prometheus告警配置注意事项

global:
　　scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
　　evaluation_interval: 15s # 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: ['100.101.201.131:9093']

rule_files:
　　- 'rules.yml'
# - "second_rules.yml"

# Here it's Prometheus itself.
scrape_configs:

 - job_name: 'beta'
    scrape_timeout: 14s #超时时间必须少于即间隔scrape_interval，这里是14s，小于15s
    relabel_configs:
    　regex: "(.*),(.+),(.*)" #正则匹配
    　replacement: $2  #第二个
    　action: replace #动作为替换
    　target_label: "nodename" #目标的key为这个
    consul_sd_configs:
    - server: '127.0.0.1:8501'    

 

 

global:
  resolve_timeout: 2h
 
route:
  group_by: ['alertname']
  group_wait: 5s
  group_interval: 10s
  repeat_interval: 1h  #告警发送到webhook的间隔时间
  receiver: 'webhook'
 
receivers:
- name: 'webhook'
  webhook_configs:
  - url: 'http://127.0.0.1:5001/send'
    send_resolved: true

 

转载于:https://www.cnblogs.com/kevincaptain/p/10531995.html