feat(container): update kube-prometheus-stack ( 66.1.1 → 66.2.1 )

[lumiere-bot]

This PR contains the following updates:

Package	Update	Change
kube-prometheus-stack (source)	minor	66.1.1 -> 66.2.1

---

Release Notes

prometheus-community/helm-charts (kube-prometheus-stack)

v66.2.1

Compare Source

v66.2.0

Compare Source

---

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

---

• If you want to rebase/retry this PR, check this box

---

This PR has been generated by Renovate Bot.

[lumiere-bot]

--- HelmRelease: monitoring/kube-prometheus-stack PrometheusRule: monitoring/kube-prometheus-stack-kube-apiserver-availability.rules

+++ HelmRelease: monitoring/kube-prometheus-stack PrometheusRule: monitoring/kube-prometheus-stack-kube-apiserver-availability.rules

@@ -24,22 +24,22 @@

         verb: read
       record: code:apiserver_request_total:increase30d
     - expr: sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
       labels:
         verb: write
       record: code:apiserver_request_total:increase30d
-    - expr: sum by (cluster, verb, scope) (increase(apiserver_request_sli_duration_seconds_count{job="apiserver"}[1h]))
-      record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase1h
-    - expr: sum by (cluster, verb, scope) (avg_over_time(cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase1h[30d])
-        * 24 * 30)
-      record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d
     - expr: sum by (cluster, verb, scope, le) (increase(apiserver_request_sli_duration_seconds_bucket[1h]))
       record: cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h
     - expr: sum by (cluster, verb, scope, le) (avg_over_time(cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h[30d])
         * 24 * 30)
       record: cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d
+    - expr: sum by (cluster, verb, scope) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h{le="+Inf"})
+      record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase1h
+    - expr: sum by (cluster, verb, scope) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{le="+Inf"}
+        * 24 * 30)
+      record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d
     - expr: |-
         1 - (
           (
             # write too slow
             sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
             -
--- HelmRelease: monitoring/kube-prometheus-stack PrometheusRule: monitoring/kube-prometheus-stack-kubernetes-apps

+++ HelmRelease: monitoring/kube-prometheus-stack PrometheusRule: monitoring/kube-prometheus-stack-kubernetes-apps

@@ -180,19 +180,19 @@

         )
       for: 15m
       labels:
         severity: warning
     - alert: KubeContainerWaiting
       annotations:
-        description: pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on
+        description: 'pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on
           container {{ $labels.container}} has been in waiting state for longer than
-          1 hour.
+          1 hour. (reason: "{{ $labels.reason }}").'
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontainerwaiting
         summary: Pod container waiting longer than 1 hour
-      expr: sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job="kube-state-metrics",
-        namespace=~".*"}) > 0
+      expr: kube_pod_container_status_waiting_reason{reason!="CrashLoopBackOff", job="kube-state-metrics",
+        namespace=~".*"} > 0
       for: 1h
       labels:
         severity: warning
     - alert: KubeDaemonSetNotScheduled
       annotations:
         description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
--- HelmRelease: monitoring/kube-prometheus-stack PrometheusRule: monitoring/kube-prometheus-stack-kubernetes-resources

+++ HelmRelease: monitoring/kube-prometheus-stack PrometheusRule: monitoring/kube-prometheus-stack-kubernetes-resources

@@ -117,14 +117,14 @@

         description: '{{ $value | humanizePercentage }} throttling of CPU in namespace
           {{ $labels.namespace }} for container {{ $labels.container }} in pod {{
           $labels.pod }}.'
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh
         summary: Processes experience elevated CPU throttling.
       expr: |-
-        sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace)
+        sum(increase(container_cpu_cfs_throttled_periods_total{container!="", job="kubelet", metrics_path="/metrics/cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)
           /
-        sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace)
+        sum(increase(container_cpu_cfs_periods_total{job="kubelet", metrics_path="/metrics/cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)
           > ( 25 / 100 )
       for: 15m
       labels:
         severity: info
 
--- HelmRelease: monitoring/kube-prometheus-stack PrometheusRule: monitoring/kube-prometheus-stack-kubernetes-system-apiserver

+++ HelmRelease: monitoring/kube-prometheus-stack PrometheusRule: monitoring/kube-prometheus-stack-kubernetes-system-apiserver

@@ -18,29 +18,29 @@

     - alert: KubeClientCertificateExpiration
       annotations:
         description: A client certificate used to authenticate to kubernetes apiserver
           is expiring in less than 7.0 days.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration
         summary: Client certificate is about to expire.
-      expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"}
-        > 0 and on (cluster, job) histogram_quantile(0.01, sum by (cluster, job, le)
-        (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m])))
-        < 604800
+      expr: |-
+        histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800
+        and
+        on (job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0
       for: 5m
       labels:
         severity: warning
     - alert: KubeClientCertificateExpiration
       annotations:
         description: A client certificate used to authenticate to kubernetes apiserver
           is expiring in less than 24.0 hours.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration
         summary: Client certificate is about to expire.
-      expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"}
-        > 0 and on (cluster, job) histogram_quantile(0.01, sum by (cluster, job, le)
-        (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m])))
-        < 86400
+      expr: |-
+        histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400
+        and
+        on (job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0
       for: 5m
       labels:
         severity: critical
     - alert: KubeAggregatedAPIErrors
       annotations:
         description: Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace

[lumiere-bot]

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

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

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

     spec:
       chart: kube-prometheus-stack
       sourceRef:
         kind: HelmRepository
         name: prometheus-community
         namespace: flux-system
-      version: 66.1.1
+      version: 66.2.1
   dependsOn:
   - name: openebs
     namespace: openebs-system
   install:
     crds: CreateReplace
     remediation: