--- kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack HelmRelease: observability/kube-prometheus-stack

+++ kubernetes/apps/observability/kube-prometheus-stack/app Kustomization: flux-system/kube-prometheus-stack HelmRelease: observability/kube-prometheus-stack

@@ -13,13 +13,13 @@

     spec:
       chart: kube-prometheus-stack
       sourceRef:
         kind: HelmRepository
         name: prometheus-community
         namespace: flux-system
-      version: 68.3.2
+      version: 68.5.0
   dependsOn:
   - name: prometheus-operator-crds
     namespace: observability
   - name: openebs
     namespace: openebs-system
   install:

--- HelmRelease: observability/kube-prometheus-stack Service: observability/kube-state-metrics

+++ HelmRelease: observability/kube-prometheus-stack Service: observability/kube-state-metrics

@@ -8,14 +8,12 @@

     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/component: metrics
     app.kubernetes.io/part-of: kube-state-metrics
     app.kubernetes.io/name: kube-state-metrics
     app.kubernetes.io/instance: kube-prometheus-stack
     release: kube-prometheus-stack
-  annotations:
-    prometheus.io/scrape: 'true'
 spec:
   type: ClusterIP
   ports:
   - name: http
     protocol: TCP
     port: 8080
--- HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-etcd

+++ HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-etcd

@@ -26,15 +26,15 @@

         or
           count without (To) (
             sum without (instance, pod) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[120s])) > 0.01
           )
         )
         > 0
-      for: 10m
-      labels:
-        severity: critical
+      for: 20m
+      labels:
+        severity: warning
     - alert: etcdInsufficientMembers
       annotations:
         description: 'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value
           }}).'
         summary: etcd cluster has insufficient number of members.
       expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance, pod) < ((count(up{job=~".*etcd.*"})
--- HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-kubernetes-system-kubelet

+++ HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-kubernetes-system-kubelet

@@ -18,14 +18,16 @@

     - alert: KubeNodeNotReady
       annotations:
         description: '{{ $labels.node }} has been unready for more than 15 minutes
           on cluster {{ $labels.cluster }}.'
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodenotready
         summary: Node is not ready.
-      expr: kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"}
-        == 0
+      expr: |-
+        kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
+        and on (cluster, node)
+        kube_node_spec_unschedulable{job="kube-state-metrics"} == 0
       for: 15m
       labels:
         severity: warning
     - alert: KubeNodeUnreachable
       annotations:
         description: '{{ $labels.node }} is unreachable and some workloads may be
@@ -62,14 +64,16 @@

     - alert: KubeNodeReadinessFlapping
       annotations:
         description: The readiness status of node {{ $labels.node }} has changed {{
           $value }} times in the last 15 minutes on cluster {{ $labels.cluster }}.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodereadinessflapping
         summary: Node readiness status is flapping.
-      expr: sum(changes(kube_node_status_condition{job="kube-state-metrics",status="true",condition="Ready"}[15m]))
-        by (cluster, node) > 2
+      expr: |-
+        sum(changes(kube_node_status_condition{job="kube-state-metrics",status="true",condition="Ready"}[15m])) by (cluster, node) > 2
+        and on (cluster, node)
+        kube_node_spec_unschedulable{job="kube-state-metrics"} == 0
       for: 15m
       labels:
         severity: warning
     - alert: KubeletPlegDurationHigh
       annotations:
         description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile