From a564dd8b677b6dd5558e94df47f0a549f4422128 Mon Sep 17 00:00:00 2001 From: mr-forust Date: Tue, 29 Sep 2026 08:12:07 +0200 Subject: [PATCH] fix(alerts): exclude netbird streams from traefik latency alert SignalExchange ConnectStream holds 60s gRPC streams by design; at night they exceed 5% of samples and pin P95 to the 5.0s bucket ceiling, flapping the alert. Also fixes the stale xui exclusion pattern, which matched no real service label. --- prometheus-stack/k8s/traefik-alerts.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/prometheus-stack/k8s/traefik-alerts.yaml b/prometheus-stack/k8s/traefik-alerts.yaml index 7f81cb1..384cbe6 100644 --- a/prometheus-stack/k8s/traefik-alerts.yaml +++ b/prometheus-stack/k8s/traefik-alerts.yaml @@ -42,7 +42,7 @@ spec: - alert: TraefikServiceHighLatency expr: | histogram_quantile(0.95, - sum(rate(traefik_service_request_duration_seconds_bucket{service!~"xui-xui-service-.*"}[5m])) by (le, service)) > 2 + sum(rate(traefik_service_request_duration_seconds_bucket{service!~"xui-service|netbird-server-service"}[5m])) by (le, service)) > 2 for: 5m labels: severity: warning