scottk/wlan-toolsmith
1
0
Fork 0
mirror of https://github.com/Telecominfraproject/wlan-toolsmith.git synced 2025-10-29 18:12:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add missing Helmfile values for core-dump-handler and separate pod termination alerts (#216)

Browse Source 
Signed-off-by: Johann Hoffmann <johann.hoffmann@mailbox.org>
This commit is contained in:
Johann Hoffmann
2022-07-28 13:33:09 +02:00
committed by GitHub
parent eee3b1690b
commit 8e314cbea7
1 changed files with 18 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
helmfile/cloud-sdk/helmfile.yaml
View File

@@ -242,8 +242,8 @@ releases:
annotations:
title: Node {{`{{ $labels.node }}`}} not becoming ready
description: The cluster node {{`{{ $labels.node }}`}} is not getting ready since 60 minutes. Please contact the cluster administrators.
- 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=~"OOMKilled|Error"}[10m]) == 1
- alert: Pod OOM killed
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="OOMKilled"}[10m]) == 1
for: 0m
labels:
severity: error
@@ -252,8 +252,20 @@ releases:
pod: "{{`{{ $labels.pod }}`}}"
reason: "{{`{{ $labels.reason }}`}}"
annotations:
title: Pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* has terminated, the last reason is *{{`{{ $labels.reason }}`}}*
description: The pod *{{`{{ $labels.namespace }}/{{ $labels.pod }}`}}* terminated because of the above-mentioned reason, please investigate the cause.
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
for: 0m
labels:
severity: error
area: testbed
namespace: "{{`{{ $labels.namespace }}`}}"
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.
- alert: Node low on memory
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 5
for: 1m
@@ -1066,3 +1078,5 @@ releases:
s3AccessKey: {{ .Environment.Values.core_dump_handler.s3_access_key }}
s3Secret: {{ .Environment.Values.core_dump_handler.s3_secret }}
s3Region: us-east-1
includeCrioExe: true
vendor: rhel7