From f554b72671426d679dea31830847392553351540 Mon Sep 17 00:00:00 2001 From: Samuel Berthe Date: Mon, 9 Mar 2020 21:55:17 +0100 Subject: [PATCH] Add alert for kubernetes api latency --- _data/rules.yml | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/_data/rules.yml b/_data/rules.yml index 9ad54d2..e2fe678 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -963,6 +963,11 @@ groups: description: A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours. query: 'apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 24*60*60' severity: error + - name: Kubernetes API server latency + description: 'Kubernetes API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.' + query: 'histogram_quantile(0.99, sum(apiserver_request_latencies_bucket{verb!~"CONNECT|WATCHLIST|WATCH|PROXY"}) WITHOUT (instance, resource)) / 1e+06 > 1' + severity: warning + - name: Nomad exporters: