kube hpa lint and improvement (#417)

* fix: hpa alerts are using label but the queries remove it Signed-off-by: R.Sicart <roger.sicart@gmail.com> * fix: hpa alert is using label but the query removes it Signed-off-by: R.Sicart <roger.sicart@gmail.com> * feat: hpa scale max should not alert when min and max are the same Signed-off-by: R.Sicart <roger.sicart@gmail.com> --------- Signed-off-by: R.Sicart <roger.sicart@gmail.com>
samber · May 14, 2024 · 262e451 · 262e451
1 parent 81079a2
commit 262e451
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 6 deletions.
diff --git a/_data/rules.yml b/_data/rules.yml
@@ -1990,7 +1990,7 @@ groups:
                 severity: warning
               - name: Kubernetes HPA scale maximum
                 description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has hit maximum number of desired pods
-                query: "kube_horizontalpodautoscaler_status_desired_replicas >= kube_horizontalpodautoscaler_spec_max_replicas"
+                query: '(kube_horizontalpodautoscaler_status_desired_replicas >= kube_horizontalpodautoscaler_spec_max_replicas) and (kube_horizontalpodautoscaler_spec_max_replicas > 1) and (kube_horizontalpodautoscaler_spec_min_replicas != kube_horizontalpodautoscaler_spec_max_replicas)'
                 severity: info
                 for: 2m
               - name: Kubernetes HPA underutilized

diff --git a/dist/rules/kubernetes/kubestate-exporter.yml b/dist/rules/kubernetes/kubestate-exporter.yml
@@ -127,7 +127,7 @@ groups:
       labels:
         severity: warning
       annotations:
-        summary: Kubernetes HPA scale inability (instance {{ $labels.instance }})
+        summary: Kubernetes HPA scale inability ({{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }})
         description: "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} is unable to scale\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: KubernetesHpaMetricsUnavailability
@@ -136,7 +136,7 @@ groups:
       labels:
         severity: warning
       annotations:
-        summary: Kubernetes HPA metrics unavailability (instance {{ $labels.instance }})
+        summary: Kubernetes HPA metrics unavailability ({{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }})
         description: "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} is unable to collect metrics\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: KubernetesHpaScaleMaximum
@@ -145,16 +145,16 @@ groups:
       labels:
         severity: info
       annotations:
-        summary: Kubernetes HPA scale maximum (instance {{ $labels.instance }})
+        summary: Kubernetes HPA scale maximum ({{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }})
         description: "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has hit maximum number of desired pods\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: KubernetesHpaUnderutilized
-      expr: 'max(quantile_over_time(0.5, kube_horizontalpodautoscaler_status_desired_replicas[1d]) == kube_horizontalpodautoscaler_spec_min_replicas) by (horizontalpodautoscaler) > 3'
+      expr: 'max(quantile_over_time(0.5, kube_horizontalpodautoscaler_status_desired_replicas[1d]) == kube_horizontalpodautoscaler_spec_min_replicas) by (horizontalpodautoscaler, namespace) > 3'
       for: 0m
       labels:
         severity: info
       annotations:
-        summary: Kubernetes HPA underutilized (instance {{ $labels.instance }})
+        summary: Kubernetes HPA underutilized ({{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }})
         description: "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} is constantly at minimum replicas for 50% of the time. Potential cost saving here.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: KubernetesPodNotHealthy