Files
homelab-infra/platform/observability/metrics/rules/shared-data-maintenance.yaml
T
panxiao81 0d633cf0cc
yaml / yaml (pull_request) Successful in 51s
ansible / collection-test (pull_request) Successful in 2m28s
ansible / lint (pull_request) Successful in 4m5s
fix: 使用 PrometheusRule 并按 exporter 版本获取官方校验和
2026-09-27 17:29:40 +00:00

64 lines
3.1 KiB
YAML

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: shared-data-maintenance
namespace: monitoring
spec:
groups:
- name: shared-data-maintenance
rules:
- alert: SharedDataMonitoringUnavailable
expr: up{job="shared-data-maintenance"} == 0 or absent(up{job="shared-data-maintenance"})
for: 3m
labels: {severity: warning, service: shared-data}
annotations:
summary: 共享数据维护指标无法采集
- alert: SharedDataCollectorStale
expr: >-
(time() - homelab_data_collection_timestamp_seconds{job="shared-data-maintenance"} > 180)
or (up{job="shared-data-maintenance"} == 1
unless on(instance) homelab_data_collection_timestamp_seconds{job="shared-data-maintenance"})
or node_textfile_scrape_error{job="shared-data-maintenance"} == 1
for: 3m
labels: {severity: warning, service: shared-data}
annotations:
summary: 共享数据本地采集结果缺失或停止更新
- alert: SharedDataCheckFailed
expr: homelab_data_check_success{job="shared-data-maintenance"} == 0
for: 3m
labels: {severity: warning, service: shared-data}
annotations:
summary: 共享数据维护检查失败,请核对对应检查项
- alert: SharedDataBackupStale
expr: time() - homelab_data_backup_timestamp_seconds{job="shared-data-maintenance"} > 36 * 3600
for: 5m
labels: {severity: warning, service: shared-data}
annotations:
summary: 共享数据备份已超过 36 小时或没有成功备份
- alert: SharedDataCertificateExpiringSoon
expr: >-
homelab_data_certificate_expiry_timestamp_seconds{job="shared-data-maintenance"} - time() < 10 * 86400
and homelab_data_certificate_expiry_timestamp_seconds{job="shared-data-maintenance"} - time() >= 3 * 86400
for: 5m
labels: {severity: warning, service: shared-data}
annotations:
summary: 共享数据证书剩余不足 10 天,请检查自动续签
- alert: SharedDataCertificateExpiryCritical
expr: homelab_data_certificate_expiry_timestamp_seconds{job="shared-data-maintenance"} - time() < 3 * 86400
for: 5m
labels: {severity: critical, service: shared-data}
annotations:
summary: 共享数据证书不足 3 天、已过期或无法读取
- alert: SharedDataRenewalStale
expr: time() - homelab_data_renewal_success_timestamp_seconds{job="shared-data-maintenance"} > 36 * 3600
for: 5m
labels: {severity: warning, service: shared-data}
annotations:
summary: 共享数据续签检查失败、停用或超过 36 小时未成功
- alert: SharedPostgresDevUnavailable
expr: homelab_data_dev_sql_ready{job="shared-data-maintenance"} == 0
for: 3m
labels: {severity: warning, service: shared-postgresql}
annotations:
summary: 共享 PG 开发实例本地 SQL 不可用或处于只读状态