feat: 补齐共享数据备份、证书续签与开发实例监控
yaml / yaml (pull_request) Successful in 27s
ansible / collection-test (pull_request) Successful in 1m59s
ansible / lint (pull_request) Successful in 3m14s

This commit is contained in:
2026-09-27 17:05:24 +00:00
parent 06943d4c65
commit 0988f5c37e
12 changed files with 642 additions and 1 deletions
@@ -0,0 +1,168 @@
rule_files:
- rules.yaml
evaluation_interval: 1m
tests:
- name: 过期证书持续 critical
interval: 1m
input_series:
- series: homelab_data_certificate_expiry_timestamp_seconds{job="shared-data-maintenance",instance="host:9109",certificate="etcd-peer"}
values: '0x15'
alert_rule_test:
- eval_time: 10m
alertname: SharedDataCertificateExpiryCritical
exp_alerts:
- exp_labels:
job: shared-data-maintenance
instance: host:9109
certificate: etcd-peer
severity: critical
service: shared-data
exp_annotations:
summary: 共享数据证书不足 3 天、已过期或无法读取
- name: critical 证书不再重复 warning
interval: 1m
input_series:
- series: homelab_data_certificate_expiry_timestamp_seconds{job="shared-data-maintenance",instance="host:9109",certificate="etcd-peer"}
values: '0x15'
alert_rule_test:
- eval_time: 10m
alertname: SharedDataCertificateExpiringSoon
exp_alerts: []
- name: 正常证书不误报
interval: 1m
input_series:
- series: homelab_data_certificate_expiry_timestamp_seconds{job="shared-data-maintenance",instance="host:9109",certificate="etcd-peer"}
values: 5184000x15
alert_rule_test:
- eval_time: 10m
alertname: SharedDataCertificateExpiringSoon
exp_alerts: []
- name: 七天内证书预警
interval: 1m
input_series:
- series: homelab_data_certificate_expiry_timestamp_seconds{job="shared-data-maintenance",instance="host:9109",certificate="etcd-peer"}
values: 604800x15
alert_rule_test:
- eval_time: 10m
alertname: SharedDataCertificateExpiringSoon
exp_alerts:
- exp_labels:
job: shared-data-maintenance
instance: host:9109
certificate: etcd-peer
severity: warning
service: shared-data
exp_annotations:
summary: 共享数据证书剩余不足 10 天,请检查自动续签
- name: 备份超过36小时
interval: 1m
input_series:
- series: homelab_data_backup_timestamp_seconds{job="shared-data-maintenance",instance="host:9109",backup="etcd"}
values: -130000x15
alert_rule_test:
- eval_time: 10m
alertname: SharedDataBackupStale
exp_alerts:
- exp_labels:
job: shared-data-maintenance
instance: host:9109
backup: etcd
severity: warning
service: shared-data
exp_annotations:
summary: 共享数据备份已超过 36 小时或没有成功备份
- name: 新备份没有告警
interval: 1m
input_series:
- series: homelab_data_backup_timestamp_seconds{job="shared-data-maintenance",instance="host:9109",backup="etcd"}
values: 0+60x15
alert_rule_test:
- eval_time: 10m
alertname: SharedDataBackupStale
exp_alerts: []
- name: exporter 存活但没有采集文件
interval: 1m
input_series:
- series: up{job="shared-data-maintenance",instance="host:9109"}
values: 1x15
alert_rule_test:
- eval_time: 10m
alertname: SharedDataCollectorStale
exp_alerts:
- exp_labels:
job: shared-data-maintenance
instance: host:9109
severity: warning
service: shared-data
exp_annotations: &id001
summary: 共享数据本地采集结果缺失或停止更新
- name: 采集心跳过期
interval: 1m
input_series:
- series: homelab_data_collection_timestamp_seconds{job="shared-data-maintenance",instance="host:9109"}
values: '0x15'
alert_rule_test:
- eval_time: 10m
alertname: SharedDataCollectorStale
exp_alerts:
- exp_labels:
job: shared-data-maintenance
instance: host:9109
severity: warning
service: shared-data
exp_annotations: *id001
- name: SQL 拒绝和只读触发 dev 告警
interval: 1m
input_series:
- series: homelab_data_dev_sql_ready{job="shared-data-maintenance",instance="host:9109"}
values: '0x15'
alert_rule_test:
- eval_time: 10m
alertname: SharedPostgresDevUnavailable
exp_alerts:
- exp_labels:
job: shared-data-maintenance
instance: host:9109
severity: warning
service: shared-postgresql
exp_annotations:
summary: 共享 PG 开发实例本地 SQL 不可用或处于只读状态
- name: dev 恢复后解除
interval: 1m
input_series:
- series: homelab_data_dev_sql_ready{job="shared-data-maintenance",instance="host:9109"}
values: 0x4 1x10
alert_rule_test:
- eval_time: 10m
alertname: SharedPostgresDevUnavailable
exp_alerts: []
- name: 续签检查超过36小时
interval: 1m
input_series:
- series: homelab_data_renewal_success_timestamp_seconds{job="shared-data-maintenance",instance="host:9109",unit="homelab-etcd-renew"}
values: -130000x15
alert_rule_test:
- eval_time: 10m
alertname: SharedDataRenewalStale
exp_alerts:
- exp_labels:
job: shared-data-maintenance
instance: host:9109
unit: homelab-etcd-renew
severity: warning
service: shared-data
exp_annotations:
summary: 共享数据续签检查失败、停用或超过 36 小时未成功
- name: 整个 scrape 消失仍报警
interval: 1m
input_series: []
alert_rule_test:
- eval_time: 10m
alertname: SharedDataMonitoringUnavailable
exp_alerts:
- exp_labels:
severity: warning
service: shared-data
job: shared-data-maintenance
exp_annotations:
summary: 共享数据维护指标无法采集