[Backport release-1.1] [piraeus-operator] Fix LINSTOR satellite alert labels and scrape flapping false positives (#2286)
# Description Backport of #2265 to `release-1.1`.
This commit is contained in:
commit
7fc6207fbc
1 changed files with 19 additions and 7 deletions
|
|
@ -7,19 +7,31 @@ spec:
|
|||
groups:
|
||||
- name: linstor.rules
|
||||
rules:
|
||||
- alert: linstorControllerOffline
|
||||
- alert: linstorControllerUnavailable
|
||||
annotations:
|
||||
description: |
|
||||
LINSTOR Controller is not reachable.
|
||||
expr: up{job="linstor-controller"} == 0
|
||||
LINSTOR Controller deployment has no available replicas.
|
||||
expr: kube_deployment_status_replicas_available{namespace="cozy-linstor",deployment="linstor-controller"} < 1
|
||||
for: 3m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: linstorControllerMetricsScrapeFailing
|
||||
annotations:
|
||||
description: |
|
||||
LINSTOR Controller metrics endpoint is not being scraped successfully.
|
||||
expr: up{job="linstor-controller"} == 0
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: linstorSatelliteErrorRate
|
||||
annotations:
|
||||
description: |
|
||||
LINSTOR Satellite "{{ $labels.name }}" reports {{ $value }} errors in the last 15 minutes.
|
||||
Use "linstor error-reports list --nodes {{ $labels.name }} --since 15minutes" to see them.
|
||||
expr: increase(linstor_error_reports_count{module="SATELLITE"}[15m]) > 0
|
||||
LINSTOR Satellite "{{ $labels.hostname }}" reports {{ $value }} errors in the last 15 minutes.
|
||||
Use "linstor error-reports list --nodes {{ $labels.hostname }}" to inspect the reports.
|
||||
expr: |
|
||||
increase(linstor_error_reports_count{module="SATELLITE"}[15m]) > 0
|
||||
and on(instance, job)
|
||||
min_over_time(up{job="linstor-controller"}[15m]) == 1
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: linstorControllerErrorRate
|
||||
|
|
@ -33,7 +45,7 @@ spec:
|
|||
- alert: linstorSatelliteNotOnline
|
||||
annotations:
|
||||
description: |
|
||||
LINSTOR Satellite "{{ $labels.name }}" is not ONLINE.
|
||||
LINSTOR Satellite "{{ $labels.hostname }}" is not ONLINE.
|
||||
Check that the Satellite is running and reachable from the LINSTOR Controller.
|
||||
expr: linstor_node_state{nodetype="SATELLITE"} != 2
|
||||
labels:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue