"} > 86400*2
      - alert: FDsNearLimit
        expr: >
          process_open_fds > process_max_fds * .8
        for: 5m

 

3. 도커 실행

run_grafana.cmd

docker run -d --name=grafana -p 3000:3000 grafana/grafana:5.0.0

 

run_alertmanager.cmd

docker run -d --rm --name alertmanager -p 127.0.0.1:9093:9093 -v %cd%/configs:/etc/prometheus quay.io/prometheus/alertmanager --config.file=/etc/prometheus/alertmanager.yml

 

run_prometheus.cmd

docker run -d --rm --name prometheus -p 9090:9090 -v %cd%/configs:/etc/prometheus prom/prometheus --config.file=/etc/prometheus/prometheus.yml