From 6f128f7a9576f78f22e87d37c9fe0f26496b7a7c Mon Sep 17 00:00:00 2001
From: David Hoese <david.hoese@ssec.wisc.edu>
Date: Wed, 25 Nov 2020 14:34:55 -0600
Subject: [PATCH] Remove KubernetesPodNotHealthy alert because it has false
positives
---
.../kubekorner_geosphere_prometheus_rules.yaml | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/admin/kubekorner_geosphere_prometheus_rules.yaml b/admin/kubekorner_geosphere_prometheus_rules.yaml
index 345d749..abafad6 100644
--- a/admin/kubekorner_geosphere_prometheus_rules.yaml
+++ b/admin/kubekorner_geosphere_prometheus_rules.yaml
@@ -434,15 +434,15 @@ spec:
summary: "Kubernetes StatefulSet down (instance {{ $labels.instance }})"
description: "A StatefulSet went down\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- - alert: KubernetesPodNotHealthy
- expr: min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[1h:5m]) > 0
- for: 5m
- labels:
- severity: critical
- ruleGroup: geosphere-kubernetes
- annotations:
- summary: "Kubernetes Pod not healthy (instance {{ $labels.instance }})"
- description: "Pod has been in a non-ready state for longer than an hour.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
+# - alert: KubernetesPodNotHealthy
+# expr: min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[1h:5m]) > 0
+# for: 5m
+# labels:
+# severity: critical
+# ruleGroup: geosphere-kubernetes
+# annotations:
+# summary: "Kubernetes Pod not healthy (instance {{ $labels.instance }})"
+# description: "Pod has been in a non-ready state for longer than an hour.\n VALUE = {{ $value }}\n LABELS: {{ $labels }}"
- alert: KubernetesPodCrashLooping
expr: rate(kube_pod_container_status_restarts_total[15m]) * 60 * 5 > 5
for: 5m
--
GitLab