69 lines
3.8 KiB
YAML
69 lines
3.8 KiB
YAML
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: openbao
|
|
namespace: monitoring
|
|
spec:
|
|
groups:
|
|
- name: openbao
|
|
rules:
|
|
- alert: OpenBaoMetricsUnavailable
|
|
expr: up{job="openbao"} == 0 or absent(up{job="openbao"})
|
|
for: 3m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: OpenBao 受鉴权指标采集不可用
|
|
description: 检查 Bao 健康与 sealed 状态、采集 Agent 登录/续期、TLS 和目标发现;此告警不区分停机与鉴权失败。
|
|
runbook_url: https://git.ddupan.top/panxiao81/homelab-wiki/src/branch/main/guides/openbao-monitoring-maintenance.md
|
|
- alert: OpenBaoInternalUnhealthy
|
|
expr: (min by(job) (vault_core_active{job="openbao"}) < 1 or min by(job) (vault_core_unsealed{job="openbao"})
|
|
< 1 or min by(job) (vault_autopilot_node_healthy{job="openbao"}) < 1) and on(job) (up{job="openbao"} ==
|
|
1)
|
|
for: 3m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: OpenBao 内部健康异常
|
|
description: 单节点部署应保持 active、unsealed 和 autopilot node healthy;检查 Raft 状态和服务日志。
|
|
runbook_url: https://git.ddupan.top/panxiao81/homelab-wiki/src/branch/main/guides/openbao-monitoring-maintenance.md
|
|
- alert: OpenBaoHealthMetricsMissing
|
|
expr: (absent(vault_core_active{job="openbao"}) or absent(vault_core_unsealed{job="openbao"}) or absent(vault_autopilot_node_healthy{job="openbao"}))
|
|
and on(job) (up{job="openbao"} == 1)
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: OpenBao 内部健康指标缺失
|
|
description: 接口可采集但核心 gauge 缺失;检查 telemetry、版本和指标过滤,不将缺数据视为健康。
|
|
runbook_url: https://git.ddupan.top/panxiao81/homelab-wiki/src/branch/main/guides/openbao-monitoring-maintenance.md
|
|
- alert: OpenBaoSnapshotFailed
|
|
expr: openbao_snapshot_last_run_success{job="node-exporter",node="bao1"} == 0
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: OpenBao 最近一次本地快照失败
|
|
description: 检查 openbao-snapshot.service 日志、sealed 状态、快照 token 续期与磁盘;修复后重跑任务。
|
|
runbook_url: https://git.ddupan.top/panxiao81/homelab-wiki/src/branch/main/guides/openbao-monitoring-maintenance.md
|
|
- alert: OpenBaoSnapshotStale
|
|
expr: time() - openbao_snapshot_last_success_timestamp_seconds{job="node-exporter",node="bao1"} > 36 * 3600
|
|
or absent(openbao_snapshot_last_success_timestamp_seconds{job="node-exporter",node="bao1"})
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: OpenBao 本地快照已超时或没有成功记录
|
|
description: 每日快照超过 36 小时未成功,或成功指标缺失;检查定时器与快照任务。此指标不证明异地备份或恢复可用。
|
|
runbook_url: https://git.ddupan.top/panxiao81/homelab-wiki/src/branch/main/guides/openbao-monitoring-maintenance.md
|
|
- alert: OpenBaoSnapshotMetricsUnavailable
|
|
expr: up{job="node-exporter",node="bao1"} == 0 or absent(up{job="node-exporter",node="bao1"}) or node_textfile_scrape_error{job="node-exporter",node="bao1"}
|
|
== 1 or absent(openbao_snapshot_last_run_success{job="node-exporter",node="bao1"}) or absent(openbao_snapshot_last_run_timestamp_seconds{job="node-exporter",node="bao1"})
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: OpenBao 快照监控不可用
|
|
description: 检查 bao1:9100 的 node_exporter、textfile 目录及快照脚本;采集独立于 Bao 的鉴权接口。
|
|
runbook_url: https://git.ddupan.top/panxiao81/homelab-wiki/src/branch/main/guides/openbao-monitoring-maintenance.md
|