From eed991a27b58d942c15c4f9540eb77abbeceb4fe Mon Sep 17 00:00:00 2001 From: Viktor Barzin Date: Mon, 9 Mar 2026 20:26:30 +0000 Subject: [PATCH] exclude nextcloud from HighServiceErrorRate alert Nextcloud has chronic 5xx errors due to SQLite lock contention causing Apache worker exhaustion. Excluding from alert until MySQL migration. --- .../platform/modules/monitoring/prometheus_chart_values.tpl | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/stacks/platform/modules/monitoring/prometheus_chart_values.tpl b/stacks/platform/modules/monitoring/prometheus_chart_values.tpl index ed532fa9..cc450d46 100755 --- a/stacks/platform/modules/monitoring/prometheus_chart_values.tpl +++ b/stacks/platform/modules/monitoring/prometheus_chart_values.tpl @@ -605,11 +605,11 @@ serverFiles: - alert: HighServiceErrorRate expr: | ( - sum(rate(traefik_service_requests_total{code=~"5.."}[5m])) by (service) - / sum(rate(traefik_service_requests_total[5m])) by (service) + sum(rate(traefik_service_requests_total{code=~"5..", service!~".*nextcloud.*"}[5m])) by (service) + / sum(rate(traefik_service_requests_total{service!~".*nextcloud.*"}[5m])) by (service) * 100 ) > 10 - and sum(rate(traefik_service_requests_total[5m])) by (service) > 0.1 + and sum(rate(traefik_service_requests_total{service!~".*nextcloud.*"}[5m])) by (service) > 0.1 for: 10m labels: severity: warning