Prometheus邮件报警配置

[Unit]Description=alertmanagerDocumentation=https://github.com/prometheus/alertmanagerAfter=network.target[Service]Type=simpleUser=rootExecStart=/usr/local/alertmanager/alertmanager --config.file=/usr/local/alertmanager/alertmanager.ymlRestart=on-failure[Install]WantedBy=multi-user.target

global:  resolve_timeout: 5m  # 邮件SMTP配置  smtp_smarthost: 'smtp.exmail.qq.com:25'  smtp_from: 'service@yangxingzhen.com'  smtp_auth_username: 'service@yangxingzhen.com'  smtp_auth_password: '123456'  smtp_require_tls: false# 自定义通知模板templates:  - '/usr/local/prometheus/alertmanager/template/email.tmpl'# route用来设置报警的分发策略route:  # 采用哪个标签来作为分组依据  group_by: ['alertname']  # 组告警等待时间。也就是告警产生后等待10s，如果有同组告警一起发出  group_wait: 10s  # 两组告警的间隔时间  group_interval: 10s  # 重复告警的间隔时间，减少相同邮件的发送频率  repeat_interval: 1h  # 设置默认接收人  receiver: 'email'  routes:   # 可以指定哪些组接手哪些消息  - receiver: 'email'    continue: true    group_wait: 10sreceivers:- name: 'email'  email_configs:  - to: 'xingzhen.yang@yangxingzhen.com'    html: '{{ template "email.to.html" . }}'    headers: { Subject: "Prometheus [Warning] 报警邮件" }    send_resolved: true

{{ define "email.to.html" }}{{- if gt (len .Alerts.Firing) 0 -}}{{ range .Alerts }}=========start==========<br>告警程序: prometheus_alert <br>告警级别: {{ .Labels.severity }} <br>告警类型: {{ .Labels.alertname }} <br>告警主机: {{ .Labels.instance }} <br>告警主题: {{ .Annotations.summary }}  <br>告警详情: {{ .Annotations.description }} <br>触发时间: {{ .StartsAt.Format "2006-01-02 15:04:05" }} <br>=========end==========<br>{{ end }}{{ end -}} {{- if gt (len .Alerts.Resolved) 0 -}}{{ range .Alerts }}=========start==========<br>告警程序: prometheus_alert <br>告警级别: {{ .Labels.severity }} <br>告警类型: {{ .Labels.alertname }} <br>告警主机: {{ .Labels.instance }} <br>告警主题: {{ .Annotations.summary }} <br>告警详情: {{ .Annotations.description }} <br>触发时间: {{ .StartsAt.Format "2006-01-02 15:04:05" }} <br>恢复时间: {{ .EndsAt.Format "2006-01-02 15:04:05" }} <br>=========end==========<br>{{ end }}{{ end -}} {{- end }}

groups:- name: Node_exporter Down  rules:  - alert: Node实例已宕机    expr: up == 0    for: 10s    labels:      user: root      severity: Warning    annotations:      summary: "{{ $labels.job }}"      address: "{{ $labels.instance }}"      description: "Node_exporter 客户端在1分钟内连接失败."

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 configurationalerting:  alertmanagers:  - static_configs:    - targets: ['localhost:9093']      # - localhost:9093 # Load rules once and periodically evaluate them according to the global 'evaluation_interval'.rule_files:  - 'rules/*.yml'  # - "first_rules.yml"  # - "second_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:9100']

groups:- name: CPU  rules:  - alert: CPU使用率过高    expr: (100 - (avg by (instance) (irate(node_cpu{mode="idle"}[5m])) * 100)) > 80    for: 1m    labels:    severity: Warning      annotations:    summary: "{{ $labels.instance }} CPU使用率过高"      description: "{{ $labels.instance }}: CPU使用率超过80%，当前使用率({{ $value }})."

groups:- name: Memory  rules:  - alert: 内存使用率过高    expr: (node_memory_MemTotal - (node_memory_MemFree+node_memory_Buffers+node_memory_Cached )) / node_memory_MemTotal * 100 > 80    for: 1m  #告警持续时间，超过这个时间才会发送给alertmanager    labels:      severity: Warning    annotations:      summary: "{{ $labels.instance }} 内存使用率过高"      description: "{{ $labels.instance }}：内存使用率超过80%，当前使用率({{ $value }})."