部署alertmanager

部署alertmanager

1 部署完成elk集群或者单节点

2 创建用户

# useradd prometheus

# chown -R prometheus:prometheus /usr/local/alertmanager

# vim /usr/lib/systemd/system/alertmanager.service

[Unit]

Description=Alertmanager

After=network.target

[Service]

Type=simple

User=prometheus

ExecStart=/usr/local/alertmanager/alertmanager --config.file=/usr/local/alertmanager/alertmanager.yml --storage.path=/usr/local/alertmanager/data

Restart=on-failure

[Install]

WantedBy=multi-user.target

启动

# systemctl enable alertmanager.service

# systemctl start alertmanager.service

3 配置报警规则

编写报警规则：（举例）

修改alertmanager的配置文件如下格式

global:

  resolve_timeout: 5m

route:

  group_by: ['alertname']

  group_wait: 10s

  group_interval: 10s

  repeat_interval: 1h

 # receiver: 'web.hook'

  receiver: 'default-receiver'

receivers:

#- name: 'web.hook'

#  webhook_configs:

#  - url: 'http://127.0.0.1:5001/'

- name: 'default-receiver'

inhibit_rules:

  - source_match:

      severity: 'critical'

    target_match:

      severity: 'warning'

    equal: ['alertname', 'dev', 'instance']

修改prometheus的配置文件的格式如下所示：

groups:

- name: memorytrule

  rules:

  - alert: "memoryalert"

    expr: 100 - ((node_memory_MemAvailable * 100) / node_memory_MemTotal) > 10

    for: 1s

    labels:

      severity: warning

    annotations:

      summary: "service:{{$labels.alertname}}"

      description: "alert: {{ $value }}"

      value: "{{ $value }}"