chore(helm-chart): update helm release kube-prometheus-stack to v54.2.0

[budimanjojo-bot]

This PR contains the following updates:

Package	Update	Change
kube-prometheus-stack (source)	minor	54.1.0 -> 54.2.0

---

Release Notes

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

v54.2.0

Compare Source

kube-prometheus-stack collects Kubernetes manifests, Grafana dashboards, and Prometheus rules combined with documentation and scripts to provide easy to operate end-to-end Kubernetes cluster monitoring with Prometheus using the Prometheus Operator.

What's Changed

• [kube-prometheus-stack] Configure additional aggregation labels + k8s.rules split by @​jkroepke in https://github.com/prometheus-community/helm-charts/pull/3883

Full Changelog: prometheus-community/helm-charts@prometheus-25.8.0...kube-prometheus-stack-54.2.0

---

Configuration

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

🚦 Automerge: Enabled.

♻ 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.

[budimanjojo-bot]

--- cluster/apps/monitoring-system/kube-prometheus-stack/base Kustomization: flux-system/monitoring-system-kube-prometheus-stack HelmRelease: monitoring-system/kube-prometheus-stack

+++ cluster/apps/monitoring-system/kube-prometheus-stack/base Kustomization: flux-system/monitoring-system-kube-prometheus-stack HelmRelease: monitoring-system/kube-prometheus-stack

@@ -10,13 +10,13 @@

       chart: kube-prometheus-stack
       interval: 15m
       sourceRef:
         kind: HelmRepository
         name: prometheus-community-charts
         namespace: flux-system
-      version: 54.1.0
+      version: 54.2.0
   install:
     crds: CreateReplace
     createNamespace: true
     remediation:
       retries: 5
   interval: 15m

[budimanjojo-bot]

--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-node.rules

+++ cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-node.rules

@@ -13,22 +13,22 @@

     heritage: Helm
 spec:
   groups:
   - name: node.rules
     rules:
     - expr: |-
-        topk by(cluster, namespace, pod) (1,
+        topk by (cluster, namespace, pod) (1,
           max by (cluster, node, namespace, pod) (
             label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)")
         ))
       record: 'node_namespace_pod:kube_pod_info:'
     - expr: |-
         count by (cluster, node) (
           node_cpu_seconds_total{mode="idle",job="node-exporter"}
           * on (namespace, pod) group_left(node)
-          topk by(namespace, pod) (1, node_namespace_pod:kube_pod_info:)
+          topk by (namespace, pod) (1, node_namespace_pod:kube_pod_info:)
         )
       record: node:node_num_cpu:sum
     - expr: |-
         sum(
           node_memory_MemAvailable_bytes{job="node-exporter"} or
           (
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-kubernetes-storage

+++ cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-kubernetes-storage

@@ -27,15 +27,15 @@

           kubelet_volume_stats_available_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"}
             /
           kubelet_volume_stats_capacity_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"}
         ) < 0.03
         and
         kubelet_volume_stats_used_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0
-        unless on(namespace, persistentvolumeclaim)
+        unless on (namespace, persistentvolumeclaim)
         kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1
-        unless on(namespace, persistentvolumeclaim)
+        unless on (namespace, persistentvolumeclaim)
         kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1
       for: 1m
       labels:
         severity: critical
     - alert: KubePersistentVolumeFillingUp
       annotations:
@@ -52,15 +52,15 @@

           kubelet_volume_stats_capacity_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"}
         ) < 0.15
         and
         kubelet_volume_stats_used_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0
         and
         predict_linear(kubelet_volume_stats_available_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0
-        unless on(namespace, persistentvolumeclaim)
+        unless on (namespace, persistentvolumeclaim)
         kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1
-        unless on(namespace, persistentvolumeclaim)
+        unless on (namespace, persistentvolumeclaim)
         kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1
       for: 1h
       labels:
         severity: warning
     - alert: KubePersistentVolumeInodesFillingUp
       annotations:
@@ -74,15 +74,15 @@

           kubelet_volume_stats_inodes_free{job="kubelet", namespace=~".*", metrics_path="/metrics"}
             /
           kubelet_volume_stats_inodes{job="kubelet", namespace=~".*", metrics_path="/metrics"}
         ) < 0.03
         and
         kubelet_volume_stats_inodes_used{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0
-        unless on(namespace, persistentvolumeclaim)
+        unless on (namespace, persistentvolumeclaim)
         kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1
-        unless on(namespace, persistentvolumeclaim)
+        unless on (namespace, persistentvolumeclaim)
         kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1
       for: 1m
       labels:
         severity: critical
     - alert: KubePersistentVolumeInodesFillingUp
       annotations:
@@ -99,15 +99,15 @@

           kubelet_volume_stats_inodes{job="kubelet", namespace=~".*", metrics_path="/metrics"}
         ) < 0.15
         and
         kubelet_volume_stats_inodes_used{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0
         and
         predict_linear(kubelet_volume_stats_inodes_free{job="kubelet", namespace=~".*", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0
-        unless on(namespace, persistentvolumeclaim)
+        unless on (namespace, persistentvolumeclaim)
         kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1
-        unless on(namespace, persistentvolumeclaim)
+        unless on (namespace, persistentvolumeclaim)
         kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1
       for: 1h
       labels:
         severity: warning
     - alert: KubePersistentVolumeErrors
       annotations:
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-kubernetes-system-kubelet

+++ cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-kubernetes-system-kubelet

@@ -41,17 +41,17 @@

       annotations:
         description: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage
           }} of its Pod capacity.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubelettoomanypods
         summary: Kubelet is running at capacity.
       expr: |-
-        count by(cluster, node) (
-          (kube_pod_status_phase{job="kube-state-metrics",phase="Running"} == 1) * on(instance,pod,namespace,cluster) group_left(node) topk by(instance,pod,namespace,cluster) (1, kube_pod_info{job="kube-state-metrics"})
+        count by (cluster, node) (
+          (kube_pod_status_phase{job="kube-state-metrics",phase="Running"} == 1) * on (instance,pod,namespace,cluster) group_left(node) topk by (instance,pod,namespace,cluster) (1, kube_pod_info{job="kube-state-metrics"})
         )
         /
-        max by(cluster, node) (
+        max by (cluster, node) (
           kube_node_status_capacity{job="kube-state-metrics",resource="pods"} != 1
         ) > 0.95
       for: 15m
       labels:
         severity: info
     - alert: KubeNodeReadinessFlapping
@@ -80,14 +80,14 @@

       annotations:
         description: Kubelet Pod startup 99th percentile latency is {{ $value }} seconds
           on node {{ $labels.node }}.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletpodstartuplatencyhigh
         summary: Kubelet Pod startup latency is too high.
       expr: histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet",
-        metrics_path="/metrics"}[5m])) by (cluster, instance, le)) * on(cluster, instance)
-        group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}
+        metrics_path="/metrics"}[5m])) by (cluster, instance, le)) * on (cluster,
+        instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}
         > 60
       for: 15m
       labels:
         severity: warning
     - alert: KubeletClientCertificateExpiration
       annotations:
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules.container-memory-swap

+++ cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules.container-memory-swap

@@ -0,0 +1,24 @@

+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: kube-prometheus-stack-k8s.rules.container-memory-swap
+  namespace: monitoring-system
+  labels:
+    app: kube-prometheus-stack
+    app.kubernetes.io/managed-by: Helm
+    app.kubernetes.io/instance: kube-prometheus-stack
+    app.kubernetes.io/part-of: kube-prometheus-stack
+    release: kube-prometheus-stack
+    heritage: Helm
+spec:
+  groups:
+  - name: k8s.rules.container_memory_swap
+    rules:
+    - expr: |-
+        container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
+        * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1,
+          max by (cluster, namespace, pod, node) (kube_pod_info{node!=""})
+        )
+      record: node_namespace_pod_container:container_memory_swap
+
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules.container-resource

+++ cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules.container-resource

@@ -0,0 +1,86 @@

+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: kube-prometheus-stack-k8s.rules.container-resource
+  namespace: monitoring-system
+  labels:
+    app: kube-prometheus-stack
+    app.kubernetes.io/managed-by: Helm
+    app.kubernetes.io/instance: kube-prometheus-stack
+    app.kubernetes.io/part-of: kube-prometheus-stack
+    release: kube-prometheus-stack
+    heritage: Helm
+spec:
+  groups:
+  - name: k8s.rules.container_resource
+    rules:
+    - expr: |-
+        kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"}  * on (namespace, pod, cluster)
+        group_left() max by (namespace, pod, cluster) (
+          (kube_pod_status_phase{phase=~"Pending|Running"} == 1)
+        )
+      record: cluster:namespace:pod_memory:active:kube_pod_container_resource_requests
+    - expr: |-
+        sum by (namespace, cluster) (
+            sum by (namespace, pod, cluster) (
+                max by (namespace, pod, container, cluster) (
+                  kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"}
+                ) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
+                  kube_pod_status_phase{phase=~"Pending|Running"} == 1
+                )
+            )
+        )
+      record: namespace_memory:kube_pod_container_resource_requests:sum
+    - expr: |-
+        kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"}  * on (namespace, pod, cluster)
+        group_left() max by (namespace, pod, cluster) (
+          (kube_pod_status_phase{phase=~"Pending|Running"} == 1)
+        )
+      record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests
+    - expr: |-
+        sum by (namespace, cluster) (
+            sum by (namespace, pod, cluster) (
+                max by (namespace, pod, container, cluster) (
+                  kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"}
+                ) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
+                  kube_pod_status_phase{phase=~"Pending|Running"} == 1
+                )
+            )
+        )
+      record: namespace_cpu:kube_pod_container_resource_requests:sum
+    - expr: |-
+        kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"}  * on (namespace, pod, cluster)
+        group_left() max by (namespace, pod, cluster) (
+          (kube_pod_status_phase{phase=~"Pending|Running"} == 1)
+        )
+      record: cluster:namespace:pod_memory:active:kube_pod_container_resource_limits
+    - expr: |-
+        sum by (namespace, cluster) (
+            sum by (namespace, pod, cluster) (
+                max by (namespace, pod, container, cluster) (
+                  kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"}
+                ) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
+                  kube_pod_status_phase{phase=~"Pending|Running"} == 1
+                )
+            )
+        )
+      record: namespace_memory:kube_pod_container_resource_limits:sum
+    - expr: |-
+        kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"}  * on (namespace, pod, cluster)
+        group_left() max by (namespace, pod, cluster) (
+         (kube_pod_status_phase{phase=~"Pending|Running"} == 1)
+         )
+      record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits
+    - expr: |-
+        sum by (namespace, cluster) (
+            sum by (namespace, pod, cluster) (
+                max by (namespace, pod, container, cluster) (
+                  kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"}
+                ) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
+                  kube_pod_status_phase{phase=~"Pending|Running"} == 1
+                )
+            )
+        )
+      record: namespace_cpu:kube_pod_container_resource_limits:sum
+
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-general.rules

+++ cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-general.rules

@@ -48,11 +48,12 @@

           other alerts.
           This alert fires whenever there's a severity="info" alert, and stops firing when another alert with a
           severity of 'warning' or 'critical' starts firing on the same namespace.
           This alert should be routed to a null receiver and configured to inhibit alerts with severity="info".
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/infoinhibitor
         summary: Info-level alert inhibition.
-      expr: ALERTS{severity = "info"} == 1 unless on(namespace) ALERTS{alertname !=
-        "InfoInhibitor", severity =~ "warning|critical", alertstate="firing"} == 1
+      expr: ALERTS{severity = "info"} == 1 unless on (namespace) ALERTS{alertname
+        != "InfoInhibitor", severity =~ "warning|critical", alertstate="firing"} ==
+        1
       labels:
         severity: none
 
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules.pod-owner

+++ cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules.pod-owner

@@ -0,0 +1,65 @@

+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: kube-prometheus-stack-k8s.rules.pod-owner
+  namespace: monitoring-system
+  labels:
+    app: kube-prometheus-stack
+    app.kubernetes.io/managed-by: Helm
+    app.kubernetes.io/instance: kube-prometheus-stack
+    app.kubernetes.io/part-of: kube-prometheus-stack
+    release: kube-prometheus-stack
+    heritage: Helm
+spec:
+  groups:
+  - name: k8s.rules.pod_owner
+    rules:
+    - expr: |-
+        max by (cluster, namespace, workload, pod) (
+          label_replace(
+            label_replace(
+              kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"},
+              "replicaset", "$1", "owner_name", "(.*)"
+            ) * on (replicaset, namespace) group_left(owner_name) topk by (replicaset, namespace) (
+              1, max by (replicaset, namespace, owner_name) (
+                kube_replicaset_owner{job="kube-state-metrics"}
+              )
+            ),
+            "workload", "$1", "owner_name", "(.*)"
+          )
+        )
+      labels:
+        workload_type: deployment
+      record: namespace_workload_pod:kube_pod_owner:relabel
+    - expr: |-
+        max by (cluster, namespace, workload, pod) (
+          label_replace(
+            kube_pod_owner{job="kube-state-metrics", owner_kind="DaemonSet"},
+            "workload", "$1", "owner_name", "(.*)"
+          )
+        )
+      labels:
+        workload_type: daemonset
+      record: namespace_workload_pod:kube_pod_owner:relabel
+    - expr: |-
+        max by (cluster, namespace, workload, pod) (
+          label_replace(
+            kube_pod_owner{job="kube-state-metrics", owner_kind="StatefulSet"},
+            "workload", "$1", "owner_name", "(.*)"
+          )
+        )
+      labels:
+        workload_type: statefulset
+      record: namespace_workload_pod:kube_pod_owner:relabel
+    - expr: |-
+        max by (cluster, namespace, workload, pod) (
+          label_replace(
+            kube_pod_owner{job="kube-state-metrics", owner_kind="Job"},
+            "workload", "$1", "owner_name", "(.*)"
+          )
+        )
+      labels:
+        workload_type: job
+      record: namespace_workload_pod:kube_pod_owner:relabel
+
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules.container-memory-rss

+++ cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules.container-memory-rss

@@ -0,0 +1,24 @@

+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: kube-prometheus-stack-k8s.rules.container-memory-rss
+  namespace: monitoring-system
+  labels:
+    app: kube-prometheus-stack
+    app.kubernetes.io/managed-by: Helm
+    app.kubernetes.io/instance: kube-prometheus-stack
+    app.kubernetes.io/part-of: kube-prometheus-stack
+    release: kube-prometheus-stack
+    heritage: Helm
+spec:
+  groups:
+  - name: k8s.rules.container_memory_rss
+    rules:
+    - expr: |-
+        container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
+        * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1,
+          max by (cluster, namespace, pod, node) (kube_pod_info{node!=""})
+        )
+      record: node_namespace_pod_container:container_memory_rss
+
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules

+++ cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules

@@ -1,164 +0,0 @@

----
-apiVersion: monitoring.coreos.com/v1
-kind: PrometheusRule
-metadata:
-  name: kube-prometheus-stack-k8s.rules
-  namespace: monitoring-system
-  labels:
-    app: kube-prometheus-stack
-    app.kubernetes.io/managed-by: Helm
-    app.kubernetes.io/instance: kube-prometheus-stack
-    app.kubernetes.io/part-of: kube-prometheus-stack
-    release: kube-prometheus-stack
-    heritage: Helm
-spec:
-  groups:
-  - name: k8s.rules
-    rules:
-    - expr: |-
-        sum by (cluster, namespace, pod, container) (
-          irate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m])
-        ) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (
-          1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
-        )
-      record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate
-    - expr: |-
-        container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
-        * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
-          max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
-        )
-      record: node_namespace_pod_container:container_memory_working_set_bytes
-    - expr: |-
-        container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
-        * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
-          max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
-        )
-      record: node_namespace_pod_container:container_memory_rss
-    - expr: |-
-        container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
-        * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
-          max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
-        )
-      record: node_namespace_pod_container:container_memory_cache
-    - expr: |-
-        container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
-        * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
-          max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
-        )
-      record: node_namespace_pod_container:container_memory_swap
-    - expr: |-
-        kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"}  * on (namespace, pod, cluster)
-        group_left() max by (namespace, pod, cluster) (
-          (kube_pod_status_phase{phase=~"Pending|Running"} == 1)
-        )
-      record: cluster:namespace:pod_memory:active:kube_pod_container_resource_requests
-    - expr: |-
-        sum by (namespace, cluster) (
-            sum by (namespace, pod, cluster) (
-                max by (namespace, pod, container, cluster) (
-                  kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"}
-                ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
-                  kube_pod_status_phase{phase=~"Pending|Running"} == 1
-                )
-            )
-        )
-      record: namespace_memory:kube_pod_container_resource_requests:sum
-    - expr: |-
-        kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"}  * on (namespace, pod, cluster)
-        group_left() max by (namespace, pod, cluster) (
-          (kube_pod_status_phase{phase=~"Pending|Running"} == 1)
-        )
-      record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests
-    - expr: |-
-        sum by (namespace, cluster) (
-            sum by (namespace, pod, cluster) (
-                max by (namespace, pod, container, cluster) (
-                  kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"}
-                ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
-                  kube_pod_status_phase{phase=~"Pending|Running"} == 1
-                )
-            )
-        )
-      record: namespace_cpu:kube_pod_container_resource_requests:sum
-    - expr: |-
-        kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"}  * on (namespace, pod, cluster)
-        group_left() max by (namespace, pod, cluster) (
-          (kube_pod_status_phase{phase=~"Pending|Running"} == 1)
-        )
-      record: cluster:namespace:pod_memory:active:kube_pod_container_resource_limits
-    - expr: |-
-        sum by (namespace, cluster) (
-            sum by (namespace, pod, cluster) (
-                max by (namespace, pod, container, cluster) (
-                  kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"}
-                ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
-                  kube_pod_status_phase{phase=~"Pending|Running"} == 1
-                )
-            )
-        )
-      record: namespace_memory:kube_pod_container_resource_limits:sum
-    - expr: |-
-        kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"}  * on (namespace, pod, cluster)
-        group_left() max by (namespace, pod, cluster) (
-         (kube_pod_status_phase{phase=~"Pending|Running"} == 1)
-         )
-      record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits
-    - expr: |-
-        sum by (namespace, cluster) (
-            sum by (namespace, pod, cluster) (
-                max by (namespace, pod, container, cluster) (
-                  kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"}
-                ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
-                  kube_pod_status_phase{phase=~"Pending|Running"} == 1
-                )
-            )
-        )
-      record: namespace_cpu:kube_pod_container_resource_limits:sum
-    - expr: |-
-        max by (cluster, namespace, workload, pod) (
-          label_replace(
-            label_replace(
-              kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"},
-              "replicaset", "$1", "owner_name", "(.*)"
-            ) * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) (
-              1, max by (replicaset, namespace, owner_name) (
-                kube_replicaset_owner{job="kube-state-metrics"}
-              )
-            ),
-            "workload", "$1", "owner_name", "(.*)"
-          )
-        )
-      labels:
-        workload_type: deployment
-      record: namespace_workload_pod:kube_pod_owner:relabel
-    - expr: |-
-        max by (cluster, namespace, workload, pod) (
-          label_replace(
-            kube_pod_owner{job="kube-state-metrics", owner_kind="DaemonSet"},
-            "workload", "$1", "owner_name", "(.*)"
-          )
-        )
-      labels:
-        workload_type: daemonset
-      record: namespace_workload_pod:kube_pod_owner:relabel
-    - expr: |-
-        max by (cluster, namespace, workload, pod) (
-          label_replace(
-            kube_pod_owner{job="kube-state-metrics", owner_kind="StatefulSet"},
-            "workload", "$1", "owner_name", "(.*)"
-          )
-        )
-      labels:
-        workload_type: statefulset
-      record: namespace_workload_pod:kube_pod_owner:relabel
-    - expr: |-
-        max by (cluster, namespace, workload, pod) (
-          label_replace(
-            kube_pod_owner{job="kube-state-metrics", owner_kind="Job"},
-            "workload", "$1", "owner_name", "(.*)"
-          )
-        )
-      labels:
-        workload_type: job
-      record: namespace_workload_pod:kube_pod_owner:relabel
-
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules.container-memory-cache

+++ cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules.container-memory-cache

@@ -0,0 +1,24 @@

+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: kube-prometheus-stack-k8s.rules.container-memory-cache
+  namespace: monitoring-system
+  labels:
+    app: kube-prometheus-stack
+    app.kubernetes.io/managed-by: Helm
+    app.kubernetes.io/instance: kube-prometheus-stack
+    app.kubernetes.io/part-of: kube-prometheus-stack
+    release: kube-prometheus-stack
+    heritage: Helm
+spec:
+  groups:
+  - name: k8s.rules.container_memory_cache
+    rules:
+    - expr: |-
+        container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
+        * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1,
+          max by (cluster, namespace, pod, node) (kube_pod_info{node!=""})
+        )
+      record: node_namespace_pod_container:container_memory_cache
+
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules.container-cpu-usage-seconds-tot

+++ cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-k8s.rules.container-cpu-usage-seconds-tot

@@ -0,0 +1,25 @@

+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: kube-prometheus-stack-k8s.rules.container-cpu-usage-seconds-tot
+  namespace: monitoring-system
+  labels:
+    app: kube-prometheus-stack
+    app.kubernetes.io/managed-by: Helm
+    app.kubernetes.io/instance: kube-prometheus-stack
+    app.kubernetes.io/part-of: kube-prometheus-stack
+    release: kube-prometheus-stack
+    heritage: Helm
+spec:
+  groups:
+  - name: k8s.rules.container_cpu_usage_seconds_total
+    rules:
+    - expr: |-
+        sum by (cluster, namespace, pod, container) (
+          irate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m])
+        ) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (
+          1, max by (cluster, namespace, pod, node) (kube_pod_info{node!=""})
+        )
+      record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate
+
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-kubernetes-system-apiserver

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

@@ -19,47 +19,47 @@

       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(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m])))
+        > 0 and on (job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m])))
         < 604800
       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(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m])))
+        > 0 and on (job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m])))
         < 86400
       for: 5m
       labels:
         severity: critical
     - alert: KubeAggregatedAPIErrors
       annotations:
         description: Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace
           }} has reported errors. It has appeared unavailable {{ $value | humanize
           }} times averaged over the past 10m.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapierrors
         summary: Kubernetes aggregated API has reported errors.
-      expr: sum by(name, namespace, cluster)(increase(aggregator_unavailable_apiservice_total{job="apiserver"}[10m]))
+      expr: sum by (name, namespace, cluster)(increase(aggregator_unavailable_apiservice_total{job="apiserver"}[10m]))
         > 4
       labels:
         severity: warning
     - alert: KubeAggregatedAPIDown
       annotations:
         description: Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace
           }} has been only {{ $value | humanize }}% available over the last 10m.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapidown
         summary: Kubernetes aggregated API is down.
-      expr: (1 - max by(name, namespace, cluster)(avg_over_time(aggregator_unavailable_apiservice{job="apiserver"}[10m])))
+      expr: (1 - max by (name, namespace, cluster)(avg_over_time(aggregator_unavailable_apiservice{job="apiserver"}[10m])))
         * 100 < 85
       for: 5m
       labels:
         severity: warning
     - alert: KubeAPIDown
       annotations:
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-kubelet.rules

+++ cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-kubelet.rules

@@ -13,24 +13,24 @@

     heritage: Helm
 spec:
   groups:
   - name: kubelet.rules
     rules:
     - expr: histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet",
-        metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on(cluster, instance)
+        metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on (cluster, instance)
         group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
       labels:
         quantile: '0.99'
       record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
     - expr: histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet",
-        metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on(cluster, instance)
+        metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on (cluster, instance)
         group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
       labels:
         quantile: '0.9'
       record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
     - expr: histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet",
-        metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on(cluster, instance)
+        metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on (cluster, instance)
         group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
       labels:
         quantile: '0.5'
       record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
 
--- cluster/base HelmRelease: monitoring-system/kube-prometheus-stack PrometheusRule: monitoring-system/kube-prometheus-stack-kubernetes-apps

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

@@ -31,16 +31,16 @@

         description: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready
           state for longer than 15 minutes.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodnotready
         summary: Pod has been in a non-ready state for more than 15 minutes.
       expr: |-
         sum by (namespace, pod, cluster) (
-          max by(namespace, pod, cluster) (
+          max by (namespace, pod, cluster) (
             kube_pod_status_phase{job="kube-state-metrics", namespace=~".*", phase=~"Pending|Unknown|Failed"}
-          ) * on(namespace, pod, cluster) group_left(owner_kind) topk by(namespace, pod, cluster) (
-            1, max by(namespace, pod, owner_kind, cluster) (kube_pod_owner{owner_kind!="Job"})
+          ) * on (namespace, pod, cluster) group_left(owner_kind) topk by (namespace, pod, cluster) (
+            1, max by (namespace, pod, owner_kind, cluster) (kube_pod_owner{owner_kind!="Job"})
           )
         ) > 0
       for: 15m
       labels:
         severity: warning
     - alert: KubeDeploymentGenerationMismatch
@@ -221,13 +221,13 @@

       annotations:
         description: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking
           more than {{ "43200" | humanizeDuration }} to complete.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobnotcompleted
         summary: Job did not complete in time
       expr: |-
-        time() - max by(namespace, job_name, cluster) (kube_job_status_start_time{job="kube-state-metrics", namespace=~".*"}
+        time() - max by (namespace, job_name, cluster) (kube_job_status_start_time{job="kube-state-metrics", namespace=~".*"}
           and
         kube_job_status_active{job="kube-state-metrics", namespace=~".*"} > 0) > 43200
       labels:
         severity: warning
     - alert: KubeJobFailed
       annotations: