#案例2##服务器磁盘监控 groups: #----------------------------------生成环境-------------------------------------------------- - name: ProdApplication1_disk_alerts rules: - alert: ProdApplication1_disk_usage_too_High # node_filesystem_avail_bytes{mountpoint/}/node_filesystem_size_bytes{mountpoint/}*100 10 expr: (node_filesystem_size_bytes{job~ProdApplication1,fstype~ext.*|xfs|nfs,mountpoint !~.*(pod|docker).*}-node_filesystem_free_bytes{job~ProdApplication1,fstype~ext.*|xfs|nfs,mountpoint !~.*(pod|docker).*}) *100/(node_filesystem_avail_bytes {job~ProdApplication1,fstype~ext.*|xfs|nfs,mountpoint !~.*(pod|docker).*}(node_filesystem_size_bytes{job~ProdApplication1,fstype~ext.*|xfs|nfs,mountpoint !~.*(pod|docker).*}-node_filesystem_free_bytes{job~ProdApplication1,fstype~ext.*|xfs|nfs,mountpoint !~.*(pod|docker).*})) 90 for: 5m labels: severity: warning team: ProdApplication1 annotations: summary: Disk usage is too high on {{ $labels.instance }} description: {{ $labels.instance }} has less than 10%!d(MISSING)isk space available.#接收规则分组route: #匹配的分组team,这里为了方便区别,每组team和job我使用相同的名字 group_by: [test,bigdata,blockchain,pressuretest,fileservice,algo,office,ProdBigData,ProdBlockChain,TDengine1,TestCarbonBrain,ProdNginx,ProdApplication1,ProdMiddleWareFortress] group_wait: 30s group_interval: 5m repeat_interval: 1h receiver: test_email #默认接收邮箱 #配置分组邮件接收 routes: - receiver: test_email # 对应下面接收邮箱 group_by: [test] matchers: - team test group_interval: 10s group_wait: 30s repeat_interval: 60m - receiver: bigdata_email group_by: [bigdata] matchers: - team bigdata group_interval: 10s group_wait: 30s repeat_interval: 60m#案例3#dev env,rule define dev - matchers: - severity~none - team ~dev group_by: [test] group_interval: 10s group_wait: 30s receiver: feishu-alert-dev mute_time_intervals: - offhours - holiday repeat_interval: 2h分组route: group_by: [alertname,instance] group_wait: 10s group_interval: 10s repeat_interval: 1m receiver: feishu-alert-default routes: - matchers: - severity~critical|Critical repeat_interval: 1m - matchers: - severity~warning|Warning repeat_interval: 1m - matchers: - severity~none receiver: feishu-alert-test1 mute_time_intervals: - offhours - holiday repeat_interval: 4h