mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-22 01:17:19 +08:00
parent
4cd3ff1d4a
commit
b324c6f32f
1 changed files with 15 additions and 1 deletions
|
|
@ -902,7 +902,21 @@ groups:
|
|||
description: Traefik backend 5xx error rate is above 5%
|
||||
query: 'sum(rate(traefik_backend_requests_total{code=~"5.*"}[3m])) by (backend) / sum(rate(traefik_backend_requests_total[3m])) by (backend) * 100 > 5'
|
||||
severity: critical
|
||||
|
||||
- name: Embedded exporter v2
|
||||
doc_url: https://docs.traefik.io/observability/metrics/prometheus/
|
||||
rules:
|
||||
- name: Traefik service down
|
||||
description: All Traefik services are down
|
||||
query: "count(traefik_service_server_up) by (service) == 0"
|
||||
severity: critical
|
||||
- name: Traefik high HTTP 4xx error rate service
|
||||
description: Traefik service 4xx error rate is above 5%
|
||||
query: 'sum(rate(traefik_service_requests_total{code=~"4.*"}[3m])) by (service) / sum(rate(traefik_service_requests_total[3m])) by (service) * 100 > 5'
|
||||
severity: critical
|
||||
- name: Traefik high HTTP 5xx error rate service
|
||||
description: Traefik service 5xx error rate is above 5%
|
||||
query: 'sum(rate(traefik_service_requests_total{code=~"5.*"}[3m])) by (service) / sum(rate(traefik_service_requests_total[3m])) by (service) * 100 > 5'
|
||||
severity: critical
|
||||
|
||||
- name: Runtimes
|
||||
services:
|
||||
|
|
|
|||
Loading…
Reference in a new issue