feat: metrics version bump

charts/kubezero-metrics/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: kubezero-metrics
 description: KubeZero Umbrella Chart for Prometheus, Grafana and Alertmanager as well as all Kubernetes integrations.
 type: application
-version: 0.5.4
+version: 0.6.1
 home: https://kubezero.com
 icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
 keywords:
@@ -11,22 +11,23 @@ keywords:
   - alertmanager
   - grafana
 maintainers:
-  - name: Quarky9
+  - name: Stefan Reimer
+    email: stefan@zero-downtime.net
 dependencies:
   - name: kubezero-lib
     version: ">= 0.1.4"
     repository: https://cdn.zero-downtime.net/charts/
   - name: kube-prometheus-stack
-    version: 18.1.0
+    version: 23.1.5
     # Switch back to upstream once all alerts are fixed eg. etcd gpcr
     # repository: https://prometheus-community.github.io/helm-charts
   - name: prometheus-adapter
-    version: 2.17
+    version: 3.0.0
     repository: https://prometheus-community.github.io/helm-charts
     condition: prometheus-adapter.enabled
   - name: prometheus-pushgateway
-    version: 1.10.1
+    version: 1.13.0
     # Switch back to upstream once namespaces are supported
     # repository: https://prometheus-community.github.io/helm-charts
     condition: prometheus-pushgateway.enabled
-kubeVersion: ">= 1.18.0"
+kubeVersion: ">= 1.20.0"

charts/kubezero-metrics/charts/kube-prometheus-stack/Chart.yaml

@@ -6,20 +6,20 @@ annotations:
       url: https://github.com/prometheus-operator/kube-prometheus
   artifacthub.io/operator: "true"
 apiVersion: v2
-appVersion: 0.50.0
+appVersion: 0.52.0
 dependencies:
 - condition: kubeStateMetrics.enabled
   name: kube-state-metrics
   repository: https://prometheus-community.github.io/helm-charts
-  version: 3.4.*
+  version: 4.1.*
 - condition: nodeExporter.enabled
   name: prometheus-node-exporter
   repository: https://prometheus-community.github.io/helm-charts
-  version: 2.0.*
+  version: 2.2.*
 - condition: grafana.enabled
   name: grafana
   repository: https://grafana.github.io/helm-charts
-  version: 6.16.*
+  version: 6.18.*
 description: 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
@@ -32,7 +32,6 @@ keywords:
 - kube-prometheus
 kubeVersion: '>=1.16.0-0'
 maintainers:
-- name: vsliouniaev
 - name: bismarck
 - email: gianrubio@gmail.com
   name: gianrubio
@@ -47,4 +46,4 @@ sources:
 - https://github.com/prometheus-community/helm-charts
 - https://github.com/prometheus-operator/kube-prometheus
 type: application
-version: 18.1.0
+version: 23.1.5

charts/kubezero-metrics/charts/kube-prometheus-stack/README.md

@@ -83,7 +83,58 @@ _See [helm upgrade](https://helm.sh/docs/helm/helm_upgrade/) for command documen
 
 A major chart version change (like v1.2.3 -> v2.0.0) indicates that there is an incompatible breaking change needing manual actions.
 
+### From 22.x to 23.x
+
+Port names have been renamed for Istio's
+[explicit protocol selection](https://istio.io/latest/docs/ops/configuration/traffic-management/protocol-selection/#explicit-protocol-selection).
+
+| | old value | new value |
+|-|-----------|-----------|
+| `alertmanager.alertmanagerSpec.portName` | `web` | `http-web` |
+| `grafana.service.portName` | `service` | `http-web` |
+| `prometheus-node-exporter.service.portName` | `metrics` (hardcoded) | `http-metrics` |
+| `prometheus.prometheusSpec.portName` | `web` | `http-web` |
+
+### From 21.x to 22.x
+
+Due to the upgrade of the `kube-state-metrics` chart, removal of its deployment/stateful needs to done manually prior to upgrading:
+
+```console
+kubectl delete deployments.apps -l app.kubernetes.io/instance=prometheus-operator,app.kubernetes.io/name=kube-state-metrics --cascade=orphan
+```
+
+or if you use autosharding:
+
+```console
+kubectl delete statefulsets.apps -l app.kubernetes.io/instance=prometheus-operator,app.kubernetes.io/name=kube-state-metrics --cascade=orphan
+```
+
+### From 20.x to 21.x
+
+The config reloader values have been refactored. All the values have been moved to the key `prometheusConfigReloader` and the limits and requests can now be set separately.
+
+### From 19.x to 20.x
+
+Version 20 upgrades prometheus-operator from 0.50.x to 0.52.x. Helm does not automatically upgrade or install new CRDs on a chart upgrade, so you have to install the CRDs manually before updating:
+
+```console
+kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_alertmanagerconfigs.yaml
+kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_alertmanagers.yaml
+kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_podmonitors.yaml
+kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_probes.yaml
+kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_prometheuses.yaml
+kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_prometheusrules.yaml
+kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_servicemonitors.yaml
+kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_thanosrulers.yaml
+```
+
+### From 18.x to 19.x
+
+`kubeStateMetrics.serviceMonitor.namespaceOverride` was removed.
+Please use `kube-state-metrics.namespaceOverride` instead.
+
 ### From 17.x to 18.x
+
 Version 18 upgrades prometheus-operator from 0.49.x to 0.50.x. Helm does not automatically upgrade or install new CRDs on a chart upgrade, so you have to install the CRDs manually before updating:
 
 ```console
@@ -98,6 +149,7 @@ kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheu
 ```
 
 ### From 16.x to 17.x
+
 Version 17 upgrades prometheus-operator from 0.48.x to 0.49.x. Helm does not automatically upgrade or install new CRDs on a chart upgrade, so you have to install the CRDs manually before updating:
 
 ```console
@@ -111,11 +163,12 @@ kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheu
 kubectl apply -f https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.49.0/example/prometheus-operator-crd/monitoring.coreos.com_thanosrulers.yaml
 ```
 
-
 ### From 15.x to 16.x
+
 Version 16 upgrades kube-state-metrics to v2.0.0. This includes changed command-line arguments and removed metrics, see this [blog post](https://kubernetes.io/blog/2021/04/13/kube-state-metrics-v-2-0/). This version also removes Grafana dashboards that supported Kubernetes 1.14 or earlier.
 
 ### From 14.x to 15.x
+
 Version 15 upgrades prometheus-operator from 0.46.x to 0.47.x. Helm does not automatically upgrade or install new CRDs on a chart upgrade, so you have to install the CRDs manually before updating:
 
 ```console

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/Chart.yaml

@@ -1,5 +1,5 @@
 apiVersion: v2
-appVersion: 8.1.5
+appVersion: 8.3.1
 description: The leading tool for querying and visualizing time series and metrics.
 home: https://grafana.net
 icon: https://raw.githubusercontent.com/grafana/grafana/master/public/img/logo_transparent_400x.png
@@ -19,4 +19,4 @@ name: grafana
 sources:
 - https://github.com/grafana/grafana
 type: application
-version: 6.16.9
+version: 6.18.2

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/README.md

@@ -59,8 +59,8 @@ This version requires Helm >= 3.1.0.
 | `securityContext`                         | Deployment securityContext                    | `{"runAsUser": 472, "runAsGroup": 472, "fsGroup": 472}`  |
 | `priorityClassName`                       | Name of Priority Class to assign pods         | `nil`                                                   |
 | `image.repository`                        | Image repository                              | `grafana/grafana`                                       |
-| `image.tag`                               | Image tag (`Must be >= 5.0.0`)                | `8.0.3`                                                 |
+| `image.tag`                               | Image tag (`Must be >= 5.0.0`)                | `8.2.5`                                                 |
-| `image.sha`                               | Image sha (optional)                          | `80c6d6ac633ba5ab3f722976fb1d9a138f87ca6a9934fcd26a5fc28cbde7dbfa` |
+| `image.sha`                               | Image sha (optional)                          | `2acf04c016c77ca2e89af3536367ce847ee326effb933121881c7c89781051d3` |
 | `image.pullPolicy`                        | Image pull policy                             | `IfNotPresent`                                          |
 | `image.pullSecrets`                       | Image pull secrets                            | `{}`                                                    |
 | `service.enabled`                         | Enable grafana service                        | `true`                                                  |
@@ -75,6 +75,7 @@ This version requires Helm >= 3.1.0.
 | `service.loadBalancerIP`                  | IP address to assign to load balancer (if supported) | `nil`                                            |
 | `service.loadBalancerSourceRanges`        | list of IP CIDRs allowed access to lb (if supported) | `[]`                                             |
 | `service.externalIPs`                     | service external IP addresses                 | `[]`                                                    |
+| `headlessService`                         | Create a headless service                     | `false`                                                 |
 | `extraExposePorts`                        | Additional service ports for sidecar containers| `[]`                                                   |
 | `hostAliases`                             | adds rules to the pod's /etc/hosts            | `[]`                                                    |
 | `ingress.enabled`                         | Enables Ingress                               | `false`                                                 |
@@ -141,7 +142,8 @@ This version requires Helm >= 3.1.0.
 | `sidecar.image.sha`                       | Sidecar image sha (optional)                  | `""`                                                    |
 | `sidecar.imagePullPolicy`                 | Sidecar image pull policy                     | `IfNotPresent`                                          |
 | `sidecar.resources`                       | Sidecar resources                             | `{}`                                                    |
-| `sidecar.enableUniqueFilenames`           | Sets the kiwigrid/k8s-sidecar UNIQUE_FILENAMES environment variable | `false`                           |
+| `sidecar.securityContext`                 | Sidecar securityContext                       | `{}`                                                    |
+| `sidecar.enableUniqueFilenames`           | Sets the kiwigrid/k8s-sidecar UNIQUE_FILENAMES environment variable. If set to `true` the sidecar will create unique filenames where duplicate data keys exist between ConfigMaps and/or Secrets within the same or multiple Namespaces. | `false`                           |
 | `sidecar.dashboards.enabled`              | Enables the cluster wide search for dashboards and adds/updates/deletes them in grafana | `false`       |
 | `sidecar.dashboards.SCProvider`           | Enables creation of sidecar provider          | `true`                                                  |
 | `sidecar.dashboards.provider.name`        | Unique name of the grafana provider           | `sidecarProvider`                                       |
@@ -158,16 +160,18 @@ This version requires Helm >= 3.1.0.
 | `sidecar.dashboards.folder`               | Folder in the pod that should hold the collected dashboards (unless `sidecar.dashboards.defaultFolderName` is set). This path will be mounted. | `/tmp/dashboards`    |
 | `sidecar.dashboards.folderAnnotation`     | The annotation the sidecar will look for in configmaps to override the destination folder for files | `nil`                                                  |
 | `sidecar.dashboards.defaultFolderName`    | The default folder name, it will create a subfolder under the `sidecar.dashboards.folder` and put dashboards in there instead | `nil`                                |
-| `sidecar.dashboards.searchNamespace`      | If specified, the sidecar will search for dashboard config-maps inside this namespace. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces | `nil`                                |
+| `sidecar.dashboards.searchNamespace`      | Namespaces list. If specified, the sidecar will search for dashboards config-maps  inside these namespaces.Otherwise the namespace in which the sidecar is running will be used.It's also possible to specify ALL to search in all namespaces. | `nil`                                |
+| `sidecar.dashboards.script`               | Absolute path to shell script to execute after a configmap got reloaded. | `nil`                                |
 | `sidecar.dashboards.resource`             | Should the sidecar looks into secrets, configmaps or both. | `both`                               |
+| `sidecar.dashboards.extraMounts`          | Additional dashboard sidecar volume mounts. | `[]`                               |
 | `sidecar.datasources.enabled`             | Enables the cluster wide search for datasources and adds/updates/deletes them in grafana |`false`       |
 | `sidecar.datasources.label`               | Label that config maps with datasources should have to be added | `grafana_datasource`                               |
 | `sidecar.datasources.labelValue`          | Label value that config maps with datasources should have to be added | `nil`                                |
-| `sidecar.datasources.searchNamespace`     | If specified, the sidecar will search for datasources config-maps inside this namespace. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces | `nil`                               |
+| `sidecar.datasources.searchNamespace`     | Namespaces list. If specified, the sidecar will search for datasources config-maps  inside these namespaces.Otherwise the namespace in which the sidecar is running will be used.It's also possible to specify ALL to search in all namespaces. | `nil`                               |
 | `sidecar.datasources.resource`            | Should the sidecar looks into secrets, configmaps or both. | `both`                               |
 | `sidecar.notifiers.enabled`               | Enables the cluster wide search for notifiers and adds/updates/deletes them in grafana | `false`        |
 | `sidecar.notifiers.label`                 | Label that config maps with notifiers should have to be added | `grafana_notifier`                               |
-| `sidecar.notifiers.searchNamespace`       | If specified, the sidecar will search for notifiers config-maps (or secrets) inside this namespace. Otherwise the namespace in which the sidecar is running will be used. It's also possible to specify ALL to search in all namespaces | `nil`                               |
+| `sidecar.notifiers.searchNamespace`       | Namespaces list. If specified, the sidecar will search for notifiers config-maps (or secrets) inside these namespaces.Otherwise the namespace in which the sidecar is running will be used.It's also possible to specify ALL to search in all namespaces. | `nil`                               |
 | `sidecar.notifiers.resource`              | Should the sidecar looks into secrets, configmaps or both. | `both`                               |
 | `smtp.existingSecret`                     | The name of an existing secret containing the SMTP credentials. | `""`                                  |
 | `smtp.userKey`                            | The key in the existing SMTP secret containing the username. | `"user"`                                 |
@@ -190,7 +194,7 @@ This version requires Helm >= 3.1.0.
 | `command`                     | Define command to be executed by grafana container at startup  | `nil`                                              |
 | `testFramework.enabled`                   | Whether to create test-related resources      | `true`                                                  |
 | `testFramework.image`                     | `test-framework` image repository.            | `bats/bats`                                             |
-| `testFramework.tag`                       | `test-framework` image tag.                   | `v1.1.0`                                                |
+| `testFramework.tag`                       | `test-framework` image tag.                   | `v1.4.1`                                                |
 | `testFramework.imagePullPolicy`           | `test-framework` image pull policy.           | `IfNotPresent`                                          |
 | `testFramework.securityContext`           | `test-framework` securityContext              | `{}`                                                    |
 | `downloadDashboards.env`                  | Environment variables to be passed to the `download-dashboards` container | `{}`                        |
@@ -230,6 +234,11 @@ This version requires Helm >= 3.1.0.
 | `imageRenderer.networkPolicy.limitIngress` | Enable a NetworkPolicy to limit inbound traffic from only the created grafana pods  | `true`                           |
 | `imageRenderer.networkPolicy.limitEgress`  | Enable a NetworkPolicy to limit outbound traffic to only the created grafana pods   | `false`                          |
 | `imageRenderer.resources`                  | Set resource limits for image-renderer pdos                                        | `{}`                             |
+| `networkPolicy.enabled`                    | Enable creation of NetworkPolicy resources.                                                                              | `false`             |
+| `networkPolicy.allowExternal`              | Don't require client label for connections                                                                               | `true`              |
+| `networkPolicy.explicitNamespacesSelector` | A Kubernetes LabelSelector to explicitly select namespaces from which traffic could be allowed                           | `{}`                |
+
+
 
 ### Example ingress with path
 
@@ -526,3 +535,23 @@ imageRenderer:
 ### Image Renderer NetworkPolicy
 
 By default the image-renderer pods will have a network policy which only allows ingress traffic from the created grafana instance
+
+### High Availability for unified alerting
+
+If you want to run Grafana in a high availability cluster you need to enable
+the headless service by setting `headlessService: true` in your `values.yaml`
+file.
+
+As next step you have to setup the `grafana.ini` in your `values.yaml` in a way
+that it will make use of the headless service to obtain all the IPs of the
+cluster. You should replace ``{{ Name }}`` with the name of your helm deployment.
+
+```yaml
+grafana.ini:
+  ...
+  unified_alerting:
+    enabled: true
+    ha_peers: {{ Name }}-headless:9094
+  alerting:
+    enabled: false
+```

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/_pod.tpl

@@ -87,7 +87,7 @@ initContainers:
     imagePullPolicy: {{ .Values.sidecar.imagePullPolicy }}
     env:
       - name: METHOD
-        value: LIST
+        value: {{ .Values.sidecar.datasources.watchMethod }}
       - name: LABEL
         value: "{{ .Values.sidecar.datasources.label }}"
       {{- if .Values.sidecar.datasources.labelValue }}
@@ -104,7 +104,7 @@ initContainers:
       {{- end }}
       {{- if .Values.sidecar.datasources.searchNamespace }}
       - name: NAMESPACE
-        value: "{{ .Values.sidecar.datasources.searchNamespace }}"
+        value: "{{ .Values.sidecar.datasources.searchNamespace | join "," }}"
       {{- end }}
       {{- if .Values.sidecar.skipTlsVerify }}
       - name: SKIP_TLS_VERIFY
@@ -112,6 +112,10 @@ initContainers:
       {{- end }}
     resources:
 {{ toYaml .Values.sidecar.resources | indent 6 }}
+{{- if .Values.sidecar.securityContext }}
+    securityContext:
+{{- toYaml .Values.sidecar.securityContext | nindent 6 }}
+{{- end }}
     volumeMounts:
       - name: sc-datasources-volume
         mountPath: "/etc/grafana/provisioning/datasources"
@@ -139,7 +143,7 @@ initContainers:
       {{- end }}
       {{- if .Values.sidecar.notifiers.searchNamespace }}
       - name: NAMESPACE
-        value: "{{ .Values.sidecar.notifiers.searchNamespace }}"
+        value: "{{ .Values.sidecar.notifiers.searchNamespace | join "," }}"
       {{- end }}
       {{- if .Values.sidecar.skipTlsVerify }}
       - name: SKIP_TLS_VERIFY
@@ -147,6 +151,10 @@ initContainers:
       {{- end }}
     resources:
 {{ toYaml .Values.sidecar.resources | indent 6 }}
+{{- if .Values.sidecar.securityContext }}
+    securityContext:
+{{- toYaml .Values.sidecar.securityContext | nindent 6 }}
+{{- end }}
     volumeMounts:
       - name: sc-notifiers-volume
         mountPath: "/etc/grafana/provisioning/notifiers"
@@ -189,7 +197,7 @@ containers:
       {{- end }}
       {{- if .Values.sidecar.dashboards.searchNamespace }}
       - name: NAMESPACE
-        value: "{{ .Values.sidecar.dashboards.searchNamespace }}"
+        value: "{{ .Values.sidecar.dashboards.searchNamespace | join "," }}"
       {{- end }}
       {{- if .Values.sidecar.skipTlsVerify }}
       - name: SKIP_TLS_VERIFY
@@ -199,16 +207,22 @@ containers:
       - name: FOLDER_ANNOTATION
         value: "{{ .Values.sidecar.dashboards.folderAnnotation }}"
       {{- end }}
+      {{- if .Values.sidecar.dashboards.script }}
       - name: SCRIPT
-        value: /opt/script.sh
+        value: "{{ .Values.sidecar.dashboards.script }}"
+      {{- end }}
     resources:
 {{ toYaml .Values.sidecar.resources | indent 6 }}
+{{- if .Values.sidecar.securityContext }}
+    securityContext:
+{{- toYaml .Values.sidecar.securityContext | nindent 6 }}
+{{- end }}
     volumeMounts:
       - name: sc-dashboard-volume
         mountPath: {{ .Values.sidecar.dashboards.folder | quote }}
-      - name: script-volume
+      {{- if .Values.sidecar.dashboards.extraMounts }}
-        mountPath: /opt/script.sh
+      {{- toYaml .Values.sidecar.dashboards.extraMounts | trim | nindent 6}}
-        subPath: script.sh
+      {{- end }}
 {{- end}}
   - name: {{ .Chart.Name }}
     {{- if .Values.image.sha }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/dashboards-json-configmap.yaml

@@ -9,6 +9,9 @@ metadata:
   labels:
     {{- include "grafana.labels" $ | nindent 4 }}
     dashboard-provider: {{ $provider }}
+    {{- if $.Values.sidecar.dashboards.label }}
+    {{ $.Values.sidecar.dashboards.label }}: "1"
+    {{- end }}
 {{- if $dashboards }}
 data:
 {{- $dashboardFound := false }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/headless-service.yaml

@@ -1,4 +1,4 @@
-{{- if and .Values.persistence.enabled (not .Values.persistence.existingClaim) (eq .Values.persistence.type "statefulset")}}
+{{- if or .Values.headlessService (and .Values.persistence.enabled (not .Values.persistence.existingClaim) (eq .Values.persistence.type "statefulset"))}}
 apiVersion: v1
 kind: Service
 metadata:
@@ -15,4 +15,8 @@ spec:
   selector:
     {{- include "grafana.selectorLabels" . | nindent 4 }}
   type: ClusterIP
+  ports:
+  - protocol: TCP
+    port: 3000
+    targetPort: 3000
 {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/image-renderer-deployment.yaml

@@ -78,6 +78,10 @@ spec:
             - name: {{ .Values.imageRenderer.service.portName }}
               containerPort: {{ .Values.imageRenderer.service.port }}
               protocol: TCP
+          livenessProbe:
+            httpGet:
+              path: /
+              port: {{ .Values.imageRenderer.service.portName }}
           env:
             - name: HTTP_PORT
               value: {{ .Values.imageRenderer.service.port | quote }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/templates/networkpolicy.yaml

@@ -0,0 +1,37 @@
+{{- if .Values.networkPolicy.enabled }}
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: {{ template "grafana.fullname" . }}
+  namespace: {{ template "grafana.namespace" . }}
+  labels:
+    {{- include "grafana.labels" . | nindent 4 }}
+{{- if .Values.labels }}
+{{ toYaml .Values.labels | indent 4 }}
+{{- end }}
+{{- with .Values.annotations }}
+  annotations:
+{{ toYaml . | indent 4 }}
+{{- end }}
+spec:
+  podSelector:
+    matchLabels:
+    {{- include "grafana.selectorLabels" . | nindent 6 }}
+  ingress:
+    - ports:
+      - port: {{ .Values.service.targetPort }}
+      {{- if not .Values.networkPolicy.allowExternal }}
+      from:
+        - podSelector:
+            matchLabels:
+              {{ template "grafana.fullname" . }}-client: "true"
+          {{- if .Values.networkPolicy.explicitNamespacesSelector }}
+          namespaceSelector:
+          {{ toYaml .Values.networkPolicy.explicitNamespacesSelector | indent 12 }}
+          {{- end }}
+        - podSelector:
+            matchLabels:
+              {{- include "grafana.labels" . | nindent 14 }}
+              role: read
+      {{- end }}
+{{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/grafana/values.yaml

@@ -23,6 +23,9 @@ serviceAccount:
 
 replicas: 1
 
+## Create a headless service for the deployment
+headlessService: false
+
 ## Create HorizontalPodAutoscaler object for deployment type
 #
 autoscaling:
@@ -70,7 +73,7 @@ livenessProbe:
 
 image:
   repository: grafana/grafana
-  tag: 8.1.5
+  tag: 8.3.1
   sha: ""
   pullPolicy: IfNotPresent
 
@@ -84,7 +87,7 @@ image:
 testFramework:
   enabled: true
   image: "bats/bats"
-  tag: "v1.1.0"
+  tag: "v1.4.1"
   imagePullPolicy: IfNotPresent
   securityContext: {}
 
@@ -615,7 +618,7 @@ smtp:
 sidecar:
   image:
     repository: quay.io/kiwigrid/k8s-sidecar
-    tag: 1.12.3
+    tag: 1.14.2
     sha: ""
   imagePullPolicy: IfNotPresent
   resources: {}
@@ -625,6 +628,7 @@ sidecar:
 #   requests:
 #     cpu: 50m
 #     memory: 50Mi
+  securityContext: {}
   # skipTlsVerify Set to true to skip tls verification for kube api calls
   # skipTlsVerify: true
   enableUniqueFilenames: false
@@ -639,15 +643,19 @@ sidecar:
     folder: /tmp/dashboards
     # The default folder name, it will create a subfolder under the `folder` and put dashboards in there instead
     defaultFolderName: null
-    # If specified, the sidecar will search for dashboard config-maps inside this namespace.
+    # Namespaces list. If specified, the sidecar will search for config-maps/secrets inside these namespaces.
     # Otherwise the namespace in which the sidecar is running will be used.
-    # It's also possible to specify ALL to search in all namespaces
+    # It's also possible to specify ALL to search in all namespaces.
     searchNamespace: null
+    # Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds.
+    watchMethod: WATCH
     # search in configmap, secret or both
     resource: both
     # If specified, the sidecar will look for annotation with this name to create folder and put graph here.
     # You can use this parameter together with `provider.foldersFromFilesStructure`to annotate configmaps and create folder structure.
     folderAnnotation: null
+    # Absolute path to shell script to execute after a configmap got reloaded
+    script: null
     # provider configuration that lets grafana manage the dashboards
     provider:
       # name of the provider, should be unique
@@ -664,6 +672,8 @@ sidecar:
       allowUiUpdates: false
       # allow Grafana to replicate dashboard structure from filesystem
       foldersFromFilesStructure: false
+    # Additional dashboard sidecar volume mounts
+    extraMounts: []
   datasources:
     enabled: false
     # label that the configmaps with datasources are marked with
@@ -674,6 +684,8 @@ sidecar:
     # Otherwise the namespace in which the sidecar is running will be used.
     # It's also possible to specify ALL to search in all namespaces
     searchNamespace: null
+    # Method to use to detect ConfigMap changes. With WATCH the sidecar will do a WATCH requests, with SLEEP it will list all ConfigMaps, then sleep for 60 seconds.
+    watchMethod: LIST
     # search in configmap, secret or both
     resource: both
   notifiers:
@@ -748,3 +760,29 @@ imageRenderer:
 #   requests:
 #     cpu: 50m
 #     memory: 50Mi
+
+networkPolicy:
+  ## @param networkPolicy.enabled Enable creation of NetworkPolicy resources. Only Ingress traffic is filtered for now.
+  ##
+  enabled: false
+  ## @param networkPolicy.allowExternal Don't require client label for connections
+  ## The Policy model to apply. When set to false, only pods with the correct
+  ## client label will have network access to  grafana port defined.
+  ## When true, grafana will accept connections from any source
+  ## (with the correct destination port).
+  ##
+  allowExternal: true
+  ## @param networkPolicy.explicitNamespacesSelector A Kubernetes LabelSelector to explicitly select namespaces from which traffic could be allowed
+  ## If explicitNamespacesSelector is missing or set to {}, only client Pods that are in the networkPolicy's namespace
+  ## and that match other criteria, the ones that have the good label, can reach the grafana.
+  ## But sometimes, we want the grafana to be accessible to clients from other namespaces, in this case, we can use this
+  ## LabelSelector to select these namespaces, note that the networkPolicy's namespace should also be explicitly added.
+  ##
+  ## Example:
+  ## explicitNamespacesSelector:
+  ##   matchLabels:
+  ##     role: frontend
+  ##   matchExpressions:
+  ##    - {key: role, operator: In, values: [frontend]}
+  ##
+  explicitNamespacesSelector: {}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/Chart.yaml

@@ -1,5 +1,5 @@
 apiVersion: v2
-appVersion: 2.1.1
+appVersion: 2.2.4
 description: Install kube-state-metrics to generate and expose cluster-level metrics
 home: https://github.com/kubernetes/kube-state-metrics/
 keywords:
@@ -16,4 +16,4 @@ name: kube-state-metrics
 sources:
 - https://github.com/kubernetes/kube-state-metrics/
 type: application
-version: 3.4.2
+version: 4.1.1

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/_helpers.tpl

@@ -45,3 +45,35 @@ Allow the release namespace to be overridden for multi-namespace deployments in
     {{- .Release.Namespace -}}
   {{- end -}}
 {{- end -}}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "kube-state-metrics.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+{{/*
+Generate basic labels
+*/}}
+{{- define "kube-state-metrics.labels" }}
+helm.sh/chart: {{ include "kube-state-metrics.chart" . }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+app.kubernetes.io/component: metrics
+app.kubernetes.io/part-of: {{ template "kube-state-metrics.name" . }}
+{{- include "kube-state-metrics.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+{{- if .Values.customLabels }}
+{{ toYaml .Values.customLabels }}
+{{- end }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "kube-state-metrics.selectorLabels" }}
+app.kubernetes.io/name: {{ include "kube-state-metrics.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/clusterrolebinding.yaml

@@ -3,10 +3,7 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
 metadata:
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }}
-    app.kubernetes.io/managed-by: {{ .Release.Service }}
-    app.kubernetes.io/instance: {{ .Release.Name }}
   name: {{ template "kube-state-metrics.fullname" . }}
 roleRef:
   apiGroup: rbac.authorization.k8s.io

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/deployment.yaml

@@ -8,18 +8,11 @@ metadata:
   name: {{ template "kube-state-metrics.fullname" . }}
   namespace: {{ template "kube-state-metrics.namespace" . }}
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: "{{ .Chart.Name }}-{{ .Chart.Version }}"
-    app.kubernetes.io/instance: "{{ .Release.Name }}"
-    app.kubernetes.io/managed-by: "{{ .Release.Service }}"
-    app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-    {{- if .Values.customLabels }}
-{{ toYaml .Values.customLabels | indent 4 }}
-    {{- end }}
 spec:
   selector:
     matchLabels:
-      app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+      {{- include "kube-state-metrics.selectorLabels" . | indent 6 }}
   replicas: {{ .Values.replicas }}
   {{- if .Values.autosharding.enabled }}
   serviceName: {{ template "kube-state-metrics.fullname" . }}
@@ -28,11 +21,7 @@ spec:
   template:
     metadata:
       labels:
-        app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+        {{- include "kube-state-metrics.labels" . | indent 8 }}
-        app.kubernetes.io/instance: "{{ .Release.Name }}"
-        {{- if .Values.customLabels }}
-{{ toYaml .Values.customLabels | indent 8 }}
-        {{- end }}
       {{- if .Values.podAnnotations }}
       annotations:
 {{ toYaml .Values.podAnnotations | indent 8 }}
@@ -77,6 +66,9 @@ spec:
         {{- if .Values.metricLabelsAllowlist }}
         - --metric-labels-allowlist={{ .Values.metricLabelsAllowlist | join "," }}
         {{- end }}
+        {{- if .Values.metricAnnotationsAllowList }}
+        - --metric-annotations-allowlist={{ .Values.metricAnnotationsAllowList | join "," }}
+        {{- end }}
         {{- if .Values.metricAllowlist }}
         - --metric-allowlist={{ .Values.metricAllowlist | join "," }}
         {{- end }}
@@ -107,8 +99,10 @@ spec:
         image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
         ports:
         - containerPort: {{ .Values.service.port | default 8080}}
+          name: "http"
         {{- if .Values.selfMonitor.enabled }}
         - containerPort: {{ .Values.selfMonitor.telemetryPort | default 8081 }}
+          name: "metrics"
         {{- end }}
         livenessProbe:
           httpGet:

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/kubeconfig-secret.yaml

@@ -5,10 +5,7 @@ metadata:
   name: {{ template "kube-state-metrics.fullname" . }}-kubeconfig
   namespace: {{ template "kube-state-metrics.namespace" . }}
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: "{{ .Chart.Name }}-{{ .Chart.Version }}"
-    app.kubernetes.io/instance: "{{ .Release.Name }}"
-    app.kubernetes.io/managed-by: "{{ .Release.Service }}"
 type: Opaque
 data:
   config: '{{ .Values.kubeconfig.secret }}'

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/pdb.yaml

@@ -5,13 +5,7 @@ metadata:
   name: {{ template "kube-state-metrics.fullname" . }}
   namespace: {{ template "kube-state-metrics.namespace" . }}
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: "{{ .Chart.Name }}-{{ .Chart.Version }}"
-    app.kubernetes.io/instance: "{{ .Release.Name }}"
-    app.kubernetes.io/managed-by: "{{ .Release.Service }}"
-{{- if .Values.customLabels }}
-{{ toYaml .Values.customLabels | indent 4 }}
-{{- end }}
 spec:
   selector:
     matchLabels:

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/podsecuritypolicy.yaml

@@ -4,10 +4,7 @@ kind: PodSecurityPolicy
 metadata:
   name: {{ template "kube-state-metrics.fullname" . }}
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }}
-    app.kubernetes.io/managed-by: {{ .Release.Service }}
-    app.kubernetes.io/instance: {{ .Release.Name }}
 {{- if .Values.podSecurityPolicy.annotations }}
   annotations:
 {{ toYaml .Values.podSecurityPolicy.annotations | indent 4 }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/psp-clusterrole.yaml

@@ -3,10 +3,7 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole
 metadata:
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }}
-    app.kubernetes.io/managed-by: {{ .Release.Service }}
-    app.kubernetes.io/instance: {{ .Release.Name }}
   name: psp-{{ template "kube-state-metrics.fullname" . }}
 rules:
 {{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/psp-clusterrolebinding.yaml

@@ -3,10 +3,7 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
 metadata:
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }}
-    app.kubernetes.io/managed-by: {{ .Release.Service }}
-    app.kubernetes.io/instance: {{ .Release.Name }}
   name: psp-{{ template "kube-state-metrics.fullname" . }}
 roleRef:
   apiGroup: rbac.authorization.k8s.io

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/role.yaml

@@ -10,9 +10,15 @@ kind: ClusterRole
 metadata:
   labels:
     app.kubernetes.io/name: {{ template "kube-state-metrics.name" $ }}
-    helm.sh/chart: {{ $.Chart.Name }}-{{ $.Chart.Version }}
-    app.kubernetes.io/managed-by: {{ $.Release.Service }}
     app.kubernetes.io/instance: {{ $.Release.Name }}
+    app.kubernetes.io/component: metrics
+    app.kubernetes.io/managed-by: {{ $.Release.Service }}
+    app.kubernetes.io/version: "{{ $.Chart.Version }}"
+    app.kubernetes.io/part-of: {{ template "kube-state-metrics.name" $ }}
+    helm.sh/chart: {{ $.Chart.Name }}-{{ $.Chart.Version }}
+    {{- if $.Values.customLabels }}
+    {{ toYaml $.Values.customLabels | nindent 4 }}
+    {{- end }}
   name: {{ template "kube-state-metrics.fullname" $ }}
 {{- if eq $.Values.rbac.useClusterRole false }}
   namespace: {{ . }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/rolebinding.yaml

@@ -5,10 +5,7 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: RoleBinding
 metadata:
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" $ }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: {{ $.Chart.Name }}-{{ $.Chart.Version }}
-    app.kubernetes.io/managed-by: {{ $.Release.Service }}
-    app.kubernetes.io/instance: {{ $.Release.Name }}
   name: {{ template "kube-state-metrics.fullname" $ }}
   namespace: {{ . }}
 roleRef:

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/service.yaml

@@ -4,13 +4,7 @@ metadata:
   name: {{ template "kube-state-metrics.fullname" . }}
   namespace: {{ template "kube-state-metrics.namespace" . }}
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: "{{ .Chart.Name }}-{{ .Chart.Version }}"
-    app.kubernetes.io/instance: "{{ .Release.Name }}"
-    app.kubernetes.io/managed-by: "{{ .Release.Service }}"
-{{- if .Values.customLabels }}
-{{ toYaml .Values.customLabels | indent 4 }}
-{{- end }}
   annotations:
     {{- if .Values.prometheusScrape }}
     prometheus.io/scrape: '{{ .Values.prometheusScrape }}'
@@ -38,5 +32,4 @@ spec:
   loadBalancerIP: "{{ .Values.service.loadBalancerIP }}"
 {{- end }}
   selector:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.selectorLabels" . | indent 4 }}
-    app.kubernetes.io/instance: {{ .Release.Name }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/serviceaccount.yaml

@@ -3,10 +3,7 @@ apiVersion: v1
 kind: ServiceAccount
 metadata:
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }}
-    app.kubernetes.io/managed-by: {{ .Release.Service }}
-    app.kubernetes.io/instance: {{ .Release.Name }}
   name: {{ template "kube-state-metrics.serviceAccountName" . }}
   namespace: {{ template "kube-state-metrics.namespace" . }}
 {{- if .Values.serviceAccount.annotations }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/servicemonitor.yaml

@@ -5,30 +5,58 @@ metadata:
   name: {{ template "kube-state-metrics.fullname" . }}
   namespace: {{ template "kube-state-metrics.namespace" . }}
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: "{{ .Chart.Name }}-{{ .Chart.Version }}"
+  {{- with .Values.prometheus.monitor.additionalLabels }}
-    app.kubernetes.io/instance: "{{ .Release.Name }}"
+    {{- toYaml . | nindent 4 }}
-    app.kubernetes.io/managed-by: "{{ .Release.Service }}"
-    {{- if .Values.prometheus.monitor.additionalLabels }}
-{{ toYaml .Values.prometheus.monitor.additionalLabels | indent 4 }}
   {{- end }}
-{{- if .Values.customLabels }}
-{{ toYaml .Values.customLabels | indent 4 }}
-{{- end }}
 spec:
+  jobLabel: app.kubernetes.io/name
   selector:
     matchLabels:
-      app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+      {{- include "kube-state-metrics.selectorLabels" . | indent 6 }}
-      app.kubernetes.io/instance: {{ .Release.Name }}
   endpoints:
     - port: http
+    {{- if .Values.prometheus.monitor.interval }}
+      interval: {{ .Values.prometheus.monitor.interval }}
+    {{- end }}
+    {{- if .Values.prometheus.monitor.scrapeTimeout }}
+      scrapeTimeout: {{ .Values.prometheus.monitor.scrapeTimeout }}
+    {{- end }}
+    {{- if .Values.prometheus.monitor.proxyUrl }}
+      proxyUrl: {{ .Values.prometheus.monitor.proxyUrl}}
+    {{- end }}
     {{- if .Values.prometheus.monitor.honorLabels }}
       honorLabels: true
     {{- end }}
-    {{ if .Values.selfMonitor.enabled }}
+    {{- if .Values.prometheus.monitor.metricRelabelings }}
+      metricRelabelings:
+        {{- toYaml .Values.prometheus.monitor.metricRelabelings | nindent 8 }}
+    {{- end }}
+    {{- if .Values.prometheus.monitor.relabelings }}
+      relabelings:
+        {{- toYaml .Values.prometheus.monitor.relabelings | nindent 8 }}
+    {{- end }}
+  {{- if .Values.selfMonitor.enabled }}
     - port: metrics
+    {{- if .Values.prometheus.monitor.interval }}
+      interval: {{ .Values.prometheus.monitor.interval }}
+    {{- end }}
+    {{- if .Values.prometheus.monitor.scrapeTimeout }}
+      scrapeTimeout: {{ .Values.prometheus.monitor.scrapeTimeout }}
+    {{- end }}
+    {{- if .Values.prometheus.monitor.proxyUrl }}
+      proxyUrl: {{ .Values.prometheus.monitor.proxyUrl}}
+    {{- end }}
     {{- if .Values.prometheus.monitor.honorLabels }}
       honorLabels: true
     {{- end }}
-    {{ end }}
+    {{- if .Values.prometheus.monitor.metricRelabelings }}
+      metricRelabelings:
+        {{- toYaml .Values.prometheus.monitor.metricRelabelings | nindent 8 }}
+    {{- end }}
+    {{- if .Values.prometheus.monitor.relabelings }}
+      relabelings:
+        {{- toYaml .Values.prometheus.monitor.relabelings | nindent 8 }}
+    {{- end }}
+  {{- end }}
 {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/stsdiscovery-role.yaml

@@ -5,10 +5,7 @@ metadata:
   name: stsdiscovery-{{ template "kube-state-metrics.fullname" . }}
   namespace: {{ template "kube-state-metrics.namespace" . }}
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }}
-    app.kubernetes.io/managed-by: {{ .Release.Service }}
-    app.kubernetes.io/instance: {{ .Release.Name }}
 rules:
 - apiGroups:
   - ""

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/templates/stsdiscovery-rolebinding.yaml

@@ -5,10 +5,7 @@ metadata:
   name: stsdiscovery-{{ template "kube-state-metrics.fullname" . }}
   namespace: {{ template "kube-state-metrics.namespace" . }}
   labels:
-    app.kubernetes.io/name: {{ template "kube-state-metrics.name" . }}
+    {{- include "kube-state-metrics.labels" . | indent 4 }}
-    helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version }}
-    app.kubernetes.io/managed-by: {{ .Release.Service }}
-    app.kubernetes.io/instance: {{ .Release.Name }}
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: Role

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/kube-state-metrics/values.yaml

@@ -2,7 +2,7 @@
 prometheusScrape: true
 image:
   repository: k8s.gcr.io/kube-state-metrics/kube-state-metrics
-  tag: v2.1.1
+  tag: v2.2.4
   pullPolicy: IfNotPresent
 
 imagePullSecrets: []
@@ -30,7 +30,9 @@ service:
   loadBalancerIP: ""
   annotations: {}
 
+## Additional labels to add to all resources
 customLabels: {}
+  # app: kube-state-metrics
 
 hostNetwork: false
 
@@ -63,7 +65,12 @@ prometheus:
     enabled: false
     additionalLabels: {}
     namespace: ""
+    interval: ""
+    scrapeTimeout: ""
+    proxyUrl: ""
     honorLabels: false
+    metricRelabelings: []
+    relabelings: []
 
 ## Specify if a Pod Security Policy for kube-state-metrics must be created
 ## Ref: https://kubernetes.io/docs/concepts/policy/pod-security-policy/
@@ -133,6 +140,15 @@ metricDenylist: []
 metricLabelsAllowlist: []
   # - namespaces=[k8s-label-1,k8s-label-n]
 
+# Comma-separated list of Kubernetes annotations keys that will be used in the resource'
+# labels metric. By default the metric contains only name and namespace labels.
+# To include additional annotations provide a list of resource names in their plural form and Kubernetes
+# annotation keys you would like to allow for them (Example: '=namespaces=[kubernetes.io/team,...],pods=[kubernetes.io/team],...)'.
+# A single '*' can be provided per resource instead to allow any annotations, but that has
+# severe performance implications (Example: '=pods=[*]').
+metricAnnotationsAllowList: []
+  # - pods=[k8s-annotation-1,k8s-annotation-n]
+
 # Available collectors for kube-state-metrics.
 # By default, all available resources are enabled, comment out to disable.
 collectors:

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/Chart.yaml

@@ -9,10 +9,9 @@ keywords:
 maintainers:
 - email: gianrubio@gmail.com
   name: gianrubio
-- name: vsliouniaev
 - name: bismarck
 name: prometheus-node-exporter
 sources:
 - https://github.com/prometheus/node_exporter/
 type: application
-version: 2.0.4
+version: 2.2.2

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/_helpers.tpl

@@ -64,3 +64,18 @@ Allow the release namespace to be overridden for multi-namespace deployments in
     {{- .Release.Namespace -}}
   {{- end -}}
 {{- end -}}
+
+{{/*
+Create the namespace name of the service monitor
+*/}}
+{{- define "prometheus-node-exporter.monitor-namespace" -}}
+  {{- if .Values.namespaceOverride -}}
+    {{- .Values.namespaceOverride -}}
+  {{- else -}}
+    {{- if .Values.prometheus.monitor.namespace -}}
+      {{- .Values.prometheus.monitor.namespace -}}
+    {{- else -}}
+      {{- .Release.Namespace -}}
+    {{- end -}}
+  {{- end -}}
+{{- end -}}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/daemonset.yaml

@@ -21,7 +21,7 @@ spec:
       {{- toYaml .Values.podAnnotations | nindent 8 }}
       {{- end }}
     spec:
-      automountServiceAccountToken: false
+      automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }}
       serviceAccountName: {{ template "prometheus-node-exporter.serviceAccountName" . }}
 {{- if .Values.securityContext }}
       securityContext:
@@ -62,7 +62,7 @@ spec:
                 fieldPath: status.hostIP
             {{- end }}
           ports:
-            - name: metrics
+            - name: {{ .Values.service.portName }}
               containerPort: {{ .Values.service.port }}
               protocol: TCP
           livenessProbe:

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/endpoints.yaml

@@ -12,7 +12,7 @@ subsets:
       - ip: {{ . }}
       {{- end }}
     ports:
-      - name: metrics
+      - name: {{ .Values.service.portName }}
         port: 9100
         protocol: TCP
 {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/monitor.yaml

@@ -3,7 +3,7 @@ apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   name: {{ template "prometheus-node-exporter.fullname" . }}
-  namespace: {{ template "prometheus-node-exporter.namespace" . }}
+  namespace: {{ template "prometheus-node-exporter.monitor-namespace" . }}
   labels: {{ include "prometheus-node-exporter.labels" . | indent 4 }}
   {{- if .Values.prometheus.monitor.additionalLabels }}
 {{ toYaml .Values.prometheus.monitor.additionalLabels | indent 4 }}
@@ -14,7 +14,7 @@ spec:
       app: {{ template "prometheus-node-exporter.name" . }}
       release: {{ .Release.Name }}
   endpoints:
-    - port: metrics
+    - port: {{ .Values.service.portName }}
       scheme: {{ $.Values.prometheus.monitor.scheme }}
       {{- if $.Values.prometheus.monitor.bearerTokenFile }}
       bearerTokenFile: {{ $.Values.prometheus.monitor.bearerTokenFile }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/templates/service.yaml

@@ -17,7 +17,7 @@ spec:
     {{- end }}
       targetPort: {{ .Values.service.targetPort }}
       protocol: TCP
-      name: metrics
+      name: {{ .Values.service.portName }}
   selector:
     app: {{ template "prometheus-node-exporter.name" . }}
     release: {{ .Release.Name }}

charts/kubezero-metrics/charts/kube-prometheus-stack/charts/prometheus-node-exporter/values.yaml

@@ -11,6 +11,7 @@ service:
   port: 9100
   targetPort: 9100
   nodePort:
+  portName: metrics
   listenOnAllInterfaces: true
   annotations:
     prometheus.io/scrape: "true"
@@ -57,6 +58,7 @@ serviceAccount:
   name:
   annotations: {}
   imagePullSecrets: []
+  automountServiceAccountToken: false
 
 securityContext:
   fsGroup: 65534

charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-alertmanagerconfigs.yaml

@@ -1,11 +1,11 @@
-# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.50.0/example/prometheus-operator-crd/monitoring.coreos.com_alertmanagerconfigs.yaml
+# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_alertmanagerconfigs.yaml
 
 ---
 apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.4.1
+    controller-gen.kubebuilder.io/version: v0.6.2
   creationTimestamp: null
   name: alertmanagerconfigs.monitoring.coreos.com
 spec:
@@ -198,7 +198,8 @@ spec:
                             description: Whether or not to notify about resolved alerts.
                             type: boolean
                           smarthost:
-                            description: The SMTP host through which emails are sent.
+                            description: The SMTP host and port through which emails
+                              are sent. E.g. example.com:25
                             type: string
                           text:
                             description: The text body of the email notification.
@@ -391,8 +392,42 @@ spec:
                           httpConfig:
                             description: HTTP client configuration.
                             properties:
+                              authorization:
+                                description: Authorization header configuration for
+                                  the client. This is mutually exclusive with BasicAuth
+                                  and is only available starting from Alertmanager
+                                  v0.22+.
+                                properties:
+                                  credentials:
+                                    description: The secret's key that contains the
+                                      credentials of the request
+                                    properties:
+                                      key:
+                                        description: The key of the secret to select
+                                          from.  Must be a valid secret key.
+                                        type: string
+                                      name:
+                                        description: 'Name of the referent. More info:
+                                          https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
+                                          TODO: Add other useful fields. apiVersion,
+                                          kind, uid?'
+                                        type: string
+                                      optional:
+                                        description: Specify whether the Secret or
+                                          its key must be defined
+                                        type: boolean
+                                    required:
+                                    - key
+                                    type: object
+                                  type:
+                                    description: Set the authentication type. Defaults
+                                      to Bearer, Basic will cause an error
+                                    type: string
+                                type: object
                               basicAuth:
-                                description: BasicAuth for the client.
+                                description: BasicAuth for the client. This is mutually
+                                  exclusive with Authorization. If both are defined,
+                                  BasicAuth takes precedence.
                                 properties:
                                   password:
                                     description: The secret in the service monitor
@@ -683,8 +718,42 @@ spec:
                           httpConfig:
                             description: HTTP client configuration.
                             properties:
+                              authorization:
+                                description: Authorization header configuration for
+                                  the client. This is mutually exclusive with BasicAuth
+                                  and is only available starting from Alertmanager
+                                  v0.22+.
+                                properties:
+                                  credentials:
+                                    description: The secret's key that contains the
+                                      credentials of the request
+                                    properties:
+                                      key:
+                                        description: The key of the secret to select
+                                          from.  Must be a valid secret key.
+                                        type: string
+                                      name:
+                                        description: 'Name of the referent. More info:
+                                          https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
+                                          TODO: Add other useful fields. apiVersion,
+                                          kind, uid?'
+                                        type: string
+                                      optional:
+                                        description: Specify whether the Secret or
+                                          its key must be defined
+                                        type: boolean
+                                    required:
+                                    - key
+                                    type: object
+                                  type:
+                                    description: Set the authentication type. Defaults
+                                      to Bearer, Basic will cause an error
+                                    type: string
+                                type: object
                               basicAuth:
-                                description: BasicAuth for the client.
+                                description: BasicAuth for the client. This is mutually
+                                  exclusive with Authorization. If both are defined,
+                                  BasicAuth takes precedence.
                                 properties:
                                   password:
                                     description: The secret in the service monitor
@@ -959,8 +1028,42 @@ spec:
                           httpConfig:
                             description: HTTP client configuration.
                             properties:
+                              authorization:
+                                description: Authorization header configuration for
+                                  the client. This is mutually exclusive with BasicAuth
+                                  and is only available starting from Alertmanager
+                                  v0.22+.
+                                properties:
+                                  credentials:
+                                    description: The secret's key that contains the
+                                      credentials of the request
+                                    properties:
+                                      key:
+                                        description: The key of the secret to select
+                                          from.  Must be a valid secret key.
+                                        type: string
+                                      name:
+                                        description: 'Name of the referent. More info:
+                                          https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
+                                          TODO: Add other useful fields. apiVersion,
+                                          kind, uid?'
+                                        type: string
+                                      optional:
+                                        description: Specify whether the Secret or
+                                          its key must be defined
+                                        type: boolean
+                                    required:
+                                    - key
+                                    type: object
+                                  type:
+                                    description: Set the authentication type. Defaults
+                                      to Bearer, Basic will cause an error
+                                    type: string
+                                type: object
                               basicAuth:
-                                description: BasicAuth for the client.
+                                description: BasicAuth for the client. This is mutually
+                                  exclusive with Authorization. If both are defined,
+                                  BasicAuth takes precedence.
                                 properties:
                                   password:
                                     description: The secret in the service monitor
@@ -1350,8 +1453,42 @@ spec:
                           httpConfig:
                             description: HTTP client configuration.
                             properties:
+                              authorization:
+                                description: Authorization header configuration for
+                                  the client. This is mutually exclusive with BasicAuth
+                                  and is only available starting from Alertmanager
+                                  v0.22+.
+                                properties:
+                                  credentials:
+                                    description: The secret's key that contains the
+                                      credentials of the request
+                                    properties:
+                                      key:
+                                        description: The key of the secret to select
+                                          from.  Must be a valid secret key.
+                                        type: string
+                                      name:
+                                        description: 'Name of the referent. More info:
+                                          https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
+                                          TODO: Add other useful fields. apiVersion,
+                                          kind, uid?'
+                                        type: string
+                                      optional:
+                                        description: Specify whether the Secret or
+                                          its key must be defined
+                                        type: boolean
+                                    required:
+                                    - key
+                                    type: object
+                                  type:
+                                    description: Set the authentication type. Defaults
+                                      to Bearer, Basic will cause an error
+                                    type: string
+                                type: object
                               basicAuth:
-                                description: BasicAuth for the client.
+                                description: BasicAuth for the client. This is mutually
+                                  exclusive with Authorization. If both are defined,
+                                  BasicAuth takes precedence.
                                 properties:
                                   password:
                                     description: The secret in the service monitor
@@ -1635,8 +1772,42 @@ spec:
                           httpConfig:
                             description: The HTTP client's configuration.
                             properties:
+                              authorization:
+                                description: Authorization header configuration for
+                                  the client. This is mutually exclusive with BasicAuth
+                                  and is only available starting from Alertmanager
+                                  v0.22+.
+                                properties:
+                                  credentials:
+                                    description: The secret's key that contains the
+                                      credentials of the request
+                                    properties:
+                                      key:
+                                        description: The key of the secret to select
+                                          from.  Must be a valid secret key.
+                                        type: string
+                                      name:
+                                        description: 'Name of the referent. More info:
+                                          https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
+                                          TODO: Add other useful fields. apiVersion,
+                                          kind, uid?'
+                                        type: string
+                                      optional:
+                                        description: Specify whether the Secret or
+                                          its key must be defined
+                                        type: boolean
+                                    required:
+                                    - key
+                                    type: object
+                                  type:
+                                    description: Set the authentication type. Defaults
+                                      to Bearer, Basic will cause an error
+                                    type: string
+                                type: object
                               basicAuth:
-                                description: BasicAuth for the client.
+                                description: BasicAuth for the client. This is mutually
+                                  exclusive with Authorization. If both are defined,
+                                  BasicAuth takes precedence.
                                 properties:
                                   password:
                                     description: The secret in the service monitor
@@ -1864,8 +2035,42 @@ spec:
                           httpConfig:
                             description: HTTP client configuration.
                             properties:
+                              authorization:
+                                description: Authorization header configuration for
+                                  the client. This is mutually exclusive with BasicAuth
+                                  and is only available starting from Alertmanager
+                                  v0.22+.
+                                properties:
+                                  credentials:
+                                    description: The secret's key that contains the
+                                      credentials of the request
+                                    properties:
+                                      key:
+                                        description: The key of the secret to select
+                                          from.  Must be a valid secret key.
+                                        type: string
+                                      name:
+                                        description: 'Name of the referent. More info:
+                                          https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
+                                          TODO: Add other useful fields. apiVersion,
+                                          kind, uid?'
+                                        type: string
+                                      optional:
+                                        description: Specify whether the Secret or
+                                          its key must be defined
+                                        type: boolean
+                                    required:
+                                    - key
+                                    type: object
+                                  type:
+                                    description: Set the authentication type. Defaults
+                                      to Bearer, Basic will cause an error
+                                    type: string
+                                type: object
                               basicAuth:
-                                description: BasicAuth for the client.
+                                description: BasicAuth for the client. This is mutually
+                                  exclusive with Authorization. If both are defined,
+                                  BasicAuth takes precedence.
                                 properties:
                                   password:
                                     description: The secret in the service monitor
@@ -2143,8 +2348,42 @@ spec:
                           httpConfig:
                             description: HTTP client configuration.
                             properties:
+                              authorization:
+                                description: Authorization header configuration for
+                                  the client. This is mutually exclusive with BasicAuth
+                                  and is only available starting from Alertmanager
+                                  v0.22+.
+                                properties:
+                                  credentials:
+                                    description: The secret's key that contains the
+                                      credentials of the request
+                                    properties:
+                                      key:
+                                        description: The key of the secret to select
+                                          from.  Must be a valid secret key.
+                                        type: string
+                                      name:
+                                        description: 'Name of the referent. More info:
+                                          https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
+                                          TODO: Add other useful fields. apiVersion,
+                                          kind, uid?'
+                                        type: string
+                                      optional:
+                                        description: Specify whether the Secret or
+                                          its key must be defined
+                                        type: boolean
+                                    required:
+                                    - key
+                                    type: object
+                                  type:
+                                    description: Set the authentication type. Defaults
+                                      to Bearer, Basic will cause an error
+                                    type: string
+                                type: object
                               basicAuth:
-                                description: BasicAuth for the client.
+                                description: BasicAuth for the client. This is mutually
+                                  exclusive with Authorization. If both are defined,
+                                  BasicAuth takes precedence.
                                 properties:
                                   password:
                                     description: The secret in the service monitor

charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-podmonitors.yaml

@@ -1,11 +1,11 @@
-# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.50.0/example/prometheus-operator-crd/monitoring.coreos.com_podmonitors.yaml
+# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_podmonitors.yaml
 
 ---
 apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.4.1
+    controller-gen.kubebuilder.io/version: v0.6.2
   creationTimestamp: null
   name: podmonitors.monitoring.coreos.com
 spec:

charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-probes.yaml

@@ -1,11 +1,11 @@
-# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.50.0/example/prometheus-operator-crd/monitoring.coreos.com_probes.yaml
+# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_probes.yaml
 
 ---
 apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.4.1
+    controller-gen.kubebuilder.io/version: v0.6.2
   creationTimestamp: null
   name: probes.monitoring.coreos.com
 spec:
@@ -153,6 +153,50 @@ spec:
                   and newer.
                 format: int64
                 type: integer
+              metricRelabelings:
+                description: MetricRelabelConfigs to apply to samples before ingestion.
+                items:
+                  description: 'RelabelConfig allows dynamic rewriting of the label
+                    set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section
+                    of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
+                  properties:
+                    action:
+                      description: Action to perform based on regex matching. Default
+                        is 'replace'
+                      type: string
+                    modulus:
+                      description: Modulus to take of the hash of the source label
+                        values.
+                      format: int64
+                      type: integer
+                    regex:
+                      description: Regular expression against which the extracted
+                        value is matched. Default is '(.*)'
+                      type: string
+                    replacement:
+                      description: Replacement value against which a regex replace
+                        is performed if the regular expression matches. Regex capture
+                        groups are available. Default is '$1'
+                      type: string
+                    separator:
+                      description: Separator placed between concatenated source label
+                        values. default is ';'.
+                      type: string
+                    sourceLabels:
+                      description: The source labels select values from existing labels.
+                        Their content is concatenated using the configured separator
+                        and matched against the configured regular expression for
+                        the replace, keep, and drop actions.
+                      items:
+                        type: string
+                      type: array
+                    targetLabel:
+                      description: Label to which the resulting value is written in
+                        a replace action. It is mandatory for replace actions. Regex
+                        capture groups are available.
+                      type: string
+                  type: object
+                type: array
               module:
                 description: 'The module to use for probing specifying how to probe
                   the target. Example module configuring in the blackbox exporter:

charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-prometheusrules.yaml

@@ -1,11 +1,11 @@
-# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.50.0/example/prometheus-operator-crd/monitoring.coreos.com_prometheusrules.yaml
+# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_prometheusrules.yaml
 
 ---
 apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.4.1
+    controller-gen.kubebuilder.io/version: v0.6.2
   creationTimestamp: null
   name: prometheusrules.monitoring.coreos.com
 spec:

charts/kubezero-metrics/charts/kube-prometheus-stack/crds/crd-servicemonitors.yaml

@@ -1,11 +1,11 @@
-# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.50.0/example/prometheus-operator-crd/monitoring.coreos.com_servicemonitors.yaml
+# https://raw.githubusercontent.com/prometheus-operator/prometheus-operator/v0.52.0/example/prometheus-operator-crd/monitoring.coreos.com_servicemonitors.yaml
 
 ---
 apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.4.1
+    controller-gen.kubebuilder.io/version: v0.6.2
   creationTimestamp: null
   name: servicemonitors.monitoring.coreos.com
 spec:

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/_helpers.tpl

@@ -96,6 +96,39 @@ Allow the release namespace to be overridden for multi-namespace deployments in
   {{- end -}}
 {{- end -}}
 
+{{/*
+Use the grafana namespace override for multi-namespace deployments in combined charts
+*/}}
+{{- define "kube-prometheus-stack-grafana.namespace" -}}
+  {{- if .Values.grafana.namespaceOverride -}}
+    {{- .Values.grafana.namespaceOverride -}}
+  {{- else -}}
+    {{- .Release.Namespace -}}
+  {{- end -}}
+{{- end -}}
+
+{{/*
+Use the kube-state-metrics namespace override for multi-namespace deployments in combined charts
+*/}}
+{{- define "kube-prometheus-stack-kube-state-metrics.namespace" -}}
+  {{- if index .Values "kube-state-metrics" "namespaceOverride" -}}
+    {{- index .Values "kube-state-metrics" "namespaceOverride" -}}
+  {{- else -}}
+    {{- .Release.Namespace -}}
+  {{- end -}}
+{{- end -}}
+
+{{/*
+Use the prometheus-node-exporter namespace override for multi-namespace deployments in combined charts
+*/}}
+{{- define "kube-prometheus-stack-prometheus-node-exporter.namespace" -}}
+  {{- if index .Values "prometheus-node-exporter" "namespaceOverride" -}}
+    {{- index .Values "prometheus-node-exporter" "namespaceOverride" -}}
+  {{- else -}}
+    {{- .Release.Namespace -}}
+  {{- end -}}
+{{- end -}}
+
 {{/* Allow KubeVersion to be overridden. */}}
 {{- define "kube-prometheus-stack.kubeVersion" -}}
   {{- default .Capabilities.KubeVersion.Version .Values.kubeVersionOverride -}}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/alertmanager.yaml

@@ -81,6 +81,7 @@ spec:
 {{- end }}
 {{- if or .Values.alertmanager.alertmanagerSpec.podAntiAffinity .Values.alertmanager.alertmanagerSpec.affinity }}
   affinity:
+{{- end }}
 {{- if .Values.alertmanager.alertmanagerSpec.affinity }}
 {{ toYaml .Values.alertmanager.alertmanagerSpec.affinity | indent 4 }}
 {{- end }}
@@ -103,7 +104,6 @@ spec:
               - {key: app, operator: In, values: [alertmanager]}
               - {key: alertmanager, operator: In, values: [{{ template "kube-prometheus-stack.fullname" . }}-alertmanager]}
 {{- end }}
-{{- end }}
 {{- if .Values.alertmanager.alertmanagerSpec.tolerations }}
   tolerations:
 {{ toYaml .Values.alertmanager.alertmanagerSpec.tolerations | indent 4 }}
@@ -140,10 +140,10 @@ spec:
 {{ toYaml .Values.alertmanager.alertmanagerSpec.volumeMounts | indent 4 }}
 {{- end }}
   portName: {{ .Values.alertmanager.alertmanagerSpec.portName }}
-{{- end }}
 {{- if .Values.alertmanager.alertmanagerSpec.clusterAdvertiseAddress }}
   clusterAdvertiseAddress: {{ .Values.alertmanager.alertmanagerSpec.clusterAdvertiseAddress }}
 {{- end }}
 {{- if .Values.alertmanager.alertmanagerSpec.forceEnableClusterMode }}
   forceEnableClusterMode: {{ .Values.alertmanager.alertmanagerSpec.forceEnableClusterMode }}
 {{- end }}
+{{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/service.yaml

@@ -44,7 +44,7 @@ spec:
 {{ toYaml .Values.alertmanager.service.additionalPorts | indent 2 }}
 {{- end }}
   selector:
-    app: alertmanager
+    app.kubernetes.io/name: alertmanager
     alertmanager: {{ template "kube-prometheus-stack.fullname" . }}-alertmanager
   type: "{{ .Values.alertmanager.service.type }}"
 {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/alertmanager/serviceperreplica.yaml

@@ -38,7 +38,7 @@ items:
           port: {{ $serviceValues.port }}
           targetPort: {{ $serviceValues.targetPort }}
       selector:
-        app: alertmanager
+        app.kubernetes.io/name: alertmanager
         alertmanager: {{ template "kube-prometheus-stack.fullname" $ }}-alertmanager
         statefulset.kubernetes.io/pod-name: alertmanager-{{ include "kube-prometheus-stack.fullname" $ }}-alertmanager-{{ $i }}
       type: "{{ $serviceValues.type }}"

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/core-dns/servicemonitor.yaml

@@ -31,6 +31,6 @@ spec:
 {{- end }}
 {{- if .Values.coreDns.serviceMonitor.relabelings }}
     relabelings:
-{{ toYaml .Values.coreDns.serviceMonitor.relabelings | indent 4 }}
+{{ tpl (toYaml .Values.coreDns.serviceMonitor.relabelings | indent 4) . }}
 {{- end }}
 {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-api-server/servicemonitor.yaml

@@ -24,7 +24,7 @@ spec:
 {{- end }}
 {{- if .Values.kubeApiServer.serviceMonitor.relabelings }}
     relabelings:
-{{ toYaml .Values.kubeApiServer.serviceMonitor.relabelings | indent 6 }}
+{{ tpl (toYaml .Values.kubeApiServer.serviceMonitor.relabelings | indent 6) . }}
 {{- end }}
     tlsConfig:
       caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-controller-manager/servicemonitor.yaml

@@ -42,6 +42,6 @@ spec:
 {{- end }}
 {{- if .Values.kubeControllerManager.serviceMonitor.relabelings }}
     relabelings:
-{{ toYaml .Values.kubeControllerManager.serviceMonitor.relabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubeControllerManager.serviceMonitor.relabelings | indent 4) . }}
 {{- end }}
 {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-dns/servicemonitor.yaml

@@ -44,6 +44,6 @@ spec:
 {{- end }}
 {{- if .Values.kubeDns.serviceMonitor.relabelings }}
     relabelings:
-{{ toYaml .Values.kubeDns.serviceMonitor.relabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubeDns.serviceMonitor.relabelings | indent 4) . }}
 {{- end }}
 {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-etcd/servicemonitor.yaml

@@ -48,6 +48,6 @@ spec:
 {{- end }}
 {{- if .Values.kubeEtcd.serviceMonitor.relabelings }}
     relabelings:
-{{ toYaml .Values.kubeEtcd.serviceMonitor.relabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubeEtcd.serviceMonitor.relabelings | indent 4) . }}
 {{- end }}
 {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-proxy/servicemonitor.yaml

@@ -32,10 +32,10 @@ spec:
     {{- end}}
 {{- if .Values.kubeProxy.serviceMonitor.metricRelabelings }}
     metricRelabelings:
-{{ toYaml .Values.kubeProxy.serviceMonitor.metricRelabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubeProxy.serviceMonitor.metricRelabelings | indent 4) . }}
 {{- end }}
 {{- if .Values.kubeProxy.serviceMonitor.relabelings }}
     relabelings:
-{{ toYaml .Values.kubeProxy.serviceMonitor.relabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubeProxy.serviceMonitor.relabelings | indent 4) . }}
 {{- end }}
 {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-scheduler/servicemonitor.yaml

@@ -42,6 +42,6 @@ spec:
 {{- end }}
 {{- if .Values.kubeScheduler.serviceMonitor.relabelings }}
     relabelings:
-{{ toYaml .Values.kubeScheduler.serviceMonitor.relabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubeScheduler.serviceMonitor.relabelings | indent 4) . }}
 {{- end }}
 {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kube-state-metrics/serviceMonitor.yaml

@@ -27,7 +27,7 @@ spec:
 {{- end }}
 {{- if .Values.kubeStateMetrics.serviceMonitor.relabelings }}
     relabelings:
-{{ toYaml .Values.kubeStateMetrics.serviceMonitor.relabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubeStateMetrics.serviceMonitor.relabelings | indent 4) . }}
 {{- end }}
 {{- if .Values.kubeStateMetrics.serviceMonitor.selfMonitor.enabled }}
   - port: metrics
@@ -44,14 +44,14 @@ spec:
 {{- end }}
 {{- if .Values.kubeStateMetrics.serviceMonitor.relabelings }}
     relabelings:
-{{ toYaml .Values.kubeStateMetrics.serviceMonitor.relabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubeStateMetrics.serviceMonitor.relabelings | indent 4) . }}
 {{- end }}
 {{- end }}
-{{- if .Values.kubeStateMetrics.serviceMonitor.namespaceOverride }}
+  {{- if ne (include "kube-prometheus-stack.namespace" .) (include "kube-prometheus-stack-kube-state-metrics.namespace" .) }}
   namespaceSelector:
     matchNames:
-      - {{ .Values.kubeStateMetrics.serviceMonitor.namespaceOverride }}
+      - {{ printf "%s" (include "kube-prometheus-stack-kube-state-metrics.namespace" .) | quote }}
-{{- end }}
+  {{- end }}
   selector:
     matchLabels:
 {{- if .Values.kubeStateMetrics.serviceMonitor.selectorOverride }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/kubelet/servicemonitor.yaml

@@ -18,6 +18,9 @@ spec:
     {{- if .Values.kubelet.serviceMonitor.proxyUrl }}
     proxyUrl: {{ .Values.kubelet.serviceMonitor.proxyUrl }}
     {{- end }}
+    {{- if .Values.kubelet.serviceMonitor.scrapeTimeout }}
+    scrapeTimeout: {{ .Values.kubelet.serviceMonitor.scrapeTimeout }}
+    {{- end }}
     tlsConfig:
       caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
       insecureSkipVerify: true
@@ -29,7 +32,7 @@ spec:
 {{- end }}
 {{- if .Values.kubelet.serviceMonitor.relabelings }}
     relabelings:
-{{ toYaml .Values.kubelet.serviceMonitor.relabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubelet.serviceMonitor.relabelings | indent 4) . }}
 {{- end }}
 {{- if .Values.kubelet.serviceMonitor.cAdvisor }}
   - port: https-metrics
@@ -55,7 +58,7 @@ spec:
 {{- end }}
 {{- if .Values.kubelet.serviceMonitor.cAdvisorRelabelings }}
     relabelings:
-{{ toYaml .Values.kubelet.serviceMonitor.cAdvisorRelabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubelet.serviceMonitor.cAdvisorRelabelings | indent 4) . }}
 {{- end }}
 {{- end }}
 {{- if .Values.kubelet.serviceMonitor.probes }}
@@ -68,6 +71,9 @@ spec:
     {{- if .Values.kubelet.serviceMonitor.proxyUrl }}
     proxyUrl: {{ .Values.kubelet.serviceMonitor.proxyUrl }}
     {{- end }}
+    {{- if .Values.kubelet.serviceMonitor.scrapeTimeout }}
+    scrapeTimeout: {{ .Values.kubelet.serviceMonitor.scrapeTimeout }}
+    {{- end }}
     honorLabels: true
     tlsConfig:
       caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
@@ -79,7 +85,7 @@ spec:
 {{- end }}
 {{- if .Values.kubelet.serviceMonitor.probesRelabelings }}
     relabelings:
-{{ toYaml .Values.kubelet.serviceMonitor.probesRelabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubelet.serviceMonitor.probesRelabelings | indent 4) . }}
 {{- end }}
 {{- end }}
 {{- if .Values.kubelet.serviceMonitor.resource }}
@@ -92,6 +98,9 @@ spec:
     {{- if .Values.kubelet.serviceMonitor.proxyUrl }}
     proxyUrl: {{ .Values.kubelet.serviceMonitor.proxyUrl }}
     {{- end }}
+    {{- if .Values.kubelet.serviceMonitor.scrapeTimeout }}
+    scrapeTimeout: {{ .Values.kubelet.serviceMonitor.scrapeTimeout }}
+    {{- end }}
     honorLabels: true
     tlsConfig:
       caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
@@ -103,7 +112,7 @@ spec:
 {{- end }}
 {{- if .Values.kubelet.serviceMonitor.resourceRelabelings }}
     relabelings:
-{{ toYaml .Values.kubelet.serviceMonitor.resourceRelabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubelet.serviceMonitor.resourceRelabelings | indent 4) . }}
 {{- end }}
 {{- end }}
   {{- else }}
@@ -114,6 +123,9 @@ spec:
     {{- if .Values.kubelet.serviceMonitor.proxyUrl }}
     proxyUrl: {{ .Values.kubelet.serviceMonitor.proxyUrl }}
     {{- end }}
+    {{- if .Values.kubelet.serviceMonitor.scrapeTimeout }}
+    scrapeTimeout: {{ .Values.kubelet.serviceMonitor.scrapeTimeout }}
+    {{- end }}
     honorLabels: true
 {{- if .Values.kubelet.serviceMonitor.metricRelabelings }}
     metricRelabelings:
@@ -121,7 +133,7 @@ spec:
 {{- end }}
 {{- if .Values.kubelet.serviceMonitor.relabelings }}
     relabelings:
-{{ toYaml .Values.kubelet.serviceMonitor.relabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubelet.serviceMonitor.relabelings | indent 4) . }}
 {{- end }}
 {{- if .Values.kubelet.serviceMonitor.cAdvisor }}
   - port: http-metrics
@@ -132,6 +144,9 @@ spec:
     {{- if .Values.kubelet.serviceMonitor.proxyUrl }}
     proxyUrl: {{ .Values.kubelet.serviceMonitor.proxyUrl }}
     {{- end }}
+    {{- if .Values.kubelet.serviceMonitor.scrapeTimeout }}
+    scrapeTimeout: {{ .Values.kubelet.serviceMonitor.scrapeTimeout }}
+    {{- end }}
     honorLabels: true
 {{- if .Values.kubelet.serviceMonitor.cAdvisorMetricRelabelings }}
     metricRelabelings:
@@ -139,7 +154,7 @@ spec:
 {{- end }}
 {{- if .Values.kubelet.serviceMonitor.cAdvisorRelabelings }}
     relabelings:
-{{ toYaml .Values.kubelet.serviceMonitor.cAdvisorRelabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubelet.serviceMonitor.cAdvisorRelabelings | indent 4) . }}
 {{- end }}
 {{- if .Values.kubelet.serviceMonitor.resource }}
   - port: http-metrics
@@ -150,6 +165,9 @@ spec:
     {{- if .Values.kubelet.serviceMonitor.proxyUrl }}
     proxyUrl: {{ .Values.kubelet.serviceMonitor.proxyUrl }}
     {{- end }}
+    {{- if .Values.kubelet.serviceMonitor.scrapeTimeout }}
+    scrapeTimeout: {{ .Values.kubelet.serviceMonitor.scrapeTimeout }}
+    {{- end }}
     honorLabels: true
 {{- if .Values.kubelet.serviceMonitor.resourceMetricRelabelings }}
     metricRelabelings:
@@ -157,7 +175,7 @@ spec:
 {{- end }}
 {{- if .Values.kubelet.serviceMonitor.resourceRelabelings }}
     relabelings:
-{{ toYaml .Values.kubelet.serviceMonitor.resourceRelabelings | indent 4 }}
+{{ tpl (toYaml .Values.kubelet.serviceMonitor.resourceRelabelings | indent 4) . }}
 {{- end }}
 {{- end }}
 {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/exporters/node-exporter/servicemonitor.yaml

@@ -13,13 +13,13 @@ spec:
     matchLabels:
       app: prometheus-node-exporter
       release: {{ $.Release.Name }}
-  {{- if (index .Values "prometheus-node-exporter" "namespaceOverride") }}
+  {{- if ne (include "kube-prometheus-stack.namespace" .) (include "kube-prometheus-stack-prometheus-node-exporter.namespace" .) }}
   namespaceSelector:
     matchNames:
-      - {{ index .Values "prometheus-node-exporter" "namespaceOverride" }}
+      - {{ printf "%s" (include "kube-prometheus-stack-prometheus-node-exporter.namespace" .) | quote }}
   {{- end }}
   endpoints:
-  - port: metrics
+  - port: {{ index .Values "prometheus-node-exporter" "service" "portName" }}
     {{- if .Values.nodeExporter.serviceMonitor.interval }}
     interval: {{ .Values.nodeExporter.serviceMonitor.interval }}
     {{- end }}
@@ -35,6 +35,6 @@ spec:
 {{- end }}
 {{- if .Values.nodeExporter.serviceMonitor.relabelings }}
     relabelings:
-{{ toYaml .Values.nodeExporter.serviceMonitor.relabelings | indent 4 }}
+{{ tpl (toYaml .Values.nodeExporter.serviceMonitor.relabelings | indent 4) . }}
 {{- end }}
 {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/configmap-dashboards.yaml

@@ -10,7 +10,7 @@ items:
   kind: ConfigMap
   metadata:
     name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) $dashboardName | trunc 63 | trimSuffix "-" }}
-    namespace: {{ template "kube-prometheus-stack.namespace" $ }}
+    namespace: {{ template "kube-prometheus-stack-grafana.namespace" $ }}
     labels:
       {{- if $.Values.grafana.sidecar.dashboards.label }}
       {{ $.Values.grafana.sidecar.dashboards.label }}: "1"

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/configmaps-datasources.yaml

@@ -3,7 +3,7 @@ apiVersion: v1
 kind: ConfigMap
 metadata:
   name: {{ template "kube-prometheus-stack.fullname" . }}-grafana-datasource
-  namespace: {{ template "kube-prometheus-stack.namespace" . }}
+  namespace: {{ template "kube-prometheus-stack-grafana.namespace" . }}
 {{- if .Values.grafana.sidecar.datasources.annotations }}
   annotations:
 {{ toYaml .Values.grafana.sidecar.datasources.annotations | indent 4 }}
@@ -15,6 +15,10 @@ metadata:
 data:
   datasource.yaml: |-
     apiVersion: 1
+{{- if .Values.grafana.deleteDatasources }}
+    deleteDatasources:
+{{ tpl (toYaml .Values.grafana.deleteDatasources | indent 6) . }}
+{{- end }}
     datasources:
 {{- $scrapeInterval := .Values.grafana.sidecar.datasources.defaultDatasourceScrapeInterval | default .Values.prometheus.prometheusSpec.scrapeInterval | default "30s" }}
 {{- if .Values.grafana.sidecar.datasources.defaultDatasourceEnabled }}
@@ -23,7 +27,7 @@ data:
       {{- if .Values.grafana.sidecar.datasources.url }}
       url: {{ .Values.grafana.sidecar.datasources.url }}
       {{- else }}
-      url: http://{{ template "kube-prometheus-stack.fullname" . }}-prometheus:{{ .Values.prometheus.service.port }}/{{ trimPrefix "/" .Values.prometheus.prometheusSpec.routePrefix }}
+      url: http://{{ template "kube-prometheus-stack.fullname" . }}-prometheus.{{ template "kube-prometheus-stack.namespace" . }}:{{ .Values.prometheus.service.port }}/{{ trimPrefix "/" .Values.prometheus.prometheusSpec.routePrefix }}
       {{- end }}
       access: proxy
       isDefault: true

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/grafana/servicemonitor.yaml

@@ -12,9 +12,11 @@ spec:
     matchLabels:
       app.kubernetes.io/name: grafana
       app.kubernetes.io/instance: {{ $.Release.Name | quote }}
+  {{- if ne (include "kube-prometheus-stack.namespace" .) (include "kube-prometheus-stack-grafana.namespace" .) }}
   namespaceSelector:
     matchNames:
-      - {{ printf "%s" (include "kube-prometheus-stack.namespace" .) | quote }}
+      - {{ printf "%s" (include "kube-prometheus-stack-grafana.namespace" .) | quote }}
+  {{- end }}
   endpoints:
   - port: {{ .Values.grafana.service.portName }}
     {{- if .Values.grafana.serviceMonitor.interval }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/psp.yaml

@@ -6,12 +6,11 @@ metadata:
   annotations:
     "helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade
     "helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
-  labels:
-    app: {{ template "kube-prometheus-stack.name" . }}-admission
 {{- if .Values.global.rbac.pspAnnotations }}
-  annotations:
 {{ toYaml .Values.global.rbac.pspAnnotations | indent 4 }}
 {{- end }}
+  labels:
+    app: {{ template "kube-prometheus-stack.name" . }}-admission
 {{ include "kube-prometheus-stack.labels" . | indent 4 }}
 spec:
   privileged: false

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus-operator/deployment.yaml

@@ -1,4 +1,5 @@
 {{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }}
+{{- $defaultKubeletSvcName := printf "%s-kubelet" (include "kube-prometheus-stack.fullname" .) }}
 {{- if .Values.prometheusOperator.enabled }}
 apiVersion: apps/v1
 kind: Deployment
@@ -40,7 +41,7 @@ spec:
           imagePullPolicy: "{{ .Values.prometheusOperator.image.pullPolicy }}"
           args:
             {{- if .Values.prometheusOperator.kubeletService.enabled }}
-            - --kubelet-service={{ .Values.prometheusOperator.kubeletService.namespace }}/{{ template "kube-prometheus-stack.fullname" . }}-kubelet
+            - --kubelet-service={{ .Values.prometheusOperator.kubeletService.namespace }}/{{ default $defaultKubeletSvcName .Values.prometheusOperator.kubeletService.name  }}
             {{- end }}
             {{- if .Values.prometheusOperator.logFormat }}
             - --log-format={{ .Values.prometheusOperator.logFormat }}
@@ -65,15 +66,15 @@ spec:
             {{- if .Values.prometheusOperator.alertmanagerDefaultBaseImage }}
             - --alertmanager-default-base-image={{ .Values.prometheusOperator.alertmanagerDefaultBaseImage }}
             {{- end }}
-            {{- if .Values.prometheusOperator.prometheusConfigReloaderImage.sha }}
+            {{- if .Values.prometheusOperator.prometheusConfigReloader.image.sha }}
-            - --prometheus-config-reloader={{ .Values.prometheusOperator.prometheusConfigReloaderImage.repository }}:{{ .Values.prometheusOperator.prometheusConfigReloaderImage.tag }}@sha256:{{ .Values.prometheusOperator.prometheusConfigReloaderImage.sha }}
+            - --prometheus-config-reloader={{ .Values.prometheusOperator.prometheusConfigReloader.image.repository }}:{{ .Values.prometheusOperator.prometheusConfigReloader.image.tag }}@sha256:{{ .Values.prometheusOperator.prometheusConfigReloader.image.sha }}
             {{- else }}
-            - --prometheus-config-reloader={{ .Values.prometheusOperator.prometheusConfigReloaderImage.repository }}:{{ .Values.prometheusOperator.prometheusConfigReloaderImage.tag }}
+            - --prometheus-config-reloader={{ .Values.prometheusOperator.prometheusConfigReloader.image.repository }}:{{ .Values.prometheusOperator.prometheusConfigReloader.image.tag }}
             {{- end }}
-            - --config-reloader-cpu-request={{ .Values.prometheusOperator.configReloaderCpu }}
+            - --config-reloader-cpu-request={{ .Values.prometheusOperator.prometheusConfigReloader.resources.requests.cpu }}
-            - --config-reloader-cpu-limit={{ .Values.prometheusOperator.configReloaderCpu }}
+            - --config-reloader-cpu-limit={{ .Values.prometheusOperator.prometheusConfigReloader.resources.limits.cpu }}
-            - --config-reloader-memory-request={{ .Values.prometheusOperator.configReloaderMemory }}
+            - --config-reloader-memory-request={{ .Values.prometheusOperator.prometheusConfigReloader.resources.requests.memory }}
-            - --config-reloader-memory-limit={{ .Values.prometheusOperator.configReloaderMemory }}
+            - --config-reloader-memory-limit={{ .Values.prometheusOperator.prometheusConfigReloader.resources.limits.memory }}
             {{- if .Values.prometheusOperator.alertmanagerInstanceNamespaces }}
             - --alertmanager-instance-namespaces={{ .Values.prometheusOperator.alertmanagerInstanceNamespaces | join "," }}
             {{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/csi-secret.yaml

@@ -0,0 +1,12 @@
+{{- if .Values.prometheus.prometheusSpec.thanos.secretProviderClass }}
+---
+apiVersion: secrets-store.csi.x-k8s.io/v1alpha1
+kind: SecretProviderClass
+metadata:
+  name: {{ template "kube-prometheus-stack.fullname" . }}-prometheus
+  namespace: {{ template "kube-prometheus-stack.namespace" . }}
+  labels:
+    app: {{ template "kube-prometheus-stack.name" . }}-prometheus
+spec:
+{{ toYaml .Values.prometheus.prometheusSpec.thanos.secretProviderClass | indent 2 }}
+{{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/prometheus.yaml

@@ -301,7 +301,6 @@ spec:
   disableCompaction: {{ .Values.prometheus.prometheusSpec.disableCompaction }}
 {{- end }}
   portName: {{ .Values.prometheus.prometheusSpec.portName }}
-{{- end }}
 {{- if .Values.prometheus.prometheusSpec.volumes }}
   volumes:
 {{ toYaml .Values.prometheus.prometheusSpec.volumes | indent 4 }}
@@ -356,3 +355,4 @@ spec:
 {{- if .Values.prometheus.prometheusSpec.allowOverlappingBlocks }}
   allowOverlappingBlocks: {{ .Values.prometheus.prometheusSpec.allowOverlappingBlocks }}
 {{- end }}
+{{- end }}

charts/kubezero-metrics/charts/kube-prometheus-stack/values.yaml

@@ -366,14 +366,16 @@ alertmanager:
 
     bearerTokenFile:
 
-    ## Metric relabel configs to apply to samples before ingestion.
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     metricRelabelings: []
     # - action: keep
     #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
     #   sourceLabels: [__name__]
 
-    #   relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     relabelings: []
     # - sourceLabels: [__meta_kubernetes_pod_node_name]
@@ -396,7 +398,7 @@ alertmanager:
     ##
     image:
       repository: quay.io/prometheus/alertmanager
-      tag: v0.22.2
+      tag: v0.23.0
       sha: ""
 
     ## If true then the user will be responsible to provide a secret with alertmanager configuration
@@ -596,7 +598,7 @@ alertmanager:
 
     ## PortName to use for Alert Manager.
     ##
-    portName: "web"
+    portName: "http-web"
 
     ## ClusterAdvertiseAddress is the explicit address to advertise in cluster. Needs to be provided for non RFC1918 [1] (public) addresses. [1] RFC1918: https://tools.ietf.org/html/rfc1918
     ##
@@ -718,6 +720,10 @@ grafana:
   #   configMap: certs-configmap
   #   readOnly: true
 
+  deleteDatasources: []
+  # - name: example-datasource
+  #   orgId: 1
+
   ## Configure additional grafana datasources (passed through tpl)
   ## ref: http://docs.grafana.org/administration/provisioning/#datasources
   additionalDataSources: []
@@ -737,7 +743,7 @@ grafana:
   ## Passed to grafana subchart and used by servicemonitor below
   ##
   service:
-    portName: service
+    portName: http-web
 
   ## If true, create a serviceMonitor for grafana
   ##
@@ -751,14 +757,17 @@ grafana:
     # in grafana.ini
     path: "/metrics"
 
-    ## Metric relabel configs to apply to samples before ingestion.
+
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     metricRelabelings: []
     # - action: keep
     #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
     #   sourceLabels: [__name__]
 
-    #   relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     relabelings: []
     # - sourceLabels: [__meta_kubernetes_pod_node_name]
@@ -789,12 +798,17 @@ kubeApiServer:
         component: apiserver
         provider: kubernetes
 
-    ## Metric relabel configs to apply to samples before ingestion.
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     metricRelabelings: []
     # - action: keep
     #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
     #   sourceLabels: [__name__]
+
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
+    ##
     relabelings: []
     # - sourceLabels:
     #     - __meta_kubernetes_namespace
@@ -839,7 +853,9 @@ kubelet:
     resource: false
     # From kubernetes 1.18, /metrics/resource/v1alpha1 renamed to /metrics/resource
     resourcePath: "/metrics/resource/v1alpha1"
-    ## Metric relabellings to apply to samples before ingestion
+
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     cAdvisorMetricRelabelings: []
     # - sourceLabels: [__name__, image]
@@ -853,7 +869,8 @@ kubelet:
     #   replacement: $1
     #   action: drop
 
-    ## Metric relabellings to apply to samples before ingestion
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     probesMetricRelabelings: []
     # - sourceLabels: [__name__, image]
@@ -867,9 +884,10 @@ kubelet:
     #   replacement: $1
     #   action: drop
 
-    #   relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
-    #   metrics_path is required to match upstream rules and charts
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
+    ## metrics_path is required to match upstream rules and charts
     cAdvisorRelabelings:
       - sourceLabels: [__metrics_path__]
         targetLabel: metrics_path
@@ -880,6 +898,9 @@ kubelet:
     #   replacement: $1
     #   action: replace
 
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
+    ##
     probesRelabelings:
       - sourceLabels: [__metrics_path__]
         targetLabel: metrics_path
@@ -890,6 +911,9 @@ kubelet:
     #   replacement: $1
     #   action: replace
 
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
+    ##
     resourceRelabelings:
       - sourceLabels: [__metrics_path__]
         targetLabel: metrics_path
@@ -900,6 +924,9 @@ kubelet:
     #   replacement: $1
     #   action: replace
 
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
+    ##
     metricRelabelings: []
     # - sourceLabels: [__name__, image]
     #   separator: ;
@@ -912,9 +939,10 @@ kubelet:
     #   replacement: $1
     #   action: drop
 
-    #   relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
-    #   metrics_path is required to match upstream rules and charts
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
+    ## metrics_path is required to match upstream rules and charts
     relabelings:
       - sourceLabels: [__metrics_path__]
         targetLabel: metrics_path
@@ -967,14 +995,16 @@ kubeControllerManager:
     # Name of the server to use when validating TLS certificate
     serverName: null
 
-    ## Metric relabel configs to apply to samples before ingestion.
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     metricRelabelings: []
     # - action: keep
     #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
     #   sourceLabels: [__name__]
 
-    #   relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     relabelings: []
     # - sourceLabels: [__meta_kubernetes_pod_node_name]
@@ -1002,14 +1032,16 @@ coreDns:
     ##
     proxyUrl: ""
 
-    ## Metric relabel configs to apply to samples before ingestion.
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     metricRelabelings: []
     # - action: keep
     #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
     #   sourceLabels: [__name__]
 
-    #   relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     relabelings: []
     # - sourceLabels: [__meta_kubernetes_pod_node_name]
@@ -1041,14 +1073,16 @@ kubeDns:
     ##
     proxyUrl: ""
 
-    ## Metric relabel configs to apply to samples before ingestion.
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     metricRelabelings: []
     # - action: keep
     #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
     #   sourceLabels: [__name__]
 
-    #   relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     relabelings: []
     # - sourceLabels: [__meta_kubernetes_pod_node_name]
@@ -1057,12 +1091,17 @@ kubeDns:
     #   targetLabel: nodename
     #   replacement: $1
     #   action: replace
+
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
+    ##
     dnsmasqMetricRelabelings: []
     # - action: keep
     #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
     #   sourceLabels: [__name__]
 
-    #   relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     dnsmasqRelabelings: []
     # - sourceLabels: [__meta_kubernetes_pod_node_name]
@@ -1119,14 +1158,16 @@ kubeEtcd:
     certFile: ""
     keyFile: ""
 
-    ## Metric relabel configs to apply to samples before ingestion.
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     metricRelabelings: []
     # - action: keep
     #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
     #   sourceLabels: [__name__]
 
-    #   relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     relabelings: []
     # - sourceLabels: [__meta_kubernetes_pod_node_name]
@@ -1177,14 +1218,16 @@ kubeScheduler:
     ## Name of the server to use when validating TLS certificate
     serverName: null
 
-    ## Metric relabel configs to apply to samples before ingestion.
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     metricRelabelings: []
     # - action: keep
     #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
     #   sourceLabels: [__name__]
 
-    #   relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     relabelings: []
     # - sourceLabels: [__meta_kubernetes_pod_node_name]
@@ -1229,14 +1272,16 @@ kubeProxy:
     ##
     https: false
 
-    ## Metric relabel configs to apply to samples before ingestion.
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     metricRelabelings: []
     # - action: keep
     #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
     #   sourceLabels: [__name__]
 
-    #   relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     relabelings: []
     # - action: keep
@@ -1261,18 +1306,17 @@ kubeStateMetrics:
     ## Override serviceMonitor selector
     ##
     selectorOverride: {}
-    ## Override namespace selector
-    ##
-    namespaceOverride: ""
 
-    ## Metric relabel configs to apply to samples before ingestion.
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     metricRelabelings: []
     # - action: keep
     #   regex: 'kube_(daemonset|deployment|pod|namespace|node|statefulset).+'
     #   sourceLabels: [__name__]
 
-    #   relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     relabelings: []
     # - sourceLabels: [__meta_kubernetes_pod_node_name]
@@ -1320,7 +1364,8 @@ nodeExporter:
     ##
     scrapeTimeout: ""
 
-    ## Metric relabel configs to apply to samples before ingestion.
+    ## MetricRelabelConfigs to apply to samples after scraping, but before ingestion.
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     metricRelabelings: []
     # - sourceLabels: [__name__]
@@ -1329,7 +1374,8 @@ nodeExporter:
     #   replacement: $1
     #   action: drop
 
-    ## relabel configs to apply to samples before ingestion.
+    ## RelabelConfigs to apply to samples before scraping
+    ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#relabelconfig
     ##
     relabelings: []
     # - sourceLabels: [__meta_kubernetes_pod_node_name]
@@ -1350,6 +1396,8 @@ prometheus-node-exporter:
   extraArgs:
     - --collector.filesystem.ignored-mount-points=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/.+)($|/)
     - --collector.filesystem.ignored-fs-types=^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$
+  service:
+    portName: http-metrics
 
 ## Manages Prometheus and Alertmanager components
 ##
@@ -1499,6 +1547,8 @@ prometheusOperator:
   kubeletService:
     enabled: true
     namespace: kube-system
+    ## Use '{{ template "kube-prometheus-stack.fullname" . }}-kubelet' by default
+    name: ""
 
   ## Create a servicemonitor for the operator
   ##
@@ -1589,7 +1639,7 @@ prometheusOperator:
   ##
   image:
     repository: quay.io/prometheus-operator/prometheus-operator
-    tag: v0.50.0
+    tag: v0.52.0
     sha: ""
     pullPolicy: IfNotPresent
 
@@ -1601,26 +1651,29 @@ prometheusOperator:
   ##
   # alertmanagerDefaultBaseImage: quay.io/prometheus/alertmanager
 
-  ## Prometheus-config-reloader image to use for config and rule reloading
+  ## Prometheus-config-reloader
   ##
-  prometheusConfigReloaderImage:
+  prometheusConfigReloader:
+    # image to use for config and rule reloading
+    image:
       repository: quay.io/prometheus-operator/prometheus-config-reloader
-    tag: v0.50.0
+      tag: v0.52.0
       sha: ""
 
-  ## Set the prometheus config reloader side-car CPU limit
+    # resource config for prometheusConfigReloader
-  ##
+    resources:
-  configReloaderCpu: 100m
+      requests:
-
+        cpu: 100m
-  ## Set the prometheus config reloader side-car memory limit
+        memory: 50Mi
-  ##
+      limits:
-  configReloaderMemory: 50Mi
+        cpu: 100m
+        memory: 50Mi
 
   ## Thanos side-car image when configured
   ##
   thanosImage:
     repository: quay.io/thanos/thanos
-    tag: v0.17.2
+    tag: v0.23.1
     sha: ""
 
   ## Set a Field Selector to filter watched secrets
@@ -2013,7 +2066,7 @@ prometheus:
     ##
     image:
       repository: quay.io/prometheus/prometheus
-      tag: v2.28.1
+      tag: v2.31.1
       sha: ""
 
     ## Tolerations for use with node taints
@@ -2425,6 +2478,13 @@ prometheus:
     ## ref: https://github.com/prometheus-operator/prometheus-operator/blob/master/Documentation/api.md#thanosspec
     ##
     thanos: {}
+      # secretProviderClass:
+      #   provider: gcp
+      #   parameters:
+      #     secrets: |
+      #       - resourceName: "projects/$PROJECT_ID/secrets/testsecret/versions/latest"
+      #         fileName: "objstore.yaml"
+      # objectStorageConfigFile: /var/secrets/object-store.yaml
 
     ## Containers allows injecting additional containers. This is meant to allow adding an authentication proxy to a Prometheus pod.
     ## if using proxy extraContainer update targetPort with proxy container port
@@ -2436,7 +2496,7 @@ prometheus:
 
     ## PortName to use for Prometheus.
     ##
-    portName: "web"
+    portName: "http-web"
 
     ## ArbitraryFSAccessThroughSMs configures whether configuration based on a service monitor can access arbitrary files
     ## on the file system of the Prometheus container e.g. bearer token files.

charts/kubezero-metrics/charts/prometheus-pushgateway/Chart.yaml

@@ -1,5 +1,5 @@
 apiVersion: v1
-appVersion: 1.3.0
+appVersion: 1.4.1
 description: A Helm chart for prometheus pushgateway
 home: https://github.com/prometheus/pushgateway
 keywords:
@@ -13,4 +13,4 @@ maintainers:
 name: prometheus-pushgateway
 sources:
 - https://github.com/prometheus/pushgateway
-version: 1.10.1
+version: 1.13.0

charts/kubezero-metrics/charts/prometheus-pushgateway/templates/deployment.yaml

@@ -61,11 +61,12 @@ spec:
             timeoutSeconds: 10
           resources:
 {{ toYaml .Values.resources | indent 12 }}
-          {{- if .Values.persistentVolume.enabled }}
           volumeMounts:
             - name: storage-volume
               mountPath: "{{ .Values.persistentVolume.mountPath }}"
               subPath: "{{ .Values.persistentVolume.subPath }}"
+          {{- if .Values.extraVolumeMounts }}
+{{ toYaml .Values.extraVolumeMounts | indent 12 }}
           {{- end }}
     {{- if .Values.nodeSelector }}
       nodeSelector:
@@ -79,13 +80,18 @@ spec:
       affinity:
 {{ toYaml .Values.affinity | indent 8 }}
     {{- end }}
-      {{- if .Values.persistentVolume.enabled }}
     {{- if .Values.securityContext }}
       securityContext:
 {{ toYaml .Values.securityContext | indent 8 }}
     {{- end }}
       volumes:
         - name: storage-volume
+      {{- if .Values.persistentVolume.enabled }}
           persistentVolumeClaim:
             claimName: {{ if .Values.persistentVolume.existingClaim }}{{ .Values.persistentVolume.existingClaim }}{{- else }}{{ template "prometheus-pushgateway.fullname" . }}{{- end }}
+      {{- else}}
+          emptyDir: {}
       {{- end -}}
+      {{- if .Values.extraVolumes }}
+{{ toYaml .Values.extraVolumes | indent 8 }}
+      {{- end }}

charts/kubezero-metrics/charts/prometheus-pushgateway/templates/ingress.yaml

@@ -2,9 +2,13 @@
 {{- $serviceName := include "prometheus-pushgateway.fullname" . }}
 {{- $servicePort := .Values.service.port -}}
 {{- $ingressPath := .Values.ingress.path -}}
-{{- if semverCompare ">=1.14.0-0" .Capabilities.KubeVersion.GitVersion }}
+{{- $ingressClassName := .Values.ingress.className -}}
+{{- $ingressPathType := .Values.ingress.pathType -}}
+{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion -}}
+apiVersion: networking.k8s.io/v1
+{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
 apiVersion: networking.k8s.io/v1beta1
-{{- else }}
+{{- else -}}
 apiVersion: extensions/v1beta1
 {{- end }}
 kind: Ingress
@@ -18,15 +22,28 @@ metadata:
   name: {{ template "prometheus-pushgateway.fullname" . }}
   namespace: {{ .Release.Namespace }}
 spec:
+  {{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }}
+  ingressClassName: {{ $ingressClassName }}
+  {{- end }}
   rules:
     {{- range $host := .Values.ingress.hosts }}
     - host: {{ $host }}
       http:
         paths:
           - path: {{ $ingressPath }}
+            {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }}
+            pathType: {{ $ingressPathType }}
+            {{- end }}
             backend:
+              {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }}
+              service:
+                name: {{ $serviceName }}
+                port:
+                  number: {{ $servicePort }}
+              {{- else }}
               serviceName: {{ $serviceName }}
               servicePort: {{ $servicePort }}
+              {{- end }}
     {{- end -}}
 {{- if .Values.ingress.tls }}
   tls:

charts/kubezero-metrics/charts/prometheus-pushgateway/values.yaml

@@ -10,7 +10,7 @@ fullnameOverride: ""
 
 image:
   repository: prom/pushgateway
-  tag: v1.3.0
+  tag: v1.4.1
   pullPolicy: IfNotPresent
 
 # Optional pod imagePullSecrets
@@ -84,7 +84,9 @@ ingress:
   ##
   enabled: false
   # AWS ALB requires path of /*
+  className: ""
   path: /
+  pathType: ImplementationSpecific
 
     ## Annotations.
     ##
@@ -218,6 +220,14 @@ persistentVolume:
   ##
   subPath: ""
 
+extraVolumes: {}
+  # - name: extra
+  #   emptyDir: {}
+extraVolumeMounts: {}
+  # - name: extra
+  #   mountPath: /usr/share/extras
+  #   readOnly: true
+
 # Configuration for clusters with restrictive network policies in place:
 # - allowAll allows access to the PushGateway from any namespace
 # - customSelector is a list of pod/namespaceSelectors to allow access from

charts/kubezero-metrics/configs/dashboards/apiserver.json

@@ -56,7 +56,11 @@
                },
                "gridPos": { },
                "id": 3,
-               "interval": null,
+               "interval": "1m",
+               "legend": {
+                  "alignAsTable": true,
+                  "rightSide": true
+               },
                "links": [ ],
                "mappingType": 1,
                "mappingTypes": [
@@ -128,13 +132,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 4,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -236,7 +241,11 @@
                },
                "gridPos": { },
                "id": 5,
-               "interval": null,
+               "interval": "1m",
+               "legend": {
+                  "alignAsTable": true,
+                  "rightSide": true
+               },
                "links": [ ],
                "mappingType": 1,
                "mappingTypes": [
@@ -307,13 +316,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 6,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -406,13 +416,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 7,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -488,13 +499,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 8,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -594,7 +606,11 @@
                },
                "gridPos": { },
                "id": 9,
-               "interval": null,
+               "interval": "1m",
+               "legend": {
+                  "alignAsTable": true,
+                  "rightSide": true
+               },
                "links": [ ],
                "mappingType": 1,
                "mappingTypes": [
@@ -665,13 +681,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 10,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -764,13 +781,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 11,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -846,13 +864,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 12,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -940,13 +959,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 13,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": false,
                   "sideWidth": null,
                   "total": false,
@@ -968,7 +988,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(rate(workqueue_adds_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, name)",
+                     "expr": "sum(rate(workqueue_adds_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{instance}} {{name}}",
@@ -1021,13 +1041,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 14,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": false,
                   "sideWidth": null,
                   "total": false,
@@ -1049,7 +1070,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(rate(workqueue_depth{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, name)",
+                     "expr": "sum(rate(workqueue_depth{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{instance}} {{name}}",
@@ -1102,6 +1123,7 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 15,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": false,
@@ -1130,7 +1152,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, name, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{instance}} {{name}}",
@@ -1196,13 +1218,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 16,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -1277,13 +1300,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 17,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -1305,7 +1329,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "rate(process_cpu_seconds_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[5m])",
+                     "expr": "rate(process_cpu_seconds_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{instance}}",
@@ -1358,13 +1382,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 18,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -1452,7 +1477,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",
@@ -1470,7 +1495,7 @@
             "multi": false,
             "name": "cluster",
             "options": [ ],
-            "query": "label_values(apiserver_request_total, cluster)",
+            "query": "label_values(up{job=\"apiserver\"}, cluster)",
             "refresh": 2,
             "regex": "",
             "sort": 1,
@@ -1490,7 +1515,7 @@
             "multi": false,
             "name": "instance",
             "options": [ ],
-            "query": "label_values(apiserver_request_total{job=\"apiserver\", cluster=\"$cluster\"}, instance)",
+            "query": "label_values(up{job=\"apiserver\", cluster=\"$cluster\"}, instance)",
             "refresh": 2,
             "regex": "",
             "sort": 1,

charts/kubezero-metrics/configs/dashboards/cluster-total.json

@@ -1619,7 +1619,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",

charts/kubezero-metrics/configs/dashboards/controller-manager.json

@@ -36,7 +36,11 @@
                },
                "gridPos": { },
                "id": 2,
-               "interval": null,
+               "interval": "1m",
+               "legend": {
+                  "alignAsTable": true,
+                  "rightSide": true
+               },
                "links": [ ],
                "mappingType": 1,
                "mappingTypes": [
@@ -106,6 +110,7 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 3,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": false,
@@ -134,7 +139,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(rate(workqueue_adds_total{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (cluster, instance, name)",
+                     "expr": "sum(rate(workqueue_adds_total{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{cluster}} {{instance}} {{name}}",
@@ -200,6 +205,7 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 4,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": false,
@@ -228,7 +234,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(rate(workqueue_depth{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (cluster, instance, name)",
+                     "expr": "sum(rate(workqueue_depth{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{cluster}} {{instance}} {{name}}",
@@ -294,6 +300,7 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 5,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": false,
@@ -322,7 +329,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (cluster, instance, name, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{cluster}} {{instance}} {{name}}",
@@ -388,13 +395,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 6,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -416,28 +424,28 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
+                     "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "2xx",
                      "refId": "A"
                   },
                   {
-                     "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
+                     "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "3xx",
                      "refId": "B"
                   },
                   {
-                     "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
+                     "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "4xx",
                      "refId": "C"
                   },
                   {
-                     "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
+                     "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "5xx",
@@ -490,13 +498,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 7,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -518,7 +527,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{verb}} {{url}}",
@@ -584,6 +593,7 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 8,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": false,
@@ -612,7 +622,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{verb}} {{url}}",
@@ -678,13 +688,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 9,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -759,13 +770,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 10,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -787,7 +799,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}[5m])",
+                     "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}[$__rate_interval])",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{instance}}",
@@ -840,13 +852,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 11,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -934,7 +947,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",

charts/kubezero-metrics/configs/dashboards/k8s-resources-cluster.json

@@ -24,10 +24,12 @@
                "id": 1,
                "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -47,7 +49,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "1 - avg(rate(node_cpu_seconds_total{mode=\"idle\", cluster=\"$cluster\"}[$__rate_interval]))",
+                     "expr": "1 - sum(avg by (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", cluster=\"$cluster\"}[$__rate_interval])))",
                      "format": "time_series",
                      "instant": true,
                      "intervalFactor": 2,
@@ -60,7 +62,7 @@
                "title": "CPU Utilisation",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "singlestat",
@@ -99,11 +101,14 @@
                "fill": 1,
                "format": "percentunit",
                "id": 2,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -123,7 +128,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{resource=\"cpu\",cluster=\"$cluster\"})",
+                     "expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})",
                      "format": "time_series",
                      "instant": true,
                      "intervalFactor": 2,
@@ -136,7 +141,7 @@
                "title": "CPU Requests Commitment",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "singlestat",
@@ -175,11 +180,14 @@
                "fill": 1,
                "format": "percentunit",
                "id": 3,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -199,7 +207,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{resource=\"cpu\",cluster=\"$cluster\"})",
+                     "expr": "sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})",
                      "format": "time_series",
                      "instant": true,
                      "intervalFactor": 2,
@@ -212,7 +220,7 @@
                "title": "CPU Limits Commitment",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "singlestat",
@@ -251,11 +259,14 @@
                "fill": 1,
                "format": "percentunit",
                "id": 4,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -275,7 +286,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(node_memory_MemTotal_bytes{cluster=\"$cluster\"})",
+                     "expr": "1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(node_memory_MemTotal_bytes{job=\"node-exporter\",cluster=\"$cluster\"})",
                      "format": "time_series",
                      "instant": true,
                      "intervalFactor": 2,
@@ -288,7 +299,7 @@
                "title": "Memory Utilisation",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "singlestat",
@@ -327,11 +338,14 @@
                "fill": 1,
                "format": "percentunit",
                "id": 5,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -351,7 +365,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{resource=\"memory\",cluster=\"$cluster\"})",
+                     "expr": "sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})",
                      "format": "time_series",
                      "instant": true,
                      "intervalFactor": 2,
@@ -364,7 +378,7 @@
                "title": "Memory Requests Commitment",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "singlestat",
@@ -403,11 +417,14 @@
                "fill": 1,
                "format": "percentunit",
                "id": 6,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -427,7 +444,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{resource=\"memory\",cluster=\"$cluster\"})",
+                     "expr": "sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})",
                      "format": "time_series",
                      "instant": true,
                      "intervalFactor": 2,
@@ -440,7 +457,7 @@
                "title": "Memory Limits Commitment",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "singlestat",
@@ -490,11 +507,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 7,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -528,7 +548,7 @@
                "title": "CPU Usage",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -578,11 +598,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 8,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -741,7 +764,7 @@
                ],
                "targets": [
                   {
-                     "expr": "sum(kube_pod_owner{cluster=\"$cluster\"}) by (namespace)",
+                     "expr": "sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$cluster\"}) by (namespace)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -810,7 +833,7 @@
                "title": "CPU Quota",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -861,11 +884,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 9,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -885,7 +911,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(container_memory_rss{cluster=\"$cluster\", container!=\"\"}) by (namespace)",
+                     "expr": "sum(container_memory_rss{job=\"cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{namespace}}",
@@ -899,7 +925,7 @@
                "title": "Memory Usage (w/o cache)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -949,11 +975,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 10,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1112,7 +1141,7 @@
                ],
                "targets": [
                   {
-                     "expr": "sum(kube_pod_owner{cluster=\"$cluster\"}) by (namespace)",
+                     "expr": "sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$cluster\"}) by (namespace)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1130,7 +1159,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_rss{cluster=\"$cluster\", container!=\"\"}) by (namespace)",
+                     "expr": "sum(container_memory_rss{job=\"cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1148,7 +1177,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_rss{cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)",
+                     "expr": "sum(container_memory_rss{job=\"cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1166,7 +1195,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_rss{cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)",
+                     "expr": "sum(container_memory_rss{job=\"cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1181,7 +1210,7 @@
                "title": "Requests by Namespace",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -1234,10 +1263,12 @@
                "id": 11,
                "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1381,7 +1412,7 @@
                ],
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "sum(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1390,7 +1421,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "sum(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1399,7 +1430,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "sum(irate(container_network_receive_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1408,7 +1439,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "sum(irate(container_network_transmit_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1417,7 +1448,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1426,7 +1457,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1441,7 +1472,7 @@
                "title": "Current Network Usage",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -1492,11 +1523,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 12,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1516,7 +1550,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "sum(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{namespace}}",
@@ -1530,7 +1564,7 @@
                "title": "Receive Bandwidth",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1568,11 +1602,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 13,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1592,7 +1629,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "sum(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{namespace}}",
@@ -1606,7 +1643,7 @@
                "title": "Transmit Bandwidth",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1656,11 +1693,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 14,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1680,7 +1720,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "avg(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{namespace}}",
@@ -1694,7 +1734,7 @@
                "title": "Average Container Bandwidth by Namespace: Received",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1732,11 +1772,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 15,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1756,7 +1799,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "avg(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{namespace}}",
@@ -1770,7 +1813,7 @@
                "title": "Average Container Bandwidth by Namespace: Transmitted",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1820,11 +1863,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 16,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1844,7 +1890,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "sum(irate(container_network_receive_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{namespace}}",
@@ -1858,7 +1904,7 @@
                "title": "Rate of Received Packets",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1896,11 +1942,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 17,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1920,7 +1969,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "sum(irate(container_network_transmit_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{namespace}}",
@@ -1934,7 +1983,7 @@
                "title": "Rate of Transmitted Packets",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1984,11 +2033,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 18,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -2008,7 +2060,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{namespace}}",
@@ -2022,7 +2074,7 @@
                "title": "Rate of Received Packets Dropped",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -2060,11 +2112,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 19,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -2084,7 +2139,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
+                     "expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{namespace}}",
@@ -2098,7 +2153,7 @@
                "title": "Rate of Transmitted Packets Dropped",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -2149,11 +2204,14 @@
                "decimals": -1,
                "fill": 10,
                "id": 20,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -2173,7 +2231,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "ceil(sum by(namespace) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\"}[5m]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\"}[5m])))",
+                     "expr": "ceil(sum by(namespace) (rate(container_fs_reads_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{namespace}}",
@@ -2187,7 +2245,7 @@
                "title": "IOPS(Reads+Writes)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -2225,11 +2283,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 21,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -2249,7 +2310,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\"}[5m]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+                     "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{namespace}}",
@@ -2263,7 +2324,7 @@
                "title": "ThroughPut(Read+Write)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -2313,11 +2374,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 22,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -2465,7 +2529,7 @@
                ],
                "targets": [
                   {
-                     "expr": "sum by(namespace) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+                     "expr": "sum by(namespace) (rate(container_fs_reads_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -2474,7 +2538,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(namespace) (rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+                     "expr": "sum by(namespace) (rate(container_fs_writes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -2483,7 +2547,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(namespace) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\"}[5m]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+                     "expr": "sum by(namespace) (rate(container_fs_reads_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -2492,7 +2556,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+                     "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -2501,7 +2565,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(namespace) (rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+                     "expr": "sum by(namespace) (rate(container_fs_writes_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -2510,7 +2574,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\"}[5m]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\"}[5m]))",
+                     "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -2525,7 +2589,7 @@
                "title": "Current Storage IO",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -2578,7 +2642,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",

charts/kubezero-metrics/configs/dashboards/k8s-resources-namespace.json

@@ -22,11 +22,14 @@
                "fill": 1,
                "format": "percentunit",
                "id": 1,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -46,7 +49,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
+                     "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
                      "format": "time_series",
                      "instant": true,
                      "intervalFactor": 2,
@@ -59,7 +62,7 @@
                "title": "CPU Utilisation (from requests)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "singlestat",
@@ -98,11 +101,14 @@
                "fill": 1,
                "format": "percentunit",
                "id": 2,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -122,7 +128,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
+                     "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
                      "format": "time_series",
                      "instant": true,
                      "intervalFactor": 2,
@@ -135,7 +141,7 @@
                "title": "CPU Utilisation (from limits)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "singlestat",
@@ -174,11 +180,14 @@
                "fill": 1,
                "format": "percentunit",
                "id": 3,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -198,7 +207,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})",
+                     "expr": "sum(container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})",
                      "format": "time_series",
                      "instant": true,
                      "intervalFactor": 2,
@@ -211,7 +220,7 @@
                "title": "Memory Utilisation (from requests)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "singlestat",
@@ -250,11 +259,14 @@
                "fill": 1,
                "format": "percentunit",
                "id": 4,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -274,7 +286,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})",
+                     "expr": "sum(container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})",
                      "format": "time_series",
                      "instant": true,
                      "intervalFactor": 2,
@@ -287,7 +299,7 @@
                "title": "Memory Utilisation (from limits)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "singlestat",
@@ -337,11 +349,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 5,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -414,7 +429,7 @@
                "title": "CPU Usage",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -464,11 +479,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 6,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -648,7 +666,7 @@
                "title": "CPU Quota",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -699,11 +717,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 7,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -746,7 +767,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}) by (pod)",
+                     "expr": "sum(container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -776,7 +797,7 @@
                "title": "Memory Usage (w/o cache)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -826,11 +847,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 8,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1004,7 +1028,7 @@
                ],
                "targets": [
                   {
-                     "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)",
+                     "expr": "sum(container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1022,7 +1046,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
+                     "expr": "sum(container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1040,7 +1064,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
+                     "expr": "sum(container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1049,7 +1073,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
+                     "expr": "sum(container_memory_rss{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1058,7 +1082,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
+                     "expr": "sum(container_memory_cache{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1067,7 +1091,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
+                     "expr": "sum(container_memory_swap{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1082,7 +1106,7 @@
                "title": "Memory Quota",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -1135,10 +1159,12 @@
                "id": 9,
                "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1282,7 +1308,7 @@
                ],
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1291,7 +1317,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1300,7 +1326,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_receive_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1309,7 +1335,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_transmit_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1318,7 +1344,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1327,7 +1353,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1342,7 +1368,7 @@
                "title": "Current Network Usage",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -1393,11 +1419,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 10,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1417,7 +1446,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1431,7 +1460,7 @@
                "title": "Receive Bandwidth",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1469,11 +1498,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 11,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1493,7 +1525,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1507,7 +1539,7 @@
                "title": "Transmit Bandwidth",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1557,11 +1589,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 12,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1581,7 +1616,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1595,7 +1630,7 @@
                "title": "Rate of Received Packets",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1633,11 +1668,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 13,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1657,7 +1695,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1671,7 +1709,7 @@
                "title": "Rate of Transmitted Packets",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1721,11 +1759,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 14,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1745,7 +1786,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1759,7 +1800,7 @@
                "title": "Rate of Received Packets Dropped",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1797,11 +1838,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 15,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1821,7 +1865,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1835,7 +1879,7 @@
                "title": "Rate of Transmitted Packets Dropped",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1886,11 +1930,14 @@
                "decimals": -1,
                "fill": 10,
                "id": 16,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1910,7 +1957,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "ceil(sum by(pod) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m])))",
+                     "expr": "ceil(sum by(pod) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1924,7 +1971,7 @@
                "title": "IOPS(Reads+Writes)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1962,11 +2009,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 17,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1986,7 +2036,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
+                     "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -2000,7 +2050,7 @@
                "title": "ThroughPut(Read+Write)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -2050,11 +2100,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 18,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -2202,7 +2255,7 @@
                ],
                "targets": [
                   {
-                     "expr": "sum by(pod) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
+                     "expr": "sum by(pod) (rate(container_fs_reads_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -2211,7 +2264,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(pod) (rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
+                     "expr": "sum by(pod) (rate(container_fs_writes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -2220,7 +2273,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(pod) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
+                     "expr": "sum by(pod) (rate(container_fs_reads_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -2229,7 +2282,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
+                     "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -2238,7 +2291,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(pod) (rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
+                     "expr": "sum by(pod) (rate(container_fs_writes_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -2247,7 +2300,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\"}[5m]))",
+                     "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -2262,7 +2315,7 @@
                "title": "Current Storage IO",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -2315,7 +2368,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",
@@ -2336,7 +2389,7 @@
             "multi": false,
             "name": "cluster",
             "options": [ ],
-            "query": "label_values(kube_pod_info, cluster)",
+            "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
             "refresh": 2,
             "regex": "",
             "sort": 1,
@@ -2359,7 +2412,7 @@
             "multi": false,
             "name": "namespace",
             "options": [ ],
-            "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
+            "query": "label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
             "refresh": 2,
             "regex": "",
             "sort": 1,

charts/kubezero-metrics/configs/dashboards/k8s-resources-node.json

@@ -21,11 +21,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 1,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -38,12 +41,32 @@
                "pointradius": 5,
                "points": false,
                "renderer": "flot",
-               "seriesOverrides": [ ],
+               "seriesOverrides": [
+                  {
+                     "alias": "max capacity",
+                     "color": "#F2495C",
+                     "dashes": true,
+                     "fill": 0,
+                     "hiddenSeries": true,
+                     "hideTooltip": true,
+                     "legend": true,
+                     "linewidth": 2,
+                     "stack": false
+                  }
+               ],
                "spaceLength": 10,
                "span": 12,
                "stack": true,
                "steppedLine": false,
                "targets": [
+                  {
+                     "expr": "sum(kube_node_status_capacity{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"})",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "max capacity",
+                     "legendLink": null,
+                     "step": 10
+                  },
                   {
                      "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
                      "format": "time_series",
@@ -59,7 +82,7 @@
                "title": "CPU Usage",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -109,11 +132,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 2,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -293,7 +319,7 @@
                "title": "CPU Quota",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -344,11 +370,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 3,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -361,12 +390,32 @@
                "pointradius": 5,
                "points": false,
                "renderer": "flot",
-               "seriesOverrides": [ ],
+               "seriesOverrides": [
+                  {
+                     "alias": "max capacity",
+                     "color": "#F2495C",
+                     "dashes": true,
+                     "fill": 0,
+                     "hiddenSeries": true,
+                     "hideTooltip": true,
+                     "legend": true,
+                     "linewidth": 2,
+                     "stack": false
+                  }
+               ],
                "spaceLength": 10,
                "span": 12,
                "stack": true,
                "steppedLine": false,
                "targets": [
+                  {
+                     "expr": "sum(kube_node_status_capacity{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"})",
+                     "format": "time_series",
+                     "intervalFactor": 2,
+                     "legendFormat": "max capacity",
+                     "legendLink": null,
+                     "step": 10
+                  },
                   {
                      "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)",
                      "format": "time_series",
@@ -382,7 +431,7 @@
                "title": "Memory Usage (w/o cache)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -432,11 +481,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 4,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -688,7 +740,7 @@
                "title": "Memory Quota",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -741,7 +793,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",
@@ -762,7 +814,7 @@
             "multi": false,
             "name": "cluster",
             "options": [ ],
-            "query": "label_values(kube_pod_info, cluster)",
+            "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
             "refresh": 2,
             "regex": "",
             "sort": 1,
@@ -785,7 +837,7 @@
             "multi": true,
             "name": "node",
             "options": [ ],
-            "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, node)",
+            "query": "label_values(kube_node_info{cluster=\"$cluster\"}, node)",
             "refresh": 2,
             "regex": "",
             "sort": 1,

charts/kubezero-metrics/configs/dashboards/k8s-resources-pod.json

@@ -21,11 +21,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 1,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -72,7 +75,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n",
+                     "expr": "sum(\n    kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "requests",
@@ -80,7 +83,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n",
+                     "expr": "sum(\n    kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "limits",
@@ -94,7 +97,7 @@
                "title": "CPU Usage",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -144,11 +147,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 2,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": true,
                   "max": true,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -168,7 +174,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(increase(container_cpu_cfs_throttled_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[5m])) by (container) /sum(increase(container_cpu_cfs_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[5m])) by (container)",
+                     "expr": "sum(increase(container_cpu_cfs_throttled_periods_total{job=\"cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container) /sum(increase(container_cpu_cfs_periods_total{job=\"cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{container}}",
@@ -191,7 +197,7 @@
                "title": "CPU Throttling",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -241,11 +247,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 3,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -425,7 +434,7 @@
                "title": "CPU Quota",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -476,11 +485,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 4,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -521,7 +533,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)",
+                     "expr": "sum(container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{container}}",
@@ -529,7 +541,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n",
+                     "expr": "sum(\n    kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "requests",
@@ -537,7 +549,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n",
+                     "expr": "sum(\n    kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "limits",
@@ -551,7 +563,7 @@
                "title": "Memory Usage (WSS)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -601,11 +613,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 5,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -779,7 +794,7 @@
                ],
                "targets": [
                   {
-                     "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)",
+                     "expr": "sum(container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -797,7 +812,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
+                     "expr": "sum(container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -815,7 +830,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
+                     "expr": "sum(container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -824,7 +839,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
+                     "expr": "sum(container_memory_rss{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -833,7 +848,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
+                     "expr": "sum(container_memory_cache{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -842,7 +857,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
+                     "expr": "sum(container_memory_swap{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -857,7 +872,7 @@
                "title": "Memory Quota",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -910,10 +925,12 @@
                "id": 6,
                "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -933,7 +950,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -947,7 +964,7 @@
                "title": "Receive Bandwidth",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -987,10 +1004,12 @@
                "id": 7,
                "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1010,7 +1029,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1024,7 +1043,7 @@
                "title": "Transmit Bandwidth",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1076,10 +1095,12 @@
                "id": 8,
                "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1099,7 +1120,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_receive_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1113,7 +1134,7 @@
                "title": "Rate of Received Packets",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1153,10 +1174,12 @@
                "id": 9,
                "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1176,7 +1199,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_transmit_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1190,7 +1213,7 @@
                "title": "Rate of Transmitted Packets",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1242,10 +1265,12 @@
                "id": 10,
                "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1265,7 +1290,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1279,7 +1304,7 @@
                "title": "Rate of Received Packets Dropped",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1319,10 +1344,12 @@
                "id": 11,
                "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1342,7 +1369,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
+                     "expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1356,7 +1383,7 @@
                "title": "Rate of Transmitted Packets Dropped",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1407,11 +1434,14 @@
                "decimals": -1,
                "fill": 10,
                "id": 12,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1431,7 +1461,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "ceil(sum by(pod) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[5m])))",
+                     "expr": "ceil(sum by(pod) (rate(container_fs_reads_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "Reads",
@@ -1439,7 +1469,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "ceil(sum by(pod) (rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[5m])))",
+                     "expr": "ceil(sum by(pod) (rate(container_fs_writes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "Writes",
@@ -1453,7 +1483,7 @@
                "title": "IOPS",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1491,11 +1521,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 13,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1515,7 +1548,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[5m]))",
+                     "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "Reads",
@@ -1523,7 +1556,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(pod) (rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[5m]))",
+                     "expr": "sum by(pod) (rate(container_fs_writes_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "Writes",
@@ -1537,7 +1570,7 @@
                "title": "ThroughPut",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1588,11 +1621,14 @@
                "decimals": -1,
                "fill": 10,
                "id": 14,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1612,7 +1648,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "ceil(sum by(container) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m])))",
+                     "expr": "ceil(sum by(container) (rate(container_fs_reads_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval])))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{container}}",
@@ -1626,7 +1662,7 @@
                "title": "IOPS(Reads+Writes)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1664,11 +1700,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 15,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1688,7 +1727,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum by(container) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+                     "expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{container}}",
@@ -1702,7 +1741,7 @@
                "title": "ThroughPut(Read+Write)",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1752,11 +1791,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 16,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1904,7 +1946,7 @@
                ],
                "targets": [
                   {
-                     "expr": "sum by(container) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+                     "expr": "sum by(container) (rate(container_fs_reads_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1913,7 +1955,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(container) (rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+                     "expr": "sum by(container) (rate(container_fs_writes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1922,7 +1964,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(container) (rate(container_fs_reads_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]) + rate(container_fs_writes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+                     "expr": "sum by(container) (rate(container_fs_reads_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1931,7 +1973,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(container) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+                     "expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1940,7 +1982,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(container) (rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+                     "expr": "sum by(container) (rate(container_fs_writes_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1949,7 +1991,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum by(container) (rate(container_fs_reads_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]) + rate(container_fs_writes_bytes_total{container!=\"\", cluster=\"$cluster\",namespace=~\"$namespace\", pod=\"$pod\"}[5m]))",
+                     "expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"cadvisor\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1964,7 +2006,7 @@
                "title": "Current Storage IO",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -2017,7 +2059,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",
@@ -2038,7 +2080,7 @@
             "multi": false,
             "name": "cluster",
             "options": [ ],
-            "query": "label_values(kube_pod_info, cluster)",
+            "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
             "refresh": 2,
             "regex": "",
             "sort": 1,
@@ -2061,7 +2103,7 @@
             "multi": false,
             "name": "namespace",
             "options": [ ],
-            "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
+            "query": "label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
             "refresh": 2,
             "regex": "",
             "sort": 1,
@@ -2084,7 +2126,7 @@
             "multi": false,
             "name": "pod",
             "options": [ ],
-            "query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=\"$namespace\"}, pod)",
+            "query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\"}, pod)",
             "refresh": 2,
             "regex": "",
             "sort": 1,

charts/kubezero-metrics/configs/dashboards/k8s-resources-workload.json

@@ -21,11 +21,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 1,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -59,7 +62,7 @@
                "title": "CPU Usage",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -109,11 +112,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 2,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -251,7 +257,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                     "expr": "sum(\n    kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -260,7 +266,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                     "expr": "sum(\n    node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -269,7 +275,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                     "expr": "sum(\n    kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -278,7 +284,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                     "expr": "sum(\n    node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -293,7 +299,7 @@
                "title": "CPU Quota",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -344,11 +350,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 3,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -382,7 +391,7 @@
                "title": "Memory Usage",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -432,11 +441,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 4,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -574,7 +586,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                     "expr": "sum(\n    kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -583,7 +595,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                     "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -592,7 +604,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                     "expr": "sum(\n    kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -601,7 +613,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                     "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -616,7 +628,7 @@
                "title": "Memory Quota",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -669,10 +681,12 @@
                "id": 5,
                "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -816,7 +830,7 @@
                ],
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(sum(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -825,7 +839,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -834,7 +848,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(sum(irate(container_network_receive_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -843,7 +857,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(sum(irate(container_network_transmit_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -852,7 +866,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -861,7 +875,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -876,7 +890,7 @@
                "title": "Current Network Usage",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -927,11 +941,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 6,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -951,7 +968,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(sum(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -965,7 +982,7 @@
                "title": "Receive Bandwidth",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1003,11 +1020,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 7,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1027,7 +1047,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1041,7 +1061,7 @@
                "title": "Transmit Bandwidth",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1091,11 +1111,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 8,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1115,7 +1138,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(avg(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1129,7 +1152,7 @@
                "title": "Average Container Bandwidth by Pod: Received",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1167,11 +1190,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 9,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1191,7 +1217,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(avg(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1205,7 +1231,7 @@
                "title": "Average Container Bandwidth by Pod: Transmitted",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1255,11 +1281,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 10,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1279,7 +1308,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(sum(irate(container_network_receive_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1293,7 +1322,7 @@
                "title": "Rate of Received Packets",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1331,11 +1360,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 11,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1355,7 +1387,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(sum(irate(container_network_transmit_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1369,7 +1401,7 @@
                "title": "Rate of Transmitted Packets",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1419,11 +1451,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 12,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1443,7 +1478,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1457,7 +1492,7 @@
                "title": "Rate of Received Packets Dropped",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1495,11 +1530,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 13,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1519,7 +1557,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{pod}}",
@@ -1533,7 +1571,7 @@
                "title": "Rate of Transmitted Packets Dropped",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1585,7 +1623,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",
@@ -1606,7 +1644,7 @@
             "multi": false,
             "name": "cluster",
             "options": [ ],
-            "query": "label_values(kube_pod_info, cluster)",
+            "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
             "refresh": 2,
             "regex": "",
             "sort": 1,
@@ -1629,30 +1667,7 @@
             "multi": false,
             "name": "namespace",
             "options": [ ],
-            "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
+            "query": "label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
-            "refresh": 2,
-            "regex": "",
-            "sort": 1,
-            "tagValuesQuery": "",
-            "tags": [ ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-         },
-         {
-            "allValue": null,
-            "current": {
-               "text": "",
-               "value": ""
-            },
-            "datasource": "$datasource",
-            "hide": 0,
-            "includeAll": false,
-            "label": null,
-            "multi": false,
-            "name": "workload",
-            "options": [ ],
-            "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)",
             "refresh": 2,
             "regex": "",
             "sort": 1,
@@ -1675,7 +1690,30 @@
             "multi": false,
             "name": "type",
             "options": [ ],
-            "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)",
+            "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload_type)",
+            "refresh": 2,
+            "regex": "",
+            "sort": 1,
+            "tagValuesQuery": "",
+            "tags": [ ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+         },
+         {
+            "allValue": null,
+            "current": {
+               "text": "",
+               "value": ""
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": false,
+            "label": null,
+            "multi": false,
+            "name": "workload",
+            "options": [ ],
+            "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}, workload)",
             "refresh": 2,
             "regex": "",
             "sort": 1,

charts/kubezero-metrics/configs/dashboards/k8s-resources-workloads-namespace.json

@@ -21,11 +21,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 1,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -98,7 +101,7 @@
                "title": "CPU Usage",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -148,11 +151,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 2,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -329,7 +335,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n  kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                     "expr": "sum(\n  kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -338,7 +344,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n  node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                     "expr": "sum(\n  node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -347,7 +353,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n  kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                     "expr": "sum(\n  kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -356,7 +362,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n  node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                     "expr": "sum(\n  node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -371,7 +377,7 @@
                "title": "CPU Quota",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -422,11 +428,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 3,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -469,7 +478,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                     "expr": "sum(\n    container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{workload}} - {{workload_type}}",
@@ -499,7 +508,7 @@
                "title": "Memory Usage",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -549,11 +558,14 @@
                "datasource": "$datasource",
                "fill": 1,
                "id": 4,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -721,7 +733,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                     "expr": "sum(\n    container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -730,7 +742,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n  kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                     "expr": "sum(\n  kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -739,7 +751,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                     "expr": "sum(\n    container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -748,7 +760,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n  kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                     "expr": "sum(\n  kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -757,7 +769,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                     "expr": "sum(\n    container_memory_working_set_bytes{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -772,7 +784,7 @@
                "title": "Memory Quota",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -825,10 +837,12 @@
                "id": 5,
                "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -987,7 +1001,7 @@
                ],
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(sum(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -996,7 +1010,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1005,7 +1019,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(sum(irate(container_network_receive_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1014,7 +1028,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(sum(irate(container_network_transmit_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1023,7 +1037,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1032,7 +1046,7 @@
                      "step": 10
                   },
                   {
-                     "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "table",
                      "instant": true,
                      "intervalFactor": 2,
@@ -1047,7 +1061,7 @@
                "title": "Current Network Usage",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "transform": "table",
@@ -1098,11 +1112,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 6,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1122,7 +1139,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(sum(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{workload}}",
@@ -1136,7 +1153,7 @@
                "title": "Receive Bandwidth",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1174,11 +1191,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 7,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1198,7 +1218,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{workload}}",
@@ -1212,7 +1232,7 @@
                "title": "Transmit Bandwidth",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1262,11 +1282,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 8,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1286,7 +1309,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(avg(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{workload}}",
@@ -1300,7 +1323,7 @@
                "title": "Average Container Bandwidth by Workload: Received",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1338,11 +1361,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 9,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1362,7 +1388,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(avg(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{workload}}",
@@ -1376,7 +1402,7 @@
                "title": "Average Container Bandwidth by Workload: Transmitted",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1426,11 +1452,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 10,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1450,7 +1479,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(sum(irate(container_network_receive_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{workload}}",
@@ -1464,7 +1493,7 @@
                "title": "Rate of Received Packets",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1502,11 +1531,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 11,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1526,7 +1558,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(sum(irate(container_network_transmit_packets_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{workload}}",
@@ -1540,7 +1572,7 @@
                "title": "Rate of Transmitted Packets",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1590,11 +1622,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 12,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1614,7 +1649,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{workload}}",
@@ -1628,7 +1663,7 @@
                "title": "Rate of Received Packets Dropped",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1666,11 +1701,14 @@
                "datasource": "$datasource",
                "fill": 10,
                "id": 13,
+               "interval": "1m",
                "legend": {
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
+                  "rightSide": true,
                   "show": true,
                   "total": false,
                   "values": false
@@ -1690,7 +1728,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{workload}}",
@@ -1704,7 +1742,7 @@
                "title": "Rate of Transmitted Packets Dropped",
                "tooltip": {
                   "shared": false,
-                  "sort": 0,
+                  "sort": 2,
                   "value_type": "individual"
                },
                "type": "graph",
@@ -1756,7 +1794,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",
@@ -1777,7 +1815,7 @@
             "multi": false,
             "name": "cluster",
             "options": [ ],
-            "query": "label_values(kube_pod_info, cluster)",
+            "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
             "refresh": 2,
             "regex": "",
             "sort": 1,
@@ -1787,34 +1825,6 @@
             "type": "query",
             "useTags": false
          },
-         {
-            "allValue": null,
-            "auto": false,
-            "auto_count": 30,
-            "auto_min": "10s",
-            "current": {
-               "text": "deployment",
-               "value": "deployment"
-            },
-            "datasource": "$datasource",
-            "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
-            "hide": 0,
-            "includeAll": false,
-            "label": null,
-            "multi": false,
-            "name": "type",
-            "options": [ ],
-            "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
-            "refresh": 2,
-            "regex": "",
-            "skipUrlSync": false,
-            "sort": 0,
-            "tagValuesQuery": "",
-            "tags": [ ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-         },
          {
             "allValue": null,
             "current": {
@@ -1828,7 +1838,7 @@
             "multi": false,
             "name": "namespace",
             "options": [ ],
-            "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
+            "query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
             "refresh": 2,
             "regex": "",
             "sort": 1,
@@ -1837,6 +1847,34 @@
             "tagsQuery": "",
             "type": "query",
             "useTags": false
+         },
+         {
+            "allValue": null,
+            "auto": false,
+            "auto_count": 30,
+            "auto_min": "10s",
+            "current": {
+               "text": "deployment",
+               "value": "deployment"
+            },
+            "datasource": "$datasource",
+            "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
+            "hide": 0,
+            "includeAll": false,
+            "label": null,
+            "multi": false,
+            "name": "type",
+            "options": [ ],
+            "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
+            "refresh": 2,
+            "regex": "",
+            "skipUrlSync": false,
+            "sort": 0,
+            "tagValuesQuery": "",
+            "tags": [ ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
          }
       ]
    },

charts/kubezero-metrics/configs/dashboards/kubelet.json

@@ -154,7 +154,7 @@
                "refId": "A"
             }
          ],
-         "title": "Running Container",
+         "title": "Running Containers",
          "transparent": false,
          "type": "stat"
       },
@@ -294,7 +294,7 @@
          "pluginVersion": "7",
          "targets": [
             {
-               "expr": "sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m]))",
+               "expr": "sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval]))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}}",
@@ -347,7 +347,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (operation_type, instance)",
+               "expr": "sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (operation_type, instance)",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}} {{operation_type}}",
@@ -432,7 +432,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_type)",
+               "expr": "sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type)",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}} {{operation_type}}",
@@ -517,7 +517,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_type, le))",
+               "expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type, le))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}} {{operation_type}}",
@@ -602,14 +602,14 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance)",
+               "expr": "sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance)",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}} pod",
                "refId": "A"
             },
             {
-               "expr": "sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance)",
+               "expr": "sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance)",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}} worker",
@@ -694,14 +694,14 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
+               "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}} pod",
                "refId": "A"
             },
             {
-               "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
+               "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}} worker",
@@ -788,7 +788,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)",
+               "expr": "sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin)",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
@@ -875,7 +875,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)",
+               "expr": "sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin)",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
@@ -962,7 +962,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin, le))",
+               "expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin, le))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
@@ -1047,7 +1047,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_type)",
+               "expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type)",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{operation_type}}",
@@ -1132,7 +1132,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_type, le))",
+               "expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type, le))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}} {{operation_type}}",
@@ -1218,7 +1218,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance)",
+               "expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval])) by (instance)",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}}",
@@ -1303,7 +1303,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
+               "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}}",
@@ -1388,7 +1388,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
+               "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}}",
@@ -1473,28 +1473,28 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
+               "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "2xx",
                "refId": "A"
             },
             {
-               "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
+               "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "3xx",
                "refId": "B"
             },
             {
-               "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
+               "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "4xx",
                "refId": "C"
             },
             {
-               "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
+               "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "5xx",
@@ -1579,7 +1579,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, verb, url, le))",
+               "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval])) by (instance, verb, url, le))",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}} {{verb}} {{url}}",
@@ -1749,7 +1749,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])",
+               "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])",
                "format": "time_series",
                "intervalFactor": 2,
                "legendFormat": "{{instance}}",
@@ -1893,7 +1893,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",
@@ -1927,11 +1927,11 @@
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": true,
-            "label": null,
+            "label": "Data Source",
             "multi": false,
             "name": "instance",
             "options": [ ],
-            "query": "label_values(kubelet_runtime_operations_total{cluster=\"$cluster\", job=\"kubelet\"}, instance)",
+            "query": "label_values(up{job=\"kubelet\",cluster=\"$cluster\"}, instance)",
             "refresh": 2,
             "regex": "",
             "sort": 1,

charts/kubezero-metrics/configs/dashboards/namespace-by-pod.json

@@ -1137,7 +1137,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",

charts/kubezero-metrics/configs/dashboards/namespace-by-workload.json

@@ -89,7 +89,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+               "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                "format": "time_series",
                "intervalFactor": 1,
                "legendFormat": "{{ workload }}",
@@ -184,7 +184,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+               "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                "format": "time_series",
                "intervalFactor": 1,
                "legendFormat": "{{ workload }}",
@@ -441,7 +441,7 @@
          ],
          "targets": [
             {
-               "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+               "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                "format": "table",
                "instant": true,
                "intervalFactor": 2,
@@ -450,7 +450,7 @@
                "step": 10
             },
             {
-               "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+               "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                "format": "table",
                "instant": true,
                "intervalFactor": 2,
@@ -459,7 +459,7 @@
                "step": 10
             },
             {
-               "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+               "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                "format": "table",
                "instant": true,
                "intervalFactor": 2,
@@ -468,7 +468,7 @@
                "step": 10
             },
             {
-               "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+               "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                "format": "table",
                "instant": true,
                "intervalFactor": 2,
@@ -477,7 +477,7 @@
                "step": 10
             },
             {
-               "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+               "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                "format": "table",
                "instant": true,
                "intervalFactor": 2,
@@ -486,7 +486,7 @@
                "step": 10
             },
             {
-               "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+               "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                "format": "table",
                "instant": true,
                "intervalFactor": 2,
@@ -495,7 +495,7 @@
                "step": 10
             },
             {
-               "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+               "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                "format": "table",
                "instant": true,
                "intervalFactor": 2,
@@ -504,7 +504,7 @@
                "step": 10
             },
             {
-               "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+               "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                "format": "table",
                "instant": true,
                "intervalFactor": 2,
@@ -578,7 +578,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 1,
                      "legendFormat": "{{ workload }}",
@@ -673,7 +673,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 1,
                      "legendFormat": "{{ workload }}",
@@ -794,7 +794,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+               "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                "format": "time_series",
                "intervalFactor": 1,
                "legendFormat": "{{workload}}",
@@ -885,7 +885,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+               "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                "format": "time_series",
                "intervalFactor": 1,
                "legendFormat": "{{workload}}",
@@ -987,7 +987,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 1,
                      "legendFormat": "{{workload}}",
@@ -1078,7 +1078,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 1,
                      "legendFormat": "{{workload}}",
@@ -1189,7 +1189,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 1,
                      "legendFormat": "{{workload}}",
@@ -1280,7 +1280,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
+                     "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                      "format": "time_series",
                      "intervalFactor": 1,
                      "legendFormat": "{{workload}}",
@@ -1349,7 +1349,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",
@@ -1415,14 +1415,14 @@
                "value": "deployment"
             },
             "datasource": "$datasource",
-            "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
+            "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
             "hide": 0,
             "includeAll": false,
             "label": null,
             "multi": false,
             "name": "type",
             "options": [ ],
-            "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
+            "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
             "refresh": 2,
             "regex": "",
             "skipUrlSync": false,

charts/kubezero-metrics/configs/dashboards/persistentvolumesusage.json

@@ -26,13 +26,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 2,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": true,
                   "current": true,
                   "max": true,
                   "min": true,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -124,7 +125,11 @@
                },
                "gridPos": { },
                "id": 3,
-               "interval": null,
+               "interval": "1m",
+               "legend": {
+                  "alignAsTable": true,
+                  "rightSide": true
+               },
                "links": [ ],
                "mappingType": 1,
                "mappingTypes": [
@@ -207,13 +212,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 4,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": true,
                   "current": true,
                   "max": true,
                   "min": true,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -305,7 +311,11 @@
                },
                "gridPos": { },
                "id": 5,
-               "interval": null,
+               "interval": "1m",
+               "legend": {
+                  "alignAsTable": true,
+                  "rightSide": true
+               },
                "links": [ ],
                "mappingType": 1,
                "mappingTypes": [
@@ -388,7 +398,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",
@@ -406,7 +416,7 @@
             "multi": false,
             "name": "cluster",
             "options": [ ],
-            "query": "label_values(kubelet_volume_stats_capacity_bytes, cluster)",
+            "query": "label_values(kubelet_volume_stats_capacity_bytes{job=\"kubelet\"}, cluster)",
             "refresh": 2,
             "regex": "",
             "sort": 1,

charts/kubezero-metrics/configs/dashboards/pod-total.json

@@ -903,7 +903,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",

charts/kubezero-metrics/configs/dashboards/proxy.json

@@ -36,7 +36,11 @@
                },
                "gridPos": { },
                "id": 2,
-               "interval": null,
+               "interval": "1m",
+               "legend": {
+                  "alignAsTable": true,
+                  "rightSide": true
+               },
                "links": [ ],
                "mappingType": 1,
                "mappingTypes": [
@@ -106,13 +110,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 3,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -134,7 +139,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(rate(kubeproxy_sync_proxy_rules_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[5m]))",
+                     "expr": "sum(rate(kubeproxy_sync_proxy_rules_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "rate",
@@ -187,6 +192,7 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 4,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": false,
@@ -215,7 +221,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "histogram_quantile(0.99,rate(kubeproxy_sync_proxy_rules_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[5m]))",
+                     "expr": "histogram_quantile(0.99,rate(kubeproxy_sync_proxy_rules_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{instance}}",
@@ -281,13 +287,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 5,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -309,7 +316,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(rate(kubeproxy_network_programming_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[5m]))",
+                     "expr": "sum(rate(kubeproxy_network_programming_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "rate",
@@ -362,6 +369,7 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 6,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": false,
@@ -390,7 +398,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[5m])) by (instance, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval])) by (instance, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{instance}}",
@@ -456,13 +464,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 7,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -484,28 +493,28 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
+                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "2xx",
                      "refId": "A"
                   },
                   {
-                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
+                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "3xx",
                      "refId": "B"
                   },
                   {
-                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
+                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "4xx",
                      "refId": "C"
                   },
                   {
-                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
+                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "5xx",
@@ -558,13 +567,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 8,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -586,7 +596,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[5m])) by (verb, url, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[$__rate_interval])) by (verb, url, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{verb}} {{url}}",
@@ -652,6 +662,7 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 9,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": false,
@@ -680,7 +691,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{verb}} {{url}}",
@@ -746,13 +757,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 10,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -827,13 +839,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 11,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -855,7 +868,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}[5m])",
+                     "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}[$__rate_interval])",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{instance}}",
@@ -908,13 +921,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 12,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -1002,7 +1016,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",
@@ -1020,7 +1034,7 @@
             "multi": false,
             "name": "cluster",
             "options": [ ],
-            "query": "label_values(kube_pod_info, cluster)",
+            "query": "label_values(up{job=\"kube-proxy\"}, cluster)",
             "refresh": 2,
             "regex": "",
             "sort": 1,
@@ -1040,7 +1054,7 @@
             "multi": false,
             "name": "instance",
             "options": [ ],
-            "query": "label_values(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\"}, instance)",
+            "query": "label_values(up{job=\"kube-proxy\", cluster=\"$cluster\", job=\"kube-proxy\"}, instance)",
             "refresh": 2,
             "regex": "",
             "sort": 1,

charts/kubezero-metrics/configs/dashboards/scheduler.json

@@ -36,7 +36,11 @@
                },
                "gridPos": { },
                "id": 2,
-               "interval": null,
+               "interval": "1m",
+               "legend": {
+                  "alignAsTable": true,
+                  "rightSide": true
+               },
                "links": [ ],
                "mappingType": 1,
                "mappingTypes": [
@@ -106,6 +110,7 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 3,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": false,
@@ -134,28 +139,28 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(rate(scheduler_e2e_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (cluster, instance)",
+                     "expr": "sum(rate(scheduler_e2e_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{cluster}} {{instance}} e2e",
                      "refId": "A"
                   },
                   {
-                     "expr": "sum(rate(scheduler_binding_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (cluster, instance)",
+                     "expr": "sum(rate(scheduler_binding_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{cluster}} {{instance}} binding",
                      "refId": "B"
                   },
                   {
-                     "expr": "sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (cluster, instance)",
+                     "expr": "sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{cluster}} {{instance}} scheduling algorithm",
                      "refId": "C"
                   },
                   {
-                     "expr": "sum(rate(scheduler_volume_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (cluster, instance)",
+                     "expr": "sum(rate(scheduler_volume_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{cluster}} {{instance}} volume",
@@ -208,6 +213,7 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 4,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": false,
@@ -236,28 +242,28 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (cluster, instance, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{cluster}} {{instance}} e2e",
                      "refId": "A"
                   },
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (cluster, instance, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{cluster}} {{instance}} binding",
                      "refId": "B"
                   },
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (cluster, instance, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{cluster}} {{instance}} scheduling algorithm",
                      "refId": "C"
                   },
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (cluster, instance, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{cluster}} {{instance}} volume",
@@ -323,13 +329,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 5,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -351,28 +358,28 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
+                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "2xx",
                      "refId": "A"
                   },
                   {
-                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
+                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "3xx",
                      "refId": "B"
                   },
                   {
-                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
+                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "4xx",
                      "refId": "C"
                   },
                   {
-                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
+                     "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "5xx",
@@ -425,13 +432,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 6,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -453,7 +461,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{verb}} {{url}}",
@@ -519,6 +527,7 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 7,
+               "interval": "1m",
                "legend": {
                   "alignAsTable": true,
                   "avg": false,
@@ -547,7 +556,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
+                     "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{verb}} {{url}}",
@@ -613,13 +622,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 8,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -694,13 +704,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 9,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -722,7 +733,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])",
+                     "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])",
                      "format": "time_series",
                      "intervalFactor": 2,
                      "legendFormat": "{{instance}}",
@@ -775,13 +786,14 @@
                "fillGradient": 0,
                "gridPos": { },
                "id": 10,
+               "interval": "1m",
                "legend": {
-                  "alignAsTable": false,
+                  "alignAsTable": true,
                   "avg": false,
                   "current": false,
                   "max": false,
                   "min": false,
-                  "rightSide": false,
+                  "rightSide": true,
                   "show": true,
                   "sideWidth": null,
                   "total": false,
@@ -869,7 +881,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",
@@ -907,7 +919,7 @@
             "multi": false,
             "name": "instance",
             "options": [ ],
-            "query": "label_values(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\"}, instance)",
+            "query": "label_values(up{job=\"kube-scheduler\", cluster=\"$cluster\"}, instance)",
             "refresh": 2,
             "regex": "",
             "sort": 1,

charts/kubezero-metrics/configs/dashboards/workload-total.json

@@ -89,7 +89,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+               "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                "format": "time_series",
                "intervalFactor": 1,
                "legendFormat": "{{ pod }}",
@@ -184,7 +184,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+               "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                "format": "time_series",
                "intervalFactor": 1,
                "legendFormat": "{{ pod }}",
@@ -290,7 +290,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 1,
                      "legendFormat": "{{ pod }}",
@@ -385,7 +385,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 1,
                      "legendFormat": "{{ pod }}",
@@ -506,7 +506,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+               "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{job=\"cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                "format": "time_series",
                "intervalFactor": 1,
                "legendFormat": "{{pod}}",
@@ -597,7 +597,7 @@
          "steppedLine": false,
          "targets": [
             {
-               "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+               "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{job=\"cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                "format": "time_series",
                "intervalFactor": 1,
                "legendFormat": "{{pod}}",
@@ -699,7 +699,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "sort_desc(sum(irate(container_network_receive_packets_total{job=\"cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 1,
                      "legendFormat": "{{pod}}",
@@ -790,7 +790,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{job=\"cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 1,
                      "legendFormat": "{{pod}}",
@@ -901,7 +901,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 1,
                      "legendFormat": "{{pod}}",
@@ -992,7 +992,7 @@
                "steppedLine": false,
                "targets": [
                   {
-                     "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
+                     "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{job=\"cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                      "format": "time_series",
                      "intervalFactor": 1,
                      "legendFormat": "{{pod}}",
@@ -1061,7 +1061,7 @@
                "value": "default"
             },
             "hide": 0,
-            "label": null,
+            "label": "Data Source",
             "name": "datasource",
             "options": [ ],
             "query": "prometheus",
@@ -1079,7 +1079,7 @@
             "multi": false,
             "name": "cluster",
             "options": [ ],
-            "query": "label_values(kube_pod_info, cluster)",
+            "query": "label_values(kube_pod_info{job=\"kube-state-metrics\"}, cluster)",
             "refresh": 2,
             "regex": "",
             "sort": 0,
@@ -1099,14 +1099,14 @@
                "value": "kube-system"
             },
             "datasource": "$datasource",
-            "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
+            "definition": "label_values(container_network_receive_packets_total{job=\"cadvisor\", cluster=\"$cluster\"}, namespace)",
             "hide": 0,
             "includeAll": true,
             "label": null,
             "multi": false,
             "name": "namespace",
             "options": [ ],
-            "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
+            "query": "label_values(container_network_receive_packets_total{job=\"cadvisor\", cluster=\"$cluster\"}, namespace)",
             "refresh": 2,
             "regex": "",
             "skipUrlSync": false,

charts/kubezero-metrics/configs/jsonnetfile.lock.json

@@ -8,8 +8,8 @@
           "subdir": "grafana"
         }
       },
-      "version": "c3b14b24b83cfe9abf1064649d19e2d679f033fb",
+      "version": "199e363523104ff8b3a12483a4e3eca86372b078",
-      "sum": "YrE4DNQsWgYWs6h0j/FjQETt8xDXdYdsslb1WK7xQEk="
+      "sum": "/jDHzVAjHB4AOLkJHw1GyATX5ogZ1iMdcJXZAgaG3+g="
     },
     {
       "source": {
@@ -18,8 +18,8 @@
           "subdir": "contrib/mixin"
         }
       },
-      "version": "3df272774672366beb02c5447782805ab5fec957",
+      "version": "29292aa7bdafaf65cb5e054591fe0ff07b36f5ee",
-      "sum": "5XhYOigrKipOWDbIn9hlrz7JcbelzvJnormxSaup9JI="
+      "sum": "cdKL5kPYfpWSpTCu4qctmh+gWQqL+4YWom6rw9qLYJU="
     },
     {
       "source": {
@@ -28,7 +28,7 @@
           "subdir": "grafonnet"
         }
       },
-      "version": "19b27b272abf4263af1365ec485784c49815a332",
+      "version": "3626fc4dc2326931c530861ac5bebe39444f6cbf",
       "sum": "gF8foHByYcB25jcUOBqP6jxk0OPifQMjPvKY0HaCk6w="
     },
     {
@@ -38,8 +38,8 @@
           "subdir": "grafana-builder"
         }
       },
-      "version": "b7eae75972a369bf8ebfb03dcb0d4c14464ef85a",
+      "version": "b102f9ac7d1290ac025c2a7ac99f7fd9a9948503",
-      "sum": "GRf2GvwEU4jhXV+JOonXSZ4wdDv8mnHBPCQ6TUVd+g8="
+      "sum": "0KkygBQd/AFzUvVzezE4qF/uDYgrwUXVpZfINBti0oc="
     },
     {
       "source": {
@@ -48,8 +48,8 @@
           "subdir": ""
         }
       },
-      "version": "ff4641bcd83314c955150bea6b147df9ca335c4a",
+      "version": "9821d07e94e9a9916575a234fb699ae3331fa939",
-      "sum": "oUVGwcCbmdH8qz9B+lbRawI9s23GY9HeW7MwYZRbZ/0="
+      "sum": "xubNXyvDwUw9GZzi9BRb6ob3bYzfoMr5F5zCVn2d7ag="
     },
     {
       "source": {
@@ -58,7 +58,7 @@
           "subdir": "lib/promgrafonnet"
         }
       },
-      "version": "ff4641bcd83314c955150bea6b147df9ca335c4a",
+      "version": "9821d07e94e9a9916575a234fb699ae3331fa939",
       "sum": "zv7hXGui6BfHzE9wPatHI/AGZa4A2WKo6pq7ZdqBsps="
     },
     {
@@ -68,8 +68,8 @@
           "subdir": "jsonnet/kube-state-metrics"
         }
       },
-      "version": "8dab6f7472c26987ab7f8899a4a2f753fed8e8a8",
+      "version": "e3056ae518d0234105276ec916296923968ad294",
-      "sum": "S5qI+PJUdNeYOv76jH5nxwYS9N6U7CRxvyuB1wI4cTE="
+      "sum": "U1wzIpTAtOvC1yj43Y8PfvT0JfvnAcMfNH12Wi+ab0Y="
     },
     {
       "source": {
@@ -78,7 +78,7 @@
           "subdir": "jsonnet/kube-state-metrics-mixin"
         }
       },
-      "version": "8dab6f7472c26987ab7f8899a4a2f753fed8e8a8",
+      "version": "e3056ae518d0234105276ec916296923968ad294",
       "sum": "u8gaydJoxEjzizQ8jY8xSjYgWooPmxw+wIWdDxifMAk="
     },
     {
@@ -88,8 +88,8 @@
           "subdir": "jsonnet/kube-prometheus"
         }
       },
-      "version": "a2eee1803a074fb40cad109d690732c22f0130cf",
+      "version": "9ca30579f61ec51e63d87927d19b9d2a433c7e25",
-      "sum": "kqVnoNBux2YF1s03m+O3w/5jreAnjXx2/NjvNP1Hoy4="
+      "sum": "EYlmVYtdVovF3ziMZ9dhV0trzXww6YSz8A2tH2YF9Zw="
     },
     {
       "source": {
@@ -98,8 +98,8 @@
           "subdir": "jsonnet/mixin"
         }
       },
-      "version": "42fc15967e35e0cca68cf935f844086edbc82d0e",
+      "version": "335ebbc2f6ecf10b699821fa8cebcbff4a718ca7",
-      "sum": "6reUygVmQrLEWQzTKcH8ceDbvM+2ztK3z2VBR2K2l+U=",
+      "sum": "qZ4WgiweaE6eeKtFK60QUjLO8sf2L9Q8fgafWvDcyfY=",
       "name": "prometheus-operator-mixin"
     },
     {
@@ -109,8 +109,8 @@
           "subdir": "jsonnet/prometheus-operator"
         }
       },
-      "version": "42fc15967e35e0cca68cf935f844086edbc82d0e",
+      "version": "335ebbc2f6ecf10b699821fa8cebcbff4a718ca7",
-      "sum": "sECNXs/aIEreFUma1BWVyknBygqh3AVJEB3msmrAYYY="
+      "sum": "Vr2IY6Uz1lYYyGDF7QaEAVkJwAtOEikCfuXJN2eAUM0="
     },
     {
       "source": {
@@ -119,7 +119,7 @@
           "subdir": "doc/alertmanager-mixin"
         }
       },
-      "version": "e35efbddb66a73fd8723be5334477e76f21fbd19",
+      "version": "e2a10119aaf7777fa523d216e05897c5b719134c",
       "sum": "pep+dHzfIjh2SU5pEkwilMCAT/NoL6YYflV4x8cr7vU=",
       "name": "alertmanager"
     },
@@ -130,8 +130,8 @@
           "subdir": "docs/node-mixin"
         }
       },
-      "version": "0e6b23c338e98809c9872c70a2f5dfa8d6d370d4",
+      "version": "7dbf35891570f9ce3bccb25a55176ea4923b35dd",
-      "sum": "MnfAA4+l2BkgJncnYfV8uHC7CxHZut8+ap8KkEqyB5Y="
+      "sum": "MlWDAKGZ+JArozRKdKEvewHeWn8j2DNBzesJfLVd0dk="
     },
     {
       "source": {
@@ -140,8 +140,8 @@
           "subdir": "documentation/prometheus-mixin"
         }
       },
-      "version": "a05b510fc32c3ecc2fc369002576179ae1cbcc23",
+      "version": "c965a7555b7ffcee1a127d782abd5bb478a16750",
-      "sum": "m4VHwft4fUcxzL4+52lLZG/V5aH5ZEdjaweb88vISL0=",
+      "sum": "ZjQoYhvgKwJNkg+h+m9lW3SYjnjv5Yx5btEipLhru88=",
       "name": "prometheus"
     },
     {
@@ -151,8 +151,8 @@
           "subdir": "mixin"
         }
       },
-      "version": "360b39e1c6ab3ac8dcefa225a6205142f9362c68",
+      "version": "d1acaea2a11a3e4db6bb435c98dea63c517e3530",
-      "sum": "Og+wEHfgzXBvBLAeeQvGNoiCw3FY4LQHlJdpsG/owj8=",
+      "sum": "1Y1cPIeoPg2nCAEhKPCt8bAGuwuOP2eZ3kVF432mlMA=",
       "name": "thanos-mixin"
     }
   ],

charts/kubezero-metrics/configs/rules/alertmanager-prometheusRule

@@ -4,6 +4,7 @@
    "metadata": {
       "labels": {
          "app.kubernetes.io/component": "alert-router",
+         "app.kubernetes.io/instance": "main",
          "app.kubernetes.io/name": "alertmanager",
          "app.kubernetes.io/part-of": "kube-prometheus",
          "app.kubernetes.io/version": "0.23.0",

charts/kubezero-metrics/configs/rules/etcd-mixin-prometheusRule

@@ -64,10 +64,10 @@
                {
                   "alert": "etcdGRPCRequestsSlow",
                   "annotations": {
-                     "description": "etcd cluster \"{{ $labels.job }}\": 99th percentile of gRPC requests is {{ $value }}s on etcd instance {{ $labels.instance }}.",
+                     "description": "etcd cluster \"{{ $labels.job }}\": 99th percentile of gRPC requests is {{ $value }}s on etcd instance {{ $labels.instance }} for {{ $labels.grpc_method }} method.",
                      "summary": "etcd grpc requests are slow"
                   },
-                  "expr": "histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~\".*etcd.*\", grpc_type=\"unary\"}[5m])) without(grpc_type))\n> 0.15\n",
+                  "expr": "histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~\".*etcd.*\", grpc_method!=\"Defragment\", grpc_type=\"unary\"}[5m])) without(grpc_type))\n> 0.15\n",
                   "for": "10m",
                   "labels": {
                      "severity": "critical"

charts/kubezero-metrics/configs/rules/kube-state-metrics-prometheusRule

@@ -6,7 +6,7 @@
          "app.kubernetes.io/component": "exporter",
          "app.kubernetes.io/name": "kube-state-metrics",
          "app.kubernetes.io/part-of": "kube-prometheus",
-         "app.kubernetes.io/version": "2.2.1",
+         "app.kubernetes.io/version": "2.2.4",
          "prometheus": "k8s",
          "role": "alert-rules"
       },

charts/kubezero-metrics/configs/rules/kubernetes-prometheusRule

@@ -19,11 +19,11 @@
                {
                   "alert": "KubePodCrashLooping",
                   "annotations": {
-                     "description": "Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is restarting {{ printf \"%.2f\" $value }} times / 10 minutes.",
+                     "description": "Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is in waiting state (reason: \"CrashLoopBackOff\").",
                      "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodcrashlooping",
                      "summary": "Pod is crash looping."
                   },
-                  "expr": "increase(kube_pod_container_status_restarts_total{job=\"kube-state-metrics\"}[10m]) > 0\nand\nkube_pod_container_status_waiting{job=\"kube-state-metrics\"} == 1\n",
+                  "expr": "max_over_time(kube_pod_container_status_waiting_reason{reason=\"CrashLoopBackOff\", job=\"kube-state-metrics\"}[5m]) >= 1\n",
                   "for": "15m",
                   "labels": {
                      "severity": "warning"
@@ -123,7 +123,7 @@
                {
                   "alert": "KubeContainerWaiting",
                   "annotations": {
-                     "description": "Pod {{ $labels.namespace }}/{{ $labels.pod }} container {{ $labels.container}} has been in waiting state for longer than 1 hour.",
+                     "description": "pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour.",
                      "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontainerwaiting",
                      "summary": "Pod container waiting longer than 1 hour"
                   },
@@ -232,7 +232,7 @@
                {
                   "alert": "KubeMemoryOvercommit",
                   "annotations": {
-                     "description": "Cluster has overcommitted memory resource requests for Pods by {{ $value }} bytes and cannot tolerate node failure.",
+                     "description": "Cluster has overcommitted memory resource requests for Pods by {{ $value | humanize }} bytes and cannot tolerate node failure.",
                      "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit",
                      "summary": "Cluster has overcommitted memory resource requests."
                   },
@@ -249,7 +249,7 @@
                      "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuquotaovercommit",
                      "summary": "Cluster has overcommitted CPU resource requests."
                   },
-                  "expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"cpu\"})\n  /\nsum(kube_node_status_allocatable{resource=\"cpu\"})\n  > 1.5\n",
+                  "expr": "sum(min without(resource) (kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=~\"(cpu|requests.cpu)\"}))\n  /\nsum(kube_node_status_allocatable{resource=\"cpu\", job=\"kube-state-metrics\"})\n  > 1.5\n",
                   "for": "5m",
                   "labels": {
                      "severity": "warning"
@@ -262,7 +262,7 @@
                      "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit",
                      "summary": "Cluster has overcommitted memory resource requests."
                   },
-                  "expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"memory\"})\n  /\nsum(kube_node_status_allocatable{resource=\"memory\",job=\"kube-state-metrics\"})\n  > 1.5\n",
+                  "expr": "sum(min without(resource) (kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=~\"(memory|requests.memory)\"}))\n  /\nsum(kube_node_status_allocatable{resource=\"memory\", job=\"kube-state-metrics\"})\n  > 1.5\n",
                   "for": "5m",
                   "labels": {
                      "severity": "warning"
@@ -332,7 +332,7 @@
                      "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup",
                      "summary": "PersistentVolume is filling up."
                   },
-                  "expr": "(\n  kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n    /\n  kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n) < 0.03\nand\nkubelet_volume_stats_used_bytes{job=\"kubelet\", metrics_path=\"/metrics\"} > 0\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\n",
+                  "expr": "(\n  kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n    /\n  kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n) < 0.03\nand\nkubelet_volume_stats_used_bytes{job=\"kubelet\", metrics_path=\"/metrics\"} > 0\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_labels{label_excluded_from_alerts=\"true\"} == 1\n",
                   "for": "1m",
                   "labels": {
                      "severity": "critical"
@@ -345,7 +345,7 @@
                      "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup",
                      "summary": "PersistentVolume is filling up."
                   },
-                  "expr": "(\n  kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n    /\n  kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n) < 0.15\nand\nkubelet_volume_stats_used_bytes{job=\"kubelet\", metrics_path=\"/metrics\"} > 0\nand\npredict_linear(kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}[6h], 4 * 24 * 3600) < 0\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\n",
+                  "expr": "(\n  kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n    /\n  kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n) < 0.15\nand\nkubelet_volume_stats_used_bytes{job=\"kubelet\", metrics_path=\"/metrics\"} > 0\nand\npredict_linear(kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}[6h], 4 * 24 * 3600) < 0\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_labels{label_excluded_from_alerts=\"true\"} == 1\n",
                   "for": "1h",
                   "labels": {
                      "severity": "warning"
@@ -468,7 +468,7 @@
                {
                   "alert": "KubeClientCertificateExpiration",
                   "annotations": {
-                     "description": "A client certificate used to authenticate to the apiserver is expiring in less than 7.0 days.",
+                     "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."
                   },
@@ -480,7 +480,7 @@
                {
                   "alert": "KubeClientCertificateExpiration",
                   "annotations": {
-                     "description": "A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.",
+                     "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."
                   },
@@ -490,11 +490,11 @@
                   }
                },
                {
-                  "alert": "AggregatedAPIErrors",
+                  "alert": "KubeAggregatedAPIErrors",
                   "annotations": {
-                     "description": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. It has appeared unavailable {{ $value | humanize }} times averaged over the past 10m.",
+                     "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/aggregatedapierrors",
+                     "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapierrors",
-                     "summary": "An aggregated API has reported errors."
+                     "summary": "Kubernetes aggregated API has reported errors."
                   },
                   "expr": "sum by(name, namespace)(increase(aggregator_unavailable_apiservice_total[10m])) > 4\n",
                   "labels": {
@@ -502,11 +502,11 @@
                   }
                },
                {
-                  "alert": "AggregatedAPIDown",
+                  "alert": "KubeAggregatedAPIDown",
                   "annotations": {
-                     "description": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m.",
+                     "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/aggregatedapidown",
+                     "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapidown",
-                     "summary": "An aggregated API is down."
+                     "summary": "Kubernetes aggregated API is down."
                   },
                   "expr": "(1 - max by(name, namespace)(avg_over_time(aggregator_unavailable_apiservice[10m]))) * 100 < 85\n",
                   "for": "5m",
@@ -530,9 +530,9 @@
                {
                   "alert": "KubeAPITerminatedRequests",
                   "annotations": {
-                     "description": "The apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests.",
+                     "description": "The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests.",
                      "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapiterminatedrequests",
-                     "summary": "The apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests."
+                     "summary": "The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests."
                   },
                   "expr": "sum(rate(apiserver_request_terminations_total{job=\"apiserver\"}[10m]))  / (  sum(rate(apiserver_request_total{job=\"apiserver\"}[10m])) + sum(rate(apiserver_request_terminations_total{job=\"apiserver\"}[10m])) ) > 0.20\n",
                   "for": "5m",
@@ -748,53 +748,71 @@
                }
             ]
          },
+         {
+            "name": "kubernetes-system-kube-proxy",
+            "rules": [
+               {
+                  "alert": "KubeProxyDown",
+                  "annotations": {
+                     "description": "KubeProxy has disappeared from Prometheus target discovery.",
+                     "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeproxydown",
+                     "summary": "Target disappeared from Prometheus target discovery."
+                  },
+                  "expr": "absent(up{job=\"kube-proxy\"} == 1)\n",
+                  "for": "15m",
+                  "labels": {
+                     "severity": "critical"
+                  }
+               }
+            ]
+         },
          {
             "name": "kube-apiserver-burnrate.rules",
             "rules": [
                {
-                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[1d]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[1d]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[1d]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n",
+                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[1d]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[1d]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[1d]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n",
                   "labels": {
                      "verb": "read"
                   },
                   "record": "apiserver_request:burnrate1d"
                },
                {
-                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[1h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[1h]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[1h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n",
+                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[1h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[1h]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[1h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n",
                   "labels": {
                      "verb": "read"
                   },
                   "record": "apiserver_request:burnrate1h"
                },
                {
-                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[2h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[2h]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[2h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n",
+                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[2h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[2h]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[2h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n",
                   "labels": {
                      "verb": "read"
                   },
                   "record": "apiserver_request:burnrate2h"
                },
                {
-                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[30m]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[30m]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[30m]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n",
+                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[30m]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[30m]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[30m]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n",
                   "labels": {
                      "verb": "read"
                   },
                   "record": "apiserver_request:burnrate30m"
                },
                {
-                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[3d]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[3d]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[3d]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n",
+                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[3d]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[3d]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[3d]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n",
                   "labels": {
                      "verb": "read"
                   },
                   "record": "apiserver_request:burnrate3d"
                },
                {
-                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[5m]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[5m]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[5m]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n",
+                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[5m]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[5m]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[5m]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n",
                   "labels": {
                      "verb": "read"
                   },
                   "record": "apiserver_request:burnrate5m"
                },
                {
-                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[6h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[6h]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[6h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n",
+                  "expr": "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[6h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[6h]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[6h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n",
                   "labels": {
                      "verb": "read"
                   },
@@ -932,14 +950,14 @@
                   "record": "cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d"
                },
                {
-                  "expr": "1 - (\n  (\n    # write too slow\n    sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n    -\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n  ) +\n  (\n    # read too slow\n    sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n    -\n    (\n      (\n        sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n      +\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"})\n    )\n  ) +\n  # errors\n  sum by (cluster) (code:apiserver_request_total:increase30d{code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d)\n",
+                  "expr": "1 - (\n  (\n    # write too slow\n    sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n    -\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n  ) +\n  (\n    # read too slow\n    sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n    -\n    (\n      (\n        sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n      +\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"})\n    )\n  ) +\n  # errors\n  sum by (cluster) (code:apiserver_request_total:increase30d{code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d)\n",
                   "labels": {
                      "verb": "all"
                   },
                   "record": "apiserver_request:availability30d"
                },
                {
-                  "expr": "1 - (\n  sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n  -\n  (\n    # too slow\n    (\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n      or\n      vector(0)\n    )\n    +\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n    +\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"})\n  )\n  +\n  # errors\n  sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\"})\n",
+                  "expr": "1 - (\n  sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n  -\n  (\n    # too slow\n    (\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n      or\n      vector(0)\n    )\n    +\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n    +\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"})\n  )\n  +\n  # errors\n  sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\"})\n",
                   "labels": {
                      "verb": "read"
                   },
@@ -1008,7 +1026,7 @@
                   "record": "node_namespace_pod_container:container_memory_swap"
                },
                {
-                  "expr": "kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n",
+                  "expr": "kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n",
                   "record": "cluster:namespace:pod_memory:active:kube_pod_container_resource_requests"
                },
                {
@@ -1016,7 +1034,7 @@
                   "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)\ngroup_left() max by (namespace, pod) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n",
+                  "expr": "kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n",
                   "record": "cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests"
                },
                {
@@ -1024,7 +1042,7 @@
                   "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)\ngroup_left() max by (namespace, pod) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n",
+                  "expr": "kube_pod_container_resource_limits{resource=\"memory\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n",
                   "record": "cluster:namespace:pod_memory:active:kube_pod_container_resource_limits"
                },
                {
@@ -1032,7 +1050,7 @@
                   "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)\ngroup_left() max by (namespace, pod) (\n (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n )\n",
+                  "expr": "kube_pod_container_resource_limits{resource=\"cpu\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n )\n",
                   "record": "cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits"
                },
                {

charts/kubezero-metrics/configs/rules/node-exporter-prometheusRule

@@ -6,7 +6,7 @@
          "app.kubernetes.io/component": "exporter",
          "app.kubernetes.io/name": "node-exporter",
          "app.kubernetes.io/part-of": "kube-prometheus",
-         "app.kubernetes.io/version": "1.2.2",
+         "app.kubernetes.io/version": "1.3.1",
          "prometheus": "k8s",
          "role": "alert-rules"
       },
@@ -259,7 +259,7 @@
                   "record": "instance:node_num_cpu:sum"
                },
                {
-                  "expr": "1 - avg without (cpu, mode) (\n  rate(node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\"}[5m])\n)\n",
+                  "expr": "1 - avg without (cpu) (\n  sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\"}[5m]))\n)\n",
                   "record": "instance:node_cpu_utilisation:rate5m"
                },
                {
@@ -267,7 +267,7 @@
                   "record": "instance:node_load1_per_cpu:ratio"
                },
                {
-                  "expr": "1 - (\n  node_memory_MemAvailable_bytes{job=\"node-exporter\"}\n  or\n  (\n    node_memory_Buffers_bytes{job=\"node-exporter\"}\n    +\n    node_memory_Cached_bytes{job=\"node-exporter\"}\n    +\n    node_memory_MemFree_bytes{job=\"node-exporter\"}\n    +\n    node_memory_Slab_bytes{job=\"node-exporter\"}\n  )\n/\n  node_memory_MemTotal_bytes{job=\"node-exporter\"}\n)\n",
+                  "expr": "1 - (\n  (\n    node_memory_MemAvailable_bytes{job=\"node-exporter\"}\n    or\n    (\n      node_memory_Buffers_bytes{job=\"node-exporter\"}\n      +\n      node_memory_Cached_bytes{job=\"node-exporter\"}\n      +\n      node_memory_MemFree_bytes{job=\"node-exporter\"}\n      +\n      node_memory_Slab_bytes{job=\"node-exporter\"}\n    )\n  )\n/\n  node_memory_MemTotal_bytes{job=\"node-exporter\"}\n)\n",
                   "record": "instance:node_memory_utilisation:ratio"
                },
                {

charts/kubezero-metrics/configs/rules/prometheus-operator-prometheusRule

@@ -6,7 +6,7 @@
          "app.kubernetes.io/component": "controller",
          "app.kubernetes.io/name": "prometheus-operator",
          "app.kubernetes.io/part-of": "kube-prometheus",
-         "app.kubernetes.io/version": "0.51.1",
+         "app.kubernetes.io/version": "0.52.1",
          "prometheus": "k8s",
          "role": "alert-rules"
       },
@@ -110,6 +110,24 @@
                   }
                }
             ]
+         },
+         {
+            "name": "config-reloaders",
+            "rules": [
+               {
+                  "alert": "ConfigReloaderSidecarErrors",
+                  "annotations": {
+                     "description": "Errors encountered while the {{$labels.pod}} config-reloader sidecar attempts to sync config in {{$labels.namespace}} namespace.\nAs a result, configuration for service running in {{$labels.pod}} may be stale and cannot be updated anymore.",
+                     "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/configreloadersidecarerrors",
+                     "summary": "config-reloader sidecar has not had a successful reload for 10m"
+                  },
+                  "expr": "max_over_time(reloader_last_reload_successful{namespace=~\".+\"}[5m]) == 0\n",
+                  "for": "10m",
+                  "labels": {
+                     "severity": "warning"
+                  }
+               }
+            ]
          }
       ]
    }

charts/kubezero-metrics/configs/rules/prometheus-prometheusRule

@@ -4,9 +4,10 @@
    "metadata": {
       "labels": {
          "app.kubernetes.io/component": "prometheus",
+         "app.kubernetes.io/instance": "k8s",
          "app.kubernetes.io/name": "prometheus",
          "app.kubernetes.io/part-of": "kube-prometheus",
-         "app.kubernetes.io/version": "2.30.0",
+         "app.kubernetes.io/version": "2.31.1",
          "prometheus": "k8s",
          "role": "alert-rules"
       },

charts/kubezero-metrics/templates/rules/etcd-mixin.yaml

@@ -49,9 +49,9 @@ spec:
         severity: warning
     - alert: etcdGRPCRequestsSlow
       annotations:
-        description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile of gRPC requests is {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.'
+        description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile of gRPC requests is {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}} for {{`{{`}} $labels.grpc_method {{`}}`}} method.'
         summary: etcd grpc requests are slow
-      expr: 'histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_type="unary"}[5m])) without(grpc_type))
+      expr: 'histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_method!="Defragment", grpc_type="unary"}[5m])) without(grpc_type))
 
         > 0.15
 

charts/kubezero-metrics/templates/rules/kubernetes.yaml

@@ -11,14 +11,10 @@ spec:
     rules:
     - alert: KubePodCrashLooping
       annotations:
-        description: Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} ({{`{{`}} $labels.container {{`}}`}}) is restarting {{`{{`}} printf "%.2f" $value {{`}}`}} times / 10 minutes.
+        description: 'Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} ({{`{{`}} $labels.container {{`}}`}}) is in waiting state (reason: "CrashLoopBackOff").'
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodcrashlooping
         summary: Pod is crash looping.
-      expr: 'increase(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[10m]) > 0
+      expr: 'max_over_time(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff", job="kube-state-metrics"}[5m]) >= 1
-
-        and
-
-        kube_pod_container_status_waiting{job="kube-state-metrics"} == 1
 
         '
       for: 15m
@@ -89,7 +85,7 @@ spec:
         severity: warning
     - alert: KubeContainerWaiting
       annotations:
-        description: Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} container {{`{{`}} $labels.container{{`}}`}} has been in waiting state for longer than 1 hour.
+        description: pod/{{`{{`}} $labels.pod {{`}}`}} in namespace {{`{{`}} $labels.namespace {{`}}`}} on container {{`{{`}} $labels.container{{`}}`}} has been in waiting state for longer than 1 hour.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontainerwaiting
         summary: Pod container waiting longer than 1 hour
       expr: 'sum by (namespace, pod, container) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0
@@ -177,7 +173,7 @@ spec:
         severity: warning
     - alert: KubeMemoryOvercommit
       annotations:
-        description: Cluster has overcommitted memory resource requests for Pods by {{`{{`}} $value {{`}}`}} bytes and cannot tolerate node failure.
+        description: Cluster has overcommitted memory resource requests for Pods by {{`{{`}} $value | humanize {{`}}`}} bytes and cannot tolerate node failure.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit
         summary: Cluster has overcommitted memory resource requests.
       expr: 'sum(namespace_memory:kube_pod_container_resource_requests:sum{}) - (sum(kube_node_status_allocatable{resource="memory"}) - max(kube_node_status_allocatable{resource="memory"})) > 0
@@ -195,7 +191,7 @@ spec:
         description: Cluster has overcommitted CPU resource requests for Namespaces.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuquotaovercommit
         summary: Cluster has overcommitted CPU resource requests.
-      expr: "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"cpu\"})\n  /\nsum(kube_node_status_allocatable{resource=\"cpu\"})\n  > 1.5\n"
+      expr: "sum(min without(resource) (kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=~\"(cpu|requests.cpu)\"}))\n  /\nsum(kube_node_status_allocatable{resource=\"cpu\", job=\"kube-state-metrics\"})\n  > 1.5\n"
       for: 5m
       labels:
         severity: warning
@@ -204,7 +200,7 @@ spec:
         description: Cluster has overcommitted memory resource requests for Namespaces.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit
         summary: Cluster has overcommitted memory resource requests.
-      expr: "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"memory\"})\n  /\nsum(kube_node_status_allocatable{resource=\"memory\",job=\"kube-state-metrics\"})\n  > 1.5\n"
+      expr: "sum(min without(resource) (kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=~\"(memory|requests.memory)\"}))\n  /\nsum(kube_node_status_allocatable{resource=\"memory\", job=\"kube-state-metrics\"})\n  > 1.5\n"
       for: 5m
       labels:
         severity: warning
@@ -251,7 +247,7 @@ spec:
         description: The PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} is only {{`{{`}} $value | humanizePercentage {{`}}`}} free.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup
         summary: PersistentVolume is filling up.
-      expr: "(\n  kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n    /\n  kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n) < 0.03\nand\nkubelet_volume_stats_used_bytes{job=\"kubelet\", metrics_path=\"/metrics\"} > 0\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\n"
+      expr: "(\n  kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n    /\n  kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n) < 0.03\nand\nkubelet_volume_stats_used_bytes{job=\"kubelet\", metrics_path=\"/metrics\"} > 0\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_labels{label_excluded_from_alerts=\"true\"} == 1\n"
       for: 1m
       labels:
         severity: critical
@@ -260,7 +256,7 @@ spec:
         description: Based on recent sampling, the PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} is expected to fill up within four days. Currently {{`{{`}} $value | humanizePercentage {{`}}`}} is available.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup
         summary: PersistentVolume is filling up.
-      expr: "(\n  kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n    /\n  kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n) < 0.15\nand\nkubelet_volume_stats_used_bytes{job=\"kubelet\", metrics_path=\"/metrics\"} > 0\nand\npredict_linear(kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}[6h], 4 * 24 * 3600) < 0\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\n"
+      expr: "(\n  kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n    /\n  kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n) < 0.15\nand\nkubelet_volume_stats_used_bytes{job=\"kubelet\", metrics_path=\"/metrics\"} > 0\nand\npredict_linear(kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}[6h], 4 * 24 * 3600) < 0\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_labels{label_excluded_from_alerts=\"true\"} == 1\n"
       for: 1h
       labels:
         severity: warning
@@ -371,7 +367,7 @@ spec:
     rules:
     - alert: KubeClientCertificateExpiration
       annotations:
-        description: A client certificate used to authenticate to the apiserver is expiring in less than 7.0 days.
+        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]))) < 604800
@@ -381,7 +377,7 @@ spec:
         severity: warning
     - alert: KubeClientCertificateExpiration
       annotations:
-        description: A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.
+        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]))) < 86400
@@ -389,21 +385,21 @@ spec:
         '
       labels:
         severity: critical
-    - alert: AggregatedAPIErrors
+    - alert: KubeAggregatedAPIErrors
       annotations:
-        description: An aggregated API {{`{{`}} $labels.name {{`}}`}}/{{`{{`}} $labels.namespace {{`}}`}} has reported errors. It has appeared unavailable {{`{{`}} $value | humanize {{`}}`}} times averaged over the past 10m.
+        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/aggregatedapierrors
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapierrors
-        summary: An aggregated API has reported errors.
+        summary: Kubernetes aggregated API has reported errors.
       expr: 'sum by(name, namespace)(increase(aggregator_unavailable_apiservice_total[10m])) > 4
 
         '
       labels:
         severity: warning
-    - alert: AggregatedAPIDown
+    - alert: KubeAggregatedAPIDown
       annotations:
-        description: An aggregated API {{`{{`}} $labels.name {{`}}`}}/{{`{{`}} $labels.namespace {{`}}`}} has been only {{`{{`}} $value | humanize {{`}}`}}% available over the last 10m.
+        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/aggregatedapidown
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapidown
-        summary: An aggregated API is down.
+        summary: Kubernetes aggregated API is down.
       expr: '(1 - max by(name, namespace)(avg_over_time(aggregator_unavailable_apiservice[10m]))) * 100 < 85
 
         '
@@ -423,9 +419,9 @@ spec:
         severity: critical
     - alert: KubeAPITerminatedRequests
       annotations:
-        description: The apiserver has terminated {{`{{`}} $value | humanizePercentage {{`}}`}} of its incoming requests.
+        description: The kubernetes apiserver has terminated {{`{{`}} $value | humanizePercentage {{`}}`}} of its incoming requests.
         runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapiterminatedrequests
-        summary: The apiserver has terminated {{`{{`}} $value | humanizePercentage {{`}}`}} of its incoming requests.
+        summary: The kubernetes apiserver has terminated {{`{{`}} $value | humanizePercentage {{`}}`}} of its incoming requests.
       expr: 'sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m]))  / (  sum(rate(apiserver_request_total{job="apiserver"}[10m])) + sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20
 
         '
@@ -597,33 +593,46 @@ spec:
       for: 15m
       labels:
         severity: critical
+  - name: kubernetes-system-kube-proxy
+    rules:
+    - alert: KubeProxyDown
+      annotations:
+        description: KubeProxy has disappeared from Prometheus target discovery.
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeproxydown
+        summary: Target disappeared from Prometheus target discovery.
+      expr: 'absent(up{job="kube-proxy"} == 1)
+
+        '
+      for: 15m
+      labels:
+        severity: critical
   - name: kube-apiserver-burnrate.rules
     rules:
-    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[1d]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[1d]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[1d]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n"
+    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[1d]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[1d]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[1d]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n"
       labels:
         verb: read
       record: apiserver_request:burnrate1d
-    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[1h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[1h]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[1h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n"
+    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[1h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[1h]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[1h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n"
       labels:
         verb: read
       record: apiserver_request:burnrate1h
-    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[2h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[2h]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[2h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n"
+    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[2h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[2h]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[2h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n"
       labels:
         verb: read
       record: apiserver_request:burnrate2h
-    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[30m]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[30m]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[30m]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n"
+    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[30m]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[30m]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[30m]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n"
       labels:
         verb: read
       record: apiserver_request:burnrate30m
-    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[3d]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[3d]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[3d]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n"
+    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[3d]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[3d]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[3d]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n"
       labels:
         verb: read
       record: apiserver_request:burnrate3d
-    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[5m]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[5m]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[5m]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n"
+    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[5m]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[5m]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[5m]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n"
       labels:
         verb: read
       record: apiserver_request:burnrate5m
-    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[6h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[6h]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"}[6h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n"
+    - expr: "(\n  (\n    # too slow\n    sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n    -\n    (\n      (\n        sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"}[6h]))\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"}[6h]))\n      +\n      sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"}[6h]))\n    )\n  )\n  +\n  # errors\n  sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n"
       labels:
         verb: read
       record: apiserver_request:burnrate6h
@@ -724,12 +733,12 @@ spec:
 
         '
       record: cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d
-    - expr: "1 - (\n  (\n    # write too slow\n    sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n    -\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n  ) +\n  (\n    # read too slow\n    sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n    -\n    (\n      (\n        sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n      +\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"\
+    - expr: "1 - (\n  (\n    # write too slow\n    sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n    -\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n  ) +\n  (\n    # read too slow\n    sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n    -\n    (\n      (\n        sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n        or\n        vector(0)\n      )\n      +\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n      +\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"\
         })\n    )\n  ) +\n  # errors\n  sum by (cluster) (code:apiserver_request_total:increase30d{code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d)\n"
       labels:
         verb: all
       record: apiserver_request:availability30d
-    - expr: "1 - (\n  sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n  -\n  (\n    # too slow\n    (\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n      or\n      vector(0)\n    )\n    +\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n    +\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"40\"})\n  )\n  +\n  # errors\n  sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\"})\n"
+    - expr: "1 - (\n  sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n  -\n  (\n    # too slow\n    (\n      sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n      or\n      vector(0)\n    )\n    +\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n    +\n    sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"})\n  )\n  +\n  # errors\n  sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\"})\n"
       labels:
         verb: read
       record: apiserver_request:availability30d
@@ -777,19 +786,19 @@ spec:
       record: node_namespace_pod_container:container_memory_cache
     - expr: "container_memory_swap{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n  max by(namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n"
       record: node_namespace_pod_container:container_memory_swap
-    - expr: "kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n"
+    - expr: "kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n"
       record: cluster:namespace:pod_memory:active:kube_pod_container_resource_requests
     - expr: "sum by (namespace, cluster) (\n    sum by (namespace, pod, cluster) (\n        max by (namespace, pod, container, cluster) (\n          kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"}\n        ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (\n          kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n        )\n    )\n)\n"
       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)\ngroup_left() max by (namespace, pod) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n"
+    - expr: "kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n"
       record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests
     - expr: "sum by (namespace, cluster) (\n    sum by (namespace, pod, cluster) (\n        max by (namespace, pod, container, cluster) (\n          kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"}\n        ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (\n          kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n        )\n    )\n)\n"
       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)\ngroup_left() max by (namespace, pod) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n"
+    - expr: "kube_pod_container_resource_limits{resource=\"memory\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n  (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n"
       record: cluster:namespace:pod_memory:active:kube_pod_container_resource_limits
     - expr: "sum by (namespace, cluster) (\n    sum by (namespace, pod, cluster) (\n        max by (namespace, pod, container, cluster) (\n          kube_pod_container_resource_limits{resource=\"memory\",job=\"kube-state-metrics\"}\n        ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (\n          kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n        )\n    )\n)\n"
       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)\ngroup_left() max by (namespace, pod) (\n (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n )\n"
+    - expr: "kube_pod_container_resource_limits{resource=\"cpu\",job=\"kube-state-metrics\"}  * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n )\n"
       record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits
     - expr: "sum by (namespace, cluster) (\n    sum by (namespace, pod, cluster) (\n        max by (namespace, pod, container, cluster) (\n          kube_pod_container_resource_limits{resource=\"cpu\",job=\"kube-state-metrics\"}\n        ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (\n          kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n        )\n    )\n)\n"
       record: namespace_cpu:kube_pod_container_resource_limits:sum

charts/kubezero-metrics/templates/rules/node-exporter.yaml

@@ -190,11 +190,11 @@ spec:
     rules:
     - expr: "count without (cpu, mode) (\n  node_cpu_seconds_total{job=\"node-exporter\",mode=\"idle\"}\n)\n"
       record: instance:node_num_cpu:sum
-    - expr: "1 - avg without (cpu, mode) (\n  rate(node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\"}[5m])\n)\n"
+    - expr: "1 - avg without (cpu) (\n  sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\"}[5m]))\n)\n"
       record: instance:node_cpu_utilisation:rate5m
     - expr: "(\n  node_load1{job=\"node-exporter\"}\n/\n  instance:node_num_cpu:sum{job=\"node-exporter\"}\n)\n"
       record: instance:node_load1_per_cpu:ratio
-    - expr: "1 - (\n  node_memory_MemAvailable_bytes{job=\"node-exporter\"}\n  or\n  (\n    node_memory_Buffers_bytes{job=\"node-exporter\"}\n    +\n    node_memory_Cached_bytes{job=\"node-exporter\"}\n    +\n    node_memory_MemFree_bytes{job=\"node-exporter\"}\n    +\n    node_memory_Slab_bytes{job=\"node-exporter\"}\n  )\n/\n  node_memory_MemTotal_bytes{job=\"node-exporter\"}\n)\n"
+    - expr: "1 - (\n  (\n    node_memory_MemAvailable_bytes{job=\"node-exporter\"}\n    or\n    (\n      node_memory_Buffers_bytes{job=\"node-exporter\"}\n      +\n      node_memory_Cached_bytes{job=\"node-exporter\"}\n      +\n      node_memory_MemFree_bytes{job=\"node-exporter\"}\n      +\n      node_memory_Slab_bytes{job=\"node-exporter\"}\n    )\n  )\n/\n  node_memory_MemTotal_bytes{job=\"node-exporter\"}\n)\n"
       record: instance:node_memory_utilisation:ratio
     - expr: 'rate(node_vmstat_pgmajfault{job="node-exporter"}[5m])
 

charts/kubezero-metrics/templates/rules/prometheus-operator.yaml

@@ -86,4 +86,19 @@ spec:
       for: 5m
       labels:
         severity: warning
+  - name: config-reloaders
+    rules:
+    - alert: ConfigReloaderSidecarErrors
+      annotations:
+        description: 'Errors encountered while the {{`{{`}}$labels.pod{{`}}`}} config-reloader sidecar attempts to sync config in {{`{{`}}$labels.namespace{{`}}`}} namespace.
+
+          As a result, configuration for service running in {{`{{`}}$labels.pod{{`}}`}} may be stale and cannot be updated anymore.'
+        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/configreloadersidecarerrors
+        summary: config-reloader sidecar has not had a successful reload for 10m
+      expr: 'max_over_time(reloader_last_reload_successful{namespace=~".+"}[5m]) == 0
+
+        '
+      for: 10m
+      labels:
+        severity: warning
 

charts/kubezero-metrics/update.sh

@@ -9,6 +9,7 @@ helm pull prometheus-community/kube-prometheus-stack --untar --untardir charts -
 rm -rf charts/prometheus-pushgateway
 helm pull prometheus-community/prometheus-pushgateway --untar --untardir charts --version $PG_VER
 
+# workaround for https://github.com/prometheus-community/helm-charts/issues/1500
 patch -p0 -i zdt.patch --no-backup-if-mismatch
 
 patch -p0 -i zdt-pushgateway.patch --no-backup-if-mismatch