monitoring: alert on soteria backup job creation spikes
This commit is contained in:
parent
20305a7181
commit
2221a2d279
@ -639,6 +639,54 @@ data:
|
||||
summary: "Soteria saw >10 authorization denials in 15m"
|
||||
labels:
|
||||
severity: warning
|
||||
- uid: maint-soteria-backup-job-storm
|
||||
title: "Soteria backup job creation spike"
|
||||
condition: C
|
||||
for: "5m"
|
||||
data:
|
||||
- refId: A
|
||||
relativeTimeRange:
|
||||
from: 600
|
||||
to: 0
|
||||
datasourceUid: atlas-vm
|
||||
model:
|
||||
expr: sum(increase(kube_job_created{namespace="maintenance",job_name=~"soteria-backup-.*"}[10m])) or on() vector(0)
|
||||
intervalMs: 60000
|
||||
maxDataPoints: 43200
|
||||
legendFormat: soteria-backup-jobs-created-10m
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: atlas-vm
|
||||
- refId: B
|
||||
datasourceUid: __expr__
|
||||
model:
|
||||
expression: A
|
||||
intervalMs: 60000
|
||||
maxDataPoints: 43200
|
||||
reducer: last
|
||||
type: reduce
|
||||
- refId: C
|
||||
datasourceUid: __expr__
|
||||
model:
|
||||
expression: B
|
||||
intervalMs: 60000
|
||||
maxDataPoints: 43200
|
||||
type: threshold
|
||||
conditions:
|
||||
- evaluator:
|
||||
params: [8]
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
reducer:
|
||||
type: last
|
||||
type: query
|
||||
noDataState: OK
|
||||
execErrState: Alerting
|
||||
annotations:
|
||||
summary: "Soteria created >8 backup jobs in 10m (possible scheduler storm)"
|
||||
labels:
|
||||
severity: warning
|
||||
- orgId: 1
|
||||
name: ariadne
|
||||
folder: Alerts
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user