31 lines
1.1 KiB
YAML
31 lines
1.1 KiB
YAML
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: openbao-backups-external-rclone
|
|
namespace: openbao
|
|
labels:
|
|
helm.sh/chart: rclone-openbao-backups-external-0.11.2
|
|
app.kubernetes.io/instance: openbao
|
|
app.kubernetes.io/part-of: openbao
|
|
app.kubernetes.io/version: "0.11.2"
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/name: openbao-backups-external-rclone
|
|
spec:
|
|
groups:
|
|
- name: rclone.alerts
|
|
rules:
|
|
- alert: RclonePodFailed
|
|
expr: |
|
|
(kube_pod_container_status_last_terminated_exitcode > 0)
|
|
* on(pod, namespace) group_left(owner_name)
|
|
kube_pod_owner{owner_kind="Job", owner_name=~"rclone-.*"}
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Rclone Pod failed in {{ $labels.namespace }}"
|
|
description: |
|
|
A pod for the Rclone sync of s3 bucket 'openbao-backups' failed with exit code {{ $value }}.
|
|
Job: {{ $labels.owner_name }}
|
|
Namespace: {{ $labels.namespace }}
|