mirror of
https://github.com/Telecominfraproject/wlan-toolsmith.git
synced 2025-10-29 01:52:27 +00:00
Adapt alert to use new exitcode metric
Signed-off-by: Johann Hoffmann <johann.hoffmann@mailbox.org>
This commit is contained in:
@@ -254,8 +254,8 @@ releases:
|
||||
annotations:
|
||||
title: Pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* has been OOM killed
|
||||
description: The pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* has been killed due to reaching its memory limit. Investigate the memory usage or increase the limit to prevent this.
|
||||
- alert: Pod terminated
|
||||
expr: (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="Error"}[10m]) == 1
|
||||
- alert: Pod exited with a segfault
|
||||
expr: (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and min_over_time(kube_pod_container_status_last_terminated_exitcode[10m]) == 139
|
||||
for: 0m
|
||||
labels:
|
||||
severity: error
|
||||
@@ -264,8 +264,8 @@ releases:
|
||||
pod: "{{`{{ $labels.pod }}`}}"
|
||||
reason: "{{`{{ $labels.reason }}`}}"
|
||||
annotations:
|
||||
title: Pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* terminated due to an error
|
||||
description: The pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* has terminated due to an error, please investigate the cause.
|
||||
title: Pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* exited with a segfault
|
||||
description: The pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* exited with a segmentation fault, please examine the coredump.
|
||||
- alert: Node low on memory
|
||||
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 5
|
||||
for: 1m
|
||||
|
||||
Reference in New Issue
Block a user