Files
helm-charts/charts/postgres-cluster/prometheus_rules/cluster-high_replication_lag.yaml
Alex Lebens 1ca985edc7
All checks were successful
release-charts-postgres-cluster / release (push) Successful in 18s
rebase this chart on cnpg provided chart
2025-05-13 00:14:16 -05:00

20 lines
766 B
YAML

{{- $alert := "CNPGClusterHighReplicationLag" -}}
{{- if not (has $alert .excludeRules) -}}
alert: {{ $alert }}
annotations:
summary: CNPG Cluster high replication lag
description: |-
CloudNativePG Cluster "{{ .namespace }}/{{ .cluster }}" is experiencing a high replication lag of
{{ .value }}ms.
High replication lag indicates network issues, busy instances, slow queries or suboptimal configuration.
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighReplicationLag.md
expr: |
max(cnpg_pg_replication_lag{namespace="{{ .namespace }}",pod=~"{{ .podSelector }}"}) * 1000 > 1000
for: 5m
labels:
severity: warning
namespace: {{ .namespace }}
cnpg_cluster: {{ .cluster }}
{{- end -}}