From b9d6131697ee4c0fb29d610f19a1a7c2f0e379c5 Mon Sep 17 00:00:00 2001 From: Gustavo Motizuki Date: Tue, 13 Apr 2021 11:42:40 +1200 Subject: [PATCH] chore(KubernetesOutOfCapacity alert): Don't include pods that are not running --- _data/rules.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/_data/rules.yml b/_data/rules.yml index 6fd9802..c09c0cc 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -1498,7 +1498,7 @@ groups: for: 2m - name: Kubernetes out of capacity description: "{{ $labels.node }} is out of capacity" - query: 'sum(kube_pod_info) by (node) / sum(kube_node_status_allocatable_pods) by (node) * 100 > 90' + query: 'sum by (node) ((kube_pod_status_phase{phase="Running"} == 1) + on(pod, namespace) group_left(node) (0 * kube_pod_info)) / sum(kube_node_status_allocatable_pods) by (node) * 100 > 90' severity: warning for: 2m - name: Kubernetes Job failed