groups: - name: Linux-Base-Alert rules: # 节点离线 = Failed - alert: Host_Down_Failed expr: up == 0 for: 30s labels: severity: critical level: Failed annotations: summary: "❌ 节点离线 Failed" description: | 主机:{{ $labels.instance }} 任务:{{ $labels.job }} - alert: Host_Ping_Offline expr: probe_success{job=~"blackbox_icmp.*"} == 0 for: 1m labels: severity: critical level: Down annotations: summary: "主机 Ping 失联 {{ $labels.instance }}" description: "主机网络不通,ICMP探测失败,大概率整机宕机或网段隔离" - alert: Port_Down expr: probe_success{port!=""} == 0 for: 1m labels: severity: critical level: Down annotations: summary: "端口 {{ $labels.port }} 通信异常 {{ $labels.instance }}" description: | 业务:{{ $labels.business }} 监控任务:{{ $labels.job }} 故障地址:{{ $labels.instance }} 异常端口:{{ $labels.port }} # CPU 警告 Warning - alert: CPU_High_Warning expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80 for: 3m labels: severity: warning level: Warning annotations: summary: "⚠️ CPU 负载过高 Warning" description: "主机 {{ $labels.instance }} CPU 使用率:{{ printf \"%.2f\" $value }} %" # 内存严重 Failed - alert: Mem_High_Failed expr: 100 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100) > 90 for: 3m labels: severity: critical level: Failed annotations: summary: "❌ 内存占用过高 Failed" description: "主机 {{ $labels.instance }} 内存使用率:{{ printf \"%.2f\" $value }} %" # 磁盘警告 Warning - alert: Disk_High_Warning expr: 100 - (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes * 100) > 85 for: 2m labels: severity: warning level: Warning annotations: summary: "⚠️ 磁盘空间不足 Warning" description: "分区 {{ $labels.mountpoint }} 使用率:{{ printf \"%.2f\" $value }} %" - name: FreeIPA-Alert rules: # FreeIPA 核心服务异常 Failed - alert: FreeIPA_Service_Failed expr: node_systemd_unit_state{name=~"ipa|dirsrv|krb5kdc|httpd|pki-tomcatd|sssd",state="active"} == 0 for: 60s labels: severity: critical level: Failed annotations: summary: "❌ FreeIPA 服务异常 Failed" description: | 故障主机:{{ $labels.instance }} 异常服务:{{ $labels.name }} 影响:域认证、LDAP、登录挂载异常