XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-23 09:58:16 +08:00
Code Issues Projects Releases Packages Wiki Activity

fix: some kube api alert lint (#416)

Browse source 
* fix: apiserver regexp matchers are automatically fully anchored

Signed-off-by: R.Sicart <roger.sicart@gmail.com>

* fix: apiserver errors alert is using  label but the query removes it

Signed-off-by: R.Sicart <roger.sicart@gmail.com>

* fix: apiserver latency alert is using  label but the query removes it

Signed-off-by: R.Sicart <roger.sicart@gmail.com>

---------

Signed-off-by: R.Sicart <roger.sicart@gmail.com>
This commit is contained in:
R.Sicart 2024-05-14 20:34:43 +02:00 committed by GitHub
parent 4963331101
commit 8460f9008e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
_data/rules.yml
View file

@ -2071,7 +2071,7 @@ groups:
for: 12h for: 12h
- name: Kubernetes API server errors - name: Kubernetes API server errors
description: Kubernetes API server is experiencing high error rate description: Kubernetes API server is experiencing high error rate
query: 'sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[1m])) / sum(rate(apiserver_request_total{job="apiserver"}[1m])) * 100 > 3' query: 'sum(rate(apiserver_request_total{job="apiserver",code=~"(?:5..)"}[1m])) by (instance, job) / sum(rate(apiserver_request_total{job="apiserver"}[1m])) by (instance, job) * 100 > 3'
severity: critical severity: critical
for: 2m for: 2m
- name: Kubernetes API client errors - name: Kubernetes API client errors
@ -2089,7 +2089,7 @@ groups:
severity: critical severity: critical
- name: Kubernetes API server latency - name: Kubernetes API server latency
description: "Kubernetes API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}." description: "Kubernetes API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}."
query: 'histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{subresource!="log",verb!~"^(?:CONNECT|WATCHLIST|WATCH|PROXY)$"} [10m])) WITHOUT (instance, resource)) > 1' query: 'histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{verb!~"(?:CONNECT|WATCHLIST|WATCH|PROXY)"} [10m])) WITHOUT (subresource)) > 1'
severity: warning severity: warning
for: 2m for: 2m