scottk/wlan-toolsmith
1
0
Fork 0
mirror of https://github.com/Telecominfraproject/wlan-toolsmith.git synced 2025-10-30 02:22:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adapt alert to use new exitcode metric

Browse Source 
Signed-off-by: Johann Hoffmann <johann.hoffmann@mailbox.org>
This commit is contained in:
Johann Hoffmann
2022-11-04 15:24:21 +01:00
parent a22959c140
commit 6d9df4453f
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
helmfile/cloud-sdk/helmfile.yaml
View File

@@ -254,8 +254,8 @@ releases:
annotations: annotations:
title: Pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* has been OOM killed 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. 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 - alert: Pod exited with a segfault
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 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 for: 0m
labels: labels:
severity: error severity: error
@@ -264,8 +264,8 @@ releases:
pod: "{{`{{ $labels.pod }}`}}" pod: "{{`{{ $labels.pod }}`}}"
reason: "{{`{{ $labels.reason }}`}}" reason: "{{`{{ $labels.reason }}`}}"
annotations: annotations:
title: Pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* terminated due to an error title: Pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* exited with a segfault
description: The pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* has terminated due to an error, please investigate the cause. description: The pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* exited with a segmentation fault, please examine the coredump.
- alert: Node low on memory - alert: Node low on memory
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 5 expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 5
for: 1m for: 1m