Alex Lebens
1ca985edc7
All checks were successful
release-charts-postgres-cluster / release (push) Successful in 18s
27 lines
1.3 KiB
YAML
27 lines
1.3 KiB
YAML
{{- $alert := "CNPGClusterHACritical" -}}
|
|
{{- if not (has $alert .excludeRules) -}}
|
|
alert: {{ $alert }}
|
|
annotations:
|
|
summary: CNPG Cluster has no standby replicas!
|
|
description: |-
|
|
CloudNativePG Cluster "{{ .labels.job }}" has no ready standby replicas. Your cluster at a severe
|
|
risk of data loss and downtime if the primary instance fails.
|
|
|
|
The primary instance is still online and able to serve queries, although connections to the `-ro` endpoint
|
|
will fail. The `-r` endpoint os operating at reduced capacity and all traffic is being served by the main.
|
|
|
|
This can happen during a normal fail-over or automated minor version upgrades in a cluster with 2 or less
|
|
instances. The replaced instance may need some time to catch-up with the cluster primary instance.
|
|
|
|
This alarm will be always trigger if your cluster is configured to run with only 1 instance. In this
|
|
case you may want to silence it.
|
|
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHACritical.md
|
|
expr: |
|
|
max by (job) (cnpg_pg_replication_streaming_replicas{namespace="{{ .namespace }}"} - cnpg_pg_replication_is_wal_receiver_up{namespace="{{ .namespace }}"}) < 1
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
namespace: {{ .namespace }}
|
|
cnpg_cluster: {{ .cluster }}
|
|
{{- end -}}
|