fix(alerts): add instance label to KubeAggregatedAPIErrors (#991)

* fix(alerts): use sum by instance max for 'KubeAggregatedAPIErrors' Signed-off-by: Sebastian Gaiser <[email protected]> * Update alerts/kube_apiserver.libsonnet Co-authored-by: Stephen Lang <[email protected]> * Update alerts/kube_apiserver.libsonnet * Update alerts/kube_apiserver.libsonnet * fix(alerts): use sum by instance max for 'KubeAggregatedAPIErrors' - adjust description Signed-off-by: Sebastian Gaiser <[email protected]> * fix(build): remove extra parenthsis Signed-off-by: Stephen Lang <[email protected]> --------- Signed-off-by: Sebastian Gaiser <[email protected]> Signed-off-by: Stephen Lang <[email protected]> Co-authored-by: Stephen Lang <[email protected]> Co-authored-by: Stephen Lang <[email protected]>
kubernetes-monitoring · Dec 10, 2024 · d6ab1a7 · d6ab1a7
1 parent a3fbf21
commit d6ab1a7
Showing 1 changed file with 5 additions and 2 deletions.
diff --git a/alerts/kube_apiserver.libsonnet b/alerts/kube_apiserver.libsonnet
@@ -88,13 +88,16 @@ local utils = import '../lib/utils.libsonnet';
           {
             alert: 'KubeAggregatedAPIErrors',
             expr: |||
-              sum by(name, namespace, %(clusterLabel)s)(increase(aggregator_unavailable_apiservice_total{%(kubeApiserverSelector)s}[10m])) > 4
+              sum by(%(clusterLabel)s, instance, name, reason)(increase(aggregator_unavailable_apiservice_total{%(kubeApiserverSelector)s}[1m])) > 0
             ||| % $._config,
+            'for': '10m',
             labels: {
               severity: 'warning',
             },
             annotations: {
-              description: 'Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. It has appeared unavailable {{ $value | humanize }} times averaged over the past 10m.',
+              description: 'Kubernetes aggregated API {{ $labels.instance }}/{{ $labels.name }} has reported {{ $labels.reason }} errors%s.' % [
+                utils.ifShowMultiCluster($._config, ' on cluster {{ $labels.%(clusterLabel)s }}' % $._config),
+              ],
               summary: 'Kubernetes aggregated API has reported errors.',
             },
           },