alertmanger

1.  安装alertmanger

wget https://github.com/prometheus/alertmanager/releases/download/v0.21.0/alertmanager-0.21.0.linux-amd64.tar.gz
tar -zxvf alertmanager-0.21.0.linux-amd64.tar.gz -C /usr/local
cd /usr/local/alertmanager-0.21.0.linux-amd64

　

2.  启动

./alertmanger

　　

3. 编写启动文件启动

[Unit]
Description=alertmanager
After=network.target

[Service]
Type=simple
User=root
Group=root
WorkingDirectory=/usr/local/alertmanager
ExecStart=/bin/sh -c '/usr/local/alertmanager/alertmanager --web.external-url=http://192.168.17.12:9093/  --log.level=debug >>/usr/local/alertmanager/alertmanager.log 2>&1 '
Restart=on-failure

[Install]
WantedBy=multi-user.target

　　

4. 启动服务

systemctl daemon-reload && systemctl enable alertmanager.service && systemctl start alertmanager.service

　　

5. 新建报警文件

cd   /usr/local/prometheus/prometheus-2.46.0.linux-amd64/
mkdir rules
cat  node_rule.yml
# groups：组告警
groups:
# name：组名。报警规则组名称
- name: general.rules
  # rules：定义角色
  rules:
  # alert：告警名称。 任何实例5分钟内无法访问发出告警
  - alert: NodeFilesystemUsage
    # expr：表达式。 获取磁盘使用率 大于百分之80 触发
    expr: 100 - (node_filesystem_free_bytes{mountpoint="/",fstype=~"ext4|xfs"} / node_filesystem_size_bytes{fstype=~"ext4|xfs"} * 100) > 80
    # for：持续时间。 表示持续一分钟获取不到信息，则触发报警。0表示不使用持续时间
    for: 1m
    # labels：定义当前告警规则级别
    labels:
      # severity: 指定告警级别。
      severity: warning
    # annotations: 注释 告警通知
    annotations:
      # 调用标签具体指附加通知信息
      summary: "Instance {{ $labels.instance  }} ：{{ $labels.mountpoint }} 分区使用率过高" # 自定义摘要
      description: "{{ $labels.instance  }} ： {{ $labels.job  }} ：{{ $labels.mountpoint  }} 这个分区使用大于百分之80% (当前值：{{ $value }})" # 自定义具体描述
  - alert: CpuUserdAlert 
    # cpu使用率大于7就报警
    expr: (1 - avg(rate(node_cpu_seconds_total{host="node1",env=~"test",mode="idle"}[5m])) by (instance)) * 100 > 7
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "cpu使用率过高"
      description: "cpu使用率过高"

6. prometheus主配置文件关联报警文件，在rule_files下面引用报警文件

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:
           - localhost:9093

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  - "/usr/local/prometheus/prometheus-2.46.0.linux-amd64/rules/node_rule.yml"
  # - "first_rules.yml"
  # - "second_rules.yml"

7. 报警效果