From b324c6f32f71c7ce9897fff61cc0e44394692b77 Mon Sep 17 00:00:00 2001 From: Nabil BENDAFI Date: Tue, 23 Jun 2020 13:40:01 +0200 Subject: [PATCH] feat(traefik): add rules for Traefik v2 Fixes #7 --- _data/rules.yml | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/_data/rules.yml b/_data/rules.yml index c60ab90..06a344d 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -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: