feat(container): update kube-prometheus-stack ( 69.3.1 → 69.5.2 )

[monosense-arc]

This PR contains the following updates:

Package	Update	Change
kube-prometheus-stack (source)	minor	69.3.1 -> 69.5.2

---

Release Notes

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

v69.5.2

Compare Source

v69.5.1

Compare Source

v69.5.0

Compare Source

v69.4.1

Compare Source

v69.4.0

Compare Source

v69.3.3

Compare Source

v69.3.2

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.

[monosense-arc]

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

+++ kubernetes/prod/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: 69.3.1
+      version: 69.5.2
   dependsOn:
   - name: prometheus-operator-crds
     namespace: observability
   - name: rook-ceph-cluster
     namespace: rook-ceph
   install:

[monosense-arc]

--- HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-node-cluster-rsrc-use

+++ HelmRelease: observability/kube-prometheus-stack ConfigMap: observability/kube-prometheus-stack-node-cluster-rsrc-use

@@ -10,597 +10,41 @@

     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
 data:
-  node-cluster-rsrc-use.json: |-
-    {
-        "graphTooltip": 1,
-        "panels": [
-            {
-                "collapsed": false,
-                "gridPos": {
-                    "h": 1,
-                    "w": 24,
-                    "x": 0,
-                    "y": 0
-                },
-                "id": 1,
-                "panels": [
+  node-cluster-rsrc-use.json: '{"graphTooltip":1,"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"CPU","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":1},"id":2,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"((\n  instance:node_cpu_utilisation:rate5m{job=\"node-exporter\",
+    cluster=\"$cluster\"}\n  *\n  instance:node_num_cpu:sum{job=\"node-exporter\",
+    cluster=\"$cluster\"}\n) != 0 )\n/ scalar(sum(instance:node_num_cpu:sum{job=\"node-exporter\",
+    cluster=\"$cluster\"}))\n","legendFormat":"{{ instance }}"}],"title":"CPU Utilisation","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":12,"y":1},"id":3,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n  instance:node_load1_per_cpu:ratio{job=\"node-exporter\",
+    cluster=\"$cluster\"}\n  / scalar(count(instance:node_load1_per_cpu:ratio{job=\"node-exporter\",
+    cluster=\"$cluster\"}))\n)  != 0\n","legendFormat":"{{ instance }}"}],"title":"CPU
+    Saturation (Load1 per CPU)","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":4,"panels":[],"title":"Memory","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":9},"id":5,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n  instance:node_memory_utilisation:ratio{job=\"node-exporter\",
+    cluster=\"$cluster\"}\n  / scalar(count(instance:node_memory_utilisation:ratio{job=\"node-exporter\",
+    cluster=\"$cluster\"}))\n) != 0\n","legendFormat":"{{ instance }}"}],"title":"Memory
+    Utilisation","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"rds"}},"gridPos":{"h":7,"w":12,"x":12,"y":9},"id":6,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\",
+    cluster=\"$cluster\"}","legendFormat":"{{ instance }}"}],"title":"Memory Saturation
+    (Major Page Faults)","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":16},"id":7,"panels":[],"title":"Network","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"Bps"},"overrides":[{"matcher":{"id":"byRegexp","options":"/Transmit/"},"properties":[{"id":"custom.transform","value":"negative-Y"}]}]},"gridPos":{"h":7,"w":12,"x":0,"y":17},"id":8,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\",
+    cluster=\"$cluster\"} != 0","legendFormat":"{{ instance }} Receive"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\",
+    cluster=\"$cluster\"} != 0","legendFormat":"{{ instance }} Transmit"}],"title":"Network
+    Utilisation (Bytes Receive/Transmit)","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"Bps"},"overrides":[{"matcher":{"id":"byRegexp","options":"/Transmit/"},"properties":[{"id":"custom.transform","value":"negative-Y"}]}]},"gridPos":{"h":7,"w":12,"x":12,"y":17},"id":9,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\",
+    cluster=\"$cluster\"} != 0","legendFormat":"{{ instance }} Receive"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\",
+    cluster=\"$cluster\"} != 0","legendFormat":"{{ instance }} Transmit"}],"title":"Network
+    Saturation (Drops Receive/Transmit)","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":24},"id":10,"panels":[],"title":"Disk
+    IO","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":25},"id":11,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\",
+    cluster=\"$cluster\"}\n/ scalar(count(instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\",
+    cluster=\"$cluster\"}))\n","legendFormat":"{{ instance }} {{device}}"}],"title":"Disk
+    IO Utilisation","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":12,"y":25},"id":12,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\",
+    cluster=\"$cluster\"}\n/ scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\",
+    cluster=\"$cluster\"}))\n","legendFormat":"{{ instance }} {{device}}"}],"title":"Disk
+    IO Saturation","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":34},"id":13,"panels":[],"title":"Disk
+    Space","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":24,"x":0,"y":35},"id":14,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum
+    without (device) (\n  max without (fstype, mountpoint) ((\n    node_filesystem_size_bytes{job=\"node-exporter\",
+    fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"}\n    -\n    node_filesystem_avail_bytes{job=\"node-exporter\",
+    fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"}\n  ) != 0)\n)\n/ scalar(sum(max
+    without (fstype, mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\",
+    fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"})))\n","legendFormat":"{{
+    instance }}"}],"title":"Disk Space Utilisation","type":"timeseries"}],"refresh":"30s","schemaVersion":39,"tags":["node-exporter-mixin"],"templating":{"list":[{"name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"includeAll":false,"name":"cluster","query":"label_values(node_time_seconds,
+    cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"}]},"time":{"from":"now-1h","to":"now"},"timezone":
+    "utc","title":"Node Exporter / USE Method / Cluster","uid":"3e97d1d02672cdd0861f4c97c64f89b2"}'
 
-                ],
-                "title": "CPU",
-                "type": "row"
-            },
-            {
-                "datasource": {
-                    "type": "prometheus",
-                    "uid": "${datasource}"
-                },
-                "fieldConfig": {
-                    "defaults": {
-                        "custom": {
-                            "fillOpacity": 100,
-                            "showPoints": "never",
-                            "stacking": {
-                                "mode": "normal"
-                            }
-                        },
-                        "unit": "percentunit"
-                    }
-                },
-                "gridPos": {
-                    "h": 7,
-                    "w": 12,
-                    "x": 0,
[Diff truncated by flux-local]
--- HelmRelease: observability/kube-prometheus-stack DaemonSet: observability/node-exporter

+++ HelmRelease: observability/kube-prometheus-stack DaemonSet: observability/node-exporter

@@ -40,13 +40,13 @@

         runAsGroup: 65534
         runAsNonRoot: true
         runAsUser: 65534
       serviceAccountName: node-exporter
       containers:
       - name: node-exporter
-        image: quay.io/prometheus/node-exporter:v1.8.2
+        image: quay.io/prometheus/node-exporter:v1.9.0
         imagePullPolicy: IfNotPresent
         args:
         - --path.procfs=/host/proc
         - --path.sysfs=/host/sys
         - --path.rootfs=/host/root
         - --path.udev.data=/host/root/run/udev/data
--- HelmRelease: observability/kube-prometheus-stack Deployment: observability/kube-state-metrics

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

@@ -44,13 +44,13 @@

       - name: kube-state-metrics
         args:
         - --port=8080
         - --resources=certificatesigningrequests,configmaps,cronjobs,daemonsets,deployments,endpoints,horizontalpodautoscalers,ingresses,jobs,leases,limitranges,mutatingwebhookconfigurations,namespaces,networkpolicies,nodes,persistentvolumeclaims,persistentvolumes,poddisruptionbudgets,pods,replicasets,replicationcontrollers,resourcequotas,secrets,services,statefulsets,storageclasses,validatingwebhookconfigurations,volumeattachments
         - --metric-labels-allowlist=pods=[*],deployments=[*],persistentvolumeclaims=[*]
         imagePullPolicy: IfNotPresent
-        image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.14.0
+        image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.15.0
         ports:
         - containerPort: 8080
           name: http
         livenessProbe:
           failureThreshold: 3
           httpGet:
--- HelmRelease: observability/kube-prometheus-stack Deployment: observability/kube-prometheus-stack-operator

+++ HelmRelease: observability/kube-prometheus-stack Deployment: observability/kube-prometheus-stack-operator

