Files
homelab-infra/platform/observability/metrics/rules/shared-etcd.yaml
T
panxiao81 3a2fe5fa0c
yaml / yaml (pull_request) Successful in 41s
ansible / collection-test (pull_request) Successful in 2m41s
terraform / validate (pull_request) Successful in 2m41s
ansible / lint (pull_request) Successful in 4m36s
feat: 纳管共享 etcd 与 k3s 外 PostgreSQL 高可用及备份
2026-09-25 19:34:48 +00:00

62 lines
2.0 KiB
YAML

# 参考 Pigsty v4.5.0 etcd 指标与阈值,适配原生 up 和现有标签;无 Pigsty UI 依赖。
apiVersion: operator.victoriametrics.com/v1beta1
kind: VMRule
metadata:
name: shared-etcd
namespace: monitoring
spec:
groups:
- name: shared-etcd
rules:
- alert: SharedEtcdMemberUnavailable
expr: up{job="shared-etcd"} == 0
for: 2m
labels:
severity: warning
service: shared-etcd
annotations:
summary: 共享 etcd 成员 {{ $labels.member }} 无法采集
- alert: SharedEtcdMonitoringQuorumUnavailable
expr: (sum(up{job="shared-etcd"}) or vector(0)) < 2
for: 2m
labels:
severity: critical
service: shared-etcd
annotations:
summary: 共享 etcd 不足两个成员可采集,请用 endpoint health 核实 quorum
- alert: SharedEtcdNoLeader
expr: etcd_server_has_leader{job="shared-etcd"} == 0
for: 1m
labels:
severity: critical
service: shared-etcd
annotations:
summary: 共享 etcd 成员 {{ $labels.member }} 无法确认 leader
- alert: SharedEtcdQuotaHigh
expr: etcd_mvcc_db_total_size_in_bytes{job="shared-etcd"} / etcd_server_quota_backend_bytes{job="shared-etcd"}
> 0.8
for: 10m
labels:
severity: warning
service: shared-etcd
annotations:
summary: 共享 etcd 后端容量超过 80%
- alert: SharedEtcdSlowFsync
expr: histogram_quantile(0.95, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job="shared-etcd"}[5m]))
> 0.05
for: 10m
labels:
severity: warning
service: shared-etcd
annotations:
summary: 共享 etcd {{ $labels.member }} WAL fsync p95 超过 50ms
- alert: SharedEtcdFrequentElections
expr: increase(etcd_server_leader_changes_seen_total{job="shared-etcd"}[15m])
> 3
for: 5m
labels:
severity: warning
service: shared-etcd
annotations:
summary: 共享 etcd 15 分钟内多次选举