groups: - name: freeipa_alerts rules: # 1. FreeIPA 节点宕机 / node_exporter 挂了 - alert: FreeIPA_Node_Down expr: up{job=~"freeipa|ipa"} == 0 for: 30s labels: severity: critical annotations: summary: "FreeIPA 节点失联" description: "节点 {{ $labels.instance }} node-exporter 掉线超过30秒,主机不可达" # 2. FreeIPA 核心综合服务异常(krb5kdc/httpd/ipa-custodia/pki-tomcatd) - alert: FreeIPA_Service_Down expr: sum by(instance,name) (node_systemd_unit_state{name=~"krb5kdc.service|httpd.service|ipa-custodia.service|pki-tomcatd@.*.service",state="active"}) != 1 for: 1m labels: severity: critical annotations: summary: "FreeIPA 核心服务异常停止" description: "节点 {{ $labels.instance }} 服务 {{ $labels.name }} 未处于运行状态" # 3. Kerberos KDC 认证服务异常 - alert: FreeIPA_Kerberos_Down expr: sum by(instance,name) (node_systemd_unit_state{name="krb5kdc.service",state="active"}) != 1 for: 1m labels: severity: critical annotations: summary: "Kerberos KDC 认证服务异常" description: "krb5kdc.service 停止,域用户无法完成Kerberos认证登录" # 4. FreeIPA Web 管理界面 httpd 服务异常 - alert: FreeIPA_HTTP_Down expr: sum by(instance,name) (node_systemd_unit_state{name="httpd.service",state="active"}) != 1 for: 1m labels: severity: critical annotations: summary: "FreeIPA Web 管理界面服务异常" description: "httpd.service 已停止,无法访问IPA网页管理端" # 5. PKI 证书签发服务 pki-tomcatd 异常 - alert: FreeIPA_PKI_Tomcat_Down expr: sum by(instance,name) (node_systemd_unit_state{name=~"pki-tomcatd@.*.service",state="active"}) != 1 for: 2m labels: severity: warning annotations: summary: "FreeIPA PKI 证书服务异常" description: "pki-tomcatd 证书签发服务停止,新证书无法申请下发" # 6. 专属监控 dirsrv@ADVANTEST-COM.service 389 LDAP目录服务停机 - alert: DirsrvServiceDown expr: sum by(instance,name) (node_systemd_unit_state{name="dirsrv@ADVANTEST-COM.service",state="active"}) != 1 for: 30s labels: severity: critical service: dirsrv-ADVANTEST annotations: summary: "389 LDAP目录服务已停止" description: "主机{{ $labels.instance }} dirsrv@ADVANTEST-COM.service 非运行状态,LDAP查询/认证失效,请立即检查" # 7. LDAP 端口 389/636 探测不通 - alert: FreeIPA_LDAP_Port_Down expr: probe_tcp_port{target=~".*:389|.*:636"} == 0 for: 30s labels: severity: critical annotations: summary: "LDAP 端口连通性异常" description: "无法TCP连接 {{ $labels.target }},防火墙/服务异常" # 8. Kerberos 88端口探测不通 - alert: FreeIPA_KRB5_Port_Down expr: probe_tcp_port{target=~".*:88"} == 0 for: 30s labels: severity: critical annotations: summary: "Kerberos 88端口不通" description: "目标 {{ $labels.target }} TCP88端口无法访问,Kerberos认证阻断" # 9. 证书剩余 <30天 预警 - alert: FreeIPA_Certificate_Will_Expire expr: ipa_cert_expiry_hours < 720 for: 1m labels: severity: warning annotations: summary: "FreeIPA 证书即将过期(剩余<30天)" description: "证书 {{ $labels.cert }} 有效期剩余不足30天,请规划续期" # 10. 证书剩余 <7天 紧急告警 - alert: FreeIPA_Certificate_Will_Expire_Critical expr: ipa_cert_expiry_hours < 168 for: 1m labels: severity: critical annotations: summary: "FreeIPA 证书即将过期!紧急处理" description: "证书 {{ $labels.cert }} 有效期剩余不足7天,逾期会导致域认证全部失效" # 11. 内存使用率超过85% - alert: FreeIPA_High_Memory_Usage expr: 100 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100) > 85 for: 2m labels: severity: warning annotations: summary: "FreeIPA主机内存使用率过高" description: "{{ $labels.instance }} 内存使用率 > 85%,存在OOM风险" # 12. CPU使用率超过90% - alert: FreeIPA_High_CPU_Usage expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 90 for: 2m labels: severity: warning annotations: summary: "FreeIPA主机CPU使用率过高" description: "{{ $labels.instance }} CPU持续占用高于90%,业务响应缓慢" # 13. 根分区磁盘使用率超85% - alert: FreeIPA_High_Disk_Usage expr: 100 - (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes * 100) > 85 for: 2m labels: severity: warning annotations: summary: "主机根分区磁盘使用率过高" description: "{{ $labels.instance }} / 分区磁盘占用 > 85%,请清理日志/扩容"