@@ -31,20 +31,20 @@

         app: kube-prometheus-stack-operator
         app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
         app.kubernetes.io/component: prometheus-operator
     spec:
       containers:
       - name: kube-prometheus-stack
-        image: quay.io/prometheus-operator/prometheus-operator:v0.80.0
+        image: quay.io/prometheus-operator/prometheus-operator:v0.80.1
         imagePullPolicy: IfNotPresent
         args:
         - --kubelet-service=kube-system/kube-prometheus-stack-kubelet
         - --kubelet-endpoints=true
         - --kubelet-endpointslice=false
         - --localhost=127.0.0.1
-        - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.80.0
+        - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.80.1
         - --config-reloader-cpu-request=0
         - --config-reloader-cpu-limit=0
         - --config-reloader-memory-request=0
         - --config-reloader-memory-limit=0
         - --thanos-default-base-image=quay.io/thanos/thanos:v0.37.2
         - --secret-field-selector=type!=kubernetes.io/dockercfg,type!=kubernetes.io/service-account-token,type!=helm.sh/release.v1
--- HelmRelease: observability/kube-prometheus-stack Prometheus: observability/kube-prometheus-stack

+++ HelmRelease: observability/kube-prometheus-stack Prometheus: observability/kube-prometheus-stack

@@ -17,14 +17,14 @@

     alertmanagers:
     - namespace: observability
       name: kube-prometheus-stack-alertmanager
       port: http-web
       pathPrefix: /
       apiVersion: v2
-  image: quay.io/prometheus/prometheus:v3.1.0
-  version: v3.1.0
+  image: quay.io/prometheus/prometheus:v3.2.0
+  version: v3.2.0
   externalUrl: http://prometheus...PLACEHOLDER_CLUSTER_SECRET_PRD_DOMAIN../
   paused: false
   replicas: 1
   shards: 1
   logLevel: info
   logFormat: logfmt
--- HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-kubernetes-apps

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

@@ -99,13 +99,13 @@

         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetreplicasmismatch
         summary: StatefulSet has not matched the expected number of replicas.
       expr: |-
         (
           kube_statefulset_status_replicas_ready{job="kube-state-metrics", namespace=~".*"}
             !=
-          kube_statefulset_status_replicas{job="kube-state-metrics", namespace=~".*"}
+          kube_statefulset_replicas{job="kube-state-metrics", namespace=~".*"}
         ) and (
           changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~".*"}[10m])
             ==
           0
         )
       for: 15m
--- 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

@@ -44,20 +44,22 @@

       annotations:
         description: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage
           }} of its Pod capacity on cluster {{ $labels.cluster }}.
         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 (cluster, namespace, pod) group_left (node)
-          group by (cluster, namespace, pod, node) (
-            kube_pod_info{job="kube-state-metrics"}
+        (
+          max by (cluster, instance) (
+            kubelet_running_pods{job="kubelet", metrics_path="/metrics"} > 1
+          )
+          * on (cluster, instance) group_left(node)
+          max by (cluster, instance, node) (
+            kubelet_node_name{job="kubelet", metrics_path="/metrics"}
           )
         )
-        /
+        / on (cluster, node) group_left()
         max by (cluster, node) (
           kube_node_status_capacity{job="kube-state-metrics", resource="pods"} != 1
         ) > 0.95
       for: 15m
       labels:
         severity: info
--- HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-node-exporter

+++ HelmRelease: observability/kube-prometheus-stack PrometheusRule: observability/kube-prometheus-stack-node-exporter

@@ -340,12 +340,24 @@

         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemdservicefailed
         summary: Systemd service has entered failed state.
       expr: node_systemd_unit_state{job="node-exporter", state="failed"} == 1
       for: 5m
       labels:
         severity: warning
+    - alert: NodeSystemdServiceCrashlooping
+      annotations:
+        description: Systemd service {{ $labels.name }} has being restarted too many
+          times at {{ $labels.instance }} for the last 15 minutes. Please check if
+          service is crash looping.
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemdservicecrashlooping
+        summary: Systemd service keeps restaring, possibly crash looping.
+      expr: increase(node_systemd_service_restart_total{job="node-exporter"}[5m])
+        > 2
+      for: 15m
+      labels:
+        severity: warning
     - alert: NodeBondingDegraded
       annotations:
         description: Bonding interface {{ $labels.master }} on {{ $labels.instance
           }} is in degraded state due to one or more slave failures.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodebondingdegraded
         summary: Bonding interface is degraded