Merge branch 'master' of github.com:samber/awesome-prometheus-alerts

_data/rules.yml

@@ -309,6 +309,19 @@ groups:
                 severity: info
                 for: 4h
 
+          # You may be want to increase the alert manager 'repeat_interval' for this type of alert to daily or weekly
+          - name: node-exporter
+            slug: node-exporter-under-utilized
+            doc_url: https://github.com/prometheus/node_exporter
+            rules:
+              - name: Host Memory is under utilized
+                description: 'Node memory is not fully used (> 80% free) for 1 week. Consider reducing memory space.'
+                query: 'min_over_time(node_memory_MemAvailable_bytes[1w]) / node_memory_MemTotal_bytes * 100 > 80'
+                severity: info
+              - name: Host Cpu is under utilized
+                description: 'CPU load is < 20% for 1 week. Consider reducing the number of CPUs.'
+                query: '100 - (max by(instance) (rate(node_cpu_seconds_total{mode="idle"}[1w])) * 100) < 20'
+                severity: info
 
       - name: Docker containers
         exporters:

dist/rules/kubernetes/kubestate-exporter.yml

@@ -113,7 +113,7 @@ groups:
         description: "Persistent volume is in bad state\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: KubernetesStatefulsetDown
-      expr: '(kube_statefulset_status_replicas_ready / kube_statefulset_status_replicas_current) != 1'
+      expr: 'kube_statefulset_replicas != kube_statefulset_status_replicas_ready > 0'
       for: 1m
       labels:
         severity: critical