viktor/infra
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

disable perms errors and server errors for grafana and nextcloud ingresses as they were too noisy [ci skip]

Browse source
This commit is contained in:
Viktor Barzin 2025-03-15 17:53:24 +00:00
parent 965d4834e0
commit dfe47657ee
1 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
modules/kubernetes/monitoring/prometheus_chart_values.tpl
View file

@ -238,20 +238,20 @@ serverFiles:
summary: No node load data. Can signal that prometheus is not scraping summary: No node load data. Can signal that prometheus is not scraping
- alert: NoiDRACData - alert: NoiDRACData
expr: (max(r730_idrac_redfish_chassis_power_average_consumed_watts) or on() vector(0)) == 0 expr: (max(r730_idrac_redfish_chassis_power_average_consumed_watts) or on() vector(0)) == 0
for: 10m for: 30m
labels: labels:
severity: page severity: page
annotations: annotations:
summary: No iDRAC amperage reading. Can signal that prometheus is not scraping summary: No iDRAC amperage reading. Can signal that prometheus is not scraping
- alert: HighIngressPermissionErrors - alert: HighIngressPermissionErrors
expr: (sum(rate(nginx_ingress_controller_requests{status=~"4.*"}[2m])) by (ingress) / sum(rate(nginx_ingress_controller_requests[2m])) by (ingress) * 100) > 10 expr: (sum(rate(nginx_ingress_controller_requests{status=~"4.*", ingress!="nextcloud", ingress!="grafana"}[2m])) by (ingress) / sum(rate(nginx_ingress_controller_requests[2m])) by (ingress) * 100) > 10
for: 10m for: 20m
labels: labels:
severity: page severity: page
annotations: annotations:
summary: "High permission error rate for {{ $labels.ingress }}: {{ $value }}%." summary: "High permission error rate for {{ $labels.ingress }}: {{ $value }}%."
- alert: HighIngressServerErrors - alert: HighIngressServerErrors
expr: (sum(rate(nginx_ingress_controller_requests{status=~"5.*"}[2m])) by (ingress) / sum(rate(nginx_ingress_controller_requests[2m])) by (ingress) * 100) > 10 expr: (sum(rate(nginx_ingress_controller_requests{status=~"5.*", ingress!="nextcloud", ingress!="grafana"}[2m])) by (ingress) / sum(rate(nginx_ingress_controller_requests[2m])) by (ingress) * 100) > 10
for: 20m for: 20m
labels: labels:
severity: page severity: page