Merge pull request 'feat: authentication prod Prometheus set-up' (#124) from feat-alert-manager into master

Reviewed-on: https://gitea.freeleaps.mathmast.com/freeleaps/freeleaps-ops/pulls/124
This commit is contained in:
Easonzyc 2025-10-15 02:53:00 +00:00
commit e029ce2d2d

View File

@ -106,3 +106,32 @@ authentication:
controlledResources: controlledResources:
- cpu - cpu
- memory - memory
prometheusRule:
name: freepeals-alpha-authentication
enabled: false
namespace: freeleaps-monitoring-system
labels:
release: kube-prometheus-stack
rules:
- alert: FreeleapsAuthenticationServiceDown
expr: up{job="authentication-service"} == 0
for: 1m
labels:
severity: critical
service: authentication-service
annotations:
summary: Freeleaps Authentication service is down (instance {{ $labels.instance }})
description: Freeleaps Authentication service has been down for more than 1 minutes.
runbook_url: https://netorgft10898514.sharepoint.com/:w:/s/FreeleapsEngineeringTeam/EUlvzumTsPxCpPAzI3gm9OIB0DCLTjQzzYVL6VsHYZFjxg?e=0dxVr7
- alert: FreeleapsAuthenticationServiceHighErrorRate
expr: rate(http_requests_total{job="authentication-service",status=~"5.."}[5m]) > 0.1
for: 5m
labels:
severity: warning
service: authentication-service
annotations:
summary: High error rate in freeleaps authentication service (instance {{ $labels.instance }})
description: Freeleaps Authentication service error rate is {{ $value }} errors per second.
runbook_url: https://netorgft10898514.sharepoint.com/:w:/s/FreeleapsEngineeringTeam/EUlvzumTsPxCpPAzI3gm9OIB0DCLTjQzzYVL6VsHYZFjxg?e=0dxVr7