Skip to content

Commit

Permalink
chore: rename a few alerts
Browse files Browse the repository at this point in the history
Signed-off-by: Christoph Görn <[email protected]>
  • Loading branch information
goern committed Sep 16, 2023
1 parent c98c391 commit 6b384d1
Show file tree
Hide file tree
Showing 2 changed files with 3 additions and 3 deletions.
2 changes: 1 addition & 1 deletion manifests/base/influxdb/monitoring_alerting.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ spec:
groups:
- name: InfluxDB2PersistentVolumes
rules:
- alert: influxdb2
- alert: InfluxDB2PersistentVolumeFull
annotations:
description: InfluxDB2 data volume is full.
summary: InfluxDB2 data volume is full.
Expand Down
4 changes: 2 additions & 2 deletions manifests/env/nostromo-stage/postgresql/alerting.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -6,14 +6,14 @@ spec:
groups:
- name: BackupAlertRules
rules:
- alert: DiffBackupTimeout
- alert: PostresqlDiffBackupTimeout
expr: time() - max( kube_job_status_start_time * ON(job_name) GROUP_RIGHT() kube_job_labels{job_name=~"db-repo1-diff.*"} * ON(job_name) GROUP_RIGHT() label_replace(kube_pod_labels, "job_name", "$1", "label_job_name", "(.*)") * ON(pod) GROUP_RIGHT() kube_pod_status_phase{job="kube-state-metrics",phase=~"Succeeded"}) BY (job_name,label_postgres_operator_crunchydata_com_pgbackrest_cronjob) > 86400
labels:
severity: critical
for: 10m
annotations:
message: "Backup job {{ $labels.job_name }} has NOT been running for more than 24 hours."
- alert: FailedBackupPods
- alert: PostgresqlFailedBackupPods
expr: kube_pod_status_phase{namespace="b4mad-racing-stage",phase="Failed"} * ON(pod) GROUP_RIGHT() kube_pod_labels{label_postgres_operator_crunchydata_com_pgbackrest_cronjob="diff",namespace="b4mad-racing-stage"} > 0
labels:
severity: critical
Expand Down

0 comments on commit 6b384d1

Please sign in to comment.