diff --git a/packages/system/postgres-operator/templates/prometheusrule.yaml b/packages/system/postgres-operator/alerts/cnpg-default-alerts.yaml similarity index 84% rename from packages/system/postgres-operator/templates/prometheusrule.yaml rename to packages/system/postgres-operator/alerts/cnpg-default-alerts.yaml index 6bc7cdb2..a23fb3f4 100644 --- a/packages/system/postgres-operator/templates/prometheusrule.yaml +++ b/packages/system/postgres-operator/alerts/cnpg-default-alerts.yaml @@ -15,8 +15,8 @@ spec: for: 1m labels: severity: warning - namespace: {{ $labels.namespace }} - job: {{ $labels.job }} + namespace: "{{ $labels.namespace }}" + job: "{{ $labels.job }}" - alert: BackendsWaiting annotations: description: Namespace {{ $labels.namespace }} Job {{ $labels.job }} Pod {{ $labels.pod }} has been waiting for longer than 5 minutes @@ -26,8 +26,8 @@ spec: for: 1m labels: severity: warning - namespace: {{ $labels.namespace }} - job: {{ $labels.job }} + namespace: "{{ $labels.namespace }}" + job: "{{ $labels.job }}" - alert: PGDatabaseXidAge annotations: description: Over 300,000,000 transactions from frozen xid on Namespace {{ $labels.namespace }} Job {{ $labels.job }} Pod {{ $labels.pod }} @@ -37,8 +37,8 @@ spec: for: 1m labels: severity: warning - namespace: {{ $labels.namespace }} - job: {{ $labels.job }} + namespace: "{{ $labels.namespace }}" + job: "{{ $labels.job }}" - alert: PGReplication annotations: description: Namespace {{ $labels.namespace }} Job {{ $labels.job }} Pod {{ $labels.pod }} Standby is lagging behind by over 300 seconds (5 minutes) @@ -48,8 +48,8 @@ spec: for: 1m labels: severity: warning - namespace: {{ $labels.namespace }} - job: {{ $labels.job }} + namespace: "{{ $labels.namespace }}" + job: "{{ $labels.job }}" - alert: LastFailedArchiveTime annotations: description: Archiving failed for Namespace {{ $labels.namespace }} Job {{ $labels.job }} Pod {{ $labels.pod }} @@ -59,8 +59,8 @@ spec: for: 1m labels: severity: warning - namespace: {{ $labels.namespace }} - job: {{ $labels.job }} + namespace: "{{ $labels.namespace }}" + job: "{{ $labels.job }}" - alert: DatabaseDeadlockConflicts annotations: description: There are over 10 deadlock conflicts in Namespace {{ $labels.namespace }} Job {{ $labels.job }} Pod {{ $labels.pod }} @@ -70,8 +70,8 @@ spec: for: 1m labels: severity: warning - namespace: {{ $labels.namespace }} - job: {{ $labels.job }} + namespace: "{{ $labels.namespace }}" + job: "{{ $labels.job }}" - alert: ReplicaFailingReplication annotations: description: Namespace {{ $labels.namespace }} Job {{ $labels.job }} Pod {{ $labels.pod }} Replica is failing to replicate @@ -81,8 +81,8 @@ spec: for: 1m labels: severity: warning - namespace: {{ $labels.namespace }} - job: {{ $labels.job }} + namespace: "{{ $labels.namespace }}" + job: "{{ $labels.job }}" - alert: CNPGClusterOffline annotations: summary: CNPG Cluster has no running instances! @@ -96,6 +96,6 @@ spec: for: 5m labels: severity: critical - namespace: {{ $labels.namespace }} - job: {{ $labels.job }} - pod: {{ $labels.pod }} + namespace: "{{ $labels.namespace }}" + job: "{{ $labels.job }}" + pod: "{{ $labels.pod }}" diff --git a/packages/system/postgres-operator/templates/alerts.yaml b/packages/system/postgres-operator/templates/alerts.yaml new file mode 100644 index 00000000..70d47014 --- /dev/null +++ b/packages/system/postgres-operator/templates/alerts.yaml @@ -0,0 +1,7 @@ +{{- $files := .Files.Glob "alerts/*.yaml" -}} +{{- range $path, $file := $files }} +--- +# from: {{ $path }} +{{ toString $file }} + +{{- end -}}