From 6c35abca541e4fc147d6efe334f4129b08c2d470 Mon Sep 17 00:00:00 2001 From: WrenIX Date: Thu, 17 Oct 2024 22:11:03 +0200 Subject: [PATCH] fix(infra-monitoring): probe failed by ignoring job label --- .../templates/exporter/blackbox/prometheus-rules.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/infra-monitoring/templates/exporter/blackbox/prometheus-rules.yaml b/infra-monitoring/templates/exporter/blackbox/prometheus-rules.yaml index bf9d002..1a4117e 100644 --- a/infra-monitoring/templates/exporter/blackbox/prometheus-rules.yaml +++ b/infra-monitoring/templates/exporter/blackbox/prometheus-rules.yaml @@ -23,7 +23,7 @@ spec: `}} - alert: "BlackboxProbeFailed" - expr: 'probe_success{ {{ $filter }}, instancetype!="server" } == 0' + expr: 'sum(probe_success{ {{ $filter }}, instancetype!="server"}) without (job) / count(probe_success{ {{ $filter }}, instancetype!="server"}) without (job) < 0.5' for: "5m" labels: severity: "critical" @@ -36,7 +36,7 @@ spec: - name: "ICMP" rules: - alert: "BlackboxProbeIcmpFailed" - expr: 'probe_success{ {{ $filter }}, instancetype="server" } == 0' + expr: 'sum(probe_success{ {{ $filter }}, instancetype="server"}) without (job) / count(probe_success{ {{ $filter }}, instancetype="server"}) without (job) < 0.5' for: "5m" labels: severity: "critical